Artificial intelligence and radiologists in prostate cancer detection on MRI (PI-CAI): an international, paired, non-inferiority, confirmatory study.

BACKGROUND: Artificial intelligence (AI) systems can potentially aid the diagnostic pathway of prostate cancer by alleviating the increasing workload, preventing overdiagnosis, and reducing the dependence on experienced radiologists. We aimed to investigate the performance of AI systems at detecting clinically significant prostate cancer on MRI in comparison with radiologists using the Prostate Imaging-Reporting and Data System version 2.1 (PI-RADS 2.1) and the standard of care in multidisciplinary routine practice at scale. METHODS: In this international, paired, non-inferiority, confirmatory study, we trained and externally validated an AI system (developed within an international consortium) for detecting Gleason grade group 2 or greater cancers using a retrospective cohort of 10 207 MRI examinations from 9129 patients. Of these examinations, 9207 cases from three centres (11 sites) based in the Netherlands were used for training and tuning, and 1000 cases from four centres (12 sites) based in the Netherlands and Norway were used for testing. In parallel, we facilitated a multireader, multicase observer study with 62 radiologists (45 centres in 20 countries; median 7 [IQR 5-10] years of experience in reading prostate MRI) using PI-RADS (2.1) on 400 paired MRI examinations from the testing cohort. Primary endpoints were the sensitivity, specificity, and the area under the receiver operating characteristic curve (AUROC) of the AI system in comparison with that of all readers using PI-RADS (2.1) and in comparison with that of the historical radiology readings made during multidisciplinary routine practice (ie, the standard of care with the aid of patient history and peer consultation). Histopathology and at least 3 years (median 5 [IQR 4-6] years) of follow-up were used to establish the reference standard. The statistical analysis plan was prespecified with a primary hypothesis of non-inferiority (considering a margin of 0·05) and a secondary hypothesis of superiority towards the AI system, if non-inferiority was confirmed. This study was registered at ClinicalTrials.gov, NCT05489341. FINDINGS: Of the 10 207 examinations included from Jan 1, 2012, through Dec 31, 2021, 2440 cases had histologically confirmed Gleason grade group 2 or greater prostate cancer. In the subset of 400 testing cases in which the AI system was compared with the radiologists participating in the reader study, the AI system showed a statistically superior and non-inferior AUROC of 0·91 (95% CI 0·87-0·94; p<0·0001), in comparison to the pool of 62 radiologists with an AUROC of 0·86 (0·83-0·89), with a lower boundary of the two-sided 95% Wald CI for the difference in AUROC of 0·02. At the mean PI-RADS 3 or greater operating point of all readers, the AI system detected 6·8% more cases with Gleason grade group 2 or greater cancers at the same specificity (57·7%, 95% CI 51·6-63·3), or 50·4% fewer false-positive results and 20·0% fewer cases with Gleason grade group 1 cancers at the same sensitivity (89·4%, 95% CI 85·3-92·9). In all 1000 testing cases where the AI system was compared with the radiology readings made during multidisciplinary practice, non-inferiority was not confirmed, as the AI system showed lower specificity (68·9% [95% CI 65·3-72·4] vs 69·0% [65·5-72·5]) at the same sensitivity (96·1%, 94·0-98·2) as the PI-RADS 3 or greater operating point. The lower boundary of the two-sided 95% Wald CI for the difference in specificity (-0·04) was greater than the non-inferiority margin (-0·05) and a p value below the significance threshold was reached (p<0·001). INTERPRETATION: An AI system was superior to radiologists using PI-RADS (2.1), on average, at detecting clinically significant prostate cancer and comparable to the standard of care. Such a system shows the potential to be a supportive tool within a primary diagnostic setting, with several associated benefits for patients and radiologists. Prospective validation is needed to test clinical applicability of this system. FUNDING: Health~Holland and EU Horizon 2020.

Is work overload associated with diagnostic errors on 18F-FDG-PET/CT?

PURPOSE: To determine the association between workload and diagnostic errors on 18F-FDG-PET/CT. MATERIALS AND METHODS: This study included 103 18F-FDG-PET/CT scans with a diagnostic error that was corrected with an addendum between March 2018 and July 2023. All scans were performed at a tertiary care center. The workload of each nuclear medicine physician or radiologist who authorized the 18F-FDG-PET/CT report was determined on the day the diagnostic error was made and normalized for his or her own average daily production (workloadnormalized). A workloadnormalized of more than 100% indicates that the nuclear medicine physician or radiologist had a relative work overload, while a value of less than 100% indicates a relative work underload on the day the diagnostic error was made. The time of the day the diagnostic error was made was also recorded. Workloadnormalized was compared to 100% using a signed rank sum test, with the hypothesis that it would significantly exceed 100%. A Mann-Kendall test was performed to test the hypothesis that diagnostic errors would increase over the course of the day. RESULTS: Workloadnormalized (median of 121%, interquartile range: 71 to 146%) on the days the diagnostic errors were made was significantly higher than 100% (P = 0.014). There was no significant upward trend in the frequency of diagnostic errors over the course of the day (Mann-Kendall tau = 0.05, P = 0.7294). CONCLUSION: Work overload seems to be associated with diagnostic errors on 18F-FDG-PET/CT. Diagnostic errors were encountered throughout the entire working day, without any upward trend towards the end of the day.

