Search

BACKGROUND. CT with adrenal-washout protocol (hereafter, adrenal-protocol CT) is commonly performed to distinguish adrenal adenomas from other adrenal tumors. However, the technique's utility among heterogeneous nodules is not well established, and the optimal method for placing ROIs in heterogeneous nodules is not clearly defined. OBJECTIVE. The purpose of our study was to determine the diagnostic performance of adrenal-protocol CT to distinguish adenomas from nonadenomas among heterogeneous adrenal nodules and to compare this performance among different methods for ROI placement. METHODS. This retrospective study included 164 patients (mean age, 59.1 years; 61 men, 103 women) with a total of 164 heterogeneous adrenal nodules evaluated using adrenal-protocol CT at seven institutions. All nodules had an available pathologic reference standard. A single investigator at each institution evaluated the CT images. ROIs were placed on portal venous phase images using four ROI methods: standard ROI, which refers to a single large ROI in the nodule's center; high ROI, a single ROI on the nodule's highest-attenuation area; low ROI, a single ROI the on nodule's lowest-attenuation area; and average ROI, the mean of the three ROIs on the nodule's superior, middle, and inferior thirds using the approach for the standard ROI. ROIs were then placed in identical locations on unenhanced and delayed phase images. Absolute washout was determined for all methods. RESULTS. The nodules comprised 82 adenomas and 82 nonadenomas (36 pheochromocytomas, 20 metastases, 12 adrenocortical carcinomas, and 14 nodules with other pathologies). The mean nodule size was 4.5 ± 2.8 (SD) cm (range, 1.6-23.0 cm). Unenhanced CT attenuation of 10 HU or less exhibited sensitivity and specificity for adenoma of 22.0% and 96.3% for standard-ROI, 11.0% and 98.8% for high-ROI, 58.5% and 84.1% for low-ROI, and 30.5% and 97.6% for average-ROI methods. Adrenal-protocol CT overall (unenhanced attenuation ≤ 10 HU or absolute washout of ≥ 60%) exhibited sensitivity and specificity for adenoma of 57.3% and 84.1% for the standard-ROI method, 63.4% and 51.2% for the high-ROI method, 68.3% and 62.2% for the low-ROI method, and 59.8% and 85.4% for the average-ROI method. CONCLUSION. Adrenal-protocol CT has poor diagnostic performance for distinguishing adenomas from nonadenomas among heterogeneous adrenal nodules regardless of the method used for ROI placement. CLINICAL IMPACT. Adrenal-protocol CT has limited utility in the evaluation of heterogeneous adrenal nodules.

Accurate survival prediction for bladder cancer patients who have undergone radical cystectomy can improve their treatment management. However, the existing predictive models do not take advantage of both clinical and radiological imaging data. This study aimed to fill this gap by developing an approach that leverages the strengths of clinical (C), radiomics (R), and deep-learning (D) descriptors to improve survival prediction. The dataset comprised 163 patients, including clinical, histopathological information, and CT urography scans. The data were divided by patient into training, validation, and test sets. We analyzed the clinical data by a nomogram and the image data by radiomics and deep-learning models. The descriptors were input into a BPNN model for survival prediction. The AUCs on the test set were (C): 0.82 ± 0.06, (R): 0.73 ± 0.07, (D): 0.71 ± 0.07, (CR): 0.86 ± 0.05, (CD): 0.86 ± 0.05, and (CRD): 0.87 ± 0.05. The predictions based on D and CRD descriptors showed a significant difference (p = 0.007). For Kaplan-Meier survival analysis, the deceased and alive groups were stratified successfully by C (p < 0.001) and CRD (p < 0.001), with CRD predicting the alive group more accurately. The results highlight the potential of combining C, R, and D descriptors to accurately predict the survival of bladder cancer patients after cystectomy.

The radiologic diagnosis of adrenal disease can be challenging in settings of atypical presentations, mimics of benign and malignant adrenal masses, and rare adrenal anomalies. Misdiagnosis may lead to suboptimal management and adverse outcomes. Adrenal adenoma is the most common benign adrenal tumor that arises from the cortex, whereas adrenocortical carcinoma (ACC) is a rare malignant tumor of the cortex. Adrenal cyst and myelolipoma are other benign adrenal lesions and are characterized by their fluid and fat content, respectively. Pheochromocytoma is a rare neuroendocrine tumor of the adrenal medulla. Metastases to the adrenal glands are the most common malignant adrenal tumors. While many of these masses have classic imaging appearances, considerable overlap exists between benign and malignant lesions and can pose a diagnostic challenge. Atypical adrenal adenomas include those that are lipid poor; contain macroscopic fat, hemorrhage, and/or iron; are heterogeneous and/or large; and demonstrate growth. Heterogeneous adrenal adenomas may mimic ACC, metastasis, or pheochromocytoma, particularly when they are 4 cm or larger, whereas smaller versions of ACC, metastasis, and pheochromocytoma and those with washout greater than 60% may mimic adenoma. Because of its nonenhanced CT attenuation of less than or equal to 10 HU, a lipid-rich adrenal adenoma may be mimicked by a benign adrenal cyst, or it may be mimicked by a tumor with central cystic and/or necrotic change such as ACC, pheochromocytoma, or metastasis. Rare adrenal tumors such as hemangioma, ganglioneuroma, and oncocytoma also may mimic adrenal adenoma, ACC, metastasis, and pheochromocytoma. The authors describe cases of adrenal neoplasms that they have encountered in clinical practice and presented to adrenal multidisciplinary tumor boards. Key lessons to aid in diagnosis and further guide appropriate management are provided. © RSNA, 2023 Online supplemental material is available for this article. Quiz questions for this article are available through the Online Learning Center.

Purpose: Substantial variation in imaging terms used to describe the adrenal gland and adrenal findings leads to ambiguity and uncertainty in radiology reports and subsequently their understanding by referring clinicians. The purpose of this study was to develop a standardized lexicon to describe adrenal imaging findings at CT and MRI., Methods: Fourteen members of the Society of Abdominal Radiology adrenal neoplasm disease-focused panel (SAR-DFP) including one endocrine surgeon participated to develop an adrenal lexicon using a modified Delphi process to reach consensus. Five radiologists prepared a preliminary list of 35 imaging terms that was sent to the full group as an online survey (19 general imaging terms, 9 specific to CT, and 7 specific to MRI). In the first round, members voted on terms to be included and proposed definitions; subsequent two rounds were used to achieve consensus on definitions (defined as ≥ 80% agreement)., Results: Consensus for inclusion was reached on 33/35 terms with two terms excluded (anterior limb and normal adrenal size measurements). Greater than 80% consensus was reached on the definitions for 15 terms following the first round, with subsequent consensus achieved for the definitions of the remaining 18 terms following two additional rounds. No included term had remaining disagreement., Conclusion: Expert consensus produced a standardized lexicon for reporting adrenal findings at CT and MRI. The use of this consensus lexicon should improve radiology report clarity, standardize clinical and research terminology, and reduce uncertainty for referring providers when adrenal findings are present., (© 2022. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.)

A high level of clinical suspicion is essential in the diagnosis and management of a suspected adrenal mass during pregnancy and the peripartum period. Timely recognition is important in order to improve fetal and maternal outcomes. Imaging is often performed to confirm a suspected adrenal lesion; however, increasing usage of diagnostic imaging during pregnancy and lactation has also increased awareness, concerns and confusion regarding the safety risks regarding fetal and maternal exposure to radiation and imaging intravenous contrast agents. This may lead to anxiety and avoidance of imaging examinations which can delay diagnosis and appropriate treatment. This article briefly reviews evidence-based recommended imaging modalities during pregnancy and the lactation period for the assessment of a suspected adrenal mass while recognizing that no examination should be withheld when the exam is necessary to confirm an important clinical suspicion. The imaging characteristics of the more common adrenal pathologies that may affect pregnant women are also discussed., (© 2022. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.)

BACKGROUND. Homogeneous microscopic fat within adrenal nodules on chemical-shift MRI (CS-MRI) is diagnostic of benign adrenal adenoma, but the clinical relevance of heterogeneous microscopic fat is not well established. OBJECTIVE. This study sought to determine the prevalence of malignancy in adrenal nodules with heterogeneous microscopic fat on dual-echo T1-weighted CS-MRI. METHODS. We performed a retrospective study of adult patients with adrenal nodules detected on MRI performed between August 2007 and November 2020 at seven institutions. Eligible nodules had a short-axis diameter of 10 mm or larger with heterogeneous microscopic fat (defined by an area of signal loss of < 80% on opposed-phase CS-MRI). Two radiologists from each center, blinded to reference standard results, determined the signal loss pattern (diffuse, two distinct parts, speckling pattern, central loss, or peripheral loss) within the nodules. The reference standard used was available for 283 nodules (pathology for 21 nodules, ≥ 1 year of imaging follow-up for 245, and ≥ 5 years of clinical follow-up for 17) in 282 patients (171 women and 111 men; mean age, 60 ± 12 [SD] years); 30% (86/282) patients had prior malignancy. RESULTS. The mean long-axis diameter was 18.7 ± 7.9 mm (range, 10-80 mm). No malignant nodules were found in patients without prior cancer (0/197; 95% CI, 0-1.5%). Four of the 86 patients with prior malignancy (hepatocellular carcinoma [HCC], renal cell carcinoma [RCC], lung cancer, or both colon cancer and RCC) (4.7%; 95% CI, 1.3-11.5%) had metastatic nodules. Detected patterns were diffuse heterogeneous signal loss (40% [114/283]), speckling (28% [80/283]), two distinct parts (18% [51/283]), central loss (9% [26/283]), and peripheral loss (4% [12/283]). Two metastases from HCC and RCC showed diffuse heterogeneous signal loss. Lung cancer metastasis manifested as two distinct parts, and the metastasis in the patient with both colon cancer and RCC showed peripheral signal loss. CONCLUSION. Presence of heterogeneous microscopic fat in adrenal nodules on CS-MRI indicates a high likelihood of benignancy, particularly in patients without prior cancer. This finding is also commonly benign in patients with cancer; however, caution is warranted when primary malignancies may contain fat or if the morphologic pattern of signal loss may indicate a collision tumor. CLINICAL IMPACT. In the absence of prior cancer, adrenal nodules with heterogeneous microscopic fat do not require additional imaging evaluation.

