An NHS Trust comparison of reporting radiographers and consultant radiologists ability to identify cancer on chest radiographs with confirmation through a Fast track CT thorax referral system.

INTRODUCTION: The National Institute for Health and Care Excellence (NICE) recommends that GPs initially refer patients with suspected lung cancer for a chest X-ray (CXR). The Radiology department has a 'fast track system' to identify those patients who may have lung cancer on CXR and are referred for a CT thorax with contrast to help determine a cancer diagnosis. This fast track system was put in place to ensure the NICE guidelines and NHS England's standards on a faster cancer diagnosis are being met. This audit studied the ability of radiologists and reporting radiographers to identify lung cancer on CXRs and the accuracy of the fast-track system. METHODS: 846 cases with lung alerts were analysed and 545 CXRs were audited. The CXRs were split into images reported by radiologists (168) and those reported by reporting radiographers (377). CT thorax results were collected through PACS and Cerner computer systems to identify if the 'fast track' system had yielded a "positive", "negative", or "other findings" result for lung cancer. RESULTS: 32.8% (179) of CXRs flagged for lung cancer were positive, 40.6% (221) were negative, and 26.6% (145) had other findings. Chi square statistical test showed no significant difference (p = 0.14) between the two reporting groups in their ability to identify lung cancer on CXRs. 27% (38) of CXRs flagged by radiologists and 35% (125) by reporting radiographers were positive for lung cancer. CONCLUSION: This clinical audit indicates, reporting radiographers and radiologists are not statistically significantly different regarding their ability to identify lung cancer on CXRs, when supported by the fast track system. The fast-track system had a 59.4 % accuracy rate, detected by the number of imaging of reports that identified a serious pathology. This concludes that the system is performing well, yet could still be improved. IMPLICATIONS FOR PRACTICE: This audit provides further evidence for the value of developing and deploying reporting radiographers for projection radiography reporting.

Competency based curriculum for cardiovascular magnetic resonance: A position statement of the Society for Cardiovascular Magnetic Resonance.

This position statement guides cardiovascular magnetic resonance (CMR) imaging program directors and learners on the key competencies required for Level II and III CMR practitioners, whether trainees come from a radiology or cardiology background. This document is built upon existing curricula and was created and vetted by an international panel of cardiologists and radiologists on behalf of the Society for Cardiovascular Magnetic Resonance (SCMR).

Patient-reported perspectives of therapeutic radiographers when undergoing radiotherapy: A European multi-centre study.

INTRODUCTION: Radiotherapy is delivered almost exclusively by therapeutic radiographers/radiation therapist (RTTs). Patient's perspectives of RTTs affect levels of trust and confidence in the profession and can have a significant impact on overall radiotherapy experience. The study reports patients' perspectives of RTTs from their experience of undergoing radiotherapy. Four partner sites collaborated in this research and included Malta, Poland, Portugal, and the UK (lead site). METHODS: A survey was developed to gather information from patients receiving radiotherapy or who had had radiotherapy within the previous 24 months. Participants ranked their responses to 23 statements relating to person-centred care on a 5-point scale of 1 (strongly disagree) to 5 (strongly agree). Mann-Whitney or Kruskal Wallis tests were applied to test differences in responses to 5 key statements for patient characteristics including gender, age group, diagnosis, country, time spent with RTTs and number of fractions remaining at survey completion. RESULTS: Three hundred and forty-seven surveys are included. Patients report a positive perception of RTTs (95.4% agree with 'I feel cared for'). Statistically significant differences in responses were found between gender, diagnosis, country, time spent with RTTs and fractions of radiotherapy remaining. Patients who had more time with RTTs and completed their surveys during radiotherapy had a more positive perception of RTTs. CONCLUSION: This study suggests that sufficient time with RTTs is key to ensuring a positive radiotherapy patient experience. RTTs being attentive, understanding, and informative are most predictive of a positive overall patient experience. Timing of survey completion can influence responses. IMPLICATIONS FOR PRACTICE: RTT education programmes should incorporate training on person-centred care at all levels. Further research into patient experience of RTTs is warranted.

Radiologists' performance in reading digital breast tomosynthesis with and without synthesized views for cancer detection.

