Search

To compare an artificial intelligence (AI)-based prototype and subjective grading for predicting disease severity in patients with emphysema.Our IRB approved HIPAA-compliant study included 113 adults (71±8 years; 47 females, 66 males) who had both non-contrast chest CT and pulmonary function tests performed within a span of 2 months. The disease severity was classified based on the forced expiratory volume in 1 second (FEV1 as % of predicted) into mild, moderate, and severe. 2 thoracic radiologists (RA), blinded to the clinical and AI results, graded severity of emphysema on a 5-point scale suggested by the Fleischner Society for each lobe. The whole lung scores were derived from the summation of lobar scores. Thin-section CT images were processed with the AI-Rad Companion Chest prototype (Siemens Healthineers) to quantify low attenuation areas (LAA- 950 HU) in whole lung and each lobe separately. Bronchial abnormality was assessed by both radiologists and a fully automated software (Philips Healthcare).Both AI (AUC of 0.77; 95% CI: 0.68 - 0.85) and RA (AUC: 0.76, 95% CI: 0.65 - 0.84) emphysema quantification could differentiate mild, moderate, and severe disease based on FEV1. There was a strong positive correlation between AI and RA (r = 0.72 - 0.80; p0.001). The combination of emphysema and bronchial abnormality quantification from radiologists' and AI assessment could differentiate between different severities with AUC of 0.80 - 0.82 and 0.87, respectively.The assessed AI-prototypes can predict the disease severity in patients with emphysema with the same predictive value as the radiologists.

Background The novel coronavirus (COVID-19) has presented a significant and urgent threat to global health and there has been a need to identify prognostic factors in COVID-19 patients. The aim of this study was to determine whether chest CT characteristics had any prognostic value in patients with COVID-19. Methods A retrospective analysis of COVID-19 patients who underwent a chest CT-scan was performed in four medical centers. The prognostic value of chest CT results was assessed using a multivariable survival analysis with the Cox model. The characteristics included in the model were the degree of lung involvement, ground glass opacities, nodular consolidations, linear consolidations, a peripheral topography, a predominantly inferior lung involvement, pleural effusion, and crazy paving. The model was also adjusted on age, sex, and the center in which the patient was hospitalized. The primary endpoint was 30-day in-hospital mortality. A second model used a composite endpoint of admission to an intensive care unit or 30-day in-hospital mortality. Results A total of 515 patients with available follow-up information were included. Advanced age, a degree of pulmonary involvement ≥ 50% (Hazard Ratio 2.25 [95% Cl: 1.378 to 3.671], p= 0.001), nodular consolidations and pleural effusions were associated with lower 30-day in-hospital survival rates. An exploratory subgroup analysis showed a 60.6% mortality rate in patients over 75 with ≥ 50% lung involvement on a CT-scan. Conclusions Chest CT findings such as the percentage of pulmonary involvement ≥ 50%, pleural effusion and nodular consolidation were strongly associated with 30-day mortality in COVID-19 patients. CT examinations are essential for the assessment of severe COVID-19 patients and their results must be considered when making care management decisions.

Objective The purpose of this study was to develop a natural language processing (NLP) pipeline to identify incidental thyroid nodules (ITNs) meeting criteria for sonographic follow-up and to assess both adherence rates to white paper recommendations and downstream outcomes related to these incidental findings. Methods 21583 non-contrast chest CT reports from 2017 and 2018 were retrospectively evaluated to identify reports which included either an explicit recommendation for thyroid ultrasound, a description of a nodule ≥ 1.5 cm, or description of a nodule with suspicious features. Reports from 2018 were used to train an NLP algorithm called fastText for automated identification of such reports. Algorithm performance was then evaluated on the 2017 reports. Next, any patient from 2017 with a report meeting criteria for ultrasound follow-up was further evaluated with manual chart review to determine follow-up adherence rates and nodule-related outcomes. Results NLP identified reports with ITNs meeting criteria for sonographic follow-up with an accuracy of 96.5% (95% CI 96.2-96.7) and sensitivity of 92.1% (95% CI 89.8-94.3). In 10006 chest CTs from 2017, ITN follow-up ultrasound was indicated according to white paper criteria in 81 patients (0.8%), explicitly recommended in 46.9% (38/81) of patients, and obtained in less than half of patients in which it was appropriately recommended (17/35, 48.6%). Discussion NLP accurately identified chest CT reports meeting criteria for ITN ultrasound follow-up. Radiologist adherence to white paper guidelines and subsequent referrer adherence to radiologist recommendations showed room for improvement.

