Deep Learning-Based Interpretable AI for Prostate T2W MRI Quality Evaluation

RATIONALE AND OBJECTIVES

Prostate MRI quality is essential in guiding prostate biopsies. However, assessment of MRI quality is subjective with variation. Quality degradation sources exert varying impacts based on the sequence under consideration, such as T2W versus DWI. As a result, employing sequence-specific techniques for quality assessment could yield more advantageous outcomes. This study aims to develop an AI tool that offers a more consistent evaluation of T2W prostate MRI quality, efficiently identifying suboptimal scans while minimizing user bias.

MATERIALS AND METHODS

This retrospective study included 1046 patients from three cohorts (ProstateX [n = 347], All-comer in-house [n = 602], enriched bad-quality MRI in-house [n = 97]) scanned between January 2011 and May 2022. An expert reader assigned T2W MRIs a quality score. A train-validation-test split of 70:15:15 was applied, ensuring equal distribution of MRI scanners and protocols across all partitions. T2W quality AI classification model was based on 3D DenseNet121 architecture using MONAI framework. In addition to multiclassification, binary classification was utilized (Classes 0/1 vs. 2). A score of 0 was given to scans considered non-diagnostic or unusable, a score of 1 was given to those with acceptable diagnostic quality with some usability but with some quality distortions present, and a score of 2 was given to those considered optimal diagnostic quality and usability. Partial occlusion sensitivity maps were generated for anatomical correlation. Three body radiologists assessed reproducibility within a subgroup of 60 test cases using weighted Cohen Kappa.

RESULTS

The best validation multiclass accuracy of 77.1% (121/157) was achieved during training. In the test dataset, multiclassification accuracy was 73.9% (116/157), whereas binary accuracy was 84.7% (133/157). Sub-class sensitivity for binary quality distortion classification for class 0 was 100% (18/18), and sub-class specificity for T2W classification of absence/minimal quality distortions for class 2 was 90.5% (95/105). All three readers showed moderate to substantial agreement with ground truth (R1-R3 κ = 0.588, κ = 0.649, κ = 0.487, respectively), moderate to substantial agreement with each other (R1-R2 κ = 0.599, R1-R3 κ = 0.612, R2-R3 κ = 0.685), fair to moderate agreement with AI (R1-R3 κ = 0.445, κ = 0.410, κ = 0.292, respectively). AI showed substantial agreement with ground truth (κ = 0.704). 3D quality heatmap evaluation revealed that the most critical non-diagnostic quality imaging features from an AI perspective related to obscuration of the rectoprostatic space (94.4%, 17/18).

CONCLUSION

The 3D AI model can assess T2W prostate MRI quality with moderate accuracy and translate whole sequence-level classification labels into 3D voxel-level quality heatmaps for interpretation. Image quality has a significant downstream impact on ruling out clinically significant cancers. AI may be able to help with reproducible identification of MRI sequences requiring re-acquisition with explainability.

Automated prostate gland segmentation in challenging clinical cases: comparison of three artificial intelligence methods

OBJECTIVE

Automated methods for prostate segmentation on MRI are typically developed under ideal scanning and anatomical conditions. This study evaluates three different prostate segmentation AI algorithms in a challenging population of patients with prior treatments, variable anatomic characteristics, complex clinical history, or atypical MRI acquisition parameters.

MATERIALS AND METHODS

A single institution retrospective database was queried for the following conditions at prostate MRI: prior prostate-specific oncologic treatment, transurethral resection of the prostate (TURP), abdominal perineal resection (APR), hip prosthesis (HP), diversity of prostate volumes (large ≥ 150 cc, small ≤ 25 cc), whole gland tumor burden, magnet strength, noted poor quality, and various scanners (outside/vendors). Final inclusion criteria required availability of axial T2-weighted (T2W) sequence and corresponding prostate organ segmentation from an expert radiologist. Three previously developed algorithms were evaluated: (1) deep learning (DL)-based model, (2) commercially available shape-based model, and (3) federated DL-based model. Dice Similarity Coefficient (DSC) was calculated compared to expert. DSC by model and scan factors were evaluated with Wilcox signed-rank test and linear mixed effects (LMER) model.