OBJECTIVE: The study aims to evaluate the diagnostic efficacy of radiologists and radiology trainees in digital breast tomosynthesis (DBT) alone vs DBT plus synthesized view (SV) for an understanding of the adequacy of DBT images to identify cancer lesions. METHODS: Fifty-five observers (30 radiologists and 25 radiology trainees) participated in reading a set of 35 cases (15 cancer) with 28 readers reading DBT and 27 readers reading DBT plus SV. Two groups of readers had similar experience in interpreting mammograms. The performances of participants in each reading mode were compared with the ground truth and calculated in term of specificity, sensitivity, and ROC AUC. The cancer detection rate in various levels of breast density, lesion types and lesion sizes between 'DBT' and 'DBT + SV' were also analyzed. The difference in diagnostic accuracy of readers between two reading modes was assessed using Man-Whitney U test. p < 0.05 indicated a significant result. RESULTS: There was no significant difference in specificity (0.67-vs-0.65; p = 0.69), sensitivity (0.77-vs-0.71; p = 0.09), ROC AUC (0.77-vs-0.73; p = 0.19) of radiologists reading DBT plus SV compared with radiologists reading DBT. Similar result was found in radiology trainees with no significant difference in specificity (0.70-vs-0.63; p = 0.29), sensitivity (0.44-vs-0.55; p = 0.19), ROC AUC (0.59-vs-0.62; p = 0.60) between two reading modes. Radiologists and trainees obtained similar results in two reading modes for cancer detection rate with different levels of breast density, cancer types and sizes of lesions (p > 0.05). CONCLUSION: Findings show that the diagnostic performances of radiologists and radiology trainees in DBT alone and DBT plus SV were equivalent in identifying cancer and normal cases. ADVANCES IN KNOWLEDGE: DBT alone had equivalent diagnostic accuracy as DBT plus SV which could imply the consideration of using DBT as a sole modality without SV.

The uncovered biases and errors in clinical determination of bone age by using deep learning models.

OBJECTIVES: To evaluate AI biases and errors in estimating bone age (BA) by comparing AI and radiologists' clinical determinations of BA. METHODS: We established three deep learning models from a Chinese private dataset (CHNm), an American public dataset (USAm), and a joint dataset combining the above two datasets (JOIm). The test data CHNt (n = 1246) were labeled by ten senior pediatric radiologists. The effects of data site differences, interpretation bias, and interobserver variability on BA assessment were evaluated. The differences between the AI models' and radiologists' clinical determinations of BA (normal, advanced, and delayed BA groups by using the Brush data) were evaluated by the chi-square test and Kappa values. The heatmaps of CHNm-CHNt were generated by using Grad-CAM. RESULTS: We obtained an MAD value of 0.42 years on CHNm-CHNt; this result indicated an appropriate accuracy for the whole group but did not indicate an accurate estimation of individual BA because with a kappa value of 0.714, the agreement between AI and human clinical determinations of BA was significantly different. The features of the heatmaps were not fully consistent with the human vision on the X-ray films. Variable performance in BA estimation by different AI models and the disagreement between AI and radiologists' clinical determinations of BA may be caused by data biases, including patients' sex and age, institutions, and radiologists. CONCLUSIONS: The deep learning models outperform external validation in predicting BA on both internal and joint datasets. However, the biases and errors in the models' clinical determinations of child development should be carefully considered. KEY POINTS: • With a kappa value of 0.714, clinical determinations of bone age by using AI did not accord well with clinical determinations by radiologists. • Several biases, including patients' sex and age, institutions, and radiologists, may cause variable performance by AI bone age models and disagreement between AI and radiologists' clinical determinations of bone age. • AI heatmaps of bone age were not fully consistent with human vision on X-ray films.

Which Aspects of the CanMEDS Competencies are Most Valued in Radiologists? Perspectives of Trainees From Other Specialties.