Rationale and Objectives A more accurate lung nodule detection algorithm is needed. We developed a modified three-dimensional (3D) U-net deep-learning model for the automated detection of lung nodules on chest CT images. The purpose of this study was to evaluate the accuracy of the developed modified 3D U-net deep-learning model. Materials and Methods In this Health Insurance Portability and Accountability Act-compliant, Institutional Review Board-approved retrospective study, the 3D U-net based deep-learning model was trained using the Lung Image Database Consortium and Image Database Resource Initiative dataset. For internal model validation, we used 89 chest CT scans that were not used for model training. For external model validation, we used 450 chest CT scans taken at an urban university hospital in Japan. Each case included at least one nodule of >5 mm identified by an experienced radiologist. We evaluated model accuracy using the competition performance metric (CPM) (average sensitivity at 1/8, 1/4, 1/2, 1, 2, 4, and 8 false-positives per scan). The 95% confidence interval (CI) was computed by bootstrapping 1000 times. Results In the internal validation, the CPM was 94.7% (95% CI: 89.1%–98.6%). In the external validation, the CPM was 83.3% (95% CI: 79.4%–86.1%). Conclusion The modified 3D U-net deep-learning model showed high performance in both internal and external validation.

To evaluate the spatial patterns of missed lung nodules in a real-life routine screening environment.In a screening institute, 4,822 consecutive adults underwent chest CT, and each image set was independently interpreted by two radiologists in three steps: (1) independently interpreted without computer-assisted detection (CAD) software, (2) independently referred to the CAD results, (3) determined by the consensus of the two radiologists. The locations of nodules and the detection performance data were semi-automatically collected using a CAD server integrated into the reporting system. Fisher's exact test was employed for evaluating findings in different lung divisions. Probability maps were drawn to illustrate the spatial distribution of radiologists' missed nodules.Radiologists significantly tended to miss lung nodules in the bilateral hilar divisions (p0.01). Some radiologists had their own spatial pattern of missed lung nodules.Radiologists tend to miss lung nodules present in the hilar regions significantly more often than in the rest of the lung.

Rationale and Objectives We aimed to present a deep learning-based malignancy prediction model (CT-lungNET) that is simpler and faster to use in the diagnosis of small (≤2 cm) pulmonary nodules on nonenhanced chest CT and to preliminarily evaluate its performance and usefulness for human reviewers. Materials and Methods A total of 173 whole nonenhanced chest CT images containing 208 pulmonary nodules (94 malignant and 11 benign nodules) ranging in size from 5 mm to 20 mm were collected. Pathologically confirmed nodules or nodules that remained unchanged for more than 1 year were included, and 30 benign and 30 malignant nodules were randomly assigned into the test set. We designed CT-lungNET to include three convolutional layers followed by two fully-connected layers and compared its diagnostic performance and processing time with those of AlexNET by using the area under the receiver operating curve (AUROC). An observer performance test was conducted involving eight human reviewers of four different groups (medical students, physicians, radiologic residents, and thoracic radiologists) at test 1 and test 2, referring to the CT-lungNET's malignancy prediction rate with pairwise comparison receiver operating curve analysis. Results CT-lungNET showed an improved AUROC (0.85; 95% confidence interval: 0.74–0.93), compared to that of the AlexNET (0.82; 95% confidence interval: 0.71–0.91). The processing speed per one image slice for CT-lungNET was about 10 times faster than that for AlexNET (0.90 vs. 8.79 seconds). During the observer performance test, the classification performance of nonradiologists was increased with the aid of CTlungNET, (mean AUC improvement: 0.13; range: 0.03–0.19) but not significantly so in the radiologists group (mean AUC improvement: 0.02; range: −0.02 to 0.07). Conclusion CT-lungNET was able to provide better classification results with a significantly shorter amount of processing time as compared to AlexNET in the diagnosis of small pulmonary nodules on nonenhanced chest CT. In this preliminary observer performance test, CT-lungNET may have a role acting as a second reviewer for less experienced reviewers, resulting in enhanced performance in the diagnosis of early lung cancer.

Rational and Objectives: This study investigated how an AI tool impacted radiologists reading time for non-contrast chest CT exams. Materials and Methods: An AI tool was implemented into the PACS reading workflow of non-contrast chest CT exams between April and May 2020. The reading time was recorded for one CONSULTANT RADIOLOGIST and one RADIOLOGY RESIDENT by an external observer. After each case radiologists answered questions regarding additional findings and perceived case overview. Reading times were recorded for 25 cases without and 20 cases with AI tool assistance for each reader. Differences in reading time with and without the AI tool were assessed using Welch's t-test for non-inferiority with non-inferiority limits defined as 100 seconds for the consultant and 200 seconds for the resident. Results: The mean reading time for the radiology resident was not significantly affected by the AI tool (without AI 370s vs with AI 437s; +67s 95% CI -28s to +163s, p = 0.16). The reading time for the radiology consultant was also not significantly affected by the AI tool (without AI 366s vs with AI 380s; +13s (95% CI - -57s to 84s, p = 0.70). The AI tool led to additional actionable findings in 5/40 (12.5%) studies and better overview in 18/20 (90%) of studies for the resident. Conclusion: A PACS based implementation of an AI tool for concurrent reading of chest CT exams did not increase reading time with additional actionable findings made as well as a perceived better case overview for the radiology resident.