RESULTS

683 scans (651 patients) met inclusion criteria (mean prostate volume 60.1 cc [9.05-329 cc]). Overall DSC scores for models 1, 2, and 3 were 0.916 (0.707-0.971), 0.873 (0-0.997), and 0.894 (0.025-0.961), respectively, with DL-based models demonstrating significantly higher performance (p < 0.01). In sub-group analysis by factors, Model 1 outperformed Model 2 (all p < 0.05) and Model 3 (all p < 0.001). Performance of all models was negatively impacted by prostate volume and poor signal quality (p < 0.01). Shape-based factors influenced DL models (p < 0.001) while signal factors influenced all (p < 0.001).

CONCLUSION

Factors affecting anatomical and signal conditions of the prostate gland can adversely impact both DL and non-deep learning-based segmentation models.

Deep Learning-Based Detection and Classification of Bone Lesions on Staging Computed Tomography in Prostate Cancer: A Development Study

RATIONALE AND OBJECTIVES

Efficiently detecting and characterizing metastatic bone lesions on staging CT is crucial for prostate cancer (PCa) care. However, it demands significant expert time and additional imaging such as PET/CT. We aimed to develop an ensemble of two automated deep learning AI models for 1) bone lesion detection and segmentation and 2) benign vs. metastatic lesion classification on staging CTs and to compare its performance with radiologists.

MATERIALS AND METHODS

This retrospective study developed two AI models using 297 staging CT scans (81 metastatic) with 4601 benign and 1911 metastatic lesions in PCa patients. Metastases were validated by follow-up scans, bone biopsy, or PET/CT. Segmentation AI (3DAISeg) was developed using the lesion contours delineated by a radiologist. 3DAISeg performance was evaluated with the Dice similarity coefficient, and classification AI (3DAIClass) performance on AI and radiologist contours was assessed with F1-score and accuracy. Training/validation/testing data partitions of 70:15:15 were used. A multi-reader study was performed with two junior and two senior radiologists within a subset of the testing dataset (n = 36).

RESULTS

In 45 unseen staging CT scans (12 metastatic PCa) with 669 benign and 364 metastatic lesions, 3DAISeg detected 73.1% of metastatic (266/364) and 72.4% of benign lesions (484/669). Each scan averaged 12 extra segmentations (range: 1-31). All metastatic scans had at least one detected metastatic lesion, achieving a 100% patient-level detection. The mean Dice score for 3DAISeg was 0.53 (median: 0.59, range: 0-0.87). The F1 for 3DAIClass was 94.8% (radiologist contours) and 92.4% (3DAISeg contours), with a median false positive of 0 (range: 0-3). Using radiologist contours, 3DAIClass had PPV and NPV rates comparable to junior and senior radiologists: PPV (semi-automated approach AI 40.0% vs. Juniors 32.0% vs. Seniors 50.0%) and NPV (AI 96.2% vs. Juniors 95.7% vs. Seniors 91.9%). When using 3DAISeg, 3DAIClass mimicked junior radiologists in PPV (pure-AI 20.0% vs. Juniors 32.0% vs. Seniors 50.0%) but surpassed seniors in NPV (pure-AI 93.8% vs. Juniors 95.7% vs. Seniors 91.9%).

CONCLUSION

Our lesion detection and classification AI model performs on par with junior and senior radiologists in discerning benign and metastatic lesions on staging CTs obtained for PCa.

PI-RADS Version 2.0 Versus Version 2.1: Comparison of Prostate Cancer Gleason Grade Upgrade and Downgrade Rates From MRI-Targeted Biopsy to Radical Prostatectomy