The Effect of Image Resampling on the Performance of Radiomics-Based Artificial Intelligence in Multicenter Prostate MRI.

BACKGROUND: Single center MRI radiomics models are sensitive to data heterogeneity, limiting the diagnostic capabilities of current prostate cancer (PCa) radiomics models. PURPOSE: To study the impact of image resampling on the diagnostic performance of radiomics in a multicenter prostate MRI setting. STUDY TYPE: Retrospective. POPULATION: Nine hundred thirty patients (nine centers, two vendors) with 737 eligible PCa lesions, randomly split into training (70%, N = 500), validation (10%, N = 89), and a held-out test set (20%, N = 148). FIELD STRENGTH/SEQUENCE: 1.5T and 3T scanners/T2-weighted imaging (T2W), diffusion-weighted imaging (DWI), and apparent diffusion coefficient maps. ASSESSMENT: A total of 48 normalized radiomics datasets were created using various resampling methods, including different target resolutions (T2W: 0.35, 0.5, and 0.8 mm; DWI: 1.37, 2, and 2.5 mm), dimensionalities (2D/3D) and interpolation techniques (nearest neighbor, linear, Bspline and Blackman windowed-sinc). Each of the datasets was used to train a radiomics model to detect clinically relevant PCa (International Society of Urological Pathology grade ≥ 2). Baseline models were constructed using 2D and 3D datasets without image resampling. The resampling configurations with highest validation performance were evaluated in the test dataset and compared to the baseline models. STATISTICAL TESTS: Area under the curve (AUC), DeLong test. The significance level used was 0.05. RESULTS: The best 2D resampling model (T2W: Bspline and 0.5 mm resolution, DWI: nearest neighbor and 2 mm resolution) significantly outperformed the 2D baseline (AUC: 0.77 vs. 0.64). The best 3D resampling model (T2W: linear and 0.8 mm resolution, DWI: nearest neighbor and 2.5 mm resolution) significantly outperformed the 3D baseline (AUC: 0.79 vs. 0.67). DATA CONCLUSION: Image resampling has a significant effect on the performance of multicenter radiomics artificial intelligence in prostate MRI. The recommended 2D resampling configuration is isotropic resampling with T2W at 0.5 mm (Bspline interpolation) and DWI at 2 mm (nearest neighbor interpolation). For the 3D radiomics, this work recommends isotropic resampling with T2W at 0.8 mm (linear interpolation) and DWI at 2.5 mm (nearest neighbor interpolation). EVIDENCE LEVEL: 3 TECHNICAL EFFICACY: Stage 2.

Prostate MRI and artificial intelligence during active surveillance: should we jump on the bandwagon?

OBJECTIVE: To review the components of past and present active surveillance (AS) protocols, provide an overview of the current studies employing artificial intelligence (AI) in AS of prostate cancer, discuss the current challenges of AI in AS, and offer recommendations for future research. METHODS: Research studies on the topic of MRI-based AI were reviewed to summarize current possibilities and diagnostic accuracies for AI methods in the context of AS. Established guidelines were used to identify possibilities for future refinement using AI. RESULTS: Preliminary results show the role of AI in a range of diagnostic tasks in AS populations, including the localization, follow-up, and prognostication of prostate cancer. Current evidence is insufficient to support a shift to AI-based AS, with studies being limited by small dataset sizes, heterogeneous inclusion and outcome definitions, or lacking appropriate benchmarks. CONCLUSION: The AI-based integration of prostate MRI is a direction that promises substantial benefits for AS in the future, but evidence is currently insufficient to support implementation. Studies with standardized inclusion criteria and standardized progression definitions are needed to support this. The increasing inclusion of patients in AS protocols and the incorporation of MRI as a scheduled examination in AS protocols may help to alleviate these challenges in future studies. CLINICAL RELEVANCE STATEMENT: This manuscript provides an overview of available evidence for the integration of prostate MRI and AI in active surveillance, addressing its potential for clinical optimizations in the context of established guidelines, while highlighting the main challenges for implementation. KEY POINTS: Active surveillance is currently based on diagnostic tests such as PSA, biopsy, and imaging. Prostate MRI and AI demonstrate promising diagnostic accuracy across a variety of tasks, including the localization, follow-up and risk estimation in active surveillance cohorts. A transition to AI-based active surveillance is not currently realistic; larger studies using standardized inclusion criteria and outcomes are necessary to improve and validate existing evidence.

