Faculty Bibliography

BACKGROUND:Access to prostate MRI remains limited due to resource constraints and the need for expert interpretation. PURPOSE/OBJECTIVE:To develop machine learning (ML) models that enable risk-based triage for prostate MRI (ProMT-ML) in the evaluation of prostate cancer. STUDY TYPE/METHODS:Retrospective and prospective. POPULATION/METHODS:A total of 11,879 retrospective MRI scans for suspected prostate cancer from a multi-hospital health system, divided into training (N = 9504) and test (N = 2375) sets. A total of 4551 records for prospective validation. FIELD STRENGTH/SEQUENCE/UNASSIGNED:1.5T and 3T/Turbo-spin echo T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), and dynamic contrast-enhanced (DCE). ASSESSMENT/RESULTS:Prostate Imaging Reporting and Data System (PI-RADS) scores were retrieved from MRI reports. The Boruta algorithm was used to select final input features from candidate features. Two models were developed using supervised ML to estimate the likelihood of an abnormal MRI, defined as PI-RADS ≥ 3: Model A (with prostate volume) and Model B (without prostate volume). Models were compared to PSA. Prostate biopsy pathology was assessed to evaluate potential clinical impact. STATISTICAL TESTS/METHODS:Area under the receiver operating characteristic curve (AUC) was the primary performance metric. RESULTS:A total of 5580 (46.9%) subjects had a PI-RADS score ≥ 3. After feature selection, Model A included age, PSA, body mass index, and prostate volume, while Model B included age, PSA, body mass index, and systolic blood pressure. Both models A (AUC 0.711) and B (AUC 0.616) significantly outperformed PSA (AUC 0.593). Compared to PSA threshold > 4 ng/mL, Model A demonstrated significantly improved specificity (28.3% vs. 21.9%) and no significant difference in sensitivity (89.0% vs. 86.7%). Among false negatives (Model A: 8.0% (62/776); Model B: 16.8% (130/776)), most (Model A: 87%; Model B: 69%) had benign or clinically insignificant disease on biopsy. On prospective validation, both versions of ProMT-ML significantly outperformed PSA. DATA CONCLUSION/CONCLUSIONS:ProMT-ML provides personalized risk estimates of abnormal prostate MRI and can support triage of this test. TECHNICAL EFFICACY/UNASSIGNED:Stage 4.

Various imaging modalities play key roles throughout the different stages of prostate cancer. Each imaging modality has different strengths and weaknesses and various scoring systems or frameworks are used to interpret their findings. Discordances between imaging modalities or interpretation frameworks, and even with clinicopathological findings are not uncommon. Discordances often lead to challenges in the decision-making process, especially with dynamically changing indications for newer imaging modalities. While more research is needed on harmonizing interpretations across different modalities, multidisciplinary team discussion is key to optimizing management of patients with prostate cancer when such discordances are present. In this comprehensive review, we take a deep dive in to these various discordances seen in clinical practice and explore their clinical implications.

PURPOSE/OBJECTIVE:To explore pragmatic approaches integrating MRI and PSMA-PET/CT for evaluating extraprostatic extension (EPE) of prostate cancer (PCa). METHODS:>12). Diagnostic performance was tested with receiver operating characteristic (ROC) curves and compared using DeLong and McNemar tests. RESULTS:>12 among which 87.5% (7/8) were corrected upgraded and had pathological EPE. CONCLUSION/CONCLUSIONS:Several pragmatic approaches were explored for integrating MRI and PSMA-PET/CT to assess EPE in PCa. Combining morphological information from MRI and PSMA expression on PET/CT demonstrated good diagnostic performance and may be a simple pragmatic integrated method that can be used.

PURPOSE/OBJECTIVE:Both MRI and PSMA PET/CT are often utilized for staging of intermediate-risk (IR) and high-risk (HR) prostate cancer (PCa). Recent studies found that PSMA PET/CT was superior to MRI in correctly identifying final pathological tumor stage, dominant nodule, extraprostatic extension (EPE), and small areas of clinically significant PCa. We sought to determine if PSMA PET/CT was superior to MRI in both locoregional staging of PCa and potential focal therapy planning. METHODS:We retrospectively analyzed our prospectively collected, IRB-approved database of all patients who underwent prostatectomy at one institution between 10/1/2019-2/29/2024. Patients were excluded if they did not pre-operatively undergo both MRI and PSMA PET/CT. 2 × 2 tables were used to compare each modality to the "gold standard" of prostatectomy specimen in both the proper detection of laterality and presence of EPE. Sensitivities and specificities were compared using a chi-squared test. HR v. IR groups were compared using a Wilcoxon rank sum test for continuous variables and Fisher's exact test for categorical variables. Results were considered significant at p < 0.05. RESULTS:580 patients underwent prostatectomy within the specified timeframe. 78 patients met inclusion criteria. MRI was more sensitive in the detection of EPE than PSMA PET/CT (23.5% v. 7.8%, p = 0.0294). MRI and PSMA PET/CT were similar in the specificity of EPE detection. In the identification of laterality, MRI was more specific (86.7% v. 56.7%, p = 0.0099), while sensitivities were similar between the modalities. CONCLUSIONS:MRI was superior to PSMA PET/CT in the proper detection of both EPE and laterality in patients with IR and HR PCa.

