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.

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.

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.

Using deep learning to optimize the prostate MRI protocol by assessing the diagnostic efficacy of MRI sequences.

PURPOSE: To explore diagnostic deep learning for optimizing the prostate MRI protocol by assessing the diagnostic efficacy of MRI sequences. METHOD: This retrospective study included 840 patients with a biparametric prostate MRI scan. The MRI protocol included a T2-weighted image, three DWI sequences (b50, b400, and b800 s/mm2), a calculated ADC map, and a calculated b1400 sequence. Two accelerated MRI protocols were simulated, using only two acquired b-values to calculate the ADC and b1400. Deep learning models were trained to detect prostate cancer lesions on accelerated and full protocols. The diagnostic performances of the protocols were compared on the patient-level with the area under the receiver operating characteristic (AUROC), using DeLong's test, and on the lesion-level with the partial area under the free response operating characteristic (pAUFROC), using a permutation test. Validation of the results was performed among expert radiologists. RESULTS: No significant differences in diagnostic performance were found between the accelerated protocols and the full bpMRI baseline. Omitting b800 reduced 53% DWI scan time, with a performance difference of + 0.01 AUROC (p = 0.20) and -0.03 pAUFROC (p = 0.45). Omitting b400 reduced 32% DWI scan time, with a performance difference of -0.01 AUROC (p = 0.65) and + 0.01 pAUFROC (p = 0.73). Multiple expert radiologists underlined the findings. CONCLUSIONS: This study shows that deep learning can assess the diagnostic efficacy of MRI sequences by comparing prostate MRI protocols on diagnostic accuracy. Omitting either the b400 or the b800 DWI sequence can optimize the prostate MRI protocol by reducing scan time without compromising diagnostic quality.

Does FDG-PET/CT for incidentally found pulmonary lesions lead to a cascade of more incidental findings?

OBJECTIVE: To determine the frequency, nature, and downstream healthcare costs of new incidental findings that are found on whole-body FDG-PET/CT in patients with a non-FDG-avid pulmonary lesion ≥10 mm that was incidentally found on previous imaging. MATERIALS AND METHODS: This retrospective study included a consecutive series of patients who underwent whole-body FDG-PET/CT because of an incidentally found pulmonary lesion ≥10 mm. RESULTS: Seventy patients were included, of whom 23 (32.9 %) had an incidentally found pulmonary lesion that proved to be non-FDG-avid. In 12 of these 23 cases (52.2 %) at least one new incidental finding was discovered on FDG-PET/CT. The total number of new incidental findings was 21, of which 7 turned out to be benign, 1 proved to be malignant (incurable metastasized cancer), and 13 whose nature remained unclear. One patient sustained permanent neurologic impairment of the left leg due to iatrogenic nerve damage during laparotomy for an incidental finding which turned out to be benign. The total costs of all additional investigations due to the detection of new incidental findings amounted to €9903.17, translating to an average of €141.47 per whole-body FDG-PET/CT scan performed for the evaluation of an incidentally found pulmonary lesion. CONCLUSION: In many patients in whom whole-body FDG-PET/CT was performed to evaluate an incidentally found pulmonary lesion that turned out to be non-FDG-avid and therefore very likely benign, FDG-PET/CT detected new incidental findings in our preliminary study. Whether the detection of these new incidental findings is cost-effective or not, requires further research with larger sample sizes.

Machine learning-based radiomic analysis and growth visualization for ablation site recurrence diagnosis in follow-up CT.

OBJECTIVES: Detecting ablation site recurrence (ASR) after thermal ablation remains a challenge for radiologists due to the similarity between tumor recurrence and post-ablative changes. Radiomic analysis and machine learning methods may show additional value in addressing this challenge. The present study primarily sought to determine the efficacy of radiomic analysis in detecting ASR on follow-up computed tomography (CT) scans. The second aim was to develop a visualization tool capable of emphasizing regions of ASR between follow-up scans in individual patients. MATERIALS AND METHODS: Lasso regression and Extreme Gradient Boosting (XGBoost) classifiers were employed for modeling radiomic features extracted from regions of interest delineated by two radiologists. A leave-one-out test (LOOT) was utilized for performance evaluation. A visualization method, creating difference heatmaps (diff-maps) between two follow-up scans, was developed to emphasize regions of growth and thereby highlighting potential ASR. RESULTS: A total of 55 patients, including 20 with and 35 without ASR, were included in the radiomic analysis. The best performing model was achieved by Lasso regression tested with the LOOT approach, reaching an area under the curve (AUC) of 0.97 and an accuracy of 92.73%. The XGBoost classifier demonstrated better performance when trained with all extracted radiomic features than without feature selection, achieving an AUC of 0.93 and an accuracy of 89.09%. The diff-maps correctly highlighted post-ablative liver tumor recurrence in all patients. CONCLUSIONS: Machine learning-based radiomic analysis and growth visualization proved effective in detecting ablation site recurrence on follow-up CT scans.