PURPOSE: Radiologists work primarily in collaboration with other healthcare professionals. As such, these stakeholder perspectives are of value to the development and assessment of educational outcomes during the transition to competency-based medical education. Our aim in this study was to determine which aspects of the Royal College CanMEDS competencies for diagnostic radiology are considered most important by future referring physicians. METHODS: Institutional ethics approval was obtained. After pilot testing, an anonymous online survey was sent to all residents and clinical fellows at our university. Open-ended questions asked respondents to describe the aspects of radiologist service they felt were most important. Thematic analysis of the free-text responses was performed using a grounded theory approach. The resulting themes were mapped to the 2015 CanMEDS Key Competencies. RESULTS: 115 completed surveys were received from residents and fellows from essentially all specialties and years of training (out of 928 invited). Major themes were 1) timeliness and accessibility of service, 2) quality of reporting, and 3) acting as a valued team member. The competencies identified as important by resident physicians were largely consistent with the CanMEDS framework, although not all key competencies were covered in the responses. CONCLUSIONS: This study illustrates how CanMEDS roles and competencies may be exemplified in a concrete and specialty-specific manner from the perspective of key stakeholders. Our survey results provide further insight into specific objectives for teaching and assessing these competencies in radiology residency training, with the ultimate goal of improving patient care through strengthened communication and working relationships.

Variations in breast cancer detection rates during mammogram-reading sessions: does experience have an impact?

OBJECTIVES: To examine whether radiologists' performances are consistent throughout a reading session and whether any changes in performance over the reading task differ depending on experience of the reader. METHODS: The performance of ten radiologists reading a test set of 60 mammographic cases without breaks was assessed using an ANOVA, 2 × 3 factorial design. Participants were categorized as more (≥2,000 mammogram readings per year) or less (<2,000 readings per year) experienced. Three series of 20 cases were chosen to ensure comparable difficulty and presented in the same sequence to all readers. It usually takes around 30 min for a radiologist to complete each of the 20-case series, resulting in a total of 90 min for the 60 mammographic cases. The sensitivity, specificity, lesion sensitivity, and area under the ROC curve were calculated for each series. We hypothesized that the order in which a series was read (i.e. fixed-series sequence) would have a significant main effect on the participants' performance. We also determined if significant interactions exist between the fixed-series sequence and radiologist experience. RESULTS: Significant linear interactions were found between experience and the fixed sequence of the series for sensitivity (F[1] =5.762, p = .04, partial η2 = .41) and lesion sensitivity. (F[1] =6.993, p = .03, partial η2 = .46). The two groups' mean scores were similar for the first series but progressively diverged. By the end of the third series, significant differences in sensitivity and lesion sensitivity were evident, with the more experienced individuals demonstrating improving and the less experienced declining performance. Neither experience nor series sequence significantly affected the specificity or the area under the ROC curve. CONCLUSIONS: Radiologists' performance may change considerably during a reading session, apparently as a function of experience, with less experienced radiologists declining in sensitivity and lesion sensitivity while more experienced radiologists actually improve. With the increasing demands on radiologists to undertake high-volume reporting, we suggest that junior radiologists be made aware of possible sensitivity and lesion sensitivity deterioration over time so they can schedule breaks during continuous reading sessions that are appropriate to them, rather than try to emulate their more experienced colleagues. ADVANCES IN KNOWLEDGE: Less-experienced radiologists demonstrated a reduction in mammographic diagnostic accuracy in later stages of the reporting sessions. This may suggest that extending the duration of reporting sessions to compensate for increasing workloads may not represent the optimal solution for less-experienced radiologists.

Global processing provides malignancy evidence complementary to the information captured by humans or machines following detailed mammogram inspection.

The information captured by the gist signal, which refers to radiologists' first impression arising from an initial global image processing, is poorly understood. We examined whether the gist signal can provide complementary information to data captured by radiologists (experiment 1), or computer algorithms (experiment 2) based on detailed mammogram inspection. In the first experiment, 19 radiologists assessed a case set twice, once based on a half-second image presentation (i.e., gist signal) and once in the usual viewing condition. Their performances in two viewing conditions were compared using repeated measure correlation (rm-corr). The cancer cases (19 cases × 19 readers) exhibited non-significant trend with rm-corr = 0.012 (p = 0.82, CI: -0.09, 0.12). For normal cases (41 cases × 19 readers), a weak correlation of rm-corr = 0.238 (p < 0.001, CI: 0.17, 0.30) was found. In the second experiment, we combined the abnormality score from a state-of-the-art deep learning-based tool (DL) with the radiological gist signal using a support vector machine (SVM). To obtain the gist signal, 53 radiologists assessed images based on half-second image presentation. The SVM performance for each radiologist and an average reader, whose gist responses were the mean abnormality scores given by all 53 readers to each image was assessed using leave-one-out cross-validation. For the average reader, the AUC for gist, DL, and the SVM, were 0.76 (CI: 0.62-0.86), 0.79 (CI: 0.63-0.89), and 0.88 (CI: 0.79-0.94). For all readers with a gist AUC significantly better than chance-level, the SVM outperformed DL. The gist signal provided malignancy evidence with no or weak associations with the information captured by humans in normal radiologic reporting, which involves detailed mammogram inspection. Adding gist signal to a state-of-the-art deep learning-based tool improved its performance for the breast cancer detection.