BACKGROUND. Precise risk stratification through MRI/ultrasound (US) fusion-guided targeted biopsy (TBx) can guide optimal prostate cancer (PCa) management. OBJECTIVE. The purpose of this study was to compare PI-RADS version 2.0 (v2.0) and PI-RADS version 2.1 (v2.1) in terms of the rates of International Society of Urological Pathology (ISUP) grade group (GG) upgrade and downgrade from TBx to radical prostatectomy (RP). METHODS. This study entailed a retrospective post hoc analysis of patients who underwent 3-T prostate MRI at a single institution from May 2015 to March 2023 as part of three prospective clinical trials. Trial participants who underwent MRI followed by MRI/US fusion-guided TBx and RP within a 1-year interval were identified. A single genitourinary radiologist performed clinical interpretations of the MRI examinations using PI-RADS v2.0 from May 2015 to March 2019 and PI-RADS v2.1 from April 2019 to March 2023. Upgrade and downgrade rates from TBx to RP were compared using chi-square tests. Clinically significant cancer was defined as ISUP GG2 or greater. RESULTS. The final analysis included 308 patients (median age, 65 years; median PSA density, 0.16 ng/mL2). The v2.0 group (n = 177) and v2.1 group (n = 131) showed no significant difference in terms of upgrade rate (29% vs 22%, respectively; p = .15), downgrade rate (19% vs 21%, p = .76), clinically significant upgrade rate (14% vs 10%, p = .27), or clinically significant downgrade rate (1% vs 1%, p > .99). The upgrade rate and downgrade rate were also not significantly different between the v2.0 and v2.1 groups when stratifying by index lesion PI-RADS category or index lesion zone, as well as when assessed only in patients without a prior PCa diagnosis (all p > .01). Among patients with GG2 or GG3 at RP (n = 121 for v2.0; n = 103 for v2.1), the concordance rate between TBx and RP was not significantly different between the v2.0 and v2.1 groups (53% vs 57%, p = .51). CONCLUSION. Upgrade and downgrade rates from TBx to RP were not significantly different between patients whose MRI examinations were clinically interpreted using v2.0 or v2.1. CLINICAL IMPACT. Implementation of the most recent PI-RADS update did not improve the incongruence in PCa grade assessment between TBx and surgery.

Quality of T2-weighted MRI re-acquisition versus deep learning GAN image reconstruction: A multi-reader study

PURPOSE

To evaluate CycleGAN's ability to enhance T2-weighted image (T2WI) quality.

METHOD

A CycleGAN algorithm was used to enhance T2WI quality. 96 patients (192 scans) were identified from patients who underwent multiple axial T2WI due to poor quality on the first attempt (RAD1) and improved quality on re-acquisition (RAD2). CycleGAN algorithm gave DL classifier scores (0-1) for quality quantification and produced enhanced versions of QI1 and QI2 from RAD1 and RAD2, respectively. A subset (n = 20 patients) was selected for a blinded, multi-reader study, where four radiologists rated T2WI on a scale of 1-4 for quality. The multi-reader study presented readers with 60 image pairs (RAD1 vs RAD2, RAD1 vs QI1, and RAD2 vs QI2), allowing for selecting sequence preferences and quantifying the quality changes.

RESULTS

The DL classifier correctly discerned 71.9 % of quality classes, with 90.6 % (96/106) as poor quality and 48.8 % (42/86) as diagnostic in original sequences (RAD1, RAD2). CycleGAN images (QI1, QI2) demonstrated quantitative improvements, with consistently higher DL classifier scores than original scans (p < 0.001). In the multi-reader analysis, CycleGAN demonstrated no qualitative improvements, with diminished overall quality and motion in QI2 in most patients compared to RAD2, with noise levels remaining similar (8/20). No readers preferred QI2 to RAD2 for diagnosis.

CONCLUSION

Despite quantitative enhancements with CycleGAN, there was no qualitative boost in T2WI diagnostic quality, noise, or motion. Expert radiologists didn't favor CycleGAN images over standard scans, highlighting the divide between quantitative and qualitative metrics.

Comparison of MRI-Based Staging and Pathologic Staging for Predicting Biochemical Recurrence of Prostate Cancer After Radical Prostatectomy