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.

European Association of Nuclear Medicine Focus 5: Consensus on Molecular Imaging and Theranostics in Prostate Cancer.

BACKGROUND: In prostate cancer (PCa), questions remain on indications for prostate-specific membrane antigen (PSMA) positron emission tomography (PET) imaging and PSMA radioligand therapy, integration of advanced imaging in nomogram-based decision-making, dosimetry, and development of new theranostic applications. OBJECTIVE: We aimed to critically review developments in molecular hybrid imaging and systemic radioligand therapy, to reach a multidisciplinary consensus on the current state of the art in PCa. DESIGN, SETTING, AND PARTICIPANTS: The results of a systematic literature search informed a two-round Delphi process with a panel of 28 PCa experts in medical or radiation oncology, urology, radiology, medical physics, and nuclear medicine. The results were discussed and ratified in a consensus meeting. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: Forty-eight statements were scored on a Likert agreement scale and six as ranking options. Agreement statements were analysed using the RAND appropriateness method. Ranking statements were analysed using weighted summed scores. RESULTS AND LIMITATIONS: After two Delphi rounds, there was consensus on 42/48 (87.5%) of the statements. The expert panel recommends PSMA PET to be used for staging the majority of patients with unfavourable intermediate and high risk, and for restaging of suspected recurrent PCa. There was consensus that oligometastatic disease should be defined as up to five metastases, even using advanced imaging modalities. The group agreed that [177Lu]Lu-PSMA should not be administered only after progression to cabazitaxel and that [223Ra]RaCl2 remains a valid therapeutic option in bone-only metastatic castration-resistant PCa. Uncertainty remains on various topics, including the need for concordant findings on both [18F]FDG and PSMA PET prior to [177Lu]Lu-PSMA therapy. CONCLUSIONS: There was a high proportion of agreement among a panel of experts on the use of molecular imaging and theranostics in PCa. Although consensus statements cannot replace high-certainty evidence, these can aid in the interpretation and dissemination of best practice from centres of excellence to the wider clinical community. PATIENT SUMMARY: There are situations when dealing with prostate cancer (PCa) where both the doctors who diagnose and track the disease development and response to treatment, and those who give treatments are unsure about what the best course of action is. Examples include what methods they should use to obtain images of the cancer and what to do when the cancer has returned or spread. We reviewed published research studies and provided a summary to a panel of experts in imaging and treating PCa. We also used the research summary to develop a questionnaire whereby we asked the experts to state whether or not they agreed with a list of statements. We used these results to provide guidance to other health care professionals on how best to image men with PCa and what treatments to give, when, and in what order, based on the information the images provide.

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.

Prostate MRI for Improving Personalized Risk Prediction of Incontinence and Surgical Planning: The Role of Membranous Urethral Length Measurements and the Use of 3D Models.

Prostate MRI has an important role in prostate cancer diagnosis and treatment, including detection, the targeting of prostate biopsies, staging and guiding radiotherapy and active surveillance. However, there are other ''less well-known'' applications which are being studied and frequently used in our highly specialized medical center. In this review, we focus on two research topics that lie within the expertise of this study group: (1) anatomical parameters predicting the risk of urinary incontinence after radical prostatectomy, allowing more personalized shared decision-making, with special emphasis on the membranous urethral length (MUL); (2) the use of three-dimensional models to help the surgical planning. These models may be used for training, patient counselling, personalized estimation of nerve sparing and extracapsular extension and may help to achieve negative surgical margins and undetectable postoperative PSA values.

Genetic Aspects and Molecular Testing in Prostate Cancer: A Report from a Dutch Multidisciplinary Consensus Meeting.

