Search

Cocaine use is associated with a variety of renal injuries. Although rhabdomyolysis is the most common cause of cocaine-induced nephropathy, cocaine can also cause renal vasculitis, acute interstitial nephritis, acute tubular necrosis, thrombotic microangiopathy, and renal infarction. We present a rare case of cocaine-induced nephropathy in a 30-year-old male who presented with acute kidney injury and abnormal nephrograms at contrast-enhanced computed tomography. Mechanisms of cocaine-induced renal injury and differential causes of abnormal nephrograms encountered at imaging are discussed. Cocaine-induced nephropathy is a rare but important cause of abnormal nephrograms and should be considered in the differential diagnosis when clinically appropriate.

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 Conclusion CDSS-T improves physician performance for identifying complete response of muscle-invasive bladder cancer to neoadjuvant chemotherapy.

We evaluated whether a computerized decision support system for bladder cancer treatment response assessment (CDSS-T) can assist physicians from different institutions in identifying patients who have complete response after neoadjuvant chemotherapy. Pre- and post-chemotherapy CTU scans of 96 patients (114 pre- and post-treatment lesion pairs) were collected retrospectively. The pathological cancer stage after treatment was collected as the reference standard of response to treatment. 24% of the lesion pairs had T0 cancer stage (complete response) after chemotherapy. Our CDSST that combined DL-CNN and radiomics features was trained to distinguish between T0 and

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 &lt, 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.

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

Purpose The aim of this work was to prioritize in a quaternary academic environment necessary elements of a replacement PACS. Methods This quality improvement work was conducted at one academic medical center and was “not regulated” by the institutional review board. Three workgroups (10-15 members each) with unique resident, fellow, and attending radiologists; IT specialists; and departmental leaders convened in 2018 to prioritize elements for a PACS replacement project, including integrated IT tools. Each workgroup met two or three times and represented one of three missions (clinical, research, and education). Six elements assigned the highest priority were distilled from each workgroup. The resulting 18 elements were condensed into survey format and distributed to all department residents, fellows, and faculty members for 5-point Likert-type prioritization stratified by mission. Data were collected over 2 weeks. Results The survey response rate was 37% (71 of 192; 17 of 44 residents, 3 of 27 fellows, and 51 of 121 faculty members). Self-reported work effort was 63 ± 26% clinical, 14 ± 11% education, 15 ± 21% research, and 8 ± 14% administration. Aggregate priority ratings across all domains were highest for “stable system with predictable behavior” (mean, 4.51), “minimizes repetitive non-value-added work” (mean, 4.40), “interoperability” (mean, 4.12), and “near-instantaneous load times” (mean, 4.07). Clinical-specific ratings for these elements were even higher (means, 4.85-4.90). The lowest aggregate scores were mobile device compatibility (mean, 3.03), connectivity to nonaffiliated sites (mean, 3.01), and integrated instant messaging (mean, 2.87). Conclusions The department prioritized a stable and interoperable system that minimized non-value-added work. In other words, participants wanted a functioning PACS. PACS vendors should prioritize a reliable experience over niche add-ons.

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.

We are developing a deep learning based U-Net (U-DL) model for bladder wall segmentation in CT urography (CTU) as a component of a computer-assisted pipeline for bladder cancer detection and treatment response assessment. This task is challenging due to variations in size and shape of the wall among cases, low contrast between the bladder wall and surrounding structures, and some walls being extremely thin and occasionally invisible compared to the overall size of the bladder. Our previous method used a deep-learning convolution neural network and level sets (DCNN-LS) within a user-input bounding box. In the current study, we propose two new methods for bladder wall segmentation: 1) the outer and inner bladder wall contour masks are generated to train two different U-DLs and the segmented bladder regions are subtracted to obtain the final bladder wall; 2) a combined wall mask for the bladder wall is generated by subtracting the hand-outlined bladder inner and outer contour masks, and a single U-DL is trained to segment the bladder wall. The new methods use only U-Net without level-set post-processing. Hand-segmented contours from 67 training and 14 validation cases were used for this study. The combined wall mask training method in particular shows promise in improving both accuracy and reducing pipeline complexity.

Stage T2 is the clinical threshold to administer neoadjuvant chemotherapy for bladder cancer. In this study a deep learning convolutional neural network (DL-CNN) was trained to aid clinicians in staging of bladder cancer in CT Urography (CTU). The DL-CNN utilized two datasets for training and testing. The primary training dataset included 84 bladder cancers from CTU scans of 76 clinically staged patients, 43 cancers were below stage T2, and 41 were stage T2 or above. The second dataset served as an independent test set containing 90 bladder cancers from CTU scans of 86 clinically staged patients, all bladder cancers were staged as T2 or above. Regions of interest (ROIs) were extracted from the lesions as input to the DL-CNN. The model structure and hyper-parameters were determined and asserted using the training dataset of 84 lesions split into two balanced partitions. Based on the lesion-based T2 likelihood score obtained by averaging the scores of all ROIs extracted from a given lesion, the decision threshold providing the highest classification accuracy was determined from the leave-one-out validation. The DL-CNN with the fixed decision threshold was then applied to the test ROIs. The classification accuracy for the independent test set of 90 cancers was 0.91. This performance is slightly higher than our previous radiomics approach based on SVM and BPNN models, which achieved 0.88 and 0.90 accuracy on the same test set, respectively, but the difference was not statistically significant. The results show the promise of using a DL-CNN in bladder cancer stage assessment.

Lymph node involvement in bladder cancer is common and has prognostic implications. Early and accurate identification of metastatic lymph nodes is, therefore, important in ensuring appropriate patient triage and management. The purpose of this review is to provide a pictorial and educational overview of the staging and imaging appearance of metastatic lymph nodes in bladder cancer. Additionally, a secondary aim of this manuscript is to provide a review of the diagnostic accuracy of common imaging modalities available for detecting metastatic lymph nodes in affected patients.