BACKGROUND. Currently most clinical models for predicting biochemical recurrence (BCR) of prostate cancer (PCa) after radical prostatectomy (RP) incorporate staging information from RP specimens, creating a gap in preoperative risk assessment. OBJECTIVE. The purpose of our study was to compare the utility of presurgical staging information from MRI and postsurgical staging information from RP pathology in predicting BCR in patients with PCa. METHODS. This retrospective study included 604 patients (median age, 60 years) with PCa who underwent prostate MRI before RP from June 2007 to December 2018. A single genitourinary radiologist assessed MRI examinations for extraprostatic extension (EPE) and seminal vesicle invasion (SVI) during clinical interpretations. The utility of EPE and SVI on MRI and RP pathology for BCR prediction was assessed through Kaplan-Meier and Cox proportional hazards analyses. Established clinical BCR prediction models, including the University of California San Francisco Cancer of the Prostate Risk Assessment (UCSF-CAPRA) model and the Cancer of the Prostate Risk Assessment Postsurgical (CAPRA-S) model, were evaluated in a subset of 374 patients with available Gleason grade groups from biopsy and RP pathology; two CAPRA-MRI models (CAPRA-S model with modifications to replace RP pathologic staging features with MRI staging features) were also assessed. RESULTS. Univariable predictors of BCR included EPE on MRI (HR = 3.6), SVI on MRI (HR = 4.4), EPE on RP pathology (HR = 5.0), and SVI on RP pathology (HR = 4.6) (all p < .001). Three-year BCR-free survival (RFS) rates for patients without versus with EPE were 84% versus 59% for MRI and 89% versus 58% for RP pathology, and 3-year RFS rates for patients without versus with SVI were 82% versus 50% for MRI and 83% versus 54% for RP histology (all p < .001). For patients with T3 disease on RP pathology, 3-year RFS rates were 67% and 41% for patients without and with T3 disease on MRI. AUCs of CAPRA models, including CAPRA-MRI models, ranged from 0.743 to 0.778. AUCs were not significantly different between CAPRA-S and CAPRA-MRI models (p > .05). RFS rates were significantly different between low- and intermediate-risk groups for only CAPRA-MRI models (80% vs 51% and 74% vs 44%; both p < .001). CONCLUSION. Presurgical MRI-based staging features perform comparably to postsurgical pathologic staging features for predicting BCR. CLINICAL IMPACT. MRI staging can preoperatively identify patients at high BCR risk, helping to inform early clinical decision-making. TRIAL REGISTRATION. ClinicalTrials.gov NCT00026884 and NCT02594202.

Is prostatic adenocarcinoma with cribriform architecture more difficult to detect on prostate MRI?

BACKGROUND

Cribriform (CBFM) pattern on prostate biopsy has been implicated as a predictor for high-risk features, potentially leading to adverse outcomes after definitive treatment. This study aims to investigate whether the CBFM pattern containing prostate cancers (PCa) were associated with false negative magnetic resonance imaging (MRI) and determine the association between MRI and histopathological disease burden.

METHODS

Patients who underwent multiparametric magnetic resonance imaging (mpMRI), combined 12-core transrectal ultrasound (TRUS) guided systematic (SB) and MRI/US fusion-guided biopsy were retrospectively queried for the presence of CBFM pattern at biopsy. Biopsy cores and lesions were categorized as follows: C0 = benign, C1 = PCa with no CBFM pattern, C2 = PCa with CBFM pattern. Correlation between cancer core length (CCL) and measured MRI lesion dimension were assessed using a modified Pearson correlation test for clustered data. Differences between the biopsy core groups were assessed with the Wilcoxon-signed rank test with clustering.

RESULTS

Between 2015 and 2022, a total of 131 consecutive patients with CBFM pattern on prostate biopsy and pre-biopsy mpMRI were included. Clinical feature analysis included 1572 systematic biopsy cores (1149 C0, 272 C1, 151 C2) and 736 MRI-targeted biopsy cores (253 C0, 272 C1, 211 C2). Of the 131 patients with confirmed CBFM pathology, targeted biopsy (TBx) alone identified CBFM in 76.3% (100/131) of patients and detected PCa in 97.7% (128/131) patients. SBx biopsy alone detected CBFM in 61.1% (80/131) of patients and PCa in 90.8% (119/131) patients. TBx and SBx had equivalent detection in patients with smaller prostates (p = 0.045). For both PCa lesion groups there was a positive and significant correlation between maximum MRI lesion dimension and CCL (C1 lesions: p < 0.01, C2 lesions: p < 0.001). There was a significant difference in CCL between C1 and C2 lesions for T2 scores of 3 and 5 (p ≤ 0.01, p ≤ 0.01, respectively) and PI-RADS 5 lesions (p ≤ 0.01), with C2 lesions having larger CCL, despite no significant difference in MRI lesion dimension.