Rationale and Objectives The purpose of this paper is to describe the integration of a commercial chest CT computer-aided detection (CAD) system into the clinical radiology reporting workflow and perform an initial investigation of its impact on radiologist efficiency. It seeks to complement research into CAD sensitivity and specificity of stand-alone systems, by focusing on report generation time when the CAD is integrated into the clinical workflow. Materials and Methods A commercial chest CT CAD software that provides automated detection and measurement of lung nodules, ascending and descending aorta, and pleural effusion was integrated with a commercial radiology report dictation application. The CAD system automatically prepopulated a radiology report template, thus offering the potential for increased efficiency. The integrated system was evaluated using 40 scans from a publicly available lung nodule database. Each scan was read using two methods: (1) without CAD analytics, i.e., manually populated report with measurements using electronic calipers, and (2) with CAD analytics to prepopulate the report for reader review and editing. Three radiologists participated as readers in this study. Results CAD assistance reduced reading times by 7%–44%, relative to the conventional manual method, for the three radiologists from opening of the case to signing of the final report. Conclusion This study provides an investigation of the impact of CAD and measurement on chest CTs within a clinical reporting workflow. Prepopulation of a report with automated nodule and aorta measurements yielded substantial time savings relative to manual measurement and entry.

Rationale and Objectives To use an automatic computed tomography (CT) dose monitoring system to analyze the institutional chest and abdominopelvic CT dose data as regards the updated 2017 American College of Radiology (ACR) diagnostic reference levels (DRLs) based on water-equivalent diameter (Dw) and size-specific dose estimates (SSDE) to detect patient-size subgroups in which CT dose can be optimized. Materials and Methods All chest CT examinations performed between July 2016 and April 2017 with and without contrast material, CT of the pulmonary arteries, and abdominopelvic CT with and without contrast material were included in this retrospective study. Dw and SSDE were automatically calculated for all scans using a previously validated in-house developed Matlab software and stored into our CT dose monitoring system. CT dose data were analyzed as regards the updated ACR DRLs (size groups: 21–25 cm, 25–29 cm, 29–33 cm, 33–37 cm, 37–41 cm). SSDE and volumetric computed tomography dose index (CTDIvol) were used as CT dose parameter. Results Overall, 30,002 CT examinations were performed in the study period, 3860 of which were included in the analysis (mean age 62.1 ± 16.4 years, Dw 29.0 ± 3.3 cm; n = 577 chest CT without contrast material, n = 628 chest CT with contrast material, n = 346 CT of chest pulmonary, n = 563 abdominopelvic CT without contrast material, n = 1746 abdominopelvic CT with contrast material). Mean SSDE and CTDIvol relative to the updated DRLs were 43.3 ± 26.4 and 45.1 ± 27.9% for noncontrast chest CT, 52.3 ± 23.1 and 52.0 ± 23.1% for contrast-enhanced chest CT, 68.8 ± 29.5 and 70.0 ± 31.0% for CT of pulmonary arteries, 41.9 ± 29.2 and 43.3 ± 31.3% for noncontrast abdominopelvic CT, and 56.8 ± 22.2 and 58.8 ± 24.4% for contrast-enhanced abdominopelvic CT. Lowest dose compared to the DRLs was found for the Dw group of 21–25 cm in noncontrast abdominopelvic CT (SSDE 30.4 ± 21.8%, CTDIvol 30.8 ± 21.4%). Solely the group of patients with a Dw of 37–41 cm undergoing noncontrast abdominopelvic CT exceeded the ACR DRL (SSDE 100.3 ± 59.0%, CTDIvol 107.1 ± 63.5%). Conclusions On average, mean SSDE and CTDIvol of our institutional chest and abdominopelvic CT protocols were lower than the updated 2017 ACR DRLs. Size-specific subgroup analysis revealed a wide variability of SSDE and CTDIvol across CT protocols and patient size groups with a transgression of DRLs in noncontrast abdominopelvic CT of large patients (Dw 37–41 cm).