What is the added value of specialist radiology review of multidisciplinary team meeting cases in a tertiary care center?

PURPOSE: Multidisciplinary team meetings (MDTMs) are an important component of the workload of radiologists. This study investigated how often subspecialized radiologists change patient management in MDTMs at a tertiary care institution. MATERIALS AND METHODS: Over 2 years, six subspecialty radiologists documented their contributions to MDTMs at a tertiary care center. Both in-house and external imaging examinations were discussed at the MDTMs. All imaging examinations (whether primary or second opinion) were interpreted and reported by subspecialty radiologist prior to the MDTMs. The management change ratio (MCratio) of the radiologist was defined as the number of cases in which the radiologist's input in the MDTM changed patient management beyond the information that was already provided by the in-house (primary or second opinion) radiology report, as a proportion of the total number of cases whose imaging examinations were prepared for demonstration in the MDTM. RESULTS: Sixty-eight MDTMs were included. The time required for preparing and attending all MDTMs (excluding imaging examinations that had not been reported yet) was 11,000 min, with a median of 172 min (IQR 113-200 min) per MDTM, and a median of 9 min (IQR 8-13 min) per patient. The radiologists' input changed patient management in 113 out of 1138 cases, corresponding to an MCratio of 8.4%. The median MCratio per MDTM was 6% (IQR 0-17%). CONCLUSION: Radiologists' time investment in MDTMs is considerable relative to the small proportion of cases in which they influence patient management in the MDTM. The use of radiologists for MDTMs should therefore be improved. CLINICAL RELEVANCE STATEMENT: The use of radiologists for MDTMs (multidisciplinary team meetings) should be improved, because their time investment in MDTMs is considerable relative to the small proportion of cases in which they influence patient management in the MDTM. KEY POINTS: • Multidisciplinary team meetings (MDTMs) are an important component of the workload of radiologists. • In a tertiary care center in which all imaging examinations have already been interpreted and reported by subspecialized radiologists before the MDTM takes place, the median time investment of a radiologist for preparing and demonstrating one MDTM patient is 9 min. • In this setting, the radiologist changes patient management in only a minority of cases in the MDTM.

Assessing deep learning reconstruction for faster prostate MRI: visual vs. diagnostic performance metrics.

OBJECTIVE: Deep learning (DL) MRI reconstruction enables fast scan acquisition with good visual quality, but the diagnostic impact is often not assessed because of large reader study requirements. This study used existing diagnostic DL to assess the diagnostic quality of reconstructed images. MATERIALS AND METHODS: A retrospective multisite study of 1535 patients assessed biparametric prostate MRI between 2016 and 2020. Likely clinically significant prostate cancer (csPCa) lesions (PI-RADS ≥ 4) were delineated by expert radiologists. T2-weighted scans were retrospectively undersampled, simulating accelerated protocols. DL reconstruction (DLRecon) and diagnostic DL detection (DLDetect) were developed. The effect on the partial area under (pAUC), the Free-Response Operating Characteristic (FROC) curve, and the structural similarity (SSIM) were compared as metrics for diagnostic and visual quality, respectively. DLDetect was validated with a reader concordance analysis. Statistical analysis included Wilcoxon, permutation, and Cohen's kappa tests for visual quality, diagnostic performance, and reader concordance. RESULTS: DLRecon improved visual quality at 4- and 8-fold (R4, R8) subsampling rates, with SSIM (range: -1 to 1) improved to 0.78 ± 0.02 (p < 0.001) and 0.67 ± 0.03 (p < 0.001) from 0.68 ± 0.03 and 0.51 ± 0.03, respectively. However, diagnostic performance at R4 showed a pAUC FROC of 1.33 (CI 1.28-1.39) for DL and 1.29 (CI 1.23-1.35) for naive reconstructions, both significantly lower than fully sampled pAUC of 1.58 (DL: p = 0.024, naïve: p = 0.02). Similar trends were noted for R8. CONCLUSION: DL reconstruction produces visually appealing images but may reduce diagnostic accuracy. Incorporating diagnostic AI into the assessment framework offers a clinically relevant metric essential for adopting reconstruction models into clinical practice. CLINICAL RELEVANCE STATEMENT: In clinical settings, caution is warranted when using DL reconstruction for MRI scans. While it recovered visual quality, it failed to match the prostate cancer detection rates observed in scans not subjected to acceleration and DL reconstruction.

Did medical doctors who order abdominal CT scans during on-call hours truly become worse at clinical reasoning? Yes, they did.