BACKGROUND. Washout CT is commonly used to evaluate indeterminate adrenal nodules, although its diagnostic performance is poorly established in true adrenal incidentalomas. OBJECTIVE. The purpose of this study was to compare, in patients without a known malignancy history, the prevalence of malignancy for incidental adrenal nodules with unenhanced attenuation more than 10 HU that do and do not show absolute washout of 60% or more, thereby determining the diagnostic performance of washout CT for differentiating benign from malignant incidental adrenal nodules. METHODS. This retrospective six-institution study included 299 patients (mean age, 57.3 years; 180 women, 119 men) without known malignancy or suspicion for functioning adrenal tumor who underwent washout CT, which showed a total of 336 adrenal nodules with a short-axis diameter of 1 cm or more, homogeneity, and unenhanced attenuation over 10 HU. The date of the first CT ranged across institutions from November 1, 2003, to January 1, 2017. Washout was determined for all nodules. Reference standard was pathology ( n = 54), imaging follow-up (≥ 1 year) ( n = 269), or clinical follow-up (≥ 5 years) ( n = 13). RESULTS. Prevalence of malignancy among all nodules, nodules less than 4 cm, and nodules 4 cm or more was 1.5% (5/336; 95% CI, 0.5-3.4%), 0.3% (1/317; 95% CI, 0.0-1.7%), and 21.1% (4/19; 95% CI, 6.1-45.6%), respectively. Prevalence of malignancy was not significantly different for nodules smaller than 4 cm with (0% [0/241]; 95% CI, 0.0-1.2%) and without (1.3% [1/76]; 95% CI, 0.0-7.1%) washout of 60% or more ( p = .08) or for nodules 4 cm or larger with (16.7% [1/6]; 95% CI, 0.4-64.1%) and without (23.1% [3/13]; 95% CI, 5.0-53.8%) washout of 60% or more ( p = .75). Washout of 60% or more was observed in 75.5% (243/322; 95% CI, 70.4-80.1%) of benign nodules (excluding pheochromocytomas), 20.0% (1/5; 95% CI, 0.5-71.6%) of malignant nodules, and 33.3% (3/9; 95% CI, 7.5-70.1%) of pheochromocytomas. For differentiating benign nodules from malignant nodules and pheochromocytomas, washout of 60% or more had 77.5% sensitivity, 70.0% specificity, 98.8% PPV, and 9.2% NPV among nodules smaller than 4 cm. CONCLUSION. Prevalence of malignancy is low among incidental homogeneous adrenal nodules smaller than 4 cm with unenhanced attenuation more than 10 HU and does not significantly differ between those with and without washout of 60% or more; wash-out of 60% or more has suboptimal performance for characterizing nodules as benign. CLINICAL IMPACT. Washout CT has limited utility in evaluating incidental adrenal nodules in patients without known malignancy.

Objective: To evaluate the effect of intra-procedural contrast-enhanced CT (CECT) and same-session repeat ablation (SSRA) on primary efficacy, the complete eradication of tumor after the first ablation session as confirmed on first imaging follow-up, of clinically localized T1a (cT1a) renal cell carcinoma (RCC)., Methods: 398 consecutive patients with cT1a RCC were treated with cryoablation between 10/2003 and 12/2017, radiofrequency (RFA) or microwave ablation (MWA) between 1/2010 and 12/2017. SSRA was performed for residual tumor identified on intra-procedural CECT. Kruskal-Wallis and Pearson's chi-squared tests were performed to assess differences in continuous and categorical variables, respectively. Multivariate linear regression was used to determine predictors for primary efficacy and decline in estimated glomerular filtration rate., Results: 347 consecutive patients (231 M, mean age 67.5 ± 9.1 years) were included. Median tumor diameter was smaller [2.5 vs 2.7 vs 2.6 (p = 0.03)] and RENAL Nephrometry Score (NS) was lower [6 vs 7 vs 7 (p = 0.009] for MWA compared to the RFA and cryoablation cohorts, respectively. Primary efficacy was higher in the MWA cohort [99.4% (170/171)] compared to the RFA [91.4% (85/93)] and cryoablation [92.8% (77/83)] cohorts (p = 0.001). Microwave ablation and SSRA was associated with higher primary efficacy on multivariate linear regression (p = 0.01-0.03)., Conclusion: MWA augmented by SSRA, when residual tumor is identified on intra-procedural CECT, may improve primary efficacy for cT1a RCC., (© 2022. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.)

Background Urinary continence after radical prostatectomy (RP) is an important determinant of patient quality of life. Anatomic measures at prostate MRI have been previously associated with continence outcomes, but their predictive ability and interrater agreement are unclear in comprehensive clinical models. Purpose To evaluate the predictive ability and interrater agreement of MRI-based anatomic measurements of post-RP continence when combined with clinical multivariable models. Materials and Methods In this retrospective cohort study, continence outcomes were evaluated in men who underwent RP from August 2015 to October 2019. Preoperative MRI-based anatomic measures were obtained retrospectively by four abdominal radiologists. Before participation, these radiologists completed measure-specific training. Logistic regression models were developed with clinical variables alone, MRI variables alone, and combined variables for predicting continence at 3, 6, and 12 months after RP; some patient data were missing at each time point. Interrater agreement of MRI variables was assessed by using intraclass correlation coefficients (ICCs). Results A total of 586 men were included (mean age ± standard deviation: 63 years ± 7). The proportion of patients with incontinence was 0.2% (one of 589) at baseline, 27% (145 of 529) at 3 months, 14% (63 of 465) at 6 months, and 9% (37 of 425) at 12 months. Longer coronal membranous urethra length (MUL) improved the odds of post-RP continence at all time points (odds ratio per 1 mm: 0.86 [95% CI: 0.80, 0.93], P < .001; 0.86 [95% CI: 0.78, 0.95], P = .003; and 0.79 [95% CI: 0.67, 0.91], P = .002, respectively) in models that incorporated both clinical and MRI predictors. No other MRI variables were predictive. Age and baseline urinary function score were the only other predictive clinical variables at every time point. Interrater agreement was moderate (ICC, 0.62) for MUL among readers with measure-specific prostate MRI training and poor among those without the training (ICC, 0.38). Conclusion Preoperative MRI-measured coronal membranous urethra length was an independent predictor of urinary continence after prostatectomy. © RSNA, 2022 Online supplemental material is available for this article.

Adrenal incidentalomas are common findings discovered at abdominal CT and MRI, yet the most appropriate management remains controversial and guidelines vary. The Society of Abdominal Radiology (SAR) Disease-Focused Panel on Adrenal Neoplasms sought to determine the practice patterns of abdominal radiologists regarding the interpretation and management of adrenal incidentalomas. An electronic survey consisting of eleven multiple choice questions about adrenal incidentalomas was developed and distributed to the email list of current and past SAR members. The response rate was 11.8% (423/3581) and most respondents were academic radiologists (80.6%). The 2017 American College of Radiology White Paper was the most used guideline, yet the management of indeterminate adrenal incidentalomas was highly variable with no single management option reaching a majority. Hormonal evaluation and endocrinology consultation was most often rarely or never recommended. The results of the survey indicate wide variability in the interpretation of imaging findings and management recommendations for incidental adrenal nodules among surveyed radiologists. Further standardization of adrenal incidentaloma guidelines and education of radiologists is needed., (© 2022. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.)

This observer study investigates the effect of computerized artificial intelligence (AI)-based decision support system (CDSS-T) on physicians' diagnostic accuracy in assessing bladder cancer treatment response. The performance of 17 observers was evaluated when assessing bladder cancer treatment response without and with CDSS-T using pre- and post-chemotherapy CTU scans in 123 patients having 157 pre- and post-treatment cancer pairs. The impact of cancer case difficulty, observers' clinical experience, institution affiliation, specialty, and the assessment times on the observers' diagnostic performance with and without using CDSS-T were analyzed. It was found that the average performance of the 17 observers was significantly improved ( p = 0.002) when aided by the CDSS-T. The cancer case difficulty, institution affiliation, specialty, and the assessment times influenced the observers' performance without CDSS-T. The AI-based decision support system has the potential to improve the diagnostic accuracy in assessing bladder cancer treatment response and result in more consistent performance among all physicians.

Objective: To evaluate the effect of intravenous iodinated contrast on estimated glomerular filtration rate (eGFR) when administered immediately after thermal ablation of clinically localized T1a (cT1a) renal cell carcinoma (RCC)., Methods: This HIPAA-compliant, dual-center retrospective study was performed under a waiver of informed consent. Three hundred forty-two consecutive patients with cT1a biopsy-proven RCC were treated with percutaneous ablation between January 2010 and December 2017. Immediate post-ablation contrast-enhanced CT was the routine standard of care at one institution (contrast group), but not the other (control group). One-month pre- and 6-month post-ablation eGFR were compared using the Wilcoxon signed-rank test or the Kruskal-Wallis test. Multivariate linear regression was used to determine the effect of contrast on eGFR. A 1:1 propensity score matching was performed for all patients with a logistic model using patient, tumor, and procedural covariates., Results: In total, 246 patients (158 M; median age 69 years, IQR 62-74) were included. Median tumor diameter (2.4 vs 2.5, p = 0.23) and RENAL nephrometry scores (6 vs 6, p = 0.92), surrogates for ablation zone size, were similar. Baseline kidney function was similar for the control and contrast groups, respectively (median eGFR: 70 vs 74 mL/min/1.73 m 2 , p = 0.29). There was an expected mild decline in eGFR after ablation (control: 70 vs 60 mL/min/1.73 m 2 , p < 0.001; contrast: 75 vs 71 mL/min/1.73 m 2 , p = 0.001). Intravenous iodinated contrast was not associated with a decline in eGFR on multivariate linear regression (1.91, 95% CI - 3.43-7.24, p = 0.46) or 1:1 propensity score-matched model (- 0.33, 95% CI - 6.81-6.15, p = 0.92)., Conclusion: Intravenous iodinated contrast administered during ablation of cT1a RCC has no effect on eGFR., Key Points: • Intravenous iodinated contrast administered during thermal ablation of clinically localized T1a renal cell carcinoma has no effect on kidney function. • Thermal ablation of clinically localized T1a renal cell carcinoma results in a mild decline in kidney function. • A decline in kidney function is similar for radiofrequency and microwave ablation of clinically localized T1a renal cell carcinoma., (© 2021. European Society of Radiology.)