Topical tissue sealants and hemostatic agents, seen on postoperative imaging in a variety of intraabdominal and pelvic locations, have the potential to be mistaken for abdominal abnormalities, especially if the radiologist is not aware of the patient's surgical history. The normal appearance of these agents may mimic abscesses, tumors, enlarged lymph nodes, or retained foreign bodies. Therefore, it is important to be familiar with their typical imaging appearances and to review the surgical records when needed to avoid misdiagnoses. The purpose of this article is to increase the radiologist's familiarity with various types of topical tissue sealants and hemostatic agents used during surgical and percutaneous procedures in the abdomen and pelvis along with their radiologic appearances.Various types of hemostatic agents are now commonly used during surgery and percutaneous procedures in the abdomen and pelvis, and it is important to recognize the various appearances of these agents. Although there are suggestive features outlined in this article, the most important factor for the radiologist is to be aware of the patient's history and the possibility that a hemostatic agent may be present. On postoperative imaging, hemostatic agents may mimic abscesses, tumors, enlarged lymph nodes, or retained foreign bodies, and accurate diagnosis can save a patient unnecessary treatment. It is therefore crucial to incorporate knowledge of the patient's surgical history with recognition of the typical imaging appearances of hemostatic agents and other pseudolesions to avoid misdiagnoses.

The purpose of this study was to determine whether individual radiologists are predictive of important relevant health outcomes among emergency department (ED) patients undergoing abdominopelvic CT for right lower quadrant pain.This single-institution retrospective cohort study included 2169 patients undergoing abdominopelvic CT for right lower quadrant pain in the ED from February 1, 2012, through August 31, 2016. CT examinations were interpreted by 15 radiologists (four emergency, 11 abdominal) who each reported on more than 70 CT examinations in the cohort. After risk adjustment for covariates thought to influence outcome, including baseline risk (demographics, 30 Elixhauser comorbidities, number of previous ED visits), clinical factors (vital signs, triage and pain scores, laboratory data), and system factors (time of CT, resident involvement, attending physician experience), multivariable models were built to analyze the effect of individual radiologists on four important health outcomes: hospital admission (primary outcome), readmission within 30 days, abdominal surgery, and image-guided percutaneous aspiration or drainage.Radiologists had a mean experience of 14 years (range, 2-36 years) and read a mean of 145 CT examinations in the study cohort (range, 73-253 examinations). Unadjusted event rates across the 15 radiologists were 38-55% (admission), 11-21% (readmission), 10-26% (surgery), and 0-3% (aspiration or drainage). After risk adjustment, individual radiologists were not a significant multivariable predictor of hospital admission, readmission within 30 days, abdominal surgery, or image-guided abdominal percutaneous aspiration or drainage (all p0.05).Individual radiologists were indistinguishable both within group and between group by emergency and abdominal specialization for the prediction of major patient outcomes after abdominopelvic CT performed for right lower quadrant pain in the ED.

RATIONALE AND OBJECTIVES The objective of this study was to determine whether noon conference attendance by diagnostic radiology residents is predictive of measurable performance. METHODS This single-center retrospective Health Insurance and Portability and Accountability Act (HIPAA)-compliant cross-sectional study was considered "not regulated" by the institutional review board. All diagnostic radiology residents who began residency training from 2008 to 2012 were included (N = 54). Metrics of clinical performance and knowledge were collected, including junior and senior precall test results, American Board of Radiology scores (z-score transformed), American College of Radiology in-training scores (years 1-3), on-call "great call" and minor and major discrepancy rates, on-call and daytime case volumes, and training rotation scores. Multivariate regression models were constructed to determine if conference attendance, match rank order, or starting year could predict these outcomes. Pearson bivariate correlations were calculated. RESULTS Senior precall test results were moderately correlated with American Board of Radiology (r = 0.41) and American College of Radiology (r = 0.38-0.48) test results and mean rotation scores (r = 0.41), indicating moderate internal validity. However, conference attendance, match rank order, and year of training did not correlate with (r = -0.16-0.16) or predict (P > .05) measurable resident knowledge. On multivariate analysis, neither match rank order (P = .14-.96) nor conference attendance (P = .10-.88) predicted measurable clinical efficiency or accuracy. Year started training predicted greater cross-sectional case volume (P

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.

Purpose To determine if the allergic-like breakthrough reaction rate of intravenous corticosteroid prophylaxis administered 5 hours before contrast material-enhanced computed tomography (CT) is noninferior to that of a traditional 13-hour oral regimen. Materials and Methods Institutional review board approval was obtained and informed consent waived for this retrospective noninferiority cohort study. Subjects (n = 202) who completed an accelerated 5-hour intravenous corticosteroid premedication regimen before low-osmolality contrast-enhanced CT for a prior allergic-like or unknown-type reaction to iodine-based contrast material from June 1, 2008, to June 30, 2016, were identified. The breakthrough reaction rate was compared by using the Farrington and Manning noninferiority likelihood score to test subjects premedicated with a traditional 13-hour oral regimen (2.1% [13 of 626]). All subjects were premedicated for a prior allergic-like or unknown-type reaction to iodine-based contrast material. A noninferiority margin of 4.0% was selected to allow for no more than a clinically negligible 6.0% breakthrough reaction rate in the cohort that received 5-hour intravenous corticosteroid prophylaxis. Results The breakthrough reaction rate for 5-hour intravenous prophylaxis was 2.5% (five of 202 patients; 95% confidence interval: 0.8%, 5.7%), which was noninferior to the 2.1% (13 of 626 patients; 95% confidence interval: 1.1%, 3.5%) rate for the 13-hour regimen (P = .0181). The upper limits of the confidence interval for the difference between the two rates was 3.7% (0.4%; 95% confidence interval: -1.6%, 3.7%), which was within the 4.0% noninferiority margin. All breakthrough reactions were of equal or lesser severity to those of the index reactions (two severe, one moderate, and one mild reaction). Conclusion Accelerated intravenous premedication with corticosteroids beginning 5 hours before contrast-enhanced CT has a breakthrough reaction rate noninferior to that of a 13-hour oral premedication regimen. © RSNA, 2017.