OBJECTIVES: To investigate the chest CT and clinical characteristics of COVID-19 pneumonia and H1N1 influenza, and explore the radiologist diagnosis differences between COVID-19 and influenza. MATERIALS AND METHODS: This cross-sectional study included a total of 43 COVID-19-confirmed patients (24 men and 19 women, 49.90 ± 18.70 years) and 41 influenza-confirmed patients (17 men and 24 women, 61.53 ± 19.50 years). Afterwards, the chest CT findings were recorded and 3 radiologists recorded their diagnoses of COVID-19 or of H1N1 influenza based on the CT findings. RESULTS: The most frequent clinical symptom in patients with COVID-19 and H1N1 pneumonia were dyspnea (96.6%) and cough (62.5%), respectively. The CT findings showed that the COVID-19 group was characterized by GGO (88.1%), while the influenza group had features such as GGO (68.4%) and consolidation (66.7%). Compared to the influenza group, the COVID-19 group was more likely to have GGO (88.1% vs. 68.4%, p = 0.032), subpleural sparing (69.0% vs. 7.7%, p

Research on implementation of artificial intelligence (AI) in radiology workflows and its impact on reports remains scarce. In this study, we aim to assess if an AI platform would perform better than clinical radiology reports in evaluating noncontrast chest computed tomography (CT) scans.Consecutive patients who had undergone noncontrast chest CT were retrospectively identified. The radiology reports were reviewed in a binary fashion for reporting of pulmonary lesions, pulmonary emphysema, aortic dilatation, coronary artery calcifications (CAC), and vertebral compression fractures (VCF). CT scans were then processed using an AI platform. The reports' findings and the AI results were subsequently compared to a consensus read by two board-certificated radiologists as reference.A total of 100 patients (mean age: 64.2 ± 14.8 years; 57% males) were included in this study. Aortic segmentation and calcium quantification failed to be processed by AI in 2 and 3 cases, respectively. AI showed superior diagnostic performance in identifying aortic dilatation (AI: sensitivity: 96.3%, specificity: 81.4%, AUC: 0.89) vs (Reports: sensitivity: 25.9%, specificity: 100%, AUC: 0.63), p0.001; and CAC (AI: sensitivity: 89.8%, specificity: 100, AUC: 0.95) vs (Reports: sensitivity: 75.4%, specificity: 94.9%, AUC: 0.85), p = 0.005. Reports had better performance than AI in identifying pulmonary lesions (Reports: sensitivity: 97.6%, specificity: 100%, AUC: 0.99) vs (AI: sensitivity: 92.8%, specificity: 82.4%, AUC: 0.88), p = 0.024; and VCF (Reports: sensitivity:100%, specificity: 100%, AUC: 1.0) vs (AI: sensitivity: 100%, specificity: 63.7%, AUC: 0.82), p0.001. A comparable diagnostic performance was noted in identifying pulmonary emphysema on AI (sensitivity: 80.6%, specificity: 66.7%. AUC: 0.74) and reports (sensitivity: 74.2%, specificity: 97.1%, AUC: 0.86), p = 0.064.Our results demonstrate that incorporating AI support platforms into radiology workflows can provide significant added value to clinical radiology reporting.

The COVID-19 epidemic, which is caused by the novel coronavirus SARS-CoV-2, has spread rapidly to become a world-wide pandemic. Chest radiography and chest CT are frequently used to support the diagnosis of COVID-19 infection. However, multiple cases of COVID-19 transmission in radiology department have been reported. Here we summarize the lessons we learned and provide suggestions to improve the infection control and prevention practices of healthcare workers in departments of radiology.

Rationale and Objectives The objectives of this study were to compare the visibility and quantification of subsolid nodules (SSNs) on computed tomography (CT) using adaptive iterative dose reduction using three-dimensional processing between 7 and 42 mAs and to assess the association of size-specific dose estimate (SSDE) with relative measured value change between 7 and 84 mAs (RMVC7–84) and relative measured value change between 42 and 84 mAs (RMVC42–84). Materials and Methods As a Japanese multicenter research project (Area-detector Computed Tomography for the Investigation of Thoracic Diseases [ACTIve] study), 50 subjects underwent chest CT with 120 kV, 0.35 second per location and three tube currents: 240 mA (84 mAs), 120 mA (42 mAs), and 20 mA (7 mAs). Axial CT images were reconstructed using adaptive iterative dose reduction using three-dimensional processing. SSN visibility was assessed with three grades (1, obscure, to 3, definitely visible) using CT at 84 mAs as reference standard and compared between 7 and 42 mAs using t test. Dimension, mean CT density, and particular SSDE to the nodular center of 71 SSNs and volume of 58 SSNs (diameter >5 mm) were measured. Measured values (MVs) were compared using Wilcoxon signed-rank tests among CTs at three doses. Pearson correlation analyses were performed to assess the association of SSDE with RMVC7–84: 100 × (MV at 7 mAs − MV at 84 mAs)/MV at 84 mAs and RMVC42–84. Results SSN visibilities were similar between 7 and 42 mAs (2.76 ± 0.45 vs 2.78 ± 0.40) (P = .67). For larger SSNs (>8 mm), MVs were similar among CTs at three doses (P > .05). For smaller SSNs ( Conclusions Comparable quantification was demonstrated irrespective of doses for larger SSNs. For smaller SSNs, nodular exaggerating effect associated with decreased SSDE on CT at 7 mAs compared to 84 mAs could result in comparable visibilities to CT at 42 mAs.