Objective: Spigelian hernia is an uncommon congenital or acquired defect in the transversus abdominis aponeurosis with non-specific symptoms posing a diagnostic challenge. There is a paucity of radiology literature on imaging findings of Spigelian hernia. The objective of this study is to explore the role of MDCT in evaluating Spigelian hernia along with clinical and surgical implications., Materials and Methods: In this IRB approved, HIPAA compliant retrospective observational analysis MDCT imaging findings of 43 Spigelian hernias were evaluated by two fellowship-trained radiologists. Imaging features evaluated were: presence of Spigelian hernia, laterality, relation to "hernia belt" (between 0 and 6 cm cranial to an imaginary axial line between both anterior superior iliac spines), the hernia neck and sac sizes, hernia content, and other coexistent hernias (umbilical, incisional, inguinal). Patient's demographics (age, gender, BMI, conditions with increased intra-abdominal pressure) were also recorded for any correlation., Results: 60% (26/43) of Spigelian hernias were located below the hernia belt while 33% (14/43) within the hernia belt and 7% (3/43) above the hernia belt. The most common subtype of Spigelian hernia encountered was interparietal (84%). The mean hernia neck diameter was 3.4 cm, mean hernia sac volume was 329 cc. Hernia content included: fat (43/43) bowel (23/43), fluid (3/43). 3 patients had no clinical history provided, the remaining 37 patients' clinical presentation was asymptomatic in 73% (27/37), acute abdominal pain in 5% (2/37) and chronic abdominal pain in 22% (8/37). None of the hernia were incarcerated and none of the patients underwent emergent surgery. No significant correlation was noted between Spigelian hernia and causes of increased intra-abdominal pressure. 90% of our patients had other abdominal hernias. 30.9 was the mean BMI (20.8-69.1)., Conclusion: Most of the Spigelian hernia occurred below the traditionally described hernia belt and the majority are of interparietal subtype that can be best diagnosed with MDCT in contrast to physical examination., (Copyright © 2021 Elsevier Inc. All rights reserved.)

Context: Adrenal tumors in noncancer patients are common., Objective: Evaluate performance of 18F-fluorodeoxyglucose positron emission tomography computed tomography (18F-FDG-PET/CT) in distinguishing between benign and malignant adrenal tumors., Design: Retrospective chart review 2010-2019., Setting: Academic institution., Patients: One hundred and seventeen noncancer patients, defined as having no history of cancer or with cancer in remission for ≥5 years, completed 18F-FDG-PET/CT to evaluate adrenal masses, with pathologic diagnoses or imaging follow-up (≥12 months)., Intervention: 18F-FDG-PET/CT of 117 indeterminate adrenal masses., Main Outcome Measures: Receiver operator characteristic curve of the ratios of adrenal lesion standardized uptake value (SUV)max to liver SUVmean and of adrenal lesion SUVmax to aortic arch blood pool SUVmean were constructed., Results: Seventy benign and 47 malignant masses (35 adrenocortical carcinomas [ACCs], 12 adrenal metastases) were identified. Malignant masses had higher median liver SUV and blood pool SUV ratios than benign masses (6.2 and 7.4 vs 1.4 and 2.0, P < .001). Median liver and blood pool SUV ratios of ACC (6.1 and 7.3, respectively) and metastases (6.7 and 7.7, respectively) were higher than those of than adenomas (1.4 and 2.2, P < .05 for all comparisons). Optimal liver SUV ratio to discern between benign and malignant masses was 2.5, yielding 85% sensitivity, 90% specificity, and 7 false negative results (including 3 ACCs). Optimal blood pool SUV ratio was 3.4, yielding 83% sensitivity, 90% specificity, and 8 false negative results (including 4 ACCs)., Conclusion: When used in conjunction with other clinical assessments, 18F-FDG-PET/CT can be a valuable tool in evaluating adrenal masses in noncancer patients., (© The Author(s) 2021. Published by Oxford University Press on behalf of the Endocrine Society. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.)

Importance: Neck ultrasonography, a mainstay of long-term surveillance for recurrence of differentiated thyroid cancer (DTC), is routinely used by endocrinologists, general surgeons, and otolaryngologists; however, physician confidence in their ability to use ultrasonography to identify lymph nodes suggestive of cancer recurrence remains unknown., Objective: To evaluate physicians' posttreatment surveillance practices for DTC recurrence, specifically their use of and confidence in ultrasonography., Design, Setting, and Participants: Cross-sectional study of 448 physicians in private and academic hospitals who completed a survey on DTC posttreatment practices from October 2018 to August 2019 (response rate, 69%) and self-reported involvement in long-term surveillance for thyroid cancer recurrence. Physicians were identified by patients affiliated with the Surveillance, Epidemiology, and End Results Program registries in Georgia State and Los Angeles County. Of the respondents, 320 physicians who reported involvement with DTC surveillance were included in the analysis., Main Outcomes and Measures: Physician-reported long-term surveillance practices for DTC, including frequency of use and level of confidence in ultrasonography for detecting lymph nodes suggestive of cancer recurrence., Results: In the cohort of 320 physicians who reported involvement with DTC surveillance, 186 (60%) had been in practice for 10 years to less than 30 years; 209 (68%) were White; and 212 (66%) were men. The physicians included 170 (56%) endocrinologists, 67 (21%) general surgeons, and 75 (23%) otolaryngologists. Just 84 (27%) physicians reported personally performing bedside ultrasonography. Only 57 (20%) had high confidence (rated quite or extremely confident) in their ability to use bedside ultrasonography to identify lymph nodes suggestive of recurrence; 94 (33%) did not report high confidence in either their ability or a radiologist's ability to use ultrasonography to detect recurrence. Higher confidence in ultrasonography was associated with the general surgery subspecialty (odds ratio [OR], 5.7; 95% CI, 2.2-14.4; reference endocrinology) and with treating a higher number of patients per year (>50 patients: OR, 14.4; 95% CI, 4.4-47.4; 31-50 patients: OR, 8.4; 95% CI, 2.6-26.7; 11-30 patients: OR, 4.3; 95% CI, 1.5-12.1; reference 0-10 patients)., Conclusions and Relevance: Given the importance of neck ultrasonography in long-term surveillance for thyroid cancer, these findings of physicians' low confidence in their own ability and that of radiologists to use ultrasonography to detect recurrence point to a major obstacle to standardizing long-term DTC surveillance practices.

We evaluated the intraobserver variability of physicians aided by a computerized decision-support system for treatment response assessment (CDSS-T) to identify patients who show complete response to neoadjuvant chemotherapy for bladder cancer, and the effects of the intraobserver variability on physicians' assessment accuracy. A CDSS-T tool was developed that uses a combination of deep learning neural network and radiomic features from computed tomography (CT) scans to detect bladder cancers that have fully responded to neoadjuvant treatment. Pre- and postchemotherapy CT scans of 157 bladder cancers from 123 patients were collected. In a multireader, multicase observer study, physician-observers estimated the likelihood of pathologic T0 disease by viewing paired pre/posttreatment CT scans placed side by side on an in-house-developed graphical user interface. Five abdominal radiologists, 4 diagnostic radiology residents, 2 oncologists, and 1 urologist participated as observers. They first provided an estimate without CDSS-T and then with CDSS-T. A subset of cases was evaluated twice to study the intraobserver variability and its effects on observer consistency. The mean areas under the curves for assessment of pathologic T0 disease were 0.85 for CDSS-T alone, 0.76 for physicians without CDSS-T and improved to 0.80 for physicians with CDSS-T ( P = .001) in the original evaluation, and 0.78 for physicians without CDSS-T and improved to 0.81 for physicians with CDSS-T ( P = .010) in the repeated evaluation. The intraobserver variability was significantly reduced with CDSS-T ( P < .0001). The CDSS-T can significantly reduce physicians' variability and improve their accuracy for identifying complete response of muscle-invasive bladder cancer to neoadjuvant chemotherapy., Competing Interests: Conflict of Interest: None reported., (© 2020 The Authors. Published by Grapho Publications, LLC.)