OBJECTIVE: To investigate temporal changes in clinical reasoning quality of physicians who requested abdominal CT scans at a tertiary care center during on-call hours within a 15-year period. METHODS: This retrospective study included 531 patients who underwent abdominal CT at a tertiary care center during on-call hours on 36 randomly sampled unique calendar days in each of the years between 2005 and 2019. Clinical reasoning quality was expressed as a percentage (0-100%), taking into account the degree by which the differential diagnoses on the CT request form matched the CT diagnosis. Temporal changes in the quality of clinical reasoning and number of CT scans were assessed using Mann-Kendall tests. Associations between the quality of clinical reasoning with patient age and gender, requesting department, and time of CT scanning were determined with linear regression analyses. RESULTS: The median annual clinical reasoning score was 0.4% (interquartile range: 0.3 to 0.6%; range: 0.1 to 1.9%). The quality of clinical reasoning significantly decreased between 2005 and 2019 (Mann-Kendall Tau of -0.829, p < 0.001), while the number of abdominal CT scans significantly increased (Mann-Kendall tau of 0.790, p < 0.001). There was a significant association between the quality of clinical reasoning and patient age (ß coefficient of 0.210, p = 0.002). The quality of clinical reasoning was not significantly associated with patient gender, requesting department, or time of CT scanning. CONCLUSION: The clinical reasoning quality of physicians who request abdominal CT scans during on-call hours has deteriorated over time. Clinical reasoning appears to be worse in younger patients. KEY POINTS: • In patients with suspected acute abdominal pathology who are scheduled to undergo CT scanning, referring physicians generally have difficulties in making an accurate pretest (differential) diagnosis. • Clinical reasoning quality of physicians who request acute abdominal CT scans has deteriorated over the years, while the number of CT scans has shown a significant increase. • Clinical reasoning quality appears to be worse in younger patients in this setting.

Focused view CT angiography for selective visualization of stroke related arteries: technical feasibility.

OBJECTIVES: This study investigated the technical feasibility of focused view CTA for the selective visualization of stroke related arteries. METHODS: A total of 141 CTA examinations for acute ischemic stroke evaluation were divided into a set of 100 cases to train a deep learning algorithm (dubbed "focused view CTA") that selectively extracts brain (including intracranial arteries) and extracranial arteries, and a test set of 41 cases. The visibility of anatomic structures at focused view and unmodified CTA was assessed using the following scoring system: 5 = completely visible, diagnostically sufficient; 4 = nearly completely visible, diagnostically sufficient; 3 = incompletely visible, barely diagnostically sufficient; 2 = hardly visible, diagnostically insufficient; 1 = not visible, diagnostically insufficient. RESULTS: At focused view CTA, median scores for the aortic arch, subclavian arteries, common carotid arteries, C1, C6, and C7 segments of the internal carotid arteries, V4 segment of the vertebral arteries, basilar artery, cerebellum including cerebellar arteries, cerebrum including cerebral arteries, and dural venous sinuses, were all 4. Median scores for the C2 to C5 segments of the internal carotid arteries, and V1 to V3 segments of the vertebral arteries ranged between 3 and 2. At unmodified CTA, median score for all above-mentioned anatomic structures was 5, which was significantly higher (p < 0.0001) than that at focused view CTA. CONCLUSION: Focused view CTA shows promise for the selective visualization of stroke-related arteries. Further improvements should focus on more accurately visualizing the smaller and tortuous internal carotid and vertebral artery segments close to bone. CLINICAL RELEVANCE: Focused view CTA may speed up image interpretation time for LVO detection and may potentially be used as a tool to study the clinical relevance of incidental findings in future prospective long-term follow-up studies. KEY POINTS: • A deep learning-based algorithm ("focused view CTA") was developed to selectively visualize relevant structures for acute ischemic stroke evaluation at CTA. • The elimination of unrequested anatomic background information was complete in all cases. • Focused view CTA may be used to study the clinical relevance of incidental findings.

Optimal radiological gallbladder lesion characterization by combining visual assessment with CT-based radiomics.