CONCLUSIONS

The extent of disease for CBFM-containing tumors is difficult to capture on mpMRI. When comparing MRI lesions of similar dimensions and PIRADS scores, CBFM-containing tumors appear to have larger cancer yield on biopsy. Proper staging and planning of therapeutic interventions is reliant on accurate mpMRI estimation. Special considerations should be taken for patients with CBFM pattern on prostate biopsy.

Evaluation of a Deep Learning-based Algorithm for Post-Radiotherapy Prostate Cancer Local Recurrence Detection Using Biparametric MRI

OBJECTIVE

To evaluate a biparametric MRI (bpMRI)-based artificial intelligence (AI) model for the detection of local prostate cancer (PCa) recurrence in patients with radiotherapy history.

MATERIALS AND METHODS

This study included post-radiotherapy patients undergoing multiparametric MRI and subsequent MRI/US fusion-guided and/or systematic biopsy. Histopathology results were used as ground truth. The recurrent cancer detection sensitivity of a bpMRI-based AI model, which was developed on a large dataset to primarily identify lesions in treatment-naïve patients, was compared to a prospective radiologist assessment using the Wald test. Subanalysis was conducted on patients stratified by the treatment modality (external beam radiation treatment [EBRT] and brachytherapy) and the prostate volume quartiles.

RESULTS

Of the 62 patients included (median age = 70 years; median PSA = 3.51 ng/ml; median prostate volume = 27.55 ml), 56 recurrent PCa foci were identified within 46 patients. The AI model detected 40 lesions in 35 patients. The AI model performance was lower than the prospective radiology interpretation (Rad) on a patient-(AI: 76.1% vs. Rad: 91.3%, p = 0.02) and lesion-level (AI: 71.4% vs. Rad: 87.5%, p = 0.01). The mean number of false positives per patient was 0.35 (range: 0-2). The AI model performance was higher in EBRT group both on patient-level (EBRT: 81.5% [22/27] vs. brachytherapy: 68.4% [13/19]) and lesion-level (EBRT: 79.4% [27/34] vs. brachytherapy: 59.1% [13/22]). In patients with gland volumes >34 ml (n = 25), detection sensitivities were 100% (11/11) and 94.1% (16/17) on patient- and lesion-level, respectively.

CONCLUSION

The reported bpMRI-based AI model detected the majority of locally recurrent prostate cancer after radiotherapy. Further testing including external validation of this model is warranted prior to clinical implementation.

Deep Learning-Based T2-weighted MR Image Quality Assessment and Its Impact on Prostate Cancer Detection Rates

BACKGROUND

Image quality evaluation of prostate MRI is important for successful implementation of MRI into localized prostate cancer diagnosis.

PURPOSE

To examine the impact of image quality on prostate cancer detection using an in-house previously developed artificial intelligence (AI) algorithm.

STUDY TYPE

Retrospective.

SUBJECTS

615 consecutive patients (median age 67 [interquartile range [IQR]: 61-71] years) with elevated serum PSA (median PSA 6.6 [IQR: 4.6-9.8] ng/mL) prior to prostate biopsy.

FIELD STRENGTH/SEQUENCE

3.0T/T2-weighted turbo-spin-echo MRI, high b-value echo-planar diffusion-weighted imaging, and gradient recalled echo dynamic contrast-enhanced.

ASSESSMENTS

Scans were prospectively evaluated during clinical readout using PI-RADSv2.1 by one genitourinary radiologist with 17 years of experience. For each patient, T2-weighted images (T2WIs) were classified as high-quality or low-quality based on evaluation of both general distortions (eg, motion, distortion, noise, and aliasing) and perceptual distortions (eg, obscured delineation of prostatic capsule, prostatic zones, and excess rectal gas) by a previously developed in-house AI algorithm. Patients with PI-RADS category 1 underwent 12-core ultrasound-guided systematic biopsy while those with PI-RADS category 2-5 underwent combined systematic and targeted biopsies. Patient-level cancer detection rates (CDRs) were calculated for clinically significant prostate cancer (csPCa, International Society of Urological Pathology Grade Group ≥2) by each biopsy method and compared between high- and low-quality images in each PI-RADS category.

STATISTICAL TESTS

Fisher's exact test. Bootstrap 95% confidence intervals (CI). A P value <0.05 was considered statistically significant.