OBJECTIVE. The objective of our study was to compare diagnostic accuracy and reliability of the 2017 American College of Radiology (ACR) Thyroid Imaging Reporting and Data System (TI-RADS) and 2015 American Thyroid Association (ATA) classifications for thyroid nodules. MATERIALS AND METHODS. This study was a retrospective cohort study of 1947 consecutive thyroid nodules sampled with fine-needle aspiration (FNA) from 2007 to 2016. Reviewers assigned TI-RADS scores to all nodules while blinded to clinical outcome and histologic diagnosis and compared TI-RADS scores with nodule-specific ATA scores from the same cohort. Five blinded radiologists independently assigned TI-RADS scores to a subset of 151 nodules (interrater agreement). The primary outcome was a comparison of the diagnostic accuracy of the TI-RADS and ATA classifications using ROC curve analysis. The reference standard was cytopathologic diagnosis according to the Bethesda system. Interrater agreement was determined using intraclass correlation (ICC) and kappa statistics. RESULTS. Of 1947 sampled thyroid nodules, 31.8% ( n = 620) met TI-RADS criteria for FNA, 28.0% ( n = 545) met TI-RADS criteria for follow-up, and 40.2% ( n = 782) met TIRADS criteria to be ignored. Applying the 2015 ATA criteria resulted in recommendations of immediate FNA procedures for more nodules than applying the 2017 TI-RADS (ATA vs TIRADS: 62.3% [1213/1947] vs 31.8% [620/1947], p < 0.0001). Diagnostic accuracies (AUCs: TI-RADS score, 0.684 [95% CI, 0.644-0.724]; ATA, 0.686 [95% CI, 0.646-0.725]) and false-negative rates (TI-RADS, 2.2% [43/1947]; ATA, 2.4% [47/1947]) for the two classifications were similar ( p = 0.75). Overall interrater agreement was fair for both (ICCs: TI-RADS, 0.437 [95% CI, 0.357-0.520]; ATA classification, 0.460 [95% CI, 0.391-0.533]). CONCLUSION. The 2017 ACR TI-RADS and 2015 ATA classifications have similar diagnostic accuracies and interrater agreement, but TI-RADS results in fewer nodules being recommended for immediate FNAs and more nodules being recommended for imaging surveillance.

Rationale and Objectives: To evaluate whether a computed tomography (CT)-based computerized decision-support system for muscle-invasive bladder cancer treatment response assessment (CDSS-T) can improve identification of patients who have responded completely to neoadjuvant chemotherapy., Materials and Methods: Following Institutional Review Board approval, pre-chemotherapy and post-chemotherapy CT scans of 123 subjects with 157 muscle-invasive bladder cancer foci were collected retrospectively. CT data were analyzed with a CDSS-T that uses a combination of deep-learning convolutional neural network and radiomic features to distinguish muscle-invasive bladder cancers that have fully responded to neoadjuvant treatment from those that have not. Leave-one-case-out cross-validation was used to minimize overfitting. Five attending abdominal radiologists, four diagnostic radiology residents, two attending oncologists, and one attending urologist estimated the likelihood of pathologic T0 disease (complete response) by viewing paired pre/post-treatment CT scans placed side-by-side on an internally-developed graphical user interface. The observers provided an estimate without use of CDSS-T and then were permitted to revise their estimate after a CDSS-T-derived likelihood score was displayed. Observer estimates were analyzed with multi-reader, multi-case receiver operating characteristic methodology. The area under the curve (AUC) and the statistical significance of the difference were estimated., Results: The mean AUCs for assessment of pathologic T0 disease were 0.80 for CDSS-T alone, 0.74 for physicians not using CDSS-T, and 0.77 for physicians using CDSS-T. The increase in the physicians' performance was statistically significant (P < .05)., Conclusion: CDSS-T improves physician performance for identifying complete response of muscle-invasive bladder cancer to neoadjuvant chemotherapy., (Copyright © 2018 The Association of University Radiologists. Published by Elsevier Inc. All rights reserved.)

Objectives: To develop a U-Net-based deep learning approach (U-DL) for bladder segmentation in computed tomography urography (CTU) as a part of a computer-assisted bladder cancer detection and treatment response assessment pipeline., Materials and Methods: A dataset of 173 cases including 81 cases in the training/validation set (42 masses, 21 with wall thickening, 18 normal bladders), and 92 cases in the test set (43 masses, 36 with wall thickening, 13 normal bladders) were used with Institutional Review Board approval. An experienced radiologist provided three-dimensional (3D) hand outlines for all cases as the reference standard. We previously developed a bladder segmentation method that used a deep learning convolution neural network and level sets (DCNN-LS) within a user-input bounding box. However, some cases with poor image quality or with advanced bladder cancer spreading into the neighboring organs caused inaccurate segmentation. We have newly developed an automated U-DL method to estimate a likelihood map of the bladder in CTU. The U-DL did not require a user-input box and the level sets for postprocessing. To identify the best model for this task, we compared the following models: (a) two-dimensional (2D) U-DL and 3D U-DL using 2D CT slices and 3D CT volumes, respectively, as input, (b) U-DLs using CT images of different resolutions as input, and (c) U-DLs with and without automated cropping of the bladder as an image preprocessing step. The segmentation accuracy relative to the reference standard was quantified by six measures: average volume intersection ratio (AVI), average percent volume error (AVE), average absolute volume error (AAVE), average minimum distance (AMD), average Hausdorff distance (AHD), and the average Jaccard index (AJI). As a baseline, the results from our previous DCNN-LS method were used., Results: In the test set, the best 2D U-DL model achieved AVI, AVE, AAVE, AMD, AHD, and AJI values of 93.4 ± 9.5%, -4.2 ± 14.2%, 9.2 ± 11.5%, 2.7 ± 2.5 mm, 9.7 ± 7.6 mm, 85.0 ± 11.3%, respectively, while the corresponding measures by the best 3D U-DL were 90.6 ± 11.9%, -2.3 ± 21.7%, 11.5 ± 18.5%, 3.1 ± 3.2 mm, 11.4 ± 10.0 mm, and 82.6 ± 14.2%, respectively. For comparison, the corresponding values obtained with the baseline method were 81.9 ± 12.1%, 10.2 ± 16.2%, 14.0 ± 13.0%, 3.6 ± 2.0 mm, 12.8 ± 6.1 mm, and 76.2 ± 11.8%, respectively, for the same test set. The improvement for all measures between the best U-DL and the DCNN-LS were statistically significant (P < 0.001)., Conclusion: Compared to a previous DCNN-LS method, which depended on a user-input bounding box, the U-DL provided more accurate bladder segmentation and was more automated than the previous approach., (© 2019 American Association of Physicists in Medicine.)

We compared the performance of different Deep learning-convolutional neural network (DL-CNN) models for bladder cancer treatment response assessment based on transfer learning by freezing different DL-CNN layers and varying the DL-CNN structure. Pre- and posttreatment computed tomography scans of 123 patients (cancers, 129; pre- and posttreatment cancer pairs, 158) undergoing chemotherapy were collected. After chemotherapy 33% of patients had T0 stage cancer (complete response). Regions of interest in pre- and posttreatment scans were extracted from the segmented lesions and combined into hybrid pre -post image pairs (h-ROIs). Training (pairs, 94; h-ROIs, 6209), validation (10 pairs) and test sets (54 pairs) were obtained. The DL-CNN consisted of 2 convolution (C1-C2), 2 locally connected (L3-L4), and 1 fully connected layers. The DL-CNN was trained with h-ROIs to classify cancers as fully responding (stage T0) or not fully responding to chemotherapy. Two radiologists provided lesion likelihood of being stage T0 posttreatment. The test area under the ROC curve (AUC) was 0.73 for T0 prediction by the base DL-CNN structure with randomly initialized weights. The base DL-CNN structure with pretrained weights and transfer learning (no frozen layers) achieved test AUC of 0.79. The test AUCs for 3 modified DL-CNN structures (different C1-C2 max pooling filter sizes, strides, and padding, with transfer learning) were 0.72, 0.86, and 0.69. For the base DL-CNN with (C1) frozen, (C1-C2) frozen, and (C1-C2-L3) frozen, the test AUCs were 0.81, 0.78, and 0.71, respectively. The radiologists' AUCs were 0.76 and 0.77. DL-CNN performed better with pretrained than randomly initialized weights.

Purpose: To determine the yield of routine image-guided core biopsy of renal cell carcinoma (RCC) thermal ablation zones., Methods: Institutional review board approval was obtained for this Health Insurance Portability and Accountability Act-compliant quality improvement effort. Routine core biopsy of RCC ablation zones was performed 2 months postablation from July 2003 to December 2014. Routine nicotinamide adenine dinucleotide staining was performed by specialized genitourinary pathologists to assess cell viability. The original purpose of performing routine postablation biopsy was to verify, in addition to imaging, whether the mass was completely treated. Imaging was stratified as negative, indeterminate, or positive for viable malignancy. Histology was stratified as negative, indeterminate, positive, or nondiagnostic for viable malignancy. Histology results were compared to prebiopsy imaging findings., Results: Routine ablation zone biopsy was performed after 50% (146/292) of index ablations (24 cryoablations, 122 radiofrequency ablations), and postablation imaging was performed more often with multiphasic computed tomography than magnetic resonance imaging (100 vs 46, p < 0.0001). When imaging was negative (n = 117), biopsy added no additional information (92% [n = 108] negative, 0.9% [n = 1] indeterminate, 7% [n = 8] nondiagnostic). When imaging was indeterminate (n = 19), 11% (n = 2) of biopsies had viable RCC and 89% (n = 17) were negative. When imaging was positive, biopsy detected viable neoplasm in only 10% (1/10) of cases; 80% (8/10) were negative and 10% (1/10) were nondiagnostic., Conclusion: Routine biopsy of renal ablation zones to validate postablation imaging results was not value-added and therefore was discontinued at the study institution., (Copyright © 2018. Published by Elsevier Inc.)