OBJECTIVES: Differentiating benign gallbladder diseases from gallbladder cancer (GBC) remains a radiological challenge because they can appear very similar on imaging. This study aimed at investigating whether CT-based radiomic features of suspicious gallbladder lesions analyzed by machine learning algorithms could adequately discriminate benign gallbladder disease from GBC. In addition, the added value of machine learning models to radiological visual CT-scan interpretation was assessed. METHODS: Patients were retrospectively selected based on confirmed histopathological diagnosis and available contrast-enhanced portal venous phase CT-scan. The radiomic features were extracted from the entire gallbladder, then further analyzed by machine learning classifiers based on Lasso regression, Ridge regression, and XG Boosting. The results of the best-performing classifier were combined with radiological visual CT diagnosis and then compared with radiological visual CT assessment alone. RESULTS: In total, 127 patients were included: 83 patients with benign gallbladder lesions and 44 patients with GBC. Among all machine learning classifiers, XG boosting achieved the best AUC of 0.81 (95% CI 0.72-0.91) and the highest accuracy rate of 73% (95% CI 65-80%). When combining radiological visual interpretation and predictions of the XG boosting classifier, the highest diagnostic performance was achieved with an AUC of 0.98 (95% CI 0.96-1.00), a sensitivity of 91% (95% CI 86-100%), a specificity of 93% (95% CI 90-100%), and an accuracy of 92% (95% CI 90-100%). CONCLUSIONS: Machine learning analysis of CT-based radiomic features shows promising results in discriminating benign from malignant gallbladder disease. Combining CT-based radiomic analysis and radiological visual interpretation provided the most optimal strategy for GBC and benign gallbladder disease differentiation. KEY POINTS: Radiomic-based machine learning algorithms are able to differentiate benign gallbladder disease from gallbladder cancer. Combining machine learning algorithms with a radiological visual interpretation of gallbladder lesions at CT increases the specificity, compared to visual interpretation alone, from 73 to 93% and the accuracy from 85 to 92%. Combined use of machine learning algorithms and radiological visual assessment seems the most optimal strategy for GBC and benign gallbladder disease differentiation.

A new medical imaging postprocessing and interpretation concept to investigate the clinical relevance of incidentalomas: can we keep Pandora's box closed?

BACKGROUND: Incidental imaging findings (incidentalomas) are common, but there is currently no effective means to investigate their clinical relevance. PURPOSE: To introduce a new concept to postprocess a medical imaging examination in a way that incidentalomas are concealed while its diagnostic potential is maintained to answer the referring physician's clinical questions. MATERIAL AND METHODS: A deep learning algorithm was developed to automatically eliminate liver, gallbladder, pancreas, spleen, adrenal glands, lungs, and bone from unenhanced computed tomography (CT). This deep learning algorithm was applied to a separately held set of unenhanced CT scans of 27 patients who underwent CT to evaluate for urolithiasis, and who had a total of 32 incidentalomas in one of the aforementioned organs. RESULTS: Median visual scores for organ elimination on modified CT were 100% for the liver, gallbladder, spleen, and right adrenal gland, 90%-99% for the pancreas, lungs, and bones, and 80%-89% for the left adrenal gland. In 26 out of 27 cases (96.3%), the renal calyces and pelves, ureters, and urinary bladder were completely visible on modified CT. In one case, a short (<1 cm) trajectory of the left ureter was not clearly visible due to adjacent atherosclerosis that was mistaken for bone by the algorithm. Of 32 incidentalomas, 28 (87.5%) were completely concealed on modified CT. CONCLUSION: This preliminary technical report demonstrated the feasibility of a new approach to postprocess and evaluate medical imaging examinations that can be used by future prospective research studies with long-term follow-up to investigate the clinical relevance of incidentalomas.

Early increase in single-kidney glomerular filtration rate after living kidney donation predicts long-term kidney function.

Single-kidney glomerular filtration rate (GFR) increases after living kidney donation due to compensatory hyperfiltration and structural changes. The implications of inter-individual variability in this increase in single-kidney GFR are unknown. Here, we aimed to identify determinants of the increase in single-kidney GFR at three-month postdonation, and to investigate its relationship with long-term kidney function. In a cohort study in 1024 donors, we found considerable inter-individual variability of the early increase in remaining single-kidney estimated GFR (eGFR) (median [25th-75th percentile]) 12 [8-18] mL/min/1.73m2. Predonation eGFR, age, and cortical kidney volume measured by CT were the main determinants of the early postdonation increase in single-kidney eGFR. Individuals with a stronger early increase in single-kidney eGFR had a significantly higher five-year postdonation eGFR, independent of predonation eGFR and age. Addition of the postdonation increase in single-kidney eGFR to a model including predonation eGFR and age significantly improved prediction of a five-year postdonation eGFR under 50 mL/min/1.73m2. Results at ten-year follow-up were comparable, while accounting for left-right differences in kidney volume did not materially change the results. Internal validation using 125I-iothalamate-based measured GFR in 529 donors and external validation using eGFR data in 647 donors yielded highly similar results. Thus, individuals with a more pronounced increase in single-kidney GFR had better long-term kidney function, independent of predonation GFR and age. Hence, the early postdonation increase in single-kidney GFR, considered indicative for kidney reserve capacity, may have additional value to eGFR and age to personalize follow-up intensity after living kidney donation.

Value-based radiology cannot thrive without reforms and research.

KEY POINTS: • A value-based system aims to achieve improved patient-relevant outcomes without increasing costs.• Value-based radiology cannot thrive as long as volume dominates as the most important metric to reward clinical performance.• Reforms and research are needed to enable radiologists to practice value-based healthcare.