Rationale and Objectives This study aims to demonstrate the feasibility of processing computed tomography (CT) images with a custom window blending algorithm that combines soft-tissue, bone, and lung window settings into a single image; to compare the time for interpretation of chest CT for thoracic trauma with window blending and conventional window settings; and to assess diagnostic performance of both techniques. Materials and Methods Adobe Photoshop was scripted to process axial DICOM images from retrospective contrast-enhanced chest CTs performed for trauma with a window-blending algorithm. Two emergency radiologists independently interpreted the axial images from 103 chest CTs with both blended and conventional windows. Interpretation time and diagnostic performance were compared with Wilcoxon signed-rank test and McNemar test, respectively. Agreement with Nexus CT Chest injury severity was assessed with the weighted kappa statistic. Results A total of 13,295 images were processed without error. Interpretation was faster with window blending, resulting in a 20.3% time saving (P Conclusions In this pilot study utilizing retrospective data, window blending allows faster preliminary interpretation of axial chest CT performed for trauma, with no significant difference in diagnostic performance compared to conventional window settings. Future studies would be required to assess the utility of window blending in clinical practice.

Rationale and Objectives This study aimed to determine the optimal tube potential for unenhanced chest computed tomographies (CTs) with age-related phantoms. Materials and Methods Three physical anthropomorphic phantoms (newborn, 5-year-old child, and adult) were scanned on a third-generation dual-source CT using CAREkV in semi-mode and CAREDose4D (ref. KV: 120; ref. mAs 50). Scans were performed with all available tube potentials (70–150 kV and Sn150 kV). The lowest volume computed tomography dose index (CTDIvol) was selected to perform additional Sn100-kV scans with matched and half (Sn100-half) CTDIvol value. Image quality was evaluated on the basis of contrast-to-noise ratio (CNR). Results For the newborn phantom, 70–110 kV was selected as the optimal range (0.36–0.37 mGy). Using Sn150 kV led to an increase in radiation dose (0.75 mGy) without improving CNR (96.9 vs 101.5). Sn100-half showed a decrease in CNR (73.1 vs 101.5). The lowest CTDIvol for the child phantom was achieved between 100 and 120 kV (0.78–0.80 mGy). Using Sn150 kV increased radiation dose (1.02 mGy) without improvement of CNR (92.4 vs 95.8). At Sn100-half CNR was decreased (61.4 vs 95.8). For adults, 140 and 150 kV revealed the lowest CTDIvol (2.68 and 2.67 mGy). The Sn150 kV scan delivered comparable CNR (54.4 vs 56.6), but a lower CTDIvol (2.08 mGy). At Sn100-half CNR was comparable to the 150 kV scan (58.1 vs 56.6). Conclusion Unenhanced chest CT performed at 100 kV or 150 kV with tin filtration enables radiation dose reduction for the adult phantom, but not for the pediatric phantoms.

Rationale and Objectives This study aimed to determine the diagnostic aid of computed tomography (CT) features for the differentiation of active alveolitis and fibrosis using a CT texture analysis (CTTA) prototype and CT densitometry in patients with systemic sclerosis (SSc) using ancillary high-resolution computed tomography (HRCT) features and their longitudinal course as standard of reference. Materials and Methods We retrospectively analyzed thin-slice noncontrast chest CT image data of 43 patients with SSc (18 men, mean age 51.55 ± 15.52 years; range 23–71 years). All of them had repeated noncontrast enhanced HRCT of the lung. Classification into active alveolitis or fibrosis was done on HRCT based on classical HRCT findings (active alveolitis [19; 44.2%] and fibrosis [24; 55.8%]) and their course at midterm. Results were compared to pulmonary functional tests and were followed up by CT. Ground glass opacity was considered suggestive of alveolitis, whereas coarse reticulation with parenchymal distortion, traction bronchiectasis, and honeycombing were assigned to fibrosis. Results Statistically significant differences in CTTA were found for first-order textural features (mean intensity, average, deviation, skewness) and second-order statistics (entropy of co-occurrence matrix, mean number of nonuniformity (NGLDM), entropy of NGLDM, entropy of heterogeneity, intensity, and average). Cut-off value for the prediction of fibrosis at baseline was significant for entropy of intensity ( P value P value P value P value At pulmonary functional tests, forced expiratory volume in 1 second and single-breath diffusion capacity for carbon monoxide were significantly lower in fibrosis than in alveolitis 2.03 ± 0.78 vs. 2.61 ± 0.83, P P Conclusions CTTA parameters are significantly different in active alveolitis vs. fibrosis in patients with SSc and may be helpful for differentiation of these two entities.