Purpose: We are developing a computerized segmentation tool for the inner and outer bladder wall as a part of an image analysis pipeline for CT urography (CTU)., Materials and Methods: A data set of 172 CTU cases was collected retrospectively with Institutional Review Board (IRB) approval. The data set was randomly split into two independent sets of training (81 cases) and testing (92 cases) which were manually outlined for both the inner and outer wall. We trained a deep-learning convolutional neural network (DL-CNN) to distinguish the bladder wall from the inside and outside of the bladder using neighborhood information. Approximately, 240 000 regions of interest (ROIs) of 16 × 16 pixels in size were extracted from regions in the training cases identified by the manually outlined inner and outer bladder walls to form a training set for the DL-CNN; half of the ROIs were selected to include the bladder wall and the other half were selected to exclude the bladder wall with some of these ROIs being inside the bladder and the rest outside the bladder entirely. The DL-CNN trained on these ROIs was applied to the cases in the test set slice-by-slice to generate a bladder wall likelihood map where the gray level of a given pixel represents the likelihood that a given pixel would belong to the bladder wall. We then used the DL-CNN likelihood map as an energy term in the energy equation of a cascaded level sets method to segment the inner and outer bladder wall. The DL-CNN segmentation with level sets was compared to the three-dimensional (3D) hand-segmented contours as a reference standard., Results: For the inner wall contour, the training set achieved the average volume intersection, average volume error, average absolute volume error, and average distance of 90.0 ± 8.7%, -4.2 ± 18.4%, 12.9 ± 13.9%, and 3.0 ± 1.6 mm, respectively. The corresponding values for the test set were 86.9 ± 9.6%, -8.3 ± 37.7%, 18.4 ± 33.8%, and 3.4 ± 1.8 mm, respectively. For the outer wall contour, the training set achieved the values of 93.7 ± 3.9%, -7.8 ± 11.4%, 10.3 ± 9.3%, and 3.0 ± 1.2 mm, respectively. The corresponding values for the test set were 87.5 ± 9.9%, -1.2 ± 20.8%, 11.9 ± 17.0%, and 3.5 ± 2.3 mm, respectively., Conclusions: Our study demonstrates that DL-CNN-assisted level sets can effectively segment bladder walls from the inner bladder and outer structures despite a lack of consistent distinctions along the inner wall. However, even with the addition of level sets, the inner and outer walls may still be over-segmented and the DL-CNN-assisted level sets may incorrectly segment parts of the prostate that overlap with the outer bladder wall. The outer wall segmentation was improved compared to our previous method and the DL-CNN-assisted level sets were also able to segment the inner bladder wall with similar performance. This study shows the DL-CNN-assisted level set segmentation tool can effectively segment the inner and outer wall of the bladder., (© 2018 American Association of Physicists in Medicine.)

Background: The 2015 American Thyroid Association (ATA) guidelines have been proposed to aid in the management of thyroid nodules by determining whether fine needle aspiration is indicated., Objective: To determine whether the ATA guidelines contribute to the overdiagnosis of thyroid cancer., Patients and Methods: This was a retrospective cohort study of ultrasound-imaged thyroid nodules (n = 1947) consecutively aspirated at a tertiary care center from 1 October 2009 to 22 February 2016. Nodules were retrospectively reviewed, assigned a 2015 ATA morphology, and placed into one of five 2015 ATA categories of risk (ATA-1, <1% risk of malignancy; ATA-2, <3% risk; ATA-3, 5% to 10% risk, ATA-4: 10% to 20% risk; ATA-5, >70% to 90% risk) by a reader who was blinded to cytology. ATA category was compared with cytopathology. The positive predictive value (PPV) of each ATA category was calculated with respect to cancer. Numbers needed to aspirate and Pearson correlations were calculated. Interrater agreement for ATA category across five readers was assessed., Results: The PPV for cancer increased by ATA category [category 1 to 5, respectively: 0% (0/14), 2% (4/249), 5% (36/733), 12% (104/850), 28% (28/101)]. The number needed to sample to detect one papillary cancer was 125 (ATA-2), 49 (ATA-3), 13 (ATA-4), and 5 (ATA-5). The overall interrater agreement for ATA score across all five readers was fair (intraclass correlation coefficient 0.460)., Conclusions: The 2015 ATA guidelines stratify risk for thyroid cancer; however, the stratification system is overly optimistic regarding cancer detection rates for the higher-risk nodules, and there is only fair interrater agreement.

Context: A subset of thyroid carcinomas expresses an oncogenic paired box 8 (PAX8) and peroxisome proliferator activated receptor γ (PPARγ) fusion protein (PPFP). The PPARγ/PPFP ligand pioglitazone is highly therapeutic in a transgenic mouse model of PPFP thyroid carcinoma, but whether pioglitazone is therapeutic in patients with PPFP thyroid carcinoma is unknown., Case Description: Tumor blocks from 40 patients with progressive thyroid cancer despite standard-of-care therapy were screened for PPFP, and the tumor from only one patient (2.5%) was positive. The patient had a 6.0-cm acetabular soft tissue metastasis from Hürthle cell carcinoma that caused severe pain on weight bearing and had a serum thyroglobulin level of 1974 ng/mL. After 24 weeks of therapy with pioglitazone, the metastatic lesion was 3.9 cm, the thyroglobulin level was 49.4 ng/mL, and the patient was pain-free. Thirteen months after discontinuation of pioglitazone, the metastatic lesion was 3.6 cm, the thyroglobulin level was 4.7 ng/mL, and the patient remained pain-free., Conclusions: Pioglitazone may be therapeutic in patients with PPFP thyroid cancer. However, thyroid cancers that are progressive despite standard-of-care therapy appear to only rarely express PPFP.

Rationale and Objective: We aimed to determine the frequency and clinical significance of homogeneous renal masses measuring 21-39 Hounsfield units on contrast-enhanced computed tomography (CT)., Methods: Subjects 40-69 years old undergoing portal-venous-phase contrast-enhanced abdominal CT from January 1, 2006 to December 31, 2010 with slice thickness ≤5 mm and no prior CT or magnetic resonance imaging were identified (n = 1387) for this institutional review board-approved retrospective cohort study. Images were manually reviewed by three radiologists in consensus to identify all circumscribed homogeneous renal masses (maximum of three per subject) ≥10 mm with a measured attenuation of 21-39 Hounsfield units. Exclusion criteria were known renal cancer or imaging performed for a renal indication. The primary outcome was retrospective characterization as a clinically significant mass, defined as a solid mass, a Bosniak IIF/III/IV mass, or extirpative therapy or metastatic renal cancer within 5 years' follow-up., Results: Eligible masses (n = 74) were found in 5% (63/1387) of subjects. Of those with a reference standard (n = 42), none (0% [95% CI: 0.0%-8.4%]) were determined to be clinically significant., Conclusion: Incidental renal masses on contrast-enhanced CT that are homogeneous and display an attenuation of 21-39 Hounsfield units are uncommon in patients 40-69 years of age, unlikely to be clinically significant, and may not need further imaging evaluation. If these results can be replicated in an independent and larger population, the practical definition of a benign cyst on imaging may be able to be expanded., (Copyright © 2018 The Association of University Radiologists. Published by Elsevier Inc. All rights reserved.)

Purpose: To evaluate the feasibility of using an objective computer-aided system to assess bladder cancer stage in CT Urography (CTU)., Materials and Methods: A dataset consisting of 84 bladder cancer lesions from 76 CTU cases was used to develop the computerized system for bladder cancer staging based on machine learning approaches. The cases were grouped into two classes based on pathological stage ≥ T2 or below T2, which is the decision threshold for neoadjuvant chemotherapy treatment clinically. There were 43 cancers below stage T2 and 41 cancers at stage T2 or above. All 84 lesions were automatically segmented using our previously developed auto-initialized cascaded level sets (AI-CALS) method. Morphological and texture features were extracted. The features were divided into subspaces of morphological features only, texture features only, and a combined set of both morphological and texture features. The dataset was split into Set 1 and Set 2 for two-fold cross-validation. Stepwise feature selection was used to select the most effective features. A linear discriminant analysis (LDA), a neural network (NN), a support vector machine (SVM), and a random forest (RAF) classifier were used to combine the features into a single score. The classification accuracy of the four classifiers was compared using the area under the receiver operating characteristic (ROC) curve (A z )., Results: Based on the texture features only, the LDA classifier achieved a test A z of 0.91 on Set 1 and a test A z of 0.88 on Set 2. The test A z of the NN classifier for Set 1 and Set 2 were 0.89 and 0.92, respectively. The SVM classifier achieved test A z of 0.91 on Set 1 and test A z of 0.89 on Set 2. The test A z of the RAF classifier for Set 1 and Set 2 was 0.89 and 0.97, respectively. The morphological features alone, the texture features alone, and the combined feature set achieved comparable classification performance., Conclusion: The predictive model developed in this study shows promise as a classification tool for stratifying bladder cancer into two staging categories: greater than or equal to stage T2 and below stage T2., (© 2017 American Association of Physicists in Medicine.)

Cross-sectional X-ray imaging has become the standard for staging most solid organ malignancies. However, for some malignancies such as urinary bladder cancer, the ability to accurately assess local extent of the disease and understand response to systemic chemotherapy is limited with current imaging approaches. In this study, we explored the feasibility that radiomics-based predictive models using pre- and post-treatment computed tomography (CT) images might be able to distinguish between bladder cancers with and without complete chemotherapy responses. We assessed three unique radiomics-based predictive models, each of which employed different fundamental design principles ranging from a pattern recognition method via deep-learning convolution neural network (DL-CNN), to a more deterministic radiomics feature-based approach and then a bridging method between the two, utilizing a system which extracts radiomics features from the image patterns. Our study indicates that the computerized assessment using radiomics information from the pre- and post-treatment CT of bladder cancer patients has the potential to assist in assessment of treatment response.

The role of percutaneous renal mass biopsy has continued to grow in the last decade. The incidence of small (≤4cm) renal masses has increased dramatically over the past 15 years, attributed to increased use of cross-sectional imaging and subsequent discovery of small renal masses that would otherwise go undetected. Despite increased early detection, there has been no change in the mortality rate from renal cell carcinoma over the past 15 years. Many small renal masses are not life-limiting, and imaging lacks specificity in distinguishing malignant from nonmalignant small renal masses. Thus, percutaneous biopsy has emerged as an integral part of the diagnosis of renal masses in order to better guide their management., (Copyright © 2017 Elsevier Inc. All rights reserved.)