Discrepancies in rib fracture severity between radiologist and surgeon: A retrospective review.

BACKGROUND: Chest computed tomography (CT) scans are important for the management of rib fracture patients, especially when determining indications for surgical stabilization of rib fractures (SSRFs). Chest CTs describe the number, patterns, and severity of rib fracture displacement, driving patient management and SSRF indications. Literature is scarce comparing radiologist versus surgeon rib fracture description. We hypothesize there is significant discrepancy between how radiologists and surgeons describe rib fractures. METHODS: This was an institutional review board-approved, retrospective study conducted at a Level I academic center from December 2016 to December 2017. Adult patients (≥18 years of age) suffering rib fractures with a CT chest where included. Basic demographics were obtained. Outcomes included the difference between radiologist versus surgeon description of rib fractures and differences in the number of fractures identified. Rib fracture description was based on current literature: 1, nondisplaced; 2, minimally displaced (<50% rib width); 3, severely displaced (≥50% rib width); 4, bicortically displaced; 5, other. Descriptive analysis was used for demographics and paired t test for statistical analysis. Significance was set at p = 0.05. RESULTS: Four hundred and ten patients and 2,337 rib fractures were analyzed. Average age was 55.6(±20.6); 70.5% were male; median Injury Severity Score was 16 (interquartile range, 9-22) and chest Abbreviated Injury Scale score was 3 (interquartile range, 3-3). For all descriptive categories, radiologists consistently underappreciated the severity of rib fracture displacement compared with surgeon assessment and severity of displacement was not mentioned for 35% of rib fractures. The mean score provided by the radiologist was 1.58 (±0.63) versus 1.78 (±0.51) by the surgeon (p < 0.001). Radiologists missed 138 (5.9%) rib fractures on initial CT. The sensitivity of the radiologist to identify a severely displaced rib fracture was 54.9% with specificity of 79.9%. CONCLUSION: Discrepancy exists between radiologist and surgeon regarding rib fracture description on chest CT as radiologists routinely underappreciate fracture severity. Surgeons need to evaluate CT scans themselves to appropriately decide management strategies and SSRF indications. LEVEL OF EVIDENCE: Prognostic/Diagnostic Test, level III.

Can family physicians accurately screen for AAA with point-of-care ultrasound?

Likely yes. Point-of-care ultrasound (POCUS) screening for abdominal aortic aneurysm (AAA) by nonradiologist physicians is 98% sensitive and 99% specific, compared with imaging performed by radiologists (strength of recommendation [SOR]: B, meta-analysis of diagnostic accuracy studies mostly involving emergency medicine physicians). European family physicians demonstrated 100% concordance with radiologist readings (SOR: C, very small subsequent diagnostic accuracy studies).

Radiologist Characteristics Associated with Interpretive Performance of Screening Mammography: A National Mammography Database (NMD) Study.