To assess the frequency with which previously reported characteristic findings of retroperitoneal fibrosis (RPF) (a circumferential or almost circumferential peri-aortic mass centered at L4, which does not displace the abdominal aorta or proximal common iliac arteries) are present in patients with RPF, in patients with other fibrosing diseases, and in cancer patients referred to a subspecialty clinic with a suspected diagnosis of RPF, in order to determine whether diagnostic percutaneous biopsy can be avoided in some patients. This HIPAA-compliant Institutional Review Board-approved retrospective study assessed clinical and CT and MR imaging abnormalities on imaging studies in 92 patients referred to a subspecialty clinic with suspected RPF over a 14-year period. Two reviewers, in consensus, determined the frequency of different CT and MRI findings in three groups of patients (Group 1: those with an eventual diagnosis of RPF, Group 2: those with a fibrosing disease associated with vascular or urologic abnormalities, and Group 3: those with cancer). Assessed imaging features included the presence of retroperitoneal masses, whether masses were single or multiple, whether such masses were circumferential or nearly circumferential, whether they displaced the aorta away from the spine (with the degree of such displacement measured), and whether there were abnormalities outside of the peri-aortic region of the retroperitoneum. The frequency with which findings previously reported as characteristic of RPF were present was determined for each of the three groups. Imaging results were correlated with the final diagnoses. Of 68 subjects eventually diagnosed with retroperitoneal fibrosis (RPF) (Group 1), 47 had peri-aortic retroperitoneal masses, 18 of which displaced the aorta anteriorly away from the spine. Of 12 subjects with fibrosing abnormalities related to vascular or urologic disease (Group 2), six had retroperitoneal masses, none of which displaced the aorta away from the spine. Of 12 subjects with malignancies (Group 3), six had peri-aortic retroperitoneal masses only two of whom had aortic displacement. Only 34 of 68 Group 1 subjects had peri-aortic masses characteristic of RPF, compared with six Group 2 subjects and one Group 3 subject. Subjects with characteristic retroperitoneal masses were significantly more likely to have benign disease than cancer (p = 0.009). Many patients with RPF do not have characteristic imaging findings. Contrary to prior publications, absence of aortic displacement is not seen in all patients with RPF and is seen in some cancer patients. Nonetheless, when infiltrative peri-aortic retroperitoneal soft tissue that does not displace the aorta is encountered on CT or MRI, RPF can be diagnosed with a high degree of confidence, obviating the need for biopsy.

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.

OBJECTIVE. The objective of our study was to explore whether clinical factors historically associated with contrast material-causative kidney injury (contrast-induced nephrotoxicity [CIN]) increase risk after use of IV iodinated low-osmolality contrast material (LOCM) in patients with stage IIIb-V chronic kidney disease. MATERIALS AND METHODS. In this retrospective hypothesis-generating study, 1:1 propensity score matching was used to assess post-CT acute kidney injury (AKI) after unenhanced or contrast-enhanced CT in patients with stable estimated glomerular filtration rate (eGFR; 1112 patients with an eGFR = 30-44 mL/min/1.73 m2 and 86 patients with an eGFR < 30 mL/min/1.73 m2 and no dialysis). Historical risk factors including diabetes mellitus, age more than 60 years, hypertension, loop diuretic use, hydrochlorothiazide use, and cardiovascular disease were evaluated for modulation of CIN risk. Stepwise multivariable logistic regression was performed. RESULTS. Overall IV LOCM was an independent risk factor for post-CT AKI in patients with an eGFR of less than 30 mL/min/1.73 m2 (odds ratio, 3.96 [95% CI, 1.29-12.21]; p = 0.016) but not in those with an eGFR of 30-44 mL/min/1.73 m2 (p = 0.24). In patients with an eGFR of less than 30 mL/min/1.73 m2, the tested covariates did not significantly modify the risk of CIN (p = 0.096-0.832). In patients with an eGFR of 30-44 mL/min/1.73 m2, risk of CIN emerged in those with cardiovascular disease (p = 0.015; number needed to harm from LOCM = 11 patients); the other tested cofactors had no significant effect (p = 0.108-0.822). CONCLUSION. CIN was observed when eGFR was less than 30 mL/min/1.73 m2. In those with an eGFR of 30-44 mL/min/1.73 m2, CIN was not observed with LOCM alone but was observed in the presence of cardiovascular disease. Other cofactors historically thought to increase CIN risk (e.g., diabetes mellitus) did not increase risk of CIN. Further study is needed to determine whether these exploratory results are true associations.

We are developing a U-Net based deep learning (U-DL) model for bladder segmentation in CT urography (CTU) as a part of a computer-assisted bladder cancer detection and treatment response assessment pipeline. We previously developed a bladder segmentation method that used a deep-learning convolution neural network and level sets (DCNNLS) within a user-input bounding box. The new method does not require a user-input box nor the level sets for postprocessing. To identify the best model for this task, we compared a number of U-DL models: 1) 2D CTU slices or 3D volume as input, 2) different image resolutions, and 3) preprocessing with and without automated cropping on each slice. We evaluated the segmentation performance of the different U-DL models using 3D hand-segmented contours as reference standard. The segmentation accuracy was quantified by the average volume intersection ratio (AVI), average percent volume error (AVE), average absolute volume error (AAVE), average minimum distance (AMD), and the Jaccard index (JI) for a data set of 81 training/validation and 92 independent test cases. For the test set, the best 2D UDL model achieved AVI, AVE, AAVE, AMD, and JI values of 93.4±9.5%, -4.2±14.2%, 9.2±11.5%, 2.7±2.5 mm, 85.0±11.3%, respectively, while the best 3D U-DL achieved 90.6±11.9%, -2.3±21.7%, 11.5±18.5%, 3.1±3.2 mm, and 82.6±14.2%, respectively. For comparison, the corresponding values obtained with our previous DCNN-LS method were 81.9±12.1%, 10.2±16.2%, 14.0±13.0%, 3.6±2.0 mm, and 76.2±11.8%, respectively, for the same test set. The UDL model provided highly accurate bladder segmentation and was more automated than the previous approach.

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 variation of the DL-CNN structure. Pre- and post-treatment CT scans of 123 patients (129 cancers, 158 pre- and posttreatment cancer pairs) undergoing chemotherapy were collected. 33% of patients had T0 stage cancer (complete response) after chemotherapy. Regions of interest (ROIs) of pre- and post-treatment scans were extracted from the segmented lesions and combined into hybrid pre-post image pairs. The dataset was split into training (94 pairs and 6209 hybrid ROIs), validation (10 pairs) and test sets (54 pairs). The DL-CNN consists of 2 convolution (C1, C2), 2 locally connected (L1, L2), and 1 fully connected layers, implemented in TensorFlow. The DL-CNN was trained to classify the bladder cancers as fully responding (stage T0) or not fully responding to chemotherapy based on the hybrid ROIs. Two blinded radiologists provided an estimate of the likelihood of the lesion being stage T0 post-treatment by reading the pairs of pre- and post-treatment CT volumes. The test AUC was 0.73 for T0 prediction by the base DL-CNN structure with randomly initialized weights. The base DL-CNN structure with transfer learning pre-trained weights (no frozen layers) achieved a 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, respectively. For the base DL-CNN with (C1) frozen, (C1, C2) frozen, and (C1, C2, L3) frozen during transfer learning, the test AUCs were 0.81, 0.78, and 0.71, respectively. The radiologists’ AUCs were 0.76 and 0.77. The DL-CNN performed better with pre-trained than randomly initialized weights.