Assessing the response of bladder cancer to neoadjuvant chemotherapy is crucial for reducing morbidity and increasing quality of life of patients. Changes in tumor volume during treatment is generally used to predict treatment outcome. We are developing a method for bladder cancer segmentation in CT using a pilot data set of 62 cases. 65 000 regions of interests were extracted from pre-treatment CT images to train a deep-learning convolution neural network (DL-CNN) for tumor boundary detection using leave-one-case-out cross-validation. The results were compared to our previous AI-CALS method. For all lesions in the data set, the longest diameter and its perpendicular were measured by two radiologists, and 3D manual segmentation was obtained from one radiologist. The World Health Organization (WHO) criteria and the Response Evaluation Criteria In Solid Tumors (RECIST) were calculated, and the prediction accuracy of complete response to chemotherapy was estimated by the area under the receiver operating characteristic curve (AUC). The AUCs were 0.73 ± 0.06, 0.70 ± 0.07, and 0.70 ± 0.06, respectively, for the volume change calculated using DL-CNN segmentation, the AI-CALS and the manual contours. The differences did not achieve statistical significance. The AUCs using the WHO criteria were 0.63 ± 0.07 and 0.61 ± 0.06, while the AUCs using RECIST were 0.65 ± 007 and 0.63 ± 0.06 for the two radiologists, respectively. Our results indicate that DL-CNN can produce accurate bladder cancer segmentation for calculation of tumor size change in response to treatment. The volume change performed better than the estimations from the WHO criteria and RECIST for the prediction of complete response.

Objective: To review our clinical T1a renal mass active surveillance (AS) cohort to determine whether renal mass biopsy was associated with maintenance of AS., Materials and Methods: From our prospectively maintained database we identified patients starting AS from June 2009 to December 2011 who had at least 5 months of radiologic follow-up, unless limited by unexpected death or delayed intervention. The primary outcome was delayed intervention. Clinical, radiologic, and pathologic variables were compared. We constructed Kaplan-Meier survival curves for maintenance of AS. Cox multivariable regression analysis was performed to assess predictors of delayed intervention., Results: We identified 118 patients who met criteria for inclusion with a median radiologic follow-up of 29.5 months. The delayed intervention group had greater initial mass size and faster growth rate compared to those who continued AS. Rate of renal mass biopsy was similar between the 2 groups. In the multivariable analysis, size >2 cm (hazard ratio [HR] 3.65, 95% confidence interval [CI] 1.28-10.38, P = .015), growth rate (continuous by mm/year: HR 1.26, 95% CI 1.12-1.41, P < .001), but not renal biopsy (HR 1.52, 95% CI 0.70-3.30, P = .29), were associated with increased risk of delayed intervention. Time-to-event curves also showed that size was closely associated with delayed intervention whereas renal mass biopsy was not., Conclusion: At our institution, growth rate and initial tumor size appear to be more influential than renal mass biopsy results in determining delayed intervention after a period of AS. Further analysis is required to determine the role of renal biopsy in the management of patients being considered for AS., (Copyright © 2016 Elsevier Inc. All rights reserved.)

Objective: To understand potential harms associated with delaying resection of small renal masses (SRMs) in patients ultimately treated, and whether these patients have factors associated with adverse pathology., Methods: Patients with SRMs (≤4cm) who underwent surgical resection at our institution (2009-2015) were classified as undergoing early resection or initial surveillance with delayed resection (defined by a time from presentation to intervention of at least 6mo). Demographic and clinical variables were compared among groups. Using multivariable logistic regression, we examined the association between delayed resection and adverse pathology (Fuhrman grade 3-4, papillary type 2, sarcomatoid histology, angiomyolipoma with epithelioid features, or stage≥pT3). For patients who underwent delayed intervention, we used similar methods to examine the association between SRM growth rate and adverse pathology., Results: Overall, 401 (81%) and 94 (19%) patients underwent early and delayed resection, respectively. Median time to resection was 84 days (interquartile range: 59-121) and 386 days (interquartile range: 272-702) (P<0.001). Patients undergoing delayed resection were older (62 vs. 58y, P = 0.01) and had smaller masses (2.3 vs. 2.7cm, P<0.001) at initial presentation. Utilization of partial vs. radical nephrectomy was similar regardless of resection timing (P = 0.5). Delayed resection was not associated with adverse pathology (P = 0.8); however, male sex was independently associated with adverse pathology (odds ratio: 1.7, 95% CI: 1.1-2.4, P = 0.009). In patients on surveillance, increasing annual SRM growth rate was associated with adverse pathology (odds ratio: 1.2, 95% CI: 1.03-1.3mm/y, P = 0.02)., Conclusions: Delayed resection was not associated with adverse pathology. Patients on surveillance with increased SRM growth rates had a modest but significant increase in the risk of adverse pathology., (Copyright © 2016 Elsevier Inc. All rights reserved.)

Objective: To compare the accuracies of renal mass biopsy (RMB) and R.E.N.A.L. nephrometry score (RNS) nomograms for predicting benign vs malignant disease, and low- vs high-risk renal tumors., Materials and Methods: We included 281 renal masses in 277 patients who had complete RNS, preoperative RMB, and final pathology from renal surgery for clinically localized renal tumors. RMB and final pathology were determined to be benign or malignant, and malignancies were classified as low-risk (Fuhrman grade I/II) or high-risk (Fuhrman grade III/IV) (benign included in low-risk group). Previously published RNS nomograms were used to determine probabilities of any cancer and high-risk cancer. The gamma statistic was used to assess strength of association between RMB or RNS with final pathology., Results: Of the 281 masses, 13 (5%) and 268 (95%) were confirmed benign and malignant, respectively, and 155 (55%) and 126 (45%) were confirmed low-risk and high-risk, respectively, on final pathology. The areas under the curve of the RNS nomograms for benign vs malignant disease and for low-risk vs high-risk renal tumors were 0.56 and 0.64, respectively. Concordances for predicting benign vs malignant disease were 99% for RMB (P < .01, gamma 0.99) and 29% for RNS nomogram (P = .16, gamma 0.38). Concordances for predicting low-risk vs high-risk renal tumors were 67% for RMB (P < .01, gamma 0.97) and 61% for RNS nomogram (P < .01, gamma 0.47), respectively., Conclusion: Although RNS nomograms are useful for discriminating between benign vs malignant renal masses, and low-risk vs high-risk renal tumors, they are outperformed by RMB., (Copyright © 2016 Elsevier Inc. All rights reserved.)

Purpose: The authors are developing a computerized system for bladder segmentation in CT urography (CTU) as a critical component for computer-aided detection of bladder cancer., Methods: A deep-learning convolutional neural network (DL-CNN) was trained to distinguish between the inside and the outside of the bladder using 160 000 regions of interest (ROI) from CTU images. The trained DL-CNN was used to estimate the likelihood of an ROI being inside the bladder for ROIs centered at each voxel in a CTU case, resulting in a likelihood map. Thresholding and hole-filling were applied to the map to generate the initial contour for the bladder, which was then refined by 3D and 2D level sets. The segmentation performance was evaluated using 173 cases: 81 cases in the training set (42 lesions, 21 wall thickenings, and 18 normal bladders) and 92 cases in the test set (43 lesions, 36 wall thickenings, and 13 normal bladders). The computerized segmentation accuracy using the DL likelihood map was compared to that using a likelihood map generated by Haar features and a random forest classifier, and that using our previous conjoint level set analysis and segmentation system (CLASS) without using a likelihood map. All methods were evaluated relative to the 3D hand-segmented reference contours., Results: With DL-CNN-based likelihood map and level sets, the average volume intersection ratio, average percent volume error, average absolute volume error, average minimum distance, and the Jaccard index for the test set were 81.9% ± 12.1%, 10.2% ± 16.2%, 14.0% ± 13.0%, 3.6 ± 2.0 mm, and 76.2% ± 11.8%, respectively. With the Haar-feature-based likelihood map and level sets, the corresponding values were 74.3% ± 12.7%, 13.0% ± 22.3%, 20.5% ± 15.7%, 5.7 ± 2.6 mm, and 66.7% ± 12.6%, respectively. With our previous CLASS with local contour refinement (LCR) method, the corresponding values were 78.0% ± 14.7%, 16.5% ± 16.8%, 18.2% ± 15.0%, 3.8 ± 2.3 mm, and 73.9% ± 13.5%, respectively., Conclusions: The authors demonstrated that the DL-CNN can overcome the strong boundary between two regions that have large difference in gray levels and provides a seamless mask to guide level set segmentation, which has been a problem for many gradient-based segmentation methods. Compared to our previous CLASS with LCR method, which required two user inputs to initialize the segmentation, DL-CNN with level sets achieved better segmentation performance while using a single user input. Compared to the Haar-feature-based likelihood map, the DL-CNN-based likelihood map could guide the level sets to achieve better segmentation. The results demonstrate the feasibility of our new approach of using DL-CNN in combination with level sets for segmentation of the bladder.

Purpose: A previously published risk stratification algorithm based on renal mass biopsy and radiographic mass size was useful to designate surveillance vs the need for immediate treatment of small renal masses. Nonetheless, there were some incorrect assignments, most notably when renal mass biopsy indicated low risk malignancy but final pathology revealed high risk malignancy. We studied other factors that might improve the accuracy of this algorithm., Materials and Methods: For 202 clinically localized small renal masses in a total of 200 patients with available R.E.N.A.L. (radius, exophytic/endophytic, nearness of tumor to collecting system or sinus, anterior/posterior, hilar tumor touching main renal artery or vein and location relative to polar lines) nephrometry score, preoperative renal mass biopsy and final pathology we assessed the accuracy of management assignment (surveillance vs treatment) based on the previously published risk stratification algorithm as confirmed by final pathology. Logistic regression was used to determine whether other factors (age, gender, R.E.N.A.L. score, R.E.N.A.L. score components and nomograms based on R.E.N.A.L. score) could improve assignment., Results: Of the 202 small renal masses 53 (26%) were assigned to surveillance and 149 (74%) were assigned to treatment by the risk stratification algorithm. Of the 53 lesions assigned to surveillance 25 (47%) had benign/favorable renal mass biopsy histology while in 28 (53%) intermediate renal mass biopsy histology showed a mass size less than 2 cm. Nine of these 53 masses (17%) were incorrectly assigned to surveillance in that final pathology indicated the need for treatment (ie intermediate histology and a mass greater than 2 cm or unfavorable histology). Final pathology confirmed a correct assignment in all 149 masses assigned to treatment. None of the additional parameters assessed improved assignment with statistical significance., Conclusions: Age, gender, R.E.N.A.L. nephrometry score, R.E.N.A.L. score components and nomograms or combinations of these factors do not improve the predictive performance of a small renal mass management risk stratification algorithm based on renal mass biopsy and radiographic mass size., (Copyright © 2016 American Urological Association Education and Research, Inc. Published by Elsevier Inc. All rights reserved.)