Background Factors affecting radiologists' performance in screening mammography interpretation remain poorly understood. Purpose To identify radiologists characteristics that affect screening mammography interpretation performance. Materials and Methods This retrospective study included 1223 radiologists in the National Mammography Database (NMD) from 2008 to 2019 who could be linked to Centers for Medicare & Medicaid Services (CMS) datasets. NMD screening performance metrics were extracted. Acceptable ranges were defined as follows: recall rate (RR) between 5% and 12%; cancer detection rate (CDR) of at least 2.5 per 1000 screening examinations; positive predictive value of recall (PPV1) between 3% and 8%; positive predictive value of biopsies recommended (PPV2) between 20% and 40%; positive predictive value of biopsies performed (PPV3) between the 25th and 75th percentile of study sample; invasive CDR of at least the 25th percentile of the study sample; and percentage of ductal carcinoma in situ (DCIS) of at least the 25th percentile of the study sample. Radiologist characteristics extracted from CMS datasets included demographics, subspecialization, and clinical practice patterns. Multivariable stepwise logistic regression models were performed to identify characteristics independently associated with acceptable performance for the seven metrics. The most influential characteristics were defined as those independently associated with the majority of the metrics (at least four). Results Relative to radiologists practicing in the Northeast, those in the Midwest were more likely to achieve acceptable RR, PPV1, PPV2, and CDR (odds ratio [OR], 1.4-2.5); those practicing in the West were more likely to achieve acceptable RR, PPV2, and PPV3 (OR, 1.7-2.1) but less likely to achieve acceptable invasive CDR (OR, 0.6). Relative to general radiologists, breast imagers were more likely to achieve acceptable PPV1, invasive CDR, percentage DCIS, and CDR (OR, 1.4-4.4). Those performing diagnostic mammography were more likely to achieve acceptable PPV1, PPV2, PPV3, invasive CDR, and CDR (OR, 1.9-2.9). Those performing breast US were less likely to achieve acceptable PPV1, PPV2, percentage DCIS, and CDR (OR, 0.5-0.7). Conclusion The geographic location of the radiology practice, subspecialization in breast imaging, and performance of diagnostic mammography are associated with better screening mammography performance; performance of breast US is associated with lower performance. ©RSNA, 2021 Online supplemental material is available for this article.

New concept: "TARN friendly trauma reporting" (what radiologists say really does matter).

AIM: To establish if detailed review of trauma reports with reference to coding manual improved accuracy of ISS and to establish if demonstrated changes in coding affected performance and tariff payment. MATERIALS AND METHODS: A study was undertaken which gathered data from 6 months across the five trusts with information on imaging undertaken, mechanism of injury (MOI), Injury Severity Score (ISS), and injury descriptors was included. Patients with ISS near to a best practice tariff boundary of 9 and 16 (5-8 and 11-15) then had their imaging reviewed by the Radiology Department with direct reference to the ISS coding manual. Injuries were then re-coded and ISS recalculated. RESULTS: Over the 6-month period, 1,693 patients were admitted to the database from the five hospitals. One hundred and sixty-nine (9.9%) patients met the inclusion criteria for review. Thirty-five (20.7%) had a change in abbreviated (region specific) injury code, with 30 a change in the resultant ISS. Three had a decrease in ISS and 27 increased ISS with all 27 moving across an ISS best practice tariff and three moving across two payment tariff boundaries. With re-coding, there was a potential £15,000 of lost revenue from the major trauma centre (MTC) alone. CONCLUSION: Reporting with reference to ISS description improves the accuracy of ISS significantly. Radiologists improving the descriptions of specific injury patterns and adopting 'Trauma Audit and Research Network friendly' reporting strategies may improve data accuracy, performance, and payment of best practice tariffs to hospitals.

Performance and educational training of radiographers in lung nodule or mass detection: Retrospective comparison with different deep learning algorithms.

ABSTRACT: The aim of this investigation was to compare the diagnostic performance of radiographers and deep learning algorithms in pulmonary nodule/mass detection on chest radiograph.A test set of 100 chest radiographs containing 53 cases with no pathology (normal) and 47 abnormal cases (pulmonary nodules/masses) independently interpreted by 6 trained radiographers and deep learning algorithems in a random order. The diagnostic performances of both deep learning algorithms and trained radiographers for pulmonary nodules/masses detection were compared.QUIBIM Chest X-ray Classifier, a deep learning through mass algorithm that performs superiorly to practicing radiographers in the detection of pulmonary nodules/masses (AUCMass: 0.916 vs AUCTrained radiographer: 0.778, P < .001). In addition, heat-map algorithm could automatically detect and localize pulmonary nodules/masses in chest radiographs with high specificity.In conclusion, the deep-learning based computer-aided diagnosis system through 4 algorithms could potentially assist trained radiographers by increasing the confidence and access to chest radiograph interpretation in the age of digital age with the growing demand of medical imaging usage and radiologist burnout.