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.

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.

PurposeThe purpose of this study was to determine the frequency in which the pelvis component of an abdominopelvic CT provides information that would influence clinical management in two separate groups of patients: those with previously resected pancreatic ductal adenocarcinoma (PDA) and those with locally advanced unresectable PDA.MethodsThis institutional review-board approved HIPAA compliant retrospective study with waived informed consent included 247 subjects with histologically proven PDA, including 153 subjects post-pancreaticoduodenectomy and 94 subjects with locally advanced unresectable disease. Imaging reports interpreted between January 2005 and December 2013 were obtained from our institution's Radiology Information System by searching a Cancer Registry database of PDA patients separately for the words "whipple" and "unresectable." CT findings were separated by location in the abdomen or pelvis, and subsequently reviewed and graded for their likelihood of representing metastatic disease. The probability of pelvic CT influencing clinical management-i.e., of finding isolated pelvic metastatic disease-was determined using 95% binomial proportion confidence intervals for both the post-pancreaticoduodenectomy and locally advanced unresectable groups.ResultsNo subjects who had undergone pancreaticoduodenectomy had an isolated pelvic metastasis on follow-up imaging (0%; 95% CI 0-2.38, p=0.0004); 33 had metastatic disease in the abdomen, and 120 had no or equivocal evidence of abdominopelvic metastatic disease. One subject with locally advanced unresectable PDA had a possible isolated pelvic metastasis on follow-up imaging (1.1%; 95% CI 0.03-5.79, p=0.048); 20 had metastatic disease in the abdomen, and 73 had no or equivocal evidence of abdominopelvic metastatic disease.ConclusionIsolated pelvic metastatic disease rarely occurs in patients with PDA who have had prior pancreaticoduodenectomy or have a locally advanced unresectable primary tumor, suggesting routine pelvic CT in follow-up imaging of these patients may not be necessary.

To estimate the effect of an oral 13-hour inpatient corticosteroid premedication regimen on length of stay, hospital cost, and hospital-acquired infections (HAIs) by using a combination of real and hypothetical study populations.Institutional review board approval was obtained and informed consent waived for this HIPAA-compliant retrospective study. Inpatients who received an oral 13-hour corticosteroid premedication regimen before contrast material-enhanced CT (n = 1424) from 2008 to 2013 were matched by age, sex, and year when CT was performed to a control cohort (n = 1425) of patients who underwent contrast-enhanced CT without premedication and who had similar rates of 13 comorbid diseases. Length of stay in the hospital and time from admission to CT were compared by using the Mann-Whitney U test. Rates of prospectively reported HAIs were compared by using χ(2) tests. The indirect cost and risk of HAI with premedication were estimated by using published data.Premedicated inpatients had a significantly longer median length of stay (+25 hours; 158 vs 133 hours, P.001), a significantly longer median time to CT (+25 hours, 42 vs 17 hours, respectively; P.001), and a significantly greater risk of HAI (5.1% [72 of 1424] vs 3.1% [44 of 1424], respectively; P = .008) compared with nonpremedicated control subjects. On the basis of these data and existing references, the prolonged length of stay was estimated to result in 0.04 HAI-related deaths and a cost of $159 131 (in U.S. dollars) for each prevented reaction of any severity and 32 HAI-related deaths and a cost of $131 211 400 for each prevented reaction-related death.Oral 13-hour inpatient corticosteroid prophylaxis is associated with substantial cost relative to its modest benefit, and may cause more indirect harm than the direct harm that it prevents.

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.

To determine if symptomatic patients referred for radiographic stool quantification have equivalent stool burden to asymptomatic patients. This was an IRB-approved HIPAA-compliant retrospective equivalence cohort study. An a priori equivalence power calculation was performed. Consecutive abdominal radiographs performed in adult outpatients with bloating, constipation, diarrhea, or abdominal pain to assess “fecal loading” [n = 242 (fecal cohort)] were compared to those performed in asymptomatic adult outpatients to assess “renal stones” [n = 242 (renal cohort)]. Radiographs were randomized and reviewed by two blinded independent abdominal radiologists. Exclusion criteria, designed to avoid unblinding, included urinary tract calculi ≥ 0.5 cm, multiple urinary tract calculi, and ureteral stent(s). Readers scored all radiographs (n = 484) for stool burden using validated Leech criteria [scale: 0 (none) to 15 (extreme diffuse)]. Mean Leech scores and 95% confidence intervals were calculated. Multivariable generalized linear modeling was performed to adjust for baseline medication use, age, and gender. The adjusted parameter estimate was used to test for equivalence in the mean difference between cohorts using Schuirmann’s method of two one-sided t-tests. Inter-reader agreement was assessed with intraclass correlation coefficients. Overall mean Leech scores for fecal [6.9 (95% CI 6.7, 7.2)] and renal [7.3 (95% CI 7.1, 7.5)] cohorts were equivalent within a margin of 0.75 (adjusted mean difference: − 0.4 [90% CI − 0.7, − 0.04]; p value = 0.02). Inter-reader agreement was good [ICC: 0.62 (95% CI 0.56, 0.68)]. Radiographic stool quantification produces equivalent results in symptomatic and asymptomatic adults and is of uncertain value.