Purpose: Data guiding selection of nonsurgical treatment of hepatocellular carcinoma (HCC) are lacking. We therefore compared outcomes between stereotactic body radiotherapy (SBRT) and radiofrequency ablation (RFA) for HCC., Patients and Methods: From 2004 to 2012, 224 patients with inoperable, nonmetastatic HCC underwent RFA (n = 161) to 249 tumors or image-guided SBRT (n = 63) to 83 tumors. We applied inverse probability of treatment weighting to adjust for imbalances in treatment assignment. Freedom from local progression (FFLP) and toxicity were retrospectively analyzed., Results: RFA and SBRT groups were similar with respect to number of lesions treated per patient, type of underlying liver disease, and tumor size (median, 1.8 v 2.2 cm in maximum diameter; P = .14). However, the SBRT group had lower pretreatment Child-Pugh scores (P = .003), higher pretreatment alpha-fetoprotein levels (P = .04), and a greater number of prior liver-directed treatments (P < .001). One- and 2-year FFLP for tumors treated with RFA were 83.6% and 80.2% v 97.4% and 83.8% for SBRT. Increasing tumor size predicted for FFLP in patients treated with RFA (hazard ratio [HR], 1.54 per cm; P = .006), but not with SBRT (HR, 1.21 per cm; P = .617). For tumors ≥ 2 cm, there was decreased FFLP for RFA compared with SBRT (HR, 3.35; P = .025). Acute grade 3+ complications occurred after 11% and 5% of RFA and SBRT treatments, respectively (P = .31). Overall survival 1 and 2 years after treatment was 70% and 53% after RFA and 74% and 46% after SBRT., Conclusion: Both RFA and SBRT are effective local treatment options for inoperable HCC. Although these data are retrospective, SBRT appears to be a reasonable first-line treatment of inoperable, larger HCC., Competing Interests: Authors’ disclosures of potential conflicts of interest are found in the article online at www.jco.org. Author contributions are found at the end of this article., (© 2015 by American Society of Clinical Oncology.)

Incidentally discovered adrenal masses are common and the clinical evaluation and surveillance aims to diagnose hormone excess and malignancy. Adrenocortical cancer (ACC) is a very rare malignancy. This study aims to define the imaging characteristics of adrenal tumors preceding the diagnosis of ACC. Patients with prior (>5 months) adrenal tumors (<6 cm) subsequently diagnosed with ACC were identified in a large registry at a tertiary referral center. Retrospective chart and image review for patient characteristics and initial, interval, and diagnostic imaging characteristics (size, homogeneity, borders, density, growth rate, etc.) was conducted. Twenty patients with a diagnosis of ACC and a prior adrenal tumor were identified among 422 patients with ACC. Of these, 17 patients were initially imaged with CT and 3 with MR. Only 2 of the 20 patients had initial imaging characteristics suggestive of a benign lesion. Of initial tumors, 25% were <2 cm in size. Surveillance led to the diagnosis of ACC within 24 months in 50% of patients. The growth pattern was variable with some lesions showing long-term stability (up to 8 years) in size. In conclusion, antecedent lesions in patients with a diagnosis of ACC are often indeterminate by imaging criteria and can be small. Surveillance over 2 years detected only 50% of ACCs. Current practice and guidelines are insufficient in diagnosing ACCs. Given the rarity of ACC, the increased risk and health care costs of additional evaluation may not be warranted.

Objective: The purpose of this study was to evaluate the accuracy of our autoinitialized cascaded level set 3D segmentation system as compared with the World Health Organization (WHO) criteria and the Response Evaluation Criteria In Solid Tumors (RECIST) for estimation of treatment response of bladder cancer in CT urography., Materials and Methods: CT urograms before and after neoadjuvant chemo-therapy treatment were collected from 18 patients with muscle-invasive localized or locally advanced bladder cancers. The disease stage as determined on pathologic samples at cystectomy after chemotherapy was considered as reference standard of treatment response. Two radiologists measured the longest diameter and its perpendicular on the pre- and posttreatment scans. Full 3D contours for all tumors were manually outlined by one radiologist. The autoinitialized cascaded level set method was used to automatically extract 3D tumor boundary. The prediction accuracy of pT0 disease (complete response) at cystectomy was estimated by the manual, autoinitialized cascaded level set, WHO, and RECIST methods on the basis of the AUC., Results: The AUC for prediction of pT0 disease at cystectomy was 0.78 ± 0.11 for autoinitialized cascaded level set compared with 0.82 ± 0.10 for manual segmentation. The difference did not reach statistical significance (p = 0.67). The AUCs using RECIST criteria were 0.62 ± 0.16 and 0.71 ± 0.12 for the two radiologists, both lower than those of the two 3D methods. The AUCs using WHO criteria were 0.56 ± 0.15 and 0.60 ± 0.13 and thus were lower than all other methods., Conclusion: The pre- and posttreatment 3D volume change estimates obtained by the radiologist's manual outlines and the autoinitialized cascaded level set segmentation were more accurate for irregularly shaped tumors than were those based on RECIST and WHO criteria.

Purpose: The authors are developing a computer-aided detection system for bladder cancer on CT urography (CTU). In this study, the authors focused on developing a system for detecting masses fully or partially within the contrast-enhanced (C) region of the bladder., Methods: With IRB approval, a data set of 70 patients with biopsy-proven bladder lesions fully or partially immersed within the contrast-enhanced region (C region) of the bladder was collected for this study: 35 patients for the training set (39 malignant, 7 benign lesions) and 35 patients for the test set (49 malignant, 4 benign lesions). The bladder in the CTU images was automatically segmented using the authors' conjoint level set analysis and segmentation system, which they developed specifically to segment the bladder. A closed contour of the C region of the bladder was generated by maximum intensity projection using the property that the dependently layering contrast material in the bladder will be filled consistently to the same level along all CTU slices due to gravity. Potential lesion candidates within the C region contour were found using the authors' Straightened Periphery ANalysis (SPAN) method. SPAN transforms a bladder wall to a straightened thickness profile, marks suspicious pixels on the profile, and clusters them into regions of interest to identify potential lesion candidates. The candidate regions were automatically segmented using the authors' autoinitialized cascaded level set segmentation method. Twenty-three morphological features were automatically extracted from the segmented lesions. The training set was used to determine the best subset of these features using simplex optimization with the leave-one-out case method. A linear discriminant classifier was designed for the classification of bladder lesions and false positives. The detection performance was evaluated on the independent test set by free-response receiver operating characteristic analysis., Results: At the prescreening step, the authors' system achieved 84.4% sensitivity with an average of 4.3 false positives per case (FPs/case) for the training set, and 84.9% sensitivity with 5.4 FPs/case for the test set. After linear discriminant analysis (LDA) classification with the selected features, the FP rate improved to 2.5 FPs/case for the training set, and 4.3 FPs/case for the test set without missing additional true lesions. By varying the threshold for the LDA scores, at 2.5 FPs/case, the sensitivities were 84.4% and 81.1% for the training and test sets, respectively. At 1.7 FPs/case, the sensitivities decreased to 77.8% and 75.5%, respectively., Conclusions: The results demonstrate the feasibility of the authors' method for detection of bladder lesions fully or partially immersed in the contrast-enhanced region of CTU.

Background: There is a paucity of literature describing and comparing the imaging features of adrenocortical adenomas and carcinomas in children and adolescents., Objective: To document the CT and MRI features of adrenocortical neoplasms in a pediatric population and to determine whether imaging findings (other than metastatic disease) can distinguish adenomas from carcinomas., Materials and Methods: We searched institutional medical records to identify pediatric patients with adrenocortical neoplasms. Pre-treatment CT and MRI examinations were reviewed by two radiologists in consensus, and pertinent imaging findings were documented. We also recorded relevant histopathological, demographic, clinical follow-up and survival data. We used the Student's t-test and Wilcoxon rank sum test to compare parametric and nonparametric continuous data, and the Fisher exact test to compare proportions. We used receiver operating characteristic (ROC) curve analyses to evaluate the diagnostic performances of tumor diameter and volume for discriminating carcinoma from adenoma. A P-value ≤0.05 was considered statistically significant., Results: Among the adrenocortical lesions, 9 were adenomas, 15 were carcinomas, and 1 was of uncertain malignant potential. There were no differences in mean age, gender or sidedness between adenomas and carcinomas. Carcinomas were significantly larger than adenomas based on mean estimated volume (581 ml, range 16-2,101 vs. 54 ml, range 3-197 ml; P-value = 0.003; ROC area under the curve = 0.92) and mean maximum transverse plane diameter (9.9 cm, range 3.0-14.9 vs. 4.4 cm, range 1.9-8.2 cm; P-value = 0.0001; ROC area under the curve = 0.92). Carcinomas also were more heterogeneous than adenomas on post-contrast imaging (13/14 vs. 2/9; odds ratio [OR] = 45.5; P-value = 0.001). Six of 13 carcinomas and 1 of 8 adenomas contained calcification at CT (OR = 6.0; P-value = 0.17). Seven of 15 children with carcinomas exhibited metastatic disease at diagnosis, and three had inferior vena cava invasion. Median survival for carcinomas was 27 months., Conclusion: In our experience, pediatric adrenocortical carcinomas are larger, more heterogeneous, and more often calcified than adenomas, although there is overlap in their imaging appearances.