Background: Germline and tumour genetic testing in prostate cancer (PCa) is becoming more broadly accepted, but testing indications and clinical consequences for carriers in each disease stage are not yet well defined. Objective: To determine the consensus of a Dutch multidisciplinary expert panel on the indication and application of germline and tumour genetic testing in PCa. Design setting and participants: The panel consisted of 39 specialists involved in PCa management. We used a modified Delphi method consisting of two voting rounds and a virtual consensus meeting. Outcome measurements and statistical analysis: Consensus was reached if ≥75% of the panellists chose the same option. Appropriateness was assessed by the RAND/UCLA appropriateness method. Results and limitations: Of the multiple-choice questions, 44% reached consensus. For men without PCa having a relevant family history (familial PCa/BRCA-related hereditary cancer), follow-up by prostate-specific antigen was considered appropriate. For patients with low-risk localised PCa and a family history of PCa, active surveillance was considered appropriate, except in case of the patient being a BRCA2 germline pathogenic variant carrier. Germline and tumour genetic testing should not be done for nonmetastatic hormone-sensitive PCa in the absence of a relevant family history of cancer. Tumour genetic testing was deemed most appropriate for the identification of actionable variants, with uncertainty for germline testing. For tumour genetic testing in metastatic castration-resistant PCa, consensus was not reached for the timing and panel composition. The principal limitations are as follows: (1) a number of topics discussed lack scientific evidence, and therefore the recommendations are partly opinion based, and (2) there was a small number of experts per discipline. Conclusions: The outcomes of this Dutch consensus meeting may provide further guidance on genetic counselling and molecular testing related to PCa. Patient summary: A group of Dutch specialists discussed the use of germline and tumour genetic testing in prostate cancer (PCa) patients, indication of these tests (which patients and when), and impact of these tests on the management and treatment of PCa.

The Value of Deep Learning in Gallbladder Lesion Characterization.

BACKGROUND: The similarity of gallbladder cancer and benign gallbladder lesions brings challenges to diagnosing gallbladder cancer (GBC). This study investigated whether a convolutional neural network (CNN) could adequately differentiate GBC from benign gallbladder diseases, and whether information from adjacent liver parenchyma could improve its performance. METHODS: Consecutive patients referred to our hospital with suspicious gallbladder lesions with histopathological diagnosis confirmation and available contrast-enhanced portal venous phase CT scans were retrospectively selected. A CT-based CNN was trained once on gallbladder only and once on gallbladder including a 2 cm adjacent liver parenchyma. The best-performing classifier was combined with the diagnostic results based on radiological visual analysis. RESULTS: A total of 127 patients were included in the study: 83 patients with benign gallbladder lesions and 44 with gallbladder cancer. The CNN trained on the gallbladder including adjacent liver parenchyma achieved the best performance with an AUC of 0.81 (95% CI 0.71-0.92), being >10% better than the CNN trained on only the gallbladder (p = 0.09). Combining the CNN with radiological visual interpretation did not improve the differentiation between GBC and benign gallbladder diseases. CONCLUSIONS: The CT-based CNN shows promising ability to differentiate gallbladder cancer from benign gallbladder lesions. In addition, the liver parenchyma adjacent to the gallbladder seems to provide additional information, thereby improving the CNN's performance for gallbladder lesion characterization. However, these findings should be confirmed in larger multicenter studies.

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.

Comparative Performance of Deep Learning and Radiologists for the Diagnosis and Localization of Clinically Significant Prostate Cancer at MRI: A Systematic Review.

BACKGROUND: Deep learning (DL)-based models have demonstrated an ability to automatically diagnose clinically significant prostate cancer (PCa) on MRI scans and are regularly reported to approach expert performance. The aim of this work was to systematically review the literature comparing deep learning (DL) systems to radiologists in order to evaluate the comparative performance of current state-of-the-art deep learning models and radiologists. METHODS: This systematic review was conducted in accordance with the 2020 Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) checklist. Studies investigating DL models for diagnosing clinically significant (cs) PCa on MRI were included. The quality and risk of bias of each study were assessed using the checklist for AI in medical imaging (CLAIM) and QUADAS-2, respectively. Patient level and lesion-based diagnostic performance were separately evaluated by comparing the sensitivity achieved by DL and radiologists at an identical specificity and the false positives per patient, respectively. RESULTS: The final selection consisted of eight studies with a combined 7337 patients. The median study quality with CLAIM was 74.1% (IQR: 70.6-77.6). DL achieved an identical patient-level performance to the radiologists for PI-RADS ≥ 3 (both 97.7%, SD = 2.1%). DL had a lower sensitivity for PI-RADS ≥ 4 (84.2% vs. 88.8%, p = 0.43). The sensitivity of DL for lesion localization was also between 2% and 12.5% lower than that of the radiologists. CONCLUSIONS: DL models for the diagnosis of csPCa on MRI appear to approach the performance of experts but currently have a lower sensitivity compared to experienced radiologists. There is a need for studies with larger datasets and for validation on external data.

Quality of Multicenter Studies Using MRI Radiomics for Diagnosing Clinically Significant Prostate Cancer: A Systematic Review.