The purpose of this study was to assess the effect of model-based iterative reconstruction (MBIR) on CT number measurements within small (10-29 mm) low-attenuation renal masses.One hundred 10- to 29-mm exophytic or endophytic low-attenuation renal lesions imaged with CT (unenhanced and nephrographic [100 seconds] phases, 120 kVp, variable mA, 2.5-mm slice thickness) were identified in 100 patients. The raw CT source data were prospectively reconstructed twice: once using Veo MBIR and once using a blend of 30% adaptive statistical iterative reconstruction (ASiR) and filtered back projection (FBP). Lesions were chosen to form four equal-sized (n = 25) groups stratified by lesion size (10-19 or 20-29 mm) and growth pattern (endophytic or exophytic). Attenuation (in HU) was measured using identical ROIs and compared with two-tailed t tests. The effects of patient diameter and lesion anatomy on attenuation discrepancies of 5 HU or more were assessed using binary logistic regression.Mean MBIR attenuation was not significantly different than mean 30% ASiR/FBP attenuation in the overall study population (unenhanced phase, 17 ± 13 vs 17 ± 13 HU, p = 0.74; nephrographic phase, 31 ± 27 vs 30 ± 26 HU, p = 0.89) or in any subgroup (p = 0.63-0.95). Only lesion size predicted discrepancies of 5 HU or more (p = 0.008; odds ratio, 1.20 [95% CI, 1.05-1.34] per 1 mm decrease) (p = 0.19-0.98 for the other variables). Seven lesions had enhancement of 20 HU or more with only one reconstruction method (MBIR = 4; 30% ASiR = 3).Veo MBIR has no significant or consistent effect on attenuation measurements within small (10-29 mm) low-attenuation renal masses and is therefore unlikely to change clinically accepted attenuation thresholds for renal mass characterization.

The purpose of this study was to determine the rate of allergiclike breakthrough reactions among inpatients at high risk receiving premedication before undergoing CT with IV iodinated low-osmolality contrast material (LOCM).Inpatients (n = 1051) completing a 13-hour corticosteroid and diphenhydramine premedication regimen before LOCM-enhanced CT from January 1, 2010, through December 31, 2013, were included in the study. Breakthrough reaction rates were compared with the ordinary allergiclike reaction rate in the general population (0.6% [545/84,928]) by use of chi-square tests. Multivariate logistic regression was performed. Number needed to treat (NNT) was calculated for patients premedicated for a previous contrast reaction.Sixty percent (626/1051) of premedicated patients had had a previous reaction to iodinated contrast material, and 40% (425/1051) were premedicated for other reasons. The overall breakthrough reaction rates were 1.2% (13/1051) (p0.0001 vs the general population), 2.1% (13/626) for those with a previous iodinated contrast reaction (p0.0001), and 0% (0/425) for those premedicated for other reasons (p = 0.18). There were no severe breakthrough reactions. Younger age (p = 0.046; odds ratio, 1.03 per year; 95% CI, 1.001-1.07) and multiple indications for premedication (p0.0001; odds ratio, 2.7 per indication; 95% CI, 1.5-4.8) significantly increased the likelihood of a breakthrough reaction. The estimated NNTs were 69 (95% CI, 39-304) to prevent a reaction of any severity and 569 (95% CI, 389-1083) to prevent a severe reaction.Patients premedicated for a previous reaction to iodinated contrast material have a breakthrough reaction rate 3-4 times the ordinary reaction rate in the general population. Patients receiving premedication for other reasons have a breakthrough reaction rate near 0%. Many patients must receive premedication to prevent one reaction.

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.

OBJECTIVE. The incidence and significance of complications related to intravascular contrast material administration have become increasingly controversial. This review will highlight current thinking regarding the imaging of patients with renal impairment and those at risk for an allergiclike contrast reaction. CONCLUSION. The risk of contrast-induced acute kidney injury remains uncertain for patients with an estimated glomerular filtration rate (GFR) less than 45 mL/min/1.73m2, but if there is a risk, it is greatest in those with estimated GFR less than 30 mL/min/1.73m2. In this population, low-risk gadolinium-based contrast agents appear to have a large safety margin. Corticosteroid prophylaxis remains the standard of care in the United States for patients identified to be at high risk of a contrast reaction, but it has an incomplete mitigating effect on contrast reaction rates and the number needed to treat is large.

In bladder cancer, stage T2 is an important threshold in the decision of administering neoadjuvant chemotherapy. Our long-term goal is to develop a quantitative computerized decision support system (CDSS-S) to aid clinicians in accurate staging. In this study, we examined the effect of stage labels of the training samples on modeling such a system. We used a data set of 84 bladder cancers imaged with CT Urography (CTU). At clinical staging prior to treatment, 43 lesions were staged as below stage T2 and 41 were stage T2 or above. After cystectomy and pathological staging that is considered the gold standard, 10 of the lesions were upstaged to stage T2 or above. After correcting the stage labels, 33 lesions were below stage T2, and 51 were stage T2 or above. For the CDSS-S, the lesions were segmented using our AI-CALS method and radiomic features were extracted. We trained a linear discriminant analysis (LDA) classifier with leave-one-case-out cross validation to distinguish between bladder lesions of stage T2 or above and those below stage T2. The CDSS-S was trained and tested with the corrected post-cystectomy labels, and as a comparison, CDSS-S was also trained with understaged pre-treatment labels and tested on lesions with corrected labels. The test AUC for the CDSS-S trained with corrected labels was 0.89 ± 0.04. For the CDSS-S trained with understaged pre-treatment labels and tested on the lesions with corrected labels, the test AUC was 0.86 ± 0.04. The likelihood of stage T2 or above for 9 out of the 10 understaged lesions was correctly increased for the CDSS-S trained with corrected labels. The CDSS-S is sensitive to the accuracy of stage labeling. The CDSS-S trained with correct labels shows promise in prediction of the bladder cancer stage.

We are developing a computer-aided detection system for bladder cancer in CT urography (CTU). Bladder wall thickening is a manifestation of bladder cancer and its detection is more challenging than the detection of bladder masses. We first segmented the inner and outer bladder walls using our method that combined deep-learning convolutional neural network with level sets. The non-contrast-enhanced region was separated from the contrast-enhanced region with a maximum-intensity-projection-based method. The non-contrast region was smoothed and gray level threshold was applied to the contrast and non-contrast regions separately to extract the bladder wall and potential lesions. The bladder wall was transformed into a straightened thickness profile, which was analyzed to identify regions of wall thickening candidates. Volume-based features of the wall thickening candidates were analyzed with linear discriminant analysis (LDA) to differentiate bladder wall thickenings from false positives. A data set of 112 patients, 87 with wall thickening and 25 with normal bladders, was collected retrospectively with IRB approval, and split into independent training and test sets. Of the 57 training cases, 44 had bladder wall thickening and 13 were normal. Of the 55 test cases, 43 had wall thickening and 12 were normal. The LDA classifier was trained with the training set and evaluated with the test set. FROC analysis showed that the system achieved sensitivities of 93.2% and 88.4% for the training and test sets, respectively, at 0.5 FPs/case.