How embryology knowledge can help radiologists in the differential diagnosis of canal of Nuck pathologies.

The Canal of Nuck (CN) is an anatomical structure which is often forgotten. It is the female equivalent of the male processus vaginalis and corresponds to a protrusion of parietal peritoneum that extends from the inguinal canal to labia majora. Radiologists rarely encounter patients with pathology of CN, especially in adult population. It is well known that CN diseases can occur in paediatric patient (especially younger than 5 years of age) and they are associated to high morbidity (for example ovarian hernia with high risk of incarceration and torsion). The aim of our work is to review embryology, anatomy and pathologies of the CN thanks to a multi modal approach-ultrasound (US), Computed Tomography (CT) and Magnetic Resonance imaging (MRI)-to make radiologists more aware of such conditions and guarantee a prompt and correct diagnosis not only in paediatric patients but also in the adult population.

Role of Key Guidelines in an Era of Precision Oncology: A Primer for the Radiologist.

OBJECTIVE. The purpose of this article is to familiarize radiologists with the evidence-based imaging guidelines of major oncologic societies and organizations and to discuss approaches to effective implementation of the most recent guidelines in daily radiology practice. CONCLUSION. In an era of precision oncology, radiologists in practice and radiologists in training are key stakeholders in multidisciplinary care, and their awareness and understanding of society guidelines is critically important.

Emergency Computed Tomography: How Misinterpretations Vary According to the Periods of the Nightshift?

OBJECTIVE: To evaluate the accuracy of initial computed tomography (CT) interpretations made by radiology residents during nightshifts in the emergency department. METHODS: Preliminary CT reports performed by radiology residents during 120 consecutive nightshifts (08:30 pm to 08:30 am) were reviewed, attendings' final interpretation being the reference standard. Nightshifts were divided into four consecutive periods of 3 hours. Major misinterpretations were related to potentially life-threatening conditions if not treated immediately after CT. The rate of misinterpretations was calculated for all CT examinations, separately for nightshift's periods and for residents' training years. RESULTS: Misinterpretations were recorded in 155 (7.4%) of 2102 CT examinations, 0.6% (13/2102) were major. There were 2.2% (4/186) major misinterpretations that occurred during the last period of the nightshift versus 0.4% (9/1916) during the first periods of the night (P < 0.05). Of all misinterpretations, 8.5% (130/1526) were made by third- and fourth-year residents and 4.3% (25/576) by fifth-year residents (P < 0.005). CONCLUSIONS: Major misinterpretations occur at the end of the nightshift, which may be explained by the fatigue effect. The rate of misinterpretations is lower among fifth-year residents, which may be related to their prior experience in reading emergency cases.

Interventional Radiology Outpatient Clinics (IROC): Clinical Impact and Patient Satisfaction.

PURPOSE: To retrospectively analyze our interventional radiology outpatient clinics (IROC) for referral patterns, impact on interventional practice, and patient satisfaction. MATERIALS AND METHODS: Consultations performed between 2011 and 2019 were extracted. The two consecutive years with the highest number of consultations (n2018 = 1426; n2019 = 1595) were compared for unattended consultations (i.e., scheduled consultations with patients not showing-up); initial/follow-up consultations; hospital clinician/general practitioner referrals; initial consultations with radiologists not recommending interventions; procedural conversion rate (PCR; i.e., No. initial consultations resulting in interventions over the total number of initial consultations performed for the same clinical indication). A survey was conducted in 159 patients to determine their satisfaction. RESULTS: Consultations increased from 2011 to 2019 by 130%. In 2018-2019, the number of unattended consultations was stable (7.0% vs 6.6%; P = .68). The referrals were for back pain (42.2%), interventional oncology (40.5%), and arteriovenous malformations (9.0%). For back pain, in 2019, there were fewer consultations with radiologists not recommending interventions and increased PCR compared to 2018 (11.9% vs. 17.7%; 88.1% vs. 82.3%; respectively; P = .01). For interventional oncology, follow-up consultations and general practitioner referrals increased in 2019 compared to 2018 (43.0% vs 35.3%; P = .01; 24.4% vs. 12.7%; P < .01; respectively). No other changes were noted. Cumulative 2018-2019 PCR was ≥ 85.4%. 99.2% responders highly appreciated their IROC experience. Quality of secretarial and medical services were the main aspects evaluated to rate the experience with IROC. CONCLUSION: IROC results in high PCR. Recent changes in referral/impact on IR practice were noted with patients referred for back pain and interventional oncology. LEVEL OF EVIDENCE IV: Level 4, Case Series.