Endometriosis is a common disease, affecting approximately 10% of women of reproductive age. Several intersecting guidelines and consensus statements provide information on imaging diagnosis and surveillance strategies for endometriomas. SRU consensus panel recommendations provide information on initial detection of endometriosis on routine pelvic imaging. Revised American Society of Reproductive Medicine (rASRM) classification, the #ENZIAN classification, and the deep pelvic endometriosis index (dPEI) aim to assess the overall extent of disease and assist in presurgical planning. The Ovarian-Adnexal Reporting and Data System (O-RADS) aims to risk stratify lesions evaluated with US or MR based on their imaging morphology, from typical benign lesions to atypical presentations and malignant transformation. Emerging data shows increased risk of ovarian cancer in patients with endometriosis, especially following menopause and in those patients with long standing endometriosis. (Chen et al. in Front Oncol. 14:1329133, 2024;Streuli et al. in Climacteric. 20:138-143, 2017;Secosan et al. in Diagnostics (Basel). 10:134, 2020;Inceboz in Womens Health (Lond Engl). 11:711-715, 2015;Cassani et al. in Maturitas. 190, 2024;Gemmell et al. in Hum Reprod Update. 23:481-500, 2017;Giannella et al. in Cancers (Basel). 13:4026, 2021;) Current O-RADS guidelines mandate follow-up of endometriomas up to 2 years with further follow-up based on clinical factors. No consensus guidelines exist for imaging surveillance of patients with deep endometriosis from a malignancy standpoint. This review explores the imaging appearance of endometriomas, imaging features of malignant transformation, surveillance strategies and gaps in current literature, and attempts to better understand the risk of malignancy and to encourage further research for long-term imaging surveillance of endometriosis patients.

OBJECTIVES/OBJECTIVE:Prostate-specific membrane antigen (PSMA)-PET/CT has become integral to management of prostate cancer; however, PSMA-avid rib lesions pose a diagnostic challenge. This study investigated clinicopathological and imaging findings that predict metastatic etiology of PSMA-avid rib lesions. MATERIALS AND METHODS/METHODS:), miPSMA score), CT features (sclerotic, lucent, fracture, no correlate), other sites of metastases, and primary tumor findings. A composite reference standard for rib lesion etiology (metastatic vs non-metastatic) based on histopathology, serial imaging, and clinical assessment was used. RESULTS:, miPSMA), more commonly involved multiple ribs, and were more often sclerotic (p < 0.01); lucency/fractures were only seen in benign lesions. CONCLUSION/CONCLUSIONS:Several imaging and clinicopathological factors differed between PSMA-avid metastatic and benign lesions. Isolated rib lesions without other sites of metastasis are almost always benign. Careful assessment of CT features can help diagnose benign lesions. KEY POINTS/CONCLUSIONS:Question While prostate-specific membrane antigen (PSMA)-PET/CT has become integral to the management of prostate cancer, PSMA-avid rib lesions pose a diagnostic challenge. Findings Approximately a quarter of patients who had PSMA-avid rib lesions were metastatic. However, only 2.1% of them had isolated rib metastasis (without PSMA-avid metastases elsewhere). Clinical relevance Isolated PSMA-avid rib lesions are almost always benign when there is no evidence of metastatic disease elsewhere. Scrutinizing CT features can help diagnose benign PSMA-avid lesions with greater certainty.