RESULTS

385 (63%) T2WIs were classified as high-quality and 230 (37%) as low-quality by AI. Targeted biopsy with high-quality T2WIs resulted in significantly higher clinically significant CDR than low-quality images for PI-RADS category 4 lesions (52% [95% CI: 43-61] vs. 32% [95% CI: 22-42]). For combined biopsy, there was no significant difference in patient-level CDRs for PI-RADS 4 between high- and low-quality T2WIs (56% [95% CI: 47-64] vs. 44% [95% CI: 34-55]; P = 0.09).

DATA CONCLUSION

Higher quality T2WIs were associated with better targeted biopsy clinically significant cancer detection performance for PI-RADS 4 lesions. Combined biopsy might be needed when T2WI is lower quality.

LEVEL OF EVIDENCE

2 TECHNICAL EFFICACY: Stage 1.

A Brief Review of Artificial Intelligence in Genitourinary Oncological Imaging

Genitourinary (GU) system is among the most commonly involved malignancy sites in the human body. Imaging plays a crucial role not only in diagnosis of cancer but also in disease management and its prognosis. However, interpretation of conventional imaging methods such as CT or MR imaging (MRI) usually demonstrates variability across different readers and institutions. Artificial intelligence (AI) has emerged as a promising technology that could improve the patient care by providing helpful input to human readers through lesion detection algorithms and lesion classification systems. Moreover, the robustness of these models may be valuable in automating time-consuming tasks such as organ and lesion segmentations. Herein, we review the current state of imaging and existing challenges in GU malignancies, particularly for cancers of prostate, kidney and bladder; and briefly summarize the recent AI-based solutions to these challenges.

Prospective Evaluation of PI-RADS Version 2.1 for Prostate Cancer Detection and Investigation of Multiparametric MRI-derived Markers

Background Data regarding the prospective performance of Prostate Imaging Reporting and Data System (PI-RADS) version 2.1 alone and in combination with quantitative MRI features for prostate cancer detection is limited. Purpose To assess lesion-based clinically significant prostate cancer (csPCa) rates in different PI-RADS version 2.1 categories and to identify MRI features that could improve csPCa detection. Materials and Methods This single-center prospective study included men with suspected or known prostate cancer who underwent multiparametric MRI and MRI/US-guided biopsy from April 2019 to December 2021. MRI scans were prospectively evaluated using PI-RADS version 2.1. Atypical transition zone (TZ) nodules were upgraded to category 3 if marked diffusion restriction was present. Lesions with an International Society of Urological Pathology (ISUP) grade of 2 or higher (range, 1-5) were considered csPCa. MRI features, including three-dimensional diameter, relative lesion volume (lesion volume divided by prostate volume), sphericity, and surface to volume ratio (SVR), were obtained from lesion contours delineated by the radiologist. Univariable and multivariable analyses were conducted at the lesion and participant levels to determine features associated with csPCa. Results In total, 454 men (median age, 67 years [IQR, 62-73 years]) with 838 lesions were included. The csPCa rates for lesions categorized as PI-RADS 1 (n = 3), 2 (n = 170), 3 (n = 197), 4 (n = 319), and 5 (n = 149) were 0%, 9%, 14%, 37%, and 77%, respectively. csPCa rates of PI-RADS 4 lesions were lower than PI-RADS 5 lesions (P < .001) but higher than PI-RADS 3 lesions (P < .001). Upgraded PI-RADS 3 TZ lesions were less likely to harbor csPCa compared with their nonupgraded counterparts (4% [one of 26] vs 20% [20 of 99], P = .02). Predictors of csPCa included relative lesion volume (odds ratio [OR], 1.6; P < .001), SVR (OR, 6.2; P = .02), and extraprostatic extension (EPE) scores of 2 (OR, 9.3; P < .001) and 3 (OR, 4.1; P = .02). Conclusion The rates of csPCa differed between consecutive PI-RADS categories of 3 and higher. MRI features, including lesion volume, shape, and EPE scores of 2 and 3, predicted csPCa. Upgrading of PI-RADS category 3 TZ lesions may result in unnecessary biopsies. ClinicalTrials.gov registration no. NCT03354416 © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Goh in this issue.