A deep learning masked segmentation alternative to manual segmentation in biparametric MRI prostate cancer radiomics.

OBJECTIVES: To determine the value of a deep learning masked (DLM) auto-fixed volume of interest (VOI) segmentation method as an alternative to manual segmentation for radiomics-based diagnosis of clinically significant (CS) prostate cancer (PCa) on biparametric magnetic resonance imaging (bpMRI). MATERIALS AND METHODS: This study included a retrospective multi-center dataset of 524 PCa lesions (of which 204 are CS PCa) on bpMRI. All lesions were both semi-automatically segmented with a DLM auto-fixed VOI method (averaging < 10 s per lesion) and manually segmented by an expert uroradiologist (averaging 5 min per lesion). The DLM auto-fixed VOI method uses a spherical VOI (with its center at the location of the lowest apparent diffusion coefficient of the prostate lesion as indicated with a single mouse click) from which non-prostate voxels are removed using a deep learning-based prostate segmentation algorithm. Thirteen different DLM auto-fixed VOI diameters (ranging from 6 to 30 mm) were explored. Extracted radiomics data were split into training and test sets (4:1 ratio). Performance was assessed with receiver operating characteristic (ROC) analysis. RESULTS: In the test set, the area under the ROC curve (AUCs) of the DLM auto-fixed VOI method with a VOI diameter of 18 mm (0.76 [95% CI: 0.66-0.85]) was significantly higher (p = 0.0198) than that of the manual segmentation method (0.62 [95% CI: 0.52-0.73]). CONCLUSIONS: A DLM auto-fixed VOI segmentation can provide a potentially more accurate radiomics diagnosis of CS PCa than expert manual segmentation while also reducing expert time investment by more than 97%. KEY POINTS: • Compared to traditional expert-based segmentation, a deep learning mask (DLM) auto-fixed VOI placement is more accurate at detecting CS PCa. • Compared to traditional expert-based segmentation, a DLM auto-fixed VOI placement is faster and can result in a 97% time reduction. • Applying deep learning to an auto-fixed VOI radiomics approach can be valuable.

Do People Favor Artificial Intelligence Over Physicians? A Survey Among the General Population and Their View on Artificial Intelligence in Medicine.

OBJECTIVES: To investigate the general population's view on artificial intelligence (AI) in medicine with specific emphasis on 3 areas that have experienced major progress in AI research in the past few years, namely radiology, robotic surgery, and dermatology. METHODS: For this prospective study, the April 2020 Online Longitudinal Internet Studies for the Social Sciences Panel Wave was used. Of the 3117 Longitudinal Internet Studies For The Social Sciences panel members contacted, 2411 completed the full questionnaire (77.4% response rate), after combining data from earlier waves, the final sample size was 1909. A total of 3 scales focusing on trust in the implementation of AI in radiology, robotic surgery, and dermatology were used. Repeated-measures analysis of variance and multivariate analysis of variance was used for comparison. RESULTS: The overall means show that respondents have slightly more trust in AI in dermatology than in radiology and surgery. The means show that higher educated males, employed or student, of Western background, and those not admitted to a hospital in the past 12 months have more trust in AI. The trust in AI in radiology, robotic surgery, and dermatology is positively associated with belief in the efficiency of AI and these specific domains were negatively associated with distrust and accountability in AI in general. CONCLUSIONS: The general population is more distrustful of AI in medicine unlike the overall optimistic views posed in the media. The level of trust is dependent on what medical area is subject to scrutiny. Certain demographic characteristics and individuals with a generally positive view on AI and its efficiency are significantly associated with higher levels of trust in AI.

Clinical implications of increased uptake in bone marrow and spleen on FDG-PET in patients with bacteremia.

PURPOSE: To investigate which clinical factors and laboratory values are associated with high FDG uptake in the bone marrow and spleen on 2-deoxy-2-[18F]fluoro-D-glucose (FDG) positron emission tomography (PET)/computed tomography (CT) in patients with bacteremia. METHODS: One hundred forty-five consecutive retrospective patients with bacteremia who underwent FDG-PET/CT between 2010 and 2017 were included. Mean standard uptake values (SUVmean) of FDG in bone marrow, liver, and spleen were measured. Bone marrow-to-liver SUV ratios (BLR) and spleen-to-liver SUV ratios (SLR) were calculated. Linear regression analyses were performed to examine the association of BLR and SLR with age, gender, hemoglobin, leukocyte count, platelets, glucose level, C-reactive protein (CRP), microorganism, days of antibiotic treatment before FDG-PET/CT, infection focus, use of immunosuppressive drugs, duration of hospital stay (after FDG-PET/CT), ICU admission, and mortality. RESULTS: C-reactive protein (p = 0.006), a cardiovascular or musculoskeletal focus of infection (p = 0.000 for both), and bacteremia caused by Gram-negative bacteria (p = 0.002) were independently and positively associated with BLR, while age (p = 0.000) and glucose level before FDG-PET/CT (p = 0.004) were independently and negatively associated with BLR. For SLR, CRP (p = 0.001) and a cardiovascular focus of infection (p = 0.020) were independently and positively associated with SLR, while age (p = 0.002) and glucose level before FDG-PET/CT (p = 0.016) were independently and negatively associated with SLR. CONCLUSION: High FDG uptake in the bone marrow is associated with a higher inflammatory response and younger age in patients with bacteremia. In patients with high FDG uptake in the bone marrow, a cardiovascular or musculoskeletal focus of infection is more likely than other foci, and the infection is more often caused by Gram-negative species. High splenic FDG uptake is associated with a higher inflammatory response as well, and a cardiovascular focus of infection is also more likely in case of high splenic FDG uptake.