BACKGROUND:MRI plays a critical role in prostate cancer (PCa) detection and management. Bi-parametric MRI (bpMRI) offers a faster, contrast-free alternative to multi-parametric MRI (mpMRI). Routine use of mpMRI for all patients may not be necessary, and a tailored imaging approach (bpMRI or mpMRI) based on individual risk might optimize resource utilization. PURPOSE/OBJECTIVE:To develop and evaluate a deep learning (DL) model for classifying clinically significant PCa (csPCa) using bpMRI and to assess its potential for optimizing MRI protocol selection by recommending the additional sequences of mpMRI only when beneficial. STUDY TYPE/METHODS:Retrospective and prospective. POPULATION/METHODS:The DL model was trained and validated on 26,129 prostate MRI studies. A retrospective cohort of 151 patients (mean age 65 ± 8) with ground-truth verification from biopsy, prostatectomy, or long-term follow-up, alongside a prospective cohort of 142 treatment-naïve patients (mean age 65 ± 9) undergoing bpMRI, was evaluated. FIELD STRENGTH/SEQUENCE/UNASSIGNED:3 T, Turbo-spin echo T2-weighted imaging (T2WI) and single shot EPI diffusion-weighted imaging (DWI). ASSESSMENT/RESULTS:The DL model, based on a 3D ResNet-50 architecture, classified csPCa using PI-RADS ≥ 3 and Gleason ≥ 7 as outcome measures. The model was evaluated on a prospective cohort labeled by consensus of three radiologists and a retrospective cohort with ground truth verification based on biopsy or long-term follow-up. Real-time inference was tested on an automated MRI workflow, providing classification results directly at the scanner. STATISTICAL TESTS/METHODS:AUROC with 95% confidence intervals (CI) was used to evaluate model performance. RESULTS:In the prospective cohort, the model achieved an AUC of 0.83 (95% CI: 0.77-0.89) for PI-RADS ≥ 3 classification, with 93% sensitivity and 54% specificity. In the retrospective cohort, the model achieved an AUC of 0.86 (95% CI: 0.80-0.91) for Gleason ≥ 7 classification, with 93% sensitivity and 62% specificity. Real-time implementation demonstrated a processing latency of 14-16 s for protocol recommendations. DATA CONCLUSION/CONCLUSIONS:The proposed DL model identifies csPCa using bpMRI and integrates it into clinical workflows. EVIDENCE LEVEL/METHODS:1. TECHNICAL EFFICACY/UNASSIGNED:Stage 2.

OBJECTIVES/OBJECTIVE:This study aims to evaluate the diagnostic accuracy of an open-source deep learning (DL) model for detecting clinically significant prostate cancer (csPCa) in biparametric MRI (bpMRI). It also aims to outline the necessary components of the model that facilitate effective sharing and external evaluation of PCa detection models. MATERIALS AND METHODS/METHODS:This retrospective diagnostic accuracy study evaluated a publicly available DL model trained to detect PCa on bpMRI. External validation was performed on bpMRI exams from 151 biologically male patients (mean age, 65 ± 8 years). The model's performance was evaluated using patient-level classification of PCa with both radiologist interpretation and histopathology serving as the ground truth. The model processed bpMRI inputs to generate lesion probability maps. Performance was assessed using the area under the receiver operating characteristic curve (AUC) for PI-RADS ≥ 3, PI-RADS ≥ 4, and csPCa (defined as Gleason ≥ 7) at an exam level. RESULTS:The model achieved AUCs of 0.86 (95% CI: 0.80-0.92) and 0.91 (95% CI: 0.85-0.96) for predicting PI-RADS ≥ 3 and ≥ 4 exams, respectively, and 0.78 (95% CI: 0.71-0.86) for csPCa. Sensitivity and specificity for csPCa were 0.87 and 0.53, respectively. Fleiss' kappa for inter-reader agreement was 0.51. CONCLUSION/CONCLUSIONS:The open-source DL model offers high sensitivity to clinically significant prostate cancer. The study underscores the importance of sharing model code and weights to enable effective external validation and further research. KEY POINTS/CONCLUSIONS:Question Inter-reader variability hinders the consistent and accurate detection of clinically significant prostate cancer in MRI. Findings An open-source deep learning model demonstrated reproducible diagnostic accuracy, achieving AUCs of 0.86 for PI-RADS ≥ 3 and 0.78 for CsPCa lesions. Clinical relevance The model's high sensitivity for MRI-positive lesions (PI-RADS ≥ 3) may provide support for radiologists. Its open-source deployment facilitates further development and evaluation across diverse clinical settings, maximizing its potential utility.