We are developing a decision support system for assisting clinicians in assessment of response to neoadjuvant chemotherapy for bladder cancer. Accurate treatment response assessment is crucial for identifying responders and improving quality of life for non-responders. An objective machine learning decision support system may help reduce variability and inaccuracy in treatment response assessment. We developed a predictive model to assess the likelihood that a patient will respond based on image and clinical features. With IRB approval, we retrospectively collected a data set of pre- and post- treatment CT scans along with clinical information from surgical pathology from 98 patients. A linear discriminant analysis (LDA) classifier was used to predict the likelihood that a patient would respond to treatment based on radiomic features extracted from CT urography (CTU), a radiologist’s semantic feature, and a clinical feature extracted from surgical and pathology reports. The classification accuracy was evaluated using the area under the ROC curve (AUC) with a leave-one-case-out cross validation. The classification accuracy was compared for the systems based on radiomic features, clinical feature, and radiologist’s semantic feature. For the system based on only radiomic features the AUC was 0.75. With the addition of clinical information from examination under anesthesia (EUA) the AUC was improved to 0.78. Our study demonstrated the potential of designing a decision support system to assist in treatment response assessment. The combination of clinical features, radiologist semantic features and CTU radiomic features improved the performance of the classifier and the accuracy of treatment response assessment.

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 data set 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 data set 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 (Az). Results Based on the texture features only, the LDA classifier achieved a test Az of 0.91 on Set 1 and a test Az of 0.88 on Set 2. The test Az of the NN classifier for Set 1 and Set 2 were 0.89 and 0.92, respectively. The SVM classifier achieved test Az of 0.91 on Set 1 and test Az of 0.89 on Set 2. The test Az 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. This article is protected by copyright. All rights reserved.

Purpose To identify computed tomographic (CT) findings that are predictive of recurrence of colonic diverticulitis. Materials and Methods Institutional review board approval was obtained for this HIPAA-compliant, retrospective cohort study. Six abdominal fellowship-trained radiologists reviewed the CT studies of 440 consecutive subjects diagnosed with acute colonic diverticulitis between January 2004 and May 2008 to determine the involved segments, maximum wall thickness in the inflamed segment, severity of diverticulosis, presence of complications (abscess, fistula, stricture, or perforation), and severity of the inflammation. Electronic medical records were reviewed for a 5-year period after the patients' first CT study to determine clinical outcomes. Predictors of diverticulitis recurrence were assessed with univariate and multiple Cox proportional hazard regression models. Results Colonic diverticulitis most commonly involved the rectosigmoid (70%, 309 of 440) and descending (30%, 133 of 440) colon segments. Complicated diverticulitis was present in 22% (98 of 440) of patients. On the basis of the results of univariate analysis, significant predictors of diverticulitis recurrence were determined to be maximum colonic wall thickness in the inflamed segment (hazard ratio [HR], 1.07 per every millimeter of increase in wall thickness; P < .001), presence of a complication (HR, 1.75; P = .002), and subjective severity of inflammation (HR, 1.36 for every increase in severity category; P value for linear trend = .003). The difference in maximum wall thickness in the inflamed segment (HR, 1.05 per millimeter; P = .016) and subjective inflammation severity (HR, 1.29 per category; P = .018)remained statistically significant in a Cox multiple regression model. Conclusion Maximum colonic wall thickness and subjective severity of acute diverticulitis allow prediction of recurrent diverticulitis and may be useful for stratifying patients according to the need for elective partial colectomy. © RSNA, 2017 Online supplemental material is available for this article.

We are developing a computer-aided detection system for bladder cancer in CT urography (CTU). We have previously developed methods for detection of bladder masses within the contrast-enhanced and the non-contrastenhanced regions of the bladder individually. In this study, we investigated methods for detection of bladder masses within the entire bladder. The bladder was segmented using our method that combined deep-learning convolutional neural network with level sets. The non-contrast-enhanced region was separated from the contrast-enhanced region with a maximum-intensity-projection-based method. The non-contrast region was smoothed and gray level threshold was applied to the contrast and non-contrast regions separately to extract the bladder wall and potential masses. The bladder wall was transformed into a straightened thickness profile, which was analyzed to identify lesion candidates in a prescreening step. The candidates were mapped back to the 3D CT volume and segmented using our auto-initialized cascaded level set (AI-CALS) segmentation method. Twenty-seven morphological features were extracted for each candidate. A data set of 57 patients with 71 biopsy-proven bladder lesions was used, which was split into independent training and test sets: 42 training cases with 52 lesions, and 15 test cases with 19 lesions. Using the training set, feature selection was performed and a linear discriminant (LDA) classifier was designed to merge the selected features for classification of bladder lesions and false positives. The trained classifier was evaluated with the test set. FROC analysis showed that the system achieved a sensitivity of 86.5% at 3.3 FPs/case for the training set, and 84.2% at 3.7 FPs/case for the test set.

We are developing a CAD system for bladder cancer treatment response assessment in CT. We compared the performance of the deep-learning convolution neural network (DL-CNN) using different network sizes, and with and without transfer learning using natural scene images or regions of interest (ROIs) inside and outside the bladder. The DL-CNN was trained to identify responders (T0 disease) and non-responders to chemotherapy. ROIs were extracted from segmented lesions in pre- and post-treatment scans of a patient and paired to generate hybrid pre-post-treatment paired ROIs. The 87 lesions from 82 patients generated 104 temporal lesion pairs and 6,700 pre-post-treatment paired ROIs. Two-fold cross-validation and receiver operating characteristic analysis were performed and the area under the curve (AUC) was calculated for the DL-CNN estimates. The AUCs for prediction of T0 disease after treatment were 0.77±0.08 and 0.75±0.08, respectively, for the two partitions using DL-CNN without transfer learning and a small network, and were 0.74±0.07 and 0.74±0.08 with a large network. The AUCs were 0.73±0.08 and 0.62±0.08 with transfer learning using a small network pre-trained with bladder ROIs. The AUC values were 0.77±0.08 and 0.73±0.07 using the large network pre-trained with the same bladder ROIs. With transfer learning using the large network pretrained with the Canadian Institute for Advanced Research (CIFAR-10) data set, the AUCs were 0.72±0.06 and 0.64±0.09, respectively, for the two partitions. None of the differences in the methods reached statistical significance. Our study demonstrated the feasibility of using DL-CNN for the estimation of treatment response in CT. Transfer learning did not improve the treatment response estimation. The DL-CNN performed better when transfer learning with bladder images was used instead of natural scene images.