Rationale and Objectives The study aimed to determine whether the addition of the Fleischner Society guidelines to chest computed tomography (CT) reports identifying incidental pulmonary nodules affects follow-up care. Patients and Methods Beginning in 2008, a template containing the Fleischner Society guidelines was added at the interpreting radiologist's discretion to chest CT reports describing incidental solid pulmonary nodules at our institution. The records of all medical centers in Olmsted county were used to capture the complete medical history of local patients >35 years old diagnosed with a pulmonary nodule from April 1, 2008 to October 1, 2011. Patients with a history of cancer or previously diagnosed nodule, or who died before follow-up, were excluded. Patients were categorized according to whether they did (“template group”) or did not (“control group”) have the template added. Nodule size and smoking history were used to determine recommended follow-up care. Differences in follow-up were compared between groups using Pearson's chi-square test. Results A total of 510 patients (276 in the template group, 234 in the control group) were included in the study. Only 198 patients (39%) received their recommended follow-up care. Template group patients were significantly more likely to receive recommended follow-up care compared to control group patients (45% vs 31%, P = .0014). Most patients whose management did not adhere to Fleischner Society guidelines did not receive a recommended follow-up chest CT (210 out of 312, 67%). Conclusions The addition of the Fleischner Society guidelines to chest CT reports significantly increases the likelihood of receiving recommended follow-up care for patients with incidental pulmonary nodules. Additional education is needed to improve appropriate guideline utilization by radiologists and adherence by ordering providers.

PURPOSE: To develop and evaluate an automated machine learning (ML) algorithm for segmenting the paraspinous muscles on chest computed tomography (CT) scans to evaluate for presence of sarcopenia. METHODS: A convolutional neural network based on the U-Net architecture was trained to perform muscle segmentation on a dataset of 1,875 single slice CT images and was tested on 209 CT images of participants in the National Lung Screening Trial (NLST). Low-dose, non-contrast CT examinations were obtained at 33 clinical sites, using scanners from 4 manufacturers. The study participants had a mean age of 71.6 years (range, 70-74 years). Ground truth was obtained by manually segmenting the left paraspinous muscle at the level of the T12 vertebra. Muscle cross-sectional area (CSA) and muscle attenuation (MA) were recorded. Comparison between the ML algorithm and ground truth measures of muscle CSA and MA were obtained using Dice similarity coefficients and Pearson correlations. RESULTS: Compared with ground truth segmentation, the ML algorithm achieved median (standard deviation) Dice scores of 0.94 (0.04) in the test set. Mean (SD) muscle CSA was 14.3 (3.6) cm(2) for ground truth and 13.7 (3.5) cm(2) for ML segmentation Mean (SD) MA was 41.6 (7.6) Hounsfeld units (HU) for ground truth and 43.5 (7.9) HU for ML segmentation. There was high correlation between ML algorithm and ground truth for muscle CSA (r(2)=0.86; p

Rationale and Objectives The study aimed to evaluate the performances of two iterative reconstruction (IR) algorithms and of filtered back projection (FBP) when using reduced-dose chest computed tomography (RDCT) compared to standard-of-care CT. Materials and Methods An institutional review board approval was obtained. Thirty-six patients with hematologic malignancies referred for a control chest CT of a known lung disease were prospectively enrolled. Patients underwent standard-of-care scan reconstructed with hybrid IR, followed by an RDCT reconstructed with FBP, hybrid IR, and iterative model reconstruction. Objective and subjective quality measurements, lesion detectability, and evolution assessment on RDCT were recorded. Results For RDCT, the CTDIvol (volumetric computed tomography dose index) was 0.43 mGy⋅cm for all patients, and the median [interquartile range] effective dose was 0.22 mSv [0.22–0.24]; corresponding measurements for standard-of-care scan were 3.4 mGy [3.1–3.9] and 1.8 mSv [1.6–2.0]. Noise significantly decreased from FBP to hybrid IR and from hybrid IR to iterative model reconstruction on RDCT, whereas lesion conspicuity and diagnostic confidence increased. Accurate evolution assessment was obtained in all cases with IR. Emphysema identification was higher with iterative model reconstruction. Conclusion Although iterative model reconstruction offered better diagnostic confidence and emphysema detection, both IR algorithms allowed an accurate evolution assessment with an effective dose of 0.22 mSv.

