Faculty Bibliography

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.

Post-radiotherapy erectile dysfunction (ED) can significantly impact the quality of life of patients with prostate cancer (PCa). Critical anatomical structures, such as the neurovascular bundle (NVB), internal pudendal arteries (IPA), penile bulb, and corporal tissues track in close proximity to the prostate, making them susceptible to radiation-related damage. This study aimed to evaluate the anatomical patterns of these structures and their relationship with the prostate, and to provide comprehensive illustrative examples on MRI. Consecutive patients with PCa who underwent MRI-linear accelerator (LINAC)-based stereotactic body radiotherapy (SBRT) in January-December 2024 were included. NVB patterns were classified into 3 categories: (1) "classical" with discrete NVB elements, (2) "adherent", dispersed and adherent to prostatic capsule, and (3) "absent". The smallest distance between the IPA and the prostate capsule and membranous urethral length (MUL), serving as a surrogate for distance between corporal tissue and prostatic apex, were also measured. These MRI findings were compared between prostate volumes >40 and <40 ml and between MRI/pathological features of the dominant intraprostatic lesion. A total of 160 men (median age 70 years, interquartile range [IQR] 64-76) were included. The most common NVB pattern was "classic" (80.0-85.0%), followed by the "adherent" NVB pattern (13.8-18.1%). The median smallest distance between the IPA and prostate was 2.3 cm (IQR 1.8-2.8 cm), with 3.1-3.8% less than 1.0 cm. The median MUL was 1.5 cm (IQR, 1.2-1.8 cm), with 2.5% of patients less than 1.0 cm. No significant association was found between these MRI features and prostate volume or other variables (p = 0.09-0.99). In conclusion, most PCa patients demonstrated favorable anatomy for potential dose sparing of critical structures. Comprehensive MRI illustrations are provided to help radiation oncologists recognize the location, trajectory, and relationship of these structures, facilitating their contouring and ultimately aiding in achieving meaningful dose reductions to these erectile function structures.

Endometriosis is a common condition primarily impacting women of childbearing age. Despite increasing awareness that endometriosis can be diagnosed non-invasively with the correct imaging techniques, there exists a significant delay in diagnosis, to the tune of 5-10 years. This gap can be narrowed by understanding that this is a disease that lends itself to pattern recognition, and learning to recognize the characteristic patterns on any imaging study will allow earlier diagnosis and prevent long-term complications that can occur with progressive, untreated endometriosis. The disease is often multifocal and thus can present with a wide array of nonspecific symptoms. When clinical findings do not suggest endometriosis, patients often undergo non-targeted imaging, such as chest, abdominal, or pelvic computed tomography (CT); Magnetic Resonance imaging (MRI) studies optimized for neurologic or musculoskeletal indications; or ultrasound (US) exams performed for palpable masses or nonspecific abdominal pain. Familiarity with endometriosis's characteristic patterns across organ systems and how it can masquerade as other diseases helps radiologists broaden their differential to include endometriosis, even on studies not originally aimed at its detection. This review article will describe those imaging findings of endometriosis affecting various organ systems that mimic other pathologies and will enable the reader to pause and question whether endometriosis should be included in the differential.

BACKGROUND:Minimally invasive focal therapy of low- to intermediate-risk prostate cancer is becoming more common and has demonstrated lower morbidity compared to other treatments. Multiparametric prostate magnetic resonance imaging (mpMRI) has the potential to be an effective posttreatment evaluation method for residual/recurrent neoplasm. OBJECTIVE:This study aimed to evaluate the ability of mpMRI to detect residual/recurrent neoplasm after focal therapy treatment of prostate cancer using a 3-point Likert scale. METHODS:This retrospective study included patients who underwent focal therapy utilizing cryoablation, high-frequency ultrasound, and radiofrequency ablation for low- to intermediate-risk prostate cancer with baseline mpMRI and biopsy and a 6- to 12-month follow-up mpMRI and biopsy. Three abdominal fellowship-trained readers were asked to evaluate the follow-up mpMRI utilizing a 3-point Likert scale based on the level of suspicion as "nonviable," "equivocal," or "viable." Diagnostic statistics and Light's κ for interreader variability were calculated. RESULTS:A total of 142 patients were included (mean age, 65 ± 7 years). When considering "equivocal" or "viable" as positive, the overall sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and area under the receiver operating characteristic curve (AUC) for detecting recurrent grade group (GG) 2 or greater disease for Reader 1 were 0.47, 0.83, 0.24, 0.93, and 0.65; for Reader 2, 0.73, 0.75, 0.26, 0.96, and 0.74; and for Reader 3, 0.73, 0.57, 0.17, 0.95, and 0.65. When considering "viable" as positive, the overall sensitivity, specificity, PPV, NPV, and AUC for Reader 1 were 0.47, 0.92, 0.41, 0.94, and 0.69; for Reader 2, 0.33, 0.97, 0.56, 0.93, and 0.65; and for Reader 3, 0.53, 0.84, 0.29, 0.94, and 0.69. κ was 0.39. CONCLUSIONS:This study suggests that DCE and DWI are the most important sequences in mpMRI and demonstrates the efficacy of utilizing a 3-point grading system in detecting and diagnosing prostate cancer after focal therapy. CLINICAL IMPACT/CONCLUSIONS:mpMRI can be used to monitor for residual/recurrent disease after focal therapy.

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.

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.

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.