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.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 occasions3 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.For NP to NP comparisons, intra-reader measurement differences ≥5 mm were seen for 3.7% (17/463) of masses4 cm, but increased to 16.8% (20/119) for masses4 cm (p0.0001). Masses with poorly defined margins (15.9% [22/138] vs. 3.4% [15/444] for well-defined margins, p0.0001) and heterogeneity (15.3% [22/144], vs. 5.0% [14/282] for minimally heterogeneous, vs. 0.6% [1/156] for homogeneous, p0.0001), 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]).A ≥5 mm intra-reader variation in measured size of solid renal masses4 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.

There has been an increase in utilization of bariatric surgery and, as with any surgical procedure, the associated risk of complications. Many of the post bariatric surgical complications can be acute, necessitating an emergency room visit and imaging evaluation. Radiologists, especially in the emergency setting, need to be familiar with normal post-operative appearances and potential surgical complications. This review focuses on various bariatric surgical procedures that are performed, and illustrates normal and abnormal radiographic appearances seen on post-operative fluoroscopic upper GI studies and abdominal pelvis CT examinations.

To compare serum creatinine (SCr) level- and estimated glomerular filtration rate (eGFR)-based screening methods for identifying adult inpatients at risk for contrast medium-induced nephrotoxicity (CIN).Institutional review board approval was obtained; informed consent was waived for this HIPAA-compliant retrospective study. Computed tomographic examinations performed during 10 years in adult inpatients with stable renal function were identified (n = 28 390). The proportion of inpatients meeting various eGFR (≥60,60,45,30, 30-44, 45-59 mL/min/1.73 m(2)) and SCr (1.5, ≥1.5, ≥1.6, ≥1.7, ≥1.8, ≥1.9, ≥2.0 mg/dL) thresholds were contrasted with each other and with published guidelines (≥2.0 mg/dL [SCr] and45 mL/min/1.73 m(2) [eGFR]) using McNemar and binomial tests.Most inpatients were considered low risk for CIN with commonly used thresholds: 92.6% (26 285 of 28 390) had SCr1.5 mg/dL; 91.3% (25 922 of 28 390) had eGFR of ≥45 mL/min/1.73 m(2). Using SCr threshold of ≥1.5 mg/dL, identified inpatients had the following eGFRs: 19.6% (413 of 2105), 45-59 mL/min/1.73 m(2); 51.1% (1075 of 2105), 30-44 mL/min/1.73 m(2); 28.6% (603 of 2105),30 mL/min/1.73 m(2); and 0.7% (14 of 2105), ≥60 mL/min/1.73 m(2) . Using SCr threshold of ≥2.0 mg/dL, identified inpatients had the following eGFRs: 100% (658 of 658),45 mL/min/1.73 m(2); 74.6% (491 of 658),30 mL/min/1.73 m(2). Threshold of SCr ≥2.0 mg/dL could not be used to identify eGFR30 mL/min/1.73 m(2) in 0.4% (112 of 28 390) and45 mL/min/1.73 m(2) in 6.4% (1810 of 28 390) of all inpatients. Using eGFR45 mL/min/1.73 m(2) instead of SCr of ≥1.5 mg/dL would result in a significant but small increase in identified inpatients (8.7% [2468 of 28 390; 95% confidence interval: 8.4%, 9.0%] vs 7.4% [2105 of 28 390; 95% confidence interval: 7.1%, 7.7%]; P.0001).Screening using eGFR45 mL/min/1.73 m(2) instead of common SCr thresholds would significantly increase the number of inpatients identified to be at risk for CIN but would reduce misidentification of a large number of inpatients at low risk according to eGFR criteria.

We are developing a computer-aided detection system for bladder cancer in CT urography (CTU). We have previously developed methods for detection of bladder masses within the contrast-enhanced region of the bladder. In this study, we investigated methods for detection of bladder masses within the non-contrast enhanced region. The bladder was first segmented using a newly developed deep-learning convolutional neural network in combination with level sets. The non-contrast-enhanced region was separated from the contrast-enhanced region with a maximum-intensityprojection- based method. The non-contrast region was smoothed and a gray level threshold was employed to segment the bladder wall and potential masses. The bladder wall was transformed into a straightened thickness profile, which was analyzed to identify lesion candidates as a prescreening step. The lesion candidates were segmented using our autoinitialized cascaded level set (AI-CALS) segmentation method, and 27 morphological features were extracted for each candidate. Stepwise feature selection with simplex optimization and leave-one-case-out resampling were used for training and validation of a false positive (FP) classifier. In each leave-one-case-out cycle, features were selected from the training cases and a linear discriminant analysis (LDA) classifier was designed to merge the selected features into a single score for classification of the left-out test case. A data set of 33 cases with 42 biopsy-proven lesions in the noncontrast enhanced region was collected. During prescreening, the system obtained 83.3% sensitivity at an average of 2.4 FPs/case. After feature extraction and FP reduction by LDA, the system achieved 81.0% sensitivity at 2.0 FPs/case, and 73.8% sensitivity at 1.5 FPs/case.

Correct staging of bladder cancer is crucial for the decision of neoadjuvant chemotherapy treatment and minimizing the risk of under- or over-treatment. Subjectivity and variability of clinicians in utilizing available diagnostic information may lead to inaccuracy in staging bladder cancer. An objective decision support system that merges the information in a predictive model based on statistical outcomes of previous cases and machine learning may assist clinicians in making more accurate and consistent staging assessments. In this study, we developed a preliminary method to stage bladder cancer. With IRB approval, 42 bladder cancer cases with CTU scans were collected from patient files. The cases were classified into two classes based on pathological stage T2, which is the decision threshold for neoadjuvant chemotherapy treatment (i.e. for stage ≥T2) clinically. There were 21 cancers below stage T2 and 21 cancers at stage T2 or above. All 42 lesions were automatically segmented using our auto-initialized cascaded level sets (AI-CALS) method. Morphological features were extracted, which were selected and merged by linear discriminant analysis (LDA) classifier. A leave-one-case-out resampling scheme was used to train and test the classifier using the 42 lesions. The classification accuracy was quantified using the area under the ROC curve (Az). The average training Az was 0.97 and the test Az was 0.85. The classifier consistently selected the lesion volume, a gray level feature and a contrast feature. This predictive model shows promise for assisting in assessing the bladder cancer stage.