Background Coronary artery calcification (CAC) is a marker of atherosclerosis and an independent risk factor for cardiac-related mortality and frequently detected on noncontrast chest CT. We aimed to investigate the reliability and accuracy of determining CAC using noncontrast, nongated chest CT with 256-detector row. Materials and Methods A total of 1318 patients for chest examination were enrolled to undergo both nongated chest CT and dedicated calcium-scoring CT (CSCT) on a 256-detector row CT scanner. The chest CT was scanned in fast-helical mode with 8 cm collimation, 0.28 second rotation speed and pitch 0.992:1 to cover entire chest. CSCT used single prospective ECG-triggered cardiac axial mode with 0.28 second rotation speed covering only the heart. CAC scores (Agatston, mass, and volume) were determined using both image sets and were statistically compared. Results Sensitivity and specificity of nongated chest CT for determining positive CAC was 94.8% (182/192) and 100%, respectively. The agreement in assessing the quantitative Agatston, volume, and mass scores between the nongated chest CT and CSCT was almost perfect, with the intraclass correlation coefficient values of 0.998, 0.999, and 0.999, respectively. Additionally, there was a good agreement in CAC quantification between the nongated chest CT and dedicated CSCT with small coefficient of variation: mass score (9.0%), volume score (9.5%), and Agatston score (12.6%). Conclusion Nongated chest CT with 256-detector row is a reliable imaging mode for detecting and quantifying calcifications in coronary arteries compared with dedicated calcium-scoring CT.

Rationale and Objectives The primary objective of this study was to compare computed tomography (CT) volumetric analysis of pleural effusions with thoracentesis volumes. The secondary objective of this study was to compare subjective grading of pleural effusion size with thoracentesis volumes. Materials and Methods This was a retrospective study of 67 patients with free-flowing pleural effusions who underwent therapeutic thoracentesis. CT volumetric analysis was performed on all patients; the CT volumes were compared with the thoracentesis volumes. In addition, the subjective grading of pleural effusion size was compared with the thoracentesis volumes. Results The average difference between CT volume and thoracentesis volume was 9.4 mL (1.3%) ± 290 mL (30%); these volumes were not statistically different (P = .79, paired two-tailed Student's t-test). The thoracentesis volume of a “small,” “moderate,” and “large” pleural effusion, as graded on chest CT, was found to be approximately 410 ± 260 cc, 770 ± 270 mL and 1370 ± 650 mL, respectively; the thoracentesis volume of a “small,” “moderate,” and “large” pleural effusion, as graded on chest radiograph, was found to be approximately 610 ± 320 mL, 1040 ± 460 mL, and 1530 ± 830 mL, respectively. Conclusions CT volumetric analysis is an accessible tool that can be used to accurately quantify the size of pleural effusions.

Rationale and Objectives To evaluate the performance of a computer-aided detection (CAD) system with bone suppression imaging when applied to unselected consecutive chest radiographs (CXRs) with computed tomography (CT) correlation. Materials and Methods This study included 586 consecutive patients with standard or portable CXRs who had a chest CT scan on the same day. Among the 586 CXRs, 438 had various abnormalities, including 46 CXRs with 66 lung nodules, and 148 CXRs had no significant abnormalities. A commercially available CAD system was applied to all 586 CXRs. True nodules and false positives (FPs) marked on CXRs by the CAD system were evaluated based on the corresponding chest CT findings. Results The CAD system marked 47 of 66 (71%) lung nodules in this consecutive series of CXRs. The mean FP rate per image was 1.3 across all 586 CXRs, with 1.5 FPs per image on the 438 abnormal CXRs and 0.8 FPs per image on the 148 normal CXRs. A total of 41% of the 752 FP marks were related to non-nodule pathologic findings. Conclusions A currently available CAD system marked 71% of radiologist-identified lung nodules in a large consecutive series of CXRs, and 41% of “false” marks were caused by pathologic findings.