Medical knowledge and clinical productivity: independently correlated metrics during radiology residency.

OBJECTIVE: To determine the association between medical knowledge relevant to radiology practice (as measured by the Dutch radiology progress test [DRPT]) and clinical productivity during radiology residency. METHODS: This study analyzed the results of 6 DRPTs and time period-matched clinical production points of radiology residents affiliated to a tertiary care academic medical center between 2013 and 2016. The Spearman correlation analysis was performed to determine the association between DRPT percentile scores and average daily clinical production points. Linear regression analyses were performed to determine the association of DRPT percentile scores with average daily clinical production points, adjusted for age and gender of the radiology resident, and postgraduate year. RESULTS: Eighty-four DRPTs with time period-matched clinical production points were included. These 84 DRPTs were made by 29 radiology residents (18 males and 11 females) with a median age of 31 years (range: 26-38 years). The Spearman correlation coefficient between DRPT percentile scores and average daily clinical production points was 0.550 (95% confidence interval: 0.381-0.694) (p < 0.001), indicating a significant moderate positive association. On multivariate analysis, average daily clinical production points (ß coefficient of 0.035, p = 0.003), female gender of the radiology resident (ß coefficient of 12.690, p = 0.001), and postgraduate year (ß coefficient of 10.179, p < 0.001) were significantly associated with DRPT percentile scores. These three independent variables achieved an adjusted R2 of 0.527. CONCLUSION: Clinical productivity is independently associated with medical knowledge relevant to radiology practice during radiology residency. These findings indicate that clinical productivity of a resident could be a potentially relevant metric in a radiology training program. KEY POINTS: • There is a significant moderate correlation between medical knowledge relevant to radiology practice and clinical productivity during radiology residency. • Medical knowledge relevant to radiology practice remains independently associated with clinical productivity during radiology residency after adjustment for postgraduate year and gender. • Clinical productivity of a resident may be regarded as a potentially relevant metric in a radiology training program.

Liver fibrosis staging by deep learning: a visual-based explanation of diagnostic decisions of the model.

OBJECTIVES: Deep learning has been proven to be able to stage liver fibrosis based on contrast-enhanced CT images. However, until now, the algorithm is used as a black box and lacks transparency. This study aimed to provide a visual-based explanation of the diagnostic decisions made by deep learning. METHODS: The liver fibrosis staging network (LFS network) was developed at contrast-enhanced CT images in the portal venous phase in 252 patients with histologically proven liver fibrosis stage. To give a visual explanation of the diagnostic decisions made by the LFS network, Gradient-weighted Class Activation Mapping (Grad-cam) was used to produce location maps indicating where the LFS network focuses on when predicting liver fibrosis stage. RESULTS: The LFS network had areas under the receiver operating characteristic curve of 0.92, 0.89, and 0.88 for staging significant fibrosis (F2-F4), advanced fibrosis (F3-F4), and cirrhosis (F4), respectively, on the test set. The location maps indicated that the LFS network had more focus on the liver surface in patients without liver fibrosis (F0), while it focused more on the parenchyma of the liver and spleen in case of cirrhosis (F4). CONCLUSIONS: Deep learning methods are able to exploit CT-based information from the liver surface, liver parenchyma, and extrahepatic information to predict liver fibrosis stage. Therefore, we suggest using the entire upper abdomen on CT images when developing deep learning-based liver fibrosis staging algorithms. KEY POINTS: • Deep learning algorithms can stage liver fibrosis using contrast-enhanced CT images, but the algorithm is still used as a black box and lacks transparency. • Location maps produced by Gradient-weighted Class Activation Mapping can indicate the focus of the liver fibrosis staging network. • Deep learning methods use CT-based information from the liver surface, liver parenchyma, and extrahepatic information to predict liver fibrosis stage.

Radiologist-patient communication of musculoskeletal ultrasonography results: a choice between added value and costs.