Prostate MRI and image Quality: It is time to take stock

Multiparametric magnetic resonance imaging (mpMRI) plays a vital role in prostate cancer diagnosis and management. With the increase in use of mpMRI, obtaining the best possible quality images has become a priority. The Prostate Imaging Reporting and Data System (PI-RADS) was introduced to standardize and optimize patient preparation, scanning techniques, and interpretation. However, the quality of the MRI sequences depends not only on the hardware/software and scanning parameters, but also on patient-related factors. Common patient-related factors include bowel peristalsis, rectal distension, and patient motion. There is currently no consensus regarding the best approaches to address these issues and improve the quality of mpMRI. New evidence has been accrued since the release of PI-RADS, and this review aims to explore the key strategies which aim to improve prostate MRI quality, such as imaging techniques, patient preparation methods, the new Prostate Imaging Quality (PI-QUAL) criteria, and artificial intelligence on prostate MRI quality.

Ipsilateral hemigland prostate biopsy may underestimate cancer burden in patients with unilateral mpMRI-visible lesions

PURPOSE

To evaluate the cancer detection rates of reduced-core biopsy schemes in patients with unilateral mpMRI-visible intraprostatic lesions and to analyze the contribution of systematic biopsy cores in clinically significant prostate cancer (csPCa) detection.

METHODS

212 patients with mpMRI-visible unilateral intraprostatic lesions undergoing MRI/TRUS fusion-guided targeted biopsy (TBx) and systematic biopsy (SBx) were included. Cancer detection rates of TBx + SBx, as determined by highest Gleason Grade Group (GG), were compared to 3 reduced-core biopsy schemes: TBx alone, TBx + ipsilateral systematic biopsy (IBx; MRI-positive hemigland), and TBx + contralateral systematic biopsy (CBx; MRI-negative hemigland). Patient-level and biopsy core-level data were analyzed using descriptive statistics with confidence intervals. Univariable and multivariable logistic regression analysis was conducted to identify predictors of csPCa (≥ GG2) detected in MRI-negative hemiglands at p < 0.05.

RESULTS

Overall, 43.4% (92/212) of patients had csPCa and 66.0% (140/212) of patients had any PCa detected by TBx + SBx. Of patients with csPCa, 81.5% had exclusively ipsilateral involvement (MRI-positive), 7.6% had only contralateral involvement (MRI-negative), and 10.9% had bilateral involvement. The csPCa detection rates of reduced-core biopsy schemes were 35.4% (75/212), 40.1% (85/212), and 39.6% (84/212) for TBx alone, TBx + IBx, and TBx + CBx, respectively, with detection sensitivities of 81.5%, 92.4%, and 91.3% compared to TBx + SBx.

CONCLUSION

Reduced-core prostate biopsy strategies confined to the ipsilateral hemigland underestimate csPCa burden by at least 8% in patients with unilateral mpMRI-visible intraprostatic lesions. The combined TBx + SBx strategy maximizes csPCa detection.

The Low Rate of Adherence to Checklist for Artificial Intelligence in Medical Imaging Criteria Among Published Prostate MRI Artificial Intelligence Algorithms

OBJECTIVE

To determine the rigor, generalizability, and reproducibility of published classification and detection artificial intelligence (AI) models for prostate cancer (PCa) on MRI using the Checklist for Artificial Intelligence in Medical Imaging (CLAIM) guidelines, a 42-item checklist that is considered a measure of best practice for presenting and reviewing medical imaging AI research.

MATERIALS AND METHODS

This review searched English literature for studies proposing PCa AI detection and classification models on MRI. Each study was evaluated with the CLAIM checklist. The additional outcomes for which data were sought included measures of AI model performance (eg, area under the curve [AUC], sensitivity, specificity, free-response operating characteristic curves), training and validation and testing group sample size, AI approach, detection versus classification AI, public data set utilization, MRI sequences used, and definition of gold standard for ground truth. The percentage of CLAIM checklist fulfillment was used to stratify studies into quartiles. Wilcoxon's rank-sum test was used for pair-wise comparisons.

