Comparison Of Radiologists Research Articles

No spectators in a pandemic: A comparison of radiologists, radiology residents, and CT technicians in interpreting chest CT scans for COVID-19

ObjectiveTo compare the diagnostic accuracy of radiology trainees, CT technicians, and radiologists in interpreting chest CT scans for the detection of COVID-19. MethodsRetrospective data were analyzed from 269 reading assessments of chest CT scans for COVID-19. These were conducted by 160 radiologists, 41 radiology residents, and 68 CT technicians from diverse countries and performed online using DetectedX software between March 30, 2020, and January 1, 2022. The readers examined and assessed realistic, de-identified, digital chest CT images—15 positive and 15 negative for COVID-19. Information about the readers' clinical roles (radiologist, radiology resident, or CT technician) was collected alongside measures of their performance in distinguishing between positive and negative cases (sensitivity, specificity, and ROC AUC). The data were evaluated with Kruskal–Wallis tests to identify any differences in performance between the roles. Post hoc comparisons using Bonferroni-corrected Dunn's tests were then used to identify any significant pairwise differences. ResultsStatistically significant differences were observed in specificity (p < 0.001) and ROC AUC (p < 0.001) when comparing the three groups. In the pairwise comparisons, differences in specificity were only found between CT technicians and radiologists (p = 0.001), while ROC AUC was significantly different between CT technicians and radiologists (p = 0.001) and between CT technicians and radiology trainees (p = 0.016). No statistically significant differences were observed in sensitivity (p = 0.309) between the groups. ConclusionsThe study identifies both diagnostic potential and areas for improvement for radiology residents and CT technicians. Notably, the performance of residents mirrored that of radiologists, underscoring their crucial role in early case management. However, while CT technicians demonstrated comparable sensitivity, their specificity and ROC AUC were lower, highlighting an opportunity for targeted training to enhance their ability to differentiate COVID-19 from other pathologies.

Mammographic density assessment: comparison of radiologists, automated volumetric measurement, and artificial intelligence-based computer-assisted diagnosis.

Artificial intelligence-based computer-assisted diagnosis (AI-CAD) is increasingly used for mammographic exams, and its role in mammographic density assessment should be evaluated. To assess the inter-modality agreement between radiologists, automated volumetric density measurement program (Volpara), and AI-CAD system in breast density categorization using the Breast Imaging-Reporting and Data System (BI-RADS) density categories. A retrospective review was conducted on 1015 screening digital mammograms that were performed in Asian female patients (mean age = 56 years ± 10 years) in our health examination center between December 2022 and January 2023. Four radiologists with two different levels of experience (expert and general radiologists) performed density assessments. Agreement between the radiologists, Volpara, and AI-CAD (Lunit INSIGHT MMG) was evaluated using weighted kappa statistics and matched rates. Inter-reader agreement between expert and general radiologists was substantial (k = 0.65) with a matched rate of 72.8%. The agreement was substantial between expert or general radiologists and Volpara (k = 0.64-0.67) with a matched rate of 72.0% but moderate between expert or general radiologists and AI-CAD (k = 0.45-0.58) with matched rates of 56.7%-67.0%. The agreement between Volpara and AI-CAD was moderate (k = 0.53) with a matched rate of 60.8%. The agreement in breast density categorization between radiologists and automated volumetric density measurement program (Volpara) was higher than the agreement between radiologists and AI-CAD (Lunit INSIGHT MMG).

Comparison of Radiologists and Deep Learning for US Grading of Hepatic Steatosis.