Background: Reproducibility and generalization are major challenges for clinically significant prostate cancer modeling using MRI radiomics. Multicenter data seem indispensable to deal with these challenges, but the quality of such studies is currently unknown. The aim of this study was to systematically review the quality of multicenter studies on MRI radiomics for diagnosing clinically significant PCa. Methods: This systematic review followed the 2020 Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) checklist. Multicenter studies investigating the value of MRI radiomics for the diagnosis of clinically significant prostate cancer were included. Quality was assessed using the checklist for artificial intelligence in medical imaging (CLAIM) and the radiomics quality score (RQS). CLAIM consisted of 42 equally important items referencing different elements of good practice AI in medical imaging. RQS consisted of 36 points awarded over 16 items related to good practice radiomics. Final CLAIM and RQS scores were percentage-based, allowing for a total quality score consisting of the average of CLAIM and RQS. Results: Four studies were included. The average total CLAIM score was 74.6% and the average RQS was 52.8%. The corresponding average total quality score (CLAIM + RQS) was 63.7%. Conclusions: A very small number of multicenter radiomics PCa classification studies have been performed with the existing studies being of bad or average quality. Good multicenter studies might increase by encouraging preferably prospective data sharing and paying extra care to documentation in regards to reproducibility and clinical utility.

On-call abdominal ultrasonography: the rate of negative examinations and incidentalomas in a European tertiary care center.

OBJECTIVES: To determine the proportions of abdominal US examinations during on-call hours that are negative and that contain an incidentaloma, and to explore temporal changes and determinants. METHODS: This study included 1615 US examinations that were done during on-call hours at a tertiary care center between 2005 and 2017. RESULTS: The total proportion of negative US examinations was 49.2% (795/1615). The total proportion of US examinations with an incidentaloma was 8.0% (130/1615). There were no significant temporal changes in either one of these proportions. The likelihood of a negative US examination was significantly higher when requested by anesthesiology [odds ratio (OR) 2.609, P = 0.011], or when the indication for US was focused on gallbladder and biliary ducts (OR 1.556, P = 0.007), transplant (OR 2.371, P = 0.005), trauma (OR 3.274, P < 0.001), or urolithiasis/postrenal obstruction (OR 3.366, P < 0.001). In contrast, US examinations were significantly less likely to be negative when requested by urology (OR 0.423, P = 0.014), or when the indication for US was acute oncology (OR 0.207, P = 0.045) or appendicitis (OR 0.260, P < 0.001). The likelihood of an incidentaloma on US was significantly higher in older patients (OR 1.020 per year of age increase, P < 0.001) or when the liver was evaluated with US (OR 3.522, P < 0.001). DISCUSSION: Nearly 50% of abdominal US examinations during on-call hours are negative, and 8% reveal an incidentaloma. Requesting specialty and indication for US affect the likelihood of a negative examination, and higher patient age and liver evaluations increase the chance of detecting an incidentaloma in this setting. These data may potentially be used to improve clinical reasoning and restrain overutilization of imaging.

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.

Incidental imaging findings referred to a specialized sarcoma center: Frequency, determinants, and downstream healthcare costs.

OBJECTIVE: To determine the frequency and factors associated with incidental imaging findings (incidentalomas) that are referred to a specialized sarcoma center and that eventually turn out to be benign or of low-risk malignant potential, and to assess their downstream healthcare costs. MATERIALS AND METHODS: This study included all consecutive new patients that were referred to a specialized sarcoma center within a 7-month period. RESULTS: Of 221 patients that were included, 28 had an incidentaloma. Of these 28 incidentalomas, 23 were benign (n = 11) or of low-risk malignant potential (n = 12), corresponding to a frequency of 10.4% Utilization of conventional radiography (odds ratio [OR] = 6.538, P = 0.018) and CT (OR = 8.167, P = 0.012) was significantly more associated with the detection of benign or low-risk malignant potential incidentalomas than ultrasonography. The likelihood of detecting benign or low-risk malignant potential incidentalomas after MRI utilization was not significantly different from that after ultrasonography (P = 0.174). All other variables (including patient age and gender, history of malignancy, specialty by whom the lesion was initially detected, and lesion location) were not significantly associated with these incidentalomas. The 23 cases with an incidentaloma that turned out to be benign or of low-risk malignant potential resulted in a total of €42,707 ($49,552) downstream healthcare costs, with an average of €1857 ($2155) per case. CONCLUSION: Incidentalomas that are referred to a specialized sarcoma center and that eventually prove to be benign or of low-risk malignant potential are common, are more frequently detected on conventional radiographs and CT, and cause relevant subsequent healthcare costs.