Rationale and Objectives Characterization of smoking-related lung disease typically consists of visual assessment of chest computed tomographic (CT) images for the presence and extent of emphysema and centrilobular nodularity (CN). Quantitative analysis of emphysema and CN may improve the accuracy, reproducibility, and efficiency of chest CT scoring. The purpose of this study was to develop a fully automated texture-based system for the detection and quantification of centrilobular emphysema (CLE) and CN in chest CT images. Materials and Methods A novel approach was used to prepare regions of interest (ROIs) within the lung parenchyma for representation by texture features associated with the gray-level run-length and gray-level gap-length methods. These texture features were used to train a multiple logistic regression classifier to discriminate between normal lung tissue, CN or “smoker's lung,” and CLE. This classifier was trained and evaluated on 24 and 71 chest CT scans, respectively. Results During training, the classifier correctly classified 89% of ROIs depicting normal lung tissue, 74% of ROIs depicting CN, and 95% of ROIs manifesting CLE. When the performance of the classifier in quantifying extent of CN and CLE was evaluated on 71 chest CT scans, 65% of ROIs in smokers without CLE were classified as CN, compared to 31% in nonsmokers ( P P Conclusions The texture-based framework described herein facilitates successful discrimination among normal lung tissue, CN, and CLE and can be used for the automated quantification of smoking-related lung disease.

Rationale and Objectives To assess practice patterns in evaluating incidental findings at chest computed tomography (CT) to determine the need for further education. Materials and Methods A survey was given to 1600 radiologists, presenting four clinical case questions regarding the evaluation/significance of the following incidental findings at chest CT: thyroid lesion; enlarged mediastinal lymph nodes; asymptomatic, small pulmonary embolus; and small lung nodule. The respondents' answers were compared with “truth,” as defined by the best evidence available in the medical literature. Additional questions elicited the respondents' demographics and comfort levels in addressing the findings. Analysis of variance models with a Tukey correction for post hoc comparisons and chi-square tests were used to determine if any demographic factors or comfort levels were predictive of higher correct response rates. Results The overall survey response rate was 28% (445/1600). Correct case response rates ranged from 26% (115/442) to 79% (343/445). Only 6% (28/438) of respondents chose the correct answers for all cases. Up to 80% (353/440) of respondents felt comfortable in addressing findings, and only 57% (252/443) of respondents felt that they needed more training in this area. Fellowship training in cardiothoracic radiology, working in a teaching practice, and subspecialization in abdominal or cardiothoracic radiology were predictive of higher correct response rates. Except for one case question, the comfort level was not predictive of correct response rate. Conclusions There was considerable variability among radiologists and substantial deviation from best medical practice with regard to the interpretation/evaluation of incidental findings at chest CT, signifying a significant need for further education.

The increasing use of computed tomography (CT) has been accompanied by rising concerns over potential radiation-related health risks, especially cancer, and a need to minimize such risks.We conducted 2186 low-dose helical chest CT scans among 1235 nuclear weapons workers at elevated risk of lung cancer, setting the CT scanner tube current at 30 mAs for all participants with BMI35 kg/m(2) and permitting technologists to raise mAs levels for participants with BMI ≥35 kg/m(2). Dose-length product (DLP) was recorded from the CT scanner, permitting calculation of effective dose. Phantom-based estimates of effective dose were also made. A chest radiologist recorded acceptability of image quality.The study population was significantly overweight: 79% exceeded a body mass index (BMI)25 kg/m(2) and 37.1% exceeded a BMI ≥30 kg/m(2). Nearly 90% of CT scans were performed using a tube current setting of 30 mAs and had a mean DLP-based effective dose of 1.3 mSv. The phantom-based estimate of effective dose was lower at 1.1 mSv. Among participants with a BMI ≥35 kg/m(2), 92% were scanned at 40 or 50 mAs, which was associated with a DLP-based effective dose of 1.6 and 2.0 mSv, respectively. Image quality was satisfactory in 99.8% of scans.Application of simple BMI-based guidelines and DLP tracking of low-dose helical chest CT scans in a lung cancer screening program minimizes radiation dose, even in a largely overweight population.

Rationale and Objectives. The purpose of this study was to evaluate nontarget locations identified in a study of lung nodule detection with spiral computed tomographic (CT) scans that compared cine and film presentations. Materials and methods. In a previous study of lung nodule detection, eight observers were asked to identify 10 nodule locations in each of five CT scans containing eight simulated nodules. In the current study, each nontarget location that was reported more than once in the previous study was inspected with a stack-mode display in both cine and static modes. The nontarget locations were evaluated for probable identity, shape, and distance from the peripheral lung surface. Results. Fifty-two nontarget locations included clinically undetected pulmonary nodules (n = 12), lymph nodes (n = 2), unclassifiable structures (n = 2), pleural scars (n = 8), and vascular structures (n = 28). Five nontarget locations contained vessels with complex courses apparent only with cine mode. As a group, nontarget locations were significantly closer to the periphery than would be expected by chance (for all locations, P Conclusion. The lower reporting threshold caused by the observer instructions to find 10 targets resulted in increased reporting of structures with a nodular appearance. The locations of these reports in the lung periphery can be attributed to the relationship between frequent disease and a nearly featureless background in the lung periphery.