Background Screening for nonalcoholic fatty liver disease (NAFLD) is suboptimal due to the subjective interpretation of US images. Purpose To evaluate the agreement and diagnostic performance of radiologists and a deep learning model in grading hepatic steatosis in NAFLD at US, with biopsy as the reference standard. Materials and Methods This retrospective study included patients with NAFLD and control patients without hepatic steatosis who underwent abdominal US and contemporaneous liver biopsy from September 2010 to October 2019. Six readers visually graded steatosis on US images twice, 2 weeks apart. Reader agreement was assessed with use of κ statistics. Three deep learning techniques applied to B-mode US images were used to classify dichotomized steatosis grades. Classification performance of human radiologists and the deep learning model for dichotomized steatosis grades (S0, S1, S2, and S3) was assessed with area under the receiver operating characteristic curve (AUC) on a separate test set. Results The study included 199 patients (mean age, 53 years ± 13 [SD]; 101 men). On the test set (n = 52), radiologists had fair interreader agreement (0.34 [95% CI: 0.31, 0.37]) for classifying steatosis grades S0 versus S1 or higher, while AUCs were between 0.49 and 0.84 for radiologists and 0.85 (95% CI: 0.83, 0.87) for the deep learning model. For S0 or S1 versus S2 or S3, radiologists had fair interreader agreement (0.30 [95% CI: 0.27, 0.33]), while AUCs were between 0.57 and 0.76 for radiologists and 0.73 (95% CI: 0.71, 0.75) for the deep learning model. For S2 or lower versus S3, radiologists had fair interreader agreement (0.37 [95% CI: 0.33, 0.40]), while AUCs were between 0.52 and 0.81 for radiologists and 0.67 (95% CI: 0.64, 0.69) for the deep learning model. Conclusion Deep learning approaches applied to B-mode US images provided comparable performance with human readers for detection and grading of hepatic steatosis. Published under a CC BY 4.0 license. Supplemental material is available for this article. See also the editorial by Tuthill in this issue.

Interstitial lung abnormalities (ILA) on routine chest CT: Comparison of radiologists’ visual evaluation and automated quantification

PurposeWe aimed to evaluate the performance of a fully automated quantitative software in detecting interstitial lung abnormalities (ILA) according to the Fleischner Society guidelines on routine chest CT compared with radiologists’ visual analysis. MethodThis retrospective single-centre study included participants with ILA findings and 1:2 matched controls who underwent routine chest CT using various CT protocols for health screening. Two thoracic radiologists independently reviewed the CT images using the Fleischner Society guidelines. We developed a fully automated quantitative tool for detecting ILA by modifying deep learning-based quantification of interstitial lung disease and evaluated its performance using the radiologists’ consensus for ILA as a reference standard. ResultsA total of 336 participants (mean age, 70.5 ± 6.1 years; M:F = 282:54) were included. Inter-reader agreements were substantial for the presence of ILA (weighted κ, 0.74) and fair for its subtypes (weighted κ, 0.38). The quantification system for identifying ILA using a threshold of 5 % in at least one zone showed 67.6 % sensitivity, 93.3 % specificity, and 90.5 % accuracy. Eight of 20 (40 %) false positives identified by the system were underestimated by readers for ILA extent. Contrast-enhancement in a certain vendor and suboptimal inspiration caused a true false-positive on the system (all P < 0.05). The best cut-off value of abnormality extent detecting ILA on the system was 3.6 % (sensitivity, 84.8 %; specificity 92.4 %). ConclusionsInter-reader agreement was substantial for ILA but only fair for its subtypes. Applying an automated quantification system in routine clinical practice may aid the objective identification of ILA.

Comparison of Radiologists and Other Specialists in the Performance of Lumbar Puncture Procedures Over Time.

Lumbar punctures may be performed by many different types of health care providers. We evaluated the percentages of lumbar punctures performed by radiologists-versus-nonradiologist providers, including changes with time and discrepancies between specialties. Lumbar puncture procedure claims were identified in a 5% sample of Medicare beneficiaries from 2004 to 2017 and classified by provider specialty, site of service, day of week, and patient complexity. Compound annual growth rates for 2004 versus 2017 were calculated; t test and χ2 statistical analyses were performed. Lumbar puncture use increased from 163.3 to 203.4 procedures per 100,000 Medicare beneficiaries from 2004 to 2017 (overall rate, 190.3). Concurrently, the percentage of lumbar punctures performed by radiologists increased from 37.1% to 54.0%, while proportions performed by other major physician specialty groups either declined (eg, neurologists from 23.5% to 10.0%) or were largely unchanged. While radiologists saw the largest absolute increase in the percentage of procedures, the largest relative increase occurred for nonphysician providers (4.2% in 2004 to 7.5% in 2017; +78.6%). In 2017, radiologists performed most procedures on weekdays (56.2%) and a plurality on weekends (38.2%). Comorbidity was slightly higher in patients undergoing lumbar puncture by radiologists (P < .001). Radiologists now perform most lumbar puncture procedures for Medicare beneficiaries in both the inpatient and outpatient settings. The continuing shift in lumbar puncture responsibility from other specialists to radiologists has implications for clinical workflows, cost, radiation exposure, and postgraduate training.