RESULTS

In all, 75 studies were identified, and 53 studies qualified for analysis. The original CLAIM items that most studies did not fulfill includes item 12 (77% no): de-identification methods; item 13 (68% no): handling missing data; item 15 (47% no): rationale for choosing ground truth reference standard; item 18 (55% no): measurements of inter- and intrareader variability; item 31 (60% no): inclusion of validated interpretability maps; item 37 (92% no): inclusion of failure analysis to elucidate AI model weaknesses. An AUC score versus percentage CLAIM fulfillment quartile revealed a significant difference of the mean AUC scores between quartile 1 versus quartile 2 (0.78 versus 0.86, P = .034) and quartile 1 versus quartile 4 (0.78 versus 0.89, P = .003) scores. Based on additional information and outcome metrics gathered in this study, additional measures of best practice are defined. These new items include disclosure of public dataset usage, ground truth definition in comparison to other referenced works in the defined task, and sample size power calculation.

CONCLUSION

A large proportion of AI studies do not fulfill key items in CLAIM guidelines within their methods and results sections. The percentage of CLAIM checklist fulfillment is weakly associated with improved AI model performance. Additions or supplementations to CLAIM are recommended to improve publishing standards and aid reviewers in determining study rigor.

Development of a 3D CNN-based AI Model for Automated Segmentation of the Prostatic Urethra

RATIONALE AND OBJECTIVE

The combined use of prostate cancer radiotherapy and MRI planning is increasingly being used in the treatment of clinically significant prostate cancers. The radiotherapy dosage quantity is limited by toxicity in organs with de-novo genitourinary toxicity occurrence remaining unperturbed. Estimation of the urethral radiation dose via anatomical contouring may improve our understanding of genitourinary toxicity and its related symptoms. Yet, urethral delineation remains an expert-dependent and time-consuming procedure. In this study, we aim to develop a fully automated segmentation tool for the prostatic urethra.

MATERIALS AND METHODS

This study incorporated 939 patients' T2-weighted MRI scans (train/validation/test/excluded: 657/141/140/1 patients), including in-house and public PROSTATE-x datasets, and their corresponding ground truth urethral contours from an expert genitourinary radiologist. The AI model was developed using MONAI framework and was based on a 3D-UNet. AI model performance was determined by Dice score (volume-based) and the Centerline Distance (CLD) between the prediction and ground truth centers (slice-based). All predictions were compared to ground truth in a systematic failure analysis to elucidate the model's strengths and weaknesses. The Wilcoxon-rank sum test was used for pair-wise comparison of group differences.

RESULTS

The overall organ-adjusted Dice score for this model was 0.61 and overall CLD was 2.56 mm. When comparing prostates with symmetrical (n = 117) and asymmetrical (n = 23) benign prostate hyperplasia (BPH), the AI model performed better on symmetrical prostates compared to asymmetrical in both Dice score (0.64 vs. 0.51 respectively, p < 0.05) and mean CLD (2.3 mm vs. 3.8 mm respectively, p < 0.05). When calculating location-specific performance, the performance was highest at the apex and lowest at the base location of the prostate for Dice and CLD. Dice location dependence: symmetrical (Apex, Mid, Base: 0.69 vs. 0.67 vs. 0.54 respectively, p < 0.05) and asymmetrical (Apex, Mid, Base: 0.68 vs. 0.52 vs. 0.39 respectively, p < 0.05). CLD location dependence: symmetrical (Apex, Mid, Base: 1.43 mm vs. 2.15 mm vs. 3.28 mm, p < 0.05) and asymmetrical (Apex, Mid, Base: 1.83 mm vs. 3.1 mm vs. 6.24 mm, p < 0.05).

CONCLUSION

We developed a fully automated prostatic urethra segmentation AI tool yielding its best performance in prostate glands with symmetric BPH features. This system can potentially be used to assist treatment planning in patients who can undergo whole gland radiation therapy or ablative focal therapy.

Tasks for artificial intelligence in prostate MRI

The advent of precision medicine, increasing clinical needs, and imaging availability among many other factors in the prostate cancer diagnostic pathway has engendered the utilization of artificial intelligence (AI). AI carries a vast number of potential applications in every step of the prostate cancer diagnostic pathway from classifying/improving prostate multiparametric magnetic resonance image quality, prostate segmentation, anatomically segmenting cancer suspicious foci, detecting and differentiating clinically insignificant cancers from