Comparison of Prostate MRI Lesion Segmentation Agreement Between Multiple Radiologists and a Fully Automatic Deep Learning System.

PURPOSE: A recently developed deep learning model (U-Net) approximated the clinical performance of radiologists in the prediction of clinically significant prostate cancer (sPC) from prostate MRI. Here, we compare the agreement between lesion segmentations by U-Net with manual lesion segmentations performed by different radiologists. MATERIALS AND METHODS: 165 patients with suspicion for sPC underwent targeted and systematic fusion biopsy following 3 Tesla multiparametric MRI (mpMRI). Five sets of segmentations were generated retrospectively: segmentations of clinical lesions, independent segmentations by three radiologists, and fully automated bi-parametric U-Net segmentations. Per-lesion agreement was calculated for each rater by averaging Dice coefficients with all overlapping lesions from other raters. Agreement was compared using descriptive statistics and linear mixed models. RESULTS: The mean Dice coefficient for manual segmentations showed only moderate agreement at 0.48-0.52, reflecting the difficult visual task of determining the outline of otherwise jointly detected lesions. U-net segmentations were significantly smaller than manual segmentations (p < 0.0001) and exhibited a lower mean Dice coefficient of 0.22, which was significantly lower compared to manual segmentations (all p < 0.0001). These differences remained after correction for lesion size and were unaffected between sPC and non-sPC lesions and between peripheral and transition zone lesions. CONCLUSION: Knowledge of the order of agreement of manual segmentations of different radiologists is important to set the expectation value for artificial intelligence (AI) systems in the task of prostate MRI lesion segmentation. Perfect agreement (Dice coefficient of one) should not be expected for AI. Lower Dice coefficients of U-Net compared to manual segmentations are only partially explained by smaller segmentation sizes and may result from a focus on the lesion core and a small relative lesion center shift. Although it is primarily important that AI detects sPC correctly, the Dice coefficient for overlapping lesions from multiple raters can be used as a secondary measure for segmentation quality in future studies. KEY POINTS: · Intermediate human Dice coefficients reflect the difficulty of outlining jointly detected lesions.. · Lower Dice coefficients of deep learning motivate further research to approximate human perception.. · Comparable predictive performance of deep learning appears independent of Dice agreement.. · Dice agreement independent of significant cancer presence indicates indistinguishability of some benign imaging findings.. · Improving DWI to T2 registration may improve the observed U-Net Dice coefficients.. CITATION FORMAT: · Schelb P, Tavakoli AA, Tubtawee T et al. Comparison of Prostate MRI Lesion Segmentation Agreement Between Multiple Radiologists and a Fully Automatic Deep Learning System. Fortschr Röntgenstr 2021; 193: 559 - 573.

2020 SCCT Guideline for Training Cardiology and Radiology Trainees as Independent Practitioners (Level II) and Advanced Practitioners (Level III) in Cardiovascular Computed Tomography: A Statement from the Society of Cardiovascular Computed Tomography.

Cardiovascular computed tomography (CCT) is a well-validated non-invasive imaging tool with an ever-expanding array of applications beyond the assessment of coronary artery disease. These include the evaluation of structural heart diseases, congenital heart diseases, peri-procedural electrophysiology applications, and the functional evaluation of ischemia. This breadth requires a robust and diverse training curriculum to ensure graduates of CCT training programs meet minimum competency standards for independent CCT interpretation. This statement from the Society of Cardiovascular Computed Tomography aims to supplement existing societal training guidelines by providing a curriculum and competency framework to inform the development of a comprehensive, integrated training experience for cardiology and radiology trainees in CCT.