Diagnostic performance for pulmonary adenocarcinoma on CT: comparison of radiologists with and without three-dimensional convolutional neural network.

To compare diagnostic performance for pulmonary invasive adenocarcinoma among radiologists with and without three-dimensional convolutional neural network (3D-CNN). Enrolled were 285 patients with adenocarcinoma in situ (AIS, n = 75), minimally invasive adenocarcinoma (MIA, n = 58), and invasive adenocarcinoma (IVA, n = 152). A 3D-CNN model was constructed with seven convolution-pooling and two max-pooling layers and fully connected layers, in which batch normalization, residual connection, and global average pooling were used. Only the flipping process was performed for augmentation. The output layer comprised two nodes for two conditions (AIS/MIA and IVA) according to prognosis. Diagnostic performance of the 3D-CNN model in 285 patients was calculated using nested 10-fold cross-validation. In 90 of 285 patients, results from each radiologist (R1, R2, and R3; with 9, 14, and 26 years of experience, respectively) with and without the 3D-CNN model were statistically compared. Without the 3D-CNN model, accuracy, sensitivity, and specificity of the radiologists were as follows: R1, 70.0%, 52.1%, and 90.5%; R2, 72.2%, 75%, and 69%; and R3, 74.4%, 89.6%, and 57.1%, respectively. With the 3D-CNN model, accuracy, sensitivity, and specificity of the radiologists were as follows: R1, 72.2%, 77.1%, and 66.7%; R2, 74.4%, 85.4%, and 61.9%; and R3, 74.4%, 93.8%, and 52.4%, respectively. Diagnostic performance of each radiologist with and without the 3D-CNN model had no significant difference (p > 0.88), but the accuracy of R1 and R2 was significantly higher with than without the 3D-CNN model (p < 0.01). The 3D-CNN model can support a less-experienced radiologist to improve diagnostic accuracy for pulmonary invasive adenocarcinoma without deteriorating any diagnostic performances. • The 3D-CNN model is a non-invasive method for predicting pulmonary invasive adenocarcinoma in CT images with high sensitivity. • Diagnostic accuracy by a less-experienced radiologist was better with the 3D-CNN model than without the model.

Man Versus Machine Part 2: Comparison of Radiologists' Interpretations and NeuroQuant Measures of Brain Asymmetry and Progressive Atrophy in Patients With Traumatic Brain Injury.

This study is an expanded version of an earlier study, which compared NeuroQuant measures of MRI brain volume with the radiologist's traditional approach in outpatients with mild or moderate traumatic brain injury. NeuroQuant volumetric analyses were compared with the radiologists' interpretations. NeuroQuant found significantly higher rates of atrophy (50.0%), abnormal asymmetry (83.3%), and progressive atrophy (70.0%) than the radiologists (12.5%, 0% and 0%, respectively). Overall, NeuroQuant was more sensitive for detecting at least one sign of atrophy, abnormal asymmetry, or progressive atrophy (95.8%) than the traditional radiologist's approach (12.5%).

NeuroQuant® Revealed Hippocampal Atrophy in a Patient With Traumatic Brain Injury

NeuroQuant® Revealed Hippocampal Atrophy in a Patient With Traumatic Brain Injury

Comparison of Radiologists and Technologists in the Performance of Air-Contrast Barium Enemas

The purpose of this study was to determine whether the rate of polyp detection and the quality of air-contrast barium enema (ACBE) procedures performed by technologists differ from those performed by radiologists. Our results showed that well-trained certified technologists can perform ACBE similar in overall quality and accuracy to ACBE performed by attending physicians and residents. Training technologists to perform ACBE may help to alleviate the radiology staffing shortage in the United States.