OBJECTIVES/OBJECTIVE:An increasing number of patients with prostate cancer (PCa) undergo assessment with magnetic resonance imaging (MRI) and prostate-specific membrane antigen positron emission tomography/computed tomography (PSMA-PET/CT). This offers comprehensive multimodality staging but can lead to discrepancies. The objective was to assess the rates and types of discordance between MRI and PSMA-PET/CT for primary PCa assessment. MATERIALS AND METHODS/METHODS:Consecutive men diagnosed with intermediate and high-risk PCa who underwent MRI and PSMA-PET/CT in 2021-2023 were retrospectively included. MRI and PSMA-PET/CT were interpreted using PI-RADS v2.1 and PRIMARY scores. Discordances between the two imaging modalities were categorized as "minor" (larger or additional lesion seen on one modality) or "major" (positive on only one modality or different index lesions between MRI and PSMA-PET/CT) and reconciled using radical prostatectomy or biopsy specimens. RESULTS:Three hundred and nine men (median age 69 years, interquartile range (IQR) 64-75) were included. Most had Gleason Grade Group ≥ 3 PCa (70.9% (219/309)). Median PSA was 9.0 ng/mL (IQR 5.6-13.6). MRI and PSMA-PET/CT were concordant in 157/309 (50.8%) and discordant in 152/309 (49.1%) patients; with 39/152 (25.7%) major and 113/152 (74.3%) minor discordances. Of 27 patients with lesions only seen on MRI, 85.2% (23/27) were clinically significant PCa (csPCa). Of 23 patients with lesions only seen on PSMA-PET/CT, 78.3% (18/23) were csPCa. Altogether, lesions seen on only one modality were csPCa in 80.0% (36/45). CONCLUSION/CONCLUSIONS:MRI and PSMA-PET/CT were discordant in half of patients for primary PCa evaluation, with major discrepancies seen in roughly one out of eight patients. KEY POINTS/CONCLUSIONS:Question While both MRI and PSMA-PET/CT can be used for primary tumor assessment, the discordances between them are not well established. Findings MRI and PSMA-PET/CT were discordant in about half of the patients. Most prostate lesions seen on only one modality were significant cancer. Clinical relevance MRI and PSMA-PET/CT are often discordant for assessing the primary prostate tumor. Using both modalities for primary prostate tumor evaluation can provide complementary information that may substantially impact treatment planning.

OBJECTIVES/OBJECTIVE:Despite its high negative predictive value (NPV) for clinically significant prostate cancer (csPCa), MRI suffers from a substantial number of false positives, especially for intermediate-risk cases. In this work, we determine whether a deep learning model trained with PI-RADS-guided representation learning can disambiguate the PI-RADS 3 classification, detect csPCa from bi-parametric prostate MR images, and avoid unnecessary benign biopsies. MATERIALS AND METHODS/METHODS:This study included 28,263 MR examinations and radiology reports from 21,938 men imaged for known or suspected prostate cancer between 2015 and 2023 at our institution (21 imaging locations with 34 readers), with 6352 subsequent biopsies. We trained a deep learning model, a representation learner (RL), to learn how radiologists interpret conventionally acquired T2-weighted and diffusion-weighted MR images, using exams in which the radiologists are confident in their risk assessments (PI-RADS 1 and 2 for the absence of csPCa vs. PI-RADS 4 and 5 for the presence of csPCa, n=21,465). We then trained biopsy-decision models to detect csPCa (Gleason score ≥7) using these learned image representations, and compared them to the performance of radiologists, and of models trained on other clinical variables (age, prostate volume, PSA, and PSA density) for treatment-naïve test cohorts consisting of only PI-RADS 3 (n=253, csPCa=103) and all PI-RADS (n=531, csPCa=300) cases. RESULTS:On the 2 test cohorts (PI-RADS-3-only, all-PI-RADS), RL-based biopsy-decision models consistently yielded higher AUCs in detecting csPCa (AUC=0.73 [0.66, 0.79], 0.88 [0.85, 0.91]) compared with radiologists (equivocal, AUC=0.79 [0.75, 0.83]) and the clinical model (AUCs=0.69 [0.62, 0.75], 0.78 [0.74, 0.82]). In the PIRADS-3-only cohort, all of whom would be biopsied using our institution's standard of care, the RL decision model avoided 41% (62/150) of benign biopsies compared with the clinical model (26%, P<0.001), and improved biopsy yield by 10% compared with the PI-RADS ≥3 decision strategy (0.50 vs. 0.40). Furthermore, on the all-PI-RADS cohort, RL decision model avoided 27% of additional benign biopsies (138/231) compared to radiologists (33%, P<0.001) with comparable sensitivity (93% vs. 92%), higher NPV (0.87 vs. 0.77), and biopsy yield (0.75 vs. 0.64). The combination of clinical and RL decision models further avoided benign biopsies (46% in PI-RADS-3-only and 62% in all-PI-RADS) while improving NPV (0.82, 0.88) and biopsy yields (0.52, 0.76) across the 2 test cohorts. CONCLUSIONS:Our PI-RADS-guided deep learning RL model learns summary representations from bi-parametric prostate MR images that can provide additional information to disambiguate intermediate-risk PI-RADS 3 assessments. The resulting RL-based biopsy decision models also outperformed radiologists in avoiding benign biopsies while maintaining comparable sensitivity to csPCa for the all-PI-RADS cohort. Such AI models can easily be integrated into clinical practice to supplement radiologists' reads in general and improve biopsy yield for any equivocal decisions.