Purpose: To determine whether focal peripheral zone enhancement on routine venous-phase CT is predictive of higher-grade (Gleason 4 + 3 and higher) prostate cancer., Materials and Methods: IRB approval was obtained and informed consent waived for this HIPAA-compliant retrospective study. Forty-three patients with higher-grade prostate cancer (≥Gleason 4 + 3) and 96 with histology-confirmed lower-grade (≤Gleason 3 + 4 [n = 47]) or absent (n = 49) prostate cancer imaged with venous-phase CT comprised the study population. CT images were reviewed by ten blinded radiologists (5 attendings, 5 residents) who scored peripheral zone enhancement on a scale of 1 (benign) to 5 (malignant). Mass-like peripheral zone enhancement was considered malignant. Likelihood ratios (LR) and specificities were calculated. Multivariate conditional logistic regression analyses were conducted., Results: Scores of "5" were strongly predictive of higher-grade prostate cancer (pooled LR+ 9.6 [95% CI 5.8-15.8]) with rare false positives (pooled specificity: 0.98 [942/960, 95% CI 0.98-0.99]; all 10 readers had specificity ≥95%). Attending scores of "5" were more predictive than resident scores of "5" (LR+: 14.7 [95% CI 5.8-37.2] vs. 7.6 [95% CI 4.2-13.7]) with similar specificity (0.99 [475/480, 95% CI 0.98-1.00] vs. 0.97 [467/480, 95% CI 0.96-0.99]). Significant predictors of an assigned score of "5" included presence of a peripheral zone mass (p < 0.0001), larger size (p < 0.0001), and less reader experience (p = 0.0008). Significant predictors of higher-grade prostate cancer included presence of a peripheral zone mass (p = 0.0002) and larger size (p < 0.0001)., Conclusion: Focal mass-like peripheral zone enhancement on routine venous-phase CT is specific and predictive of higher-grade (Gleason 4 + 3 and higher) prostate cancer.

Purpose: The authors are developing a computerized system for automated segmentation of ureters in CTU, referred to as combined model-guided path-finding analysis and segmentation system (COMPASS). Ureter segmentation is a critical component for computer-aided diagnosis of ureter cancer., Methods: COMPASS consists of three stages: (1) rule-based adaptive thresholding and region growing, (2) path-finding and propagation, and (3) edge profile extraction and feature analysis. With institutional review board approval, 79 CTU scans performed with intravenous (IV) contrast material enhancement were collected retrospectively from 79 patient files. One hundred twenty-four ureters were selected from the 79 CTU volumes. On average, the ureters spanned 283 computed tomography slices (range: 116-399, median: 301). More than half of the ureters contained malignant or benign lesions and some had ureter wall thickening due to malignancy. A starting point for each of the 124 ureters was identified manually to initialize the tracking by COMPASS. In addition, the centerline of each ureter was manually marked and used as reference standard for evaluation of tracking performance. The performance of COMPASS was quantitatively assessed by estimating the percentage of the length that was successfully tracked and segmented for each ureter and by estimating the average distance and the average maximum distance between the computer and the manually tracked centerlines., Results: Of the 124 ureters, 120 (97%) were segmented completely (100%), 121 (98%) were segmented through at least 70%, and 123 (99%) were segmented through at least 50% of its length. In comparison, using our previous method, 85 (69%) ureters were segmented completely (100%), 100 (81%) were segmented through at least 70%, and 107 (86%) were segmented at least 50% of its length. With COMPASS, the average distance between the computer and the manually generated centerlines is 0.54 mm, and the average maximum distance is 2.02 mm. With our previous method, the average distance between the centerlines was 0.80 mm, and the average maximum distance was 3.38 mm. The improvements in the ureteral tracking length and both distance measures were statistically significant (p < 0.0001)., Conclusions: COMPASS improved significantly the ureter tracking, including regions across ureter lesions, wall thickening, and the narrowing of the lumen.

Purpose: To compare frequency and severity of arterial phase respiratory motion-related artifact following gadoxetate disodium and gadobenate dimeglumine in matched patients administered both contrast media at different times., Materials and Methods: Institutional review board approval was obtained, with patient consent waived, for this retrospective, HIPAA-compliant study. Ninety patients underwent gadobenate dimeglumine-enhanced abdominal magnetic resonance (MR) followed by gadoxetate disodium-enhanced abdominal MR and were matched to 90 patients who were administered the same contrast media in reverse order (180 patients). Matching was based on length of time between paired examinations. Gadobenate dimeglumine dose was weight based (0.1 mmol per kilogram body weight). Gadoxetate disodium dose was typically fixed (10 or 20 mL [off label]). Three readers blinded to contrast agent assigned a respiratory motion-related artifact score (1 [none] to 5 [nondiagnostic]) for nonenhanced, arterial, venous, and late dynamic phases. Frequency of greater new arterial phase respiratory motion-related artifact in each within-patient pair and aggregate rate of new severe transient arterial phase respiratory motion-related artifact (scores ≤ 2, nonenhanced and venous and/or late dynamic phases; ≥ 4, arterial phase) were compared (McNemar test)., Results: For groups 1 and 2, respectively, mean dose (gadoxetate disodium, 16.6 mL vs 16.6 mL, P = .99; gadobenate dimeglumine, 18.0 mL vs 17.8 mL, P = .77) and mean time between examinations (191 days vs 191 days, P = .99) were not significantly different between matched populations. Gadoxetate disodium was associated with significantly higher incidence of new arterial phase respiratory motion-related artifact compared with gadobenate dimeglumine (39% vs 10%, P < .0001) and of new severe transient arterial phase respiratory motion-related artifact (18% vs 2%, P < .0001) in patients administered both agents at different times., Conclusion: Fixed off-label dose (10 or 20 mL) of gadoxetate disodium is associated with arterial phase respiratory motion-related artifact that is sometimes severe and occurs significantly more often than after gadobenate dimeglumine in patients who received both contrast media., (© RSNA, 2014.)

We are developing a computerized system for bladder segmentation on CT urography (CTU), as a critical component for computer-aided detection of bladder cancer. The presence of regions filled with intravenous contrast and without contrast presents a challenge for bladder segmentation. Previously, we proposed a conjoint level set analysis and segmentation system (CLASS). In case the bladder is partially filled with contrast, CLASS segments the non-contrast (NC) region and the contrast-filled (C) region separately and automatically conjoins the NC and C region contours; however, inaccuracies in the NC and C region contours may cause the conjoint contour to exclude portions of the bladder. To alleviate this problem, we implemented a local contour refinement (LCR) method that exploits model-guided refinement (MGR) and energy-driven wavefront propagation (EDWP). MGR propagates the C region contours if the level set propagation in the C region stops prematurely due to substantial non-uniformity of the contrast. EDWP with regularized energies further propagates the conjoint contours to the correct bladder boundary. EDWP uses changes in energies, smoothness criteria of the contour, and previous slice contour to determine when to stop the propagation, following decision rules derived from training. A data set of 173 cases was collected for this study: 81 cases in the training set (42 lesions, 21 wall thickenings, 18 normal bladders) and 92 cases in the test set (43 lesions, 36 wall thickenings, 13 normal bladders). For all cases, 3D hand segmented contours were obtained as reference standard and used for the evaluation of the computerized segmentation accuracy. For CLASS with LCR, the average volume intersection ratio, average volume error, absolute average volume error, average minimum distance and Jaccard index were 84.2 ± 11.4%, 8.2 ± 17.4%, 13.0 ± 14.1%, 3.5 ± 1.9 mm, 78.8 ± 11.6%, respectively, for the training set and 78.0 ± 14.7%, 16.4 ± 16.9%, 18.2 ± 15.0%, 3.8 ± 2.3 mm, 73.8 ± 13.4% respectively, for the test set. With CLASS only, the corresponding values were 75.1 ± 13.2%, 18.7 ± 19.5%, 22.5 ± 14.9%, 4.3 ± 2.2 mm, 71.0 ± 12.6%, respectively, for the training set and 67.3 ± 14.3%, 29.3 ± 15.9%, 29.4 ± 15.6%, 4.9 ± 2.6 mm, 65.0 ± 13.3%, respectively, for the test set. The differences between the two methods for all five measures were statistically significant (p < 0.001) for both the training and test sets. The results demonstrate the potential of CLASS with LCR for segmentation of the bladder.

Purpose: To determine whether the frequency of intra-observer measurement discrepancies ≥5 mm for solid renal masses varies by renal mass characteristics and CT contrast phase., Materials and Methods: This HIPAA-compliant retrospective study was approved by our IRB. We selected single CT images performed during the nephrographic phase (NP) of renal enhancement in 97 patients, each with a single solid renal mass. Mass location, margin, heterogeneity, and growth pattern were assessed. Six readers measured each mass on two occasions >3 weeks apart. Readers also measured the masses on images in 50 patients who had corticomedullary phase (CMP) images obtained during the same study. Results were assessed using Chi-square/Fisher's exact and Wilcoxon Signed Rank tests, and logistic regression analyses., Results: For NP to NP comparisons, intra-reader measurement differences ≥5 mm were seen for 3.7% (17/463) of masses <4 cm, but increased to 16.8% (20/119) for masses >4 cm (p < 0.0001). Masses with poorly defined margins (15.9% [22/138] vs. 3.4% [15/444] for well-defined margins, p < 0.0001) and heterogeneity (15.3% [22/144], vs. 5.0% [14/282] for minimally heterogeneous, vs. 0.6% [1/156] for homogeneous, p < 0.0001), were more frequently associated with measurement differences ≥5 mm. Differences ≥5 mm were more frequent when only CMP images were utilized (14% [42/299]), or when CMP images were compared with NP images (26% [77/299])., Conclusions: A ≥5 mm intra-reader variation in measured size of solid renal masses <4 cm is uncommon for NP to NP comparisons. Variation increases when masses are ≥4 cm, poorly defined, or heterogeneous; or when CMP images are utilized.