We are developing a CAD system for detection of bladder cancer in CTU. In this study we investigated the application of deep-learning convolutional neural network (DL-CNN) to the segmentation of the bladder, which is a challenging problem because of the strong boundary between the non-contrast and contrast-filled regions in the bladder. We trained a DL-CNN to estimate the likelihood of a pixel being inside the bladder using neighborhood information. The segmented bladder was obtained from thresholding and hole-filling of the likelihood map. We compared the segmentation performance of the DL-CNN alone and with additional cascaded 3D and 2D level sets to refine the segmentation using 3D hand-segmented contours as reference standard. The segmentation accuracy was evaluated by five performance measures: average volume intersection %, average % volume error, average absolute % error, average minimum distance, and average Jaccard index for a data set of 81 training and 92 test cases. For the training set, DLCNN with level sets achieved performance measures of 87.2±6.1%, 6.0±9.1%, 8.7±6.1%, 3.0±1.2 mm, and 81.9±7.6%, respectively, while the DL-CNN alone obtained the values of 73.6±8.5%, 23.0±8.5%, 23.0±8.5%, 5.1±1.5 mm, and 71.5±9.2%, respectively. For the test set, the DL-CNN with level sets achieved performance measures of 81.9±12.1%, 10.2±16.2%, 14.0±13.0%, 3.6±2.0 mm, and 76.2±11.8%, respectively, while DL-CNN alone obtained 68.7±12.0%, 27.2±13.7%, 27.4±13.6%, 5.7±2.2 mm, and 66.2±11.8%, respectively. DL-CNN alone is effective in segmenting bladders but may not follow the details of the bladder wall. The combination of DL-CNN with level sets provides highly accurate bladder segmentation.

We are developing a CAD system for automated detection of ureter abnormalities in multi-detector row CT urography (CTU). Our CAD system consists of two stages. The first stage automatically tracks the ureter via the previously proposed COmbined Model-guided Path-finding Analysis and Segmentation System (COMPASS). The second stage consists of lesion enhancement filtering, adaptive thresholding, edge extraction, and noise removal. With IRB approval, 36 cases were collected from patient files, including 15 cases (17 ureters with 32 lesions) for training, and 10 abnormal cases (11 ureters with 17 lesions) and 11 normal cases (22 ureters) for testing. All lesions were identified by experienced radiologists on the CTU images and COMPASS was able to track the ureters in 100% of the cases. The average lesion size was 5.1 mm (range: 2.1 mm – 21.9 mm) for the training set and 6.1 mm (range: 2.0 mm – 18.9 mm) for the test set. The average conspicuity was 4.1 (range: 2 to 5) and 3.9 (range: 1 to 5) on a scale of 1 to 5 (5 very subtle), for the training and test sets, respectively. The system achieved 90.6% sensitivity at 2.41 (41/17) FPs/ureter for the training set and 70.6% sensitivity at 2 (44/22) FPs/normal ureter for the test set. These initial results demonstrate the feasibility of the CAD system to track the ureter and detect ureter cancer of medium conspicuity and relatively small sizes.

Rationale and Objectives Knowledge of the management of acute contrast reactions is lacking among radiologists. Training in the management of acute contrast reactions occurs at the investigators’ institution and others, but the durability of that training and the need for refresher training have not been assessed. Materials and Methods A prospective assessment of changes in trainees’ knowledge and confidence following a required educational course concerning reactions to contrast material was conducted. Assessments were performed prior to and immediately following the course and at 1, 3, 6, and 9 months after the course. Results Trainees’ knowledge significantly improved following the course and remained improved for 6 months (P Conclusions These data suggest the need for biannual refresher training in the management of acute contrast reactions to maintain trainees’ knowledge and confidence.

The purpose of our study was to compare the effects of i.v. iohexol and iopamidol on renal function in outpatients undergoing CT.We performed a prospective, double-blind, randomized clinical trial of 389 adults with low risk for contrast-induced nephropathy, comparing i.v. iohexol with iopamidol (300 mg I/mL). Serum creatinine (SCr) concentration was measured at baseline and 2 and 3 days after contrast administration. A noninferiority analysis was planned to compare the mean maximum SCr change from baseline between subject groups. Contrast-induced nephropathy rates (three definitions) for both contrast agents were compared as a secondary end point.One hundred ninety and 199 subjects received iohexol and iopamidol, respectively. The mean change in SCr from baseline using the maximum day 2 or 3 measurement was 0.07 ± 0.12 mg/dL (95% CI, 0.05-0.09 mg/dL) for the iohexol group and 0.05 ± 0.12 mg/dL (95% CI, 0.03-0.07 mg/dL) for the iopamidol group. The difference between contrast agents with respect to the mean change in SCr from baseline was -0.02 ± 0.12 mg/dL (95% CI, -0.045 to 0.003 mg/dL; p = 0.08). Contrast-induced nephropathy rates were not statistically different using any definition.Although our results were unable to show absolute noninferiority of iohexol compared with iopamidol because of a very small difference in increase in mean SCr from baseline (using a noninferiority margin of 0.04 mg/dL), this difference is likely of minimal or no clinical importance in outpatients undergoing CT with low risk for contrast-induced nephropathy.

OBJECTIVE. The purpose of this article is to describe and illustrate multimodality imaging features of various pathologic abnormalities involving the ureteric wall and periureteric space, with emphasis on the role of cross-sectional imaging. CONCLUSION. Ureteric and periureteric pathologic abnormalities may be identified on imaging studies, and although urothelial neoplasm remains the most concerning ureteric pathologic abnormality, there are several other nonneoplastic entities that may involve the ureter and the periureteric spaces. Knowledge of the spectrum of imaging findings in these entities may help the interpreting radiologist to formulate appropriate differential diagnoses.