BACKGROUND: Literature on radiologist-patient communication of musculoskeletal ultrasonography (US) results is currently lacking. PURPOSE: To investigate the patient's view on receiving the results from a radiologist after a musculoskeletal US examination, and the additional time required to provide such a service. MATERIAL AND METHODS: This prospective study included 106 outpatients who underwent musculoskeletal US, and who were equally randomized to either receive or not receive the results from the radiologist directly after the examination. RESULTS: In both randomization groups, all quality performance metrics (radiologist's friendliness, explanation, skill, concern for comfort, concern for patient questions/worries, overall rating of the examination, and likelihood of recommending the examination) received median scores of good/high to very good/very high. Patients who had received their US results from the radiologist rated the radiologist's explanation and concern for patient questions/worries as significantly higher (P = 0.009 and P = 0.002) than patients who had not. In both randomization groups, there were no significant differences between anxiety levels before and after the US examination (P = 0.222 and P = 1.000). Of the 48 responding patients, 46 (95.8%) rated a radiologist-patient discussion of US findings as important. US examinations with a radiologist-patient communication regarding US findings (median = 11.29 min) were significantly longer (P < 0.0001) than those without (median = 8.08 min). CONCLUSION: Even without communicating musculoskeletal US results directly to patients, radiologists can still achieve high ratings from patients for their communication and empathy. Nevertheless, patient experience can be further enhanced if a radiologist adds this communication to the examination. However, this increases total examination time and therefore costs.

Patient safety incidents in radiology: frequency and distribution of incident types.

BACKGROUND: Patient safety incidents may be a valuable source of information to learn from and to prevent future errors. PURPOSE: To determine the distribution of patient safety incident types in radiology according to the International Classification for Patient Safety (ICPS), and to comprehensively review those incidents that were either harmful or serious in terms of risk of patient harm and reoccurrence. MATERIAL AND METHODS: The most recent five-year database (2014-2019) of a radiology incident reporting system was evaluated. RESULTS: A total of 480 patient safety incidents were included. Top three ICPS incident types were clinical administration (119/480, 24.8%), resources/organizational management (112/480, 23.3%), and clinical process/procedure (91/480, 19.0%). Harm severities were none in 457 (95.2%) cases, mild in 14 (2.9%), moderate in 4 (0.8%), severe in 3 (0.6%), and unknown in one case. Subsequent Prevention Recovery Information System for Monitoring and Analysis (PRISMA) reviews were performed in 4 (0.8%) cases. The three patient safety incidents that caused severe harm (of which one underwent PRISMA review) involved resources/organizational management (n = 1), clinical process/procedure (n = 1), and medication/IV fluids (n = 1). Three other cases (with no harm in two cases and moderate harm in one case) that underwent PRISMA review involved resources/organizational management (n = 2) and medical device/equipment/property (n = 1). CONCLUSION: Radiology-related patient safety incidents predominantly occur in three ICPS domains (clinical administration, resources/organizational management, and clinical process/procedure). Harmful/serious incidents are relatively rare. The standardly and transparently reported findings from this study may be used for healthcare quality improvement, benchmarking purposes, and as a primer for future studies.

MRI after Whoops procedure: diagnostic value for residual sarcoma and predictive value for an incomplete second resection.

OBJECTIVE: To determine the value of MRI for the detection and assessment of the anatomic extent of residual sarcoma after a Whoops procedure (unplanned sarcoma resection) and its utility for the prediction of an incomplete second resection. MATERIALS AND METHODS: This study included consecutive patients who underwent a Whoops procedure, successively followed by gadolinium chelate-enhanced MRI and second surgery at a tertiary care sarcoma center. RESULTS: Twenty-six patients were included, of whom 19 with residual tumor at the second surgery and 8 with an incomplete second resection (R1: n = 6 and R2: n = 2). Interobserver agreement for residual tumor at MRI after a Whoops procedure was perfect (κ value: 1.000). MRI achieved a sensitivity of 47.4% (9/19), a specificity of 100% (7/7), a positive predictive value of 100% (9/9), and a negative predictive value of 70.0% (7/17) for the detection of residual tumor. MRI correctly classified 2 of 19 residual sarcomas as deep-seated (i.e., extending beyond the superficial muscle fascia) but failed to correctly classify 3 of 19 residual sarcomas as deep-seated. There were no significant associations between MRI findings (presence of residual tumor, maximum tumor diameter, anatomic tumor extent, tumor margins, tumor spiculae, and tumor tail on the superficial fascia) with an incomplete (R1 or R2) second resection. CONCLUSION: Gadolinium chelate-enhanced MRI is a reproducible method to rule in residual sarcoma, but it is insufficiently accurate to rule out and assess the anatomic extent or residual sarcoma after a Whoops procedure. Furthermore, MRI has no utility in predicting an incomplete second resection.