Comparison of Radiologists' confidence in excluding significant colorectal neoplasia with multidetector-row CT colonography compared with double contrast barium enema

The aim of this study was to compare the confidence of experienced radiologists in excluding colonic neoplasia with CT colonography (CTC) compared with barium enema. 78 patients (median age 70 years, range 61-87 years, 44 women) underwent same day CTC and barium enema. Two radiologists experienced in reporting barium enema assessed whether the examination had excluded a polyp 6 mm or greater as "yes", "probably" or "no" for each of 6 colonic segments. Two different radiologists experienced in CTC independently performed the same assessment on the CT datasets. Responses were compared using a paired exact test. Formal barium enema and CT reports were compared with any endoscopic examination performed within 1 year. Studies reporting polyps 6 mm+ in patients not subsequently undergoing endoscopy were reviewed by two independent observers. Radiologists stated they had confidently excluded a significant lesion in 314 (71%) and 382 (86%) of 444 segments with barium enema and CTC, respectively (p<0.001). Confidence was significantly higher with CTC in the in the descending and ascending colon (p = 0.02 and p<0.001, respectively), and caecum (p<0.001). 22 patients underwent some form of endoscopy. Of five patients with proven colorectal neoplasia (including two with cancer), CTC and barium enema correctly identified five and three, respectively. In 56 patients not undergoing endoscopy, CTC reported 17 polyps 6 mm+, of which 16 were retrospectively classified as definite or probable. 11 could not be identified on the barium enema, even in retrospect. Confidence in excluding polyps 6 mm or larger is significantly greater with CT colonography particularly in the proximal colon.

Measuring the Academic Radiologist's Clinical Productivity: Applying RVU Adjustment Factors

Rationale and Objectives To improve understanding of academic radiologists' clinical workloads, the Society of Chairmen of Academic Radiology Departments (SCARD) performed surveys to collect workload data for radiologists in 20 departments; workload was measured in relative value units (RVUs) per full-time equivalent (FTE). Although they were useful for comparisons within some subspecialties, the workload data proved inadequate for comparisons across sections, and adjustment factors were needed for each Current Procedure Terminology (CPT) code. Materials and Methods All CPT codes for examinations were divided into groups with similar radiologist work effort. Focusing on radiologists who worked almost exclusively in each group, the authors created adjustment factors by using data from the individual radiologists at each institution. Results The adjustment factors are 0.50 for angiography, 0.58 for computed tomography and magnetic resonance imaging, and 1.0 for nuclear medicine, plain radiography, and special procedures (no adjustment needed for these groups). These factors are multiplied by the work RVUs for each examination to create the adjusted workload RVUs. Conclusion The SCARD survey provided very useful clinical workload data, with workload measured in work RVUs per FTE for specific subspecialty sections. The new adjusted workload RVUs allow comparison of radiologists' workload across subspecialties.

Wisconsin cystic fibrosis chest radiograph scoring system: validation and standardization for application to longitudinal studies.

This study was designed to achieve a final modeling, validation, and standardization plan for the Wisconsin cystic fibrosis (CF) chest radiographic scoring system. Sixty chest radiographs were selected to reflect a range of severity of lung pathology in children with CF. Seven experienced volunteer raters (three radiologists and four pediatric pulmonologists) from five institutions were recruited to evaluate and score the films. Analysis of scores revealed that the subcomponents of the Wisconsin system showed considerable variation from rater to rater, but reliability assessment indicated satisfactory Cronbach's alpha coefficients (0.83-0.90) among the seven raters. It was found that an additive method of total score computation is significantly more reliable (P < 0.05) than either the original multiplicative model or the traditional Brasfield scoring system. Comparison of radiologists and pulmonologists revealed a marked, systematic difference in scoring with the former group being more conservative in interpretation of abnormalities than the pulmonologists, and some of the raters showing very limited sensitivity. Quantitative chest radiology applied to children with cystic fibrosis studied long-term in longitudinal research projects requires the careful use of sensitive scoring methods and careful selection and training of multiple raters. This is particularly important since pulmonologists and radiologists can differ systematically in interpreting/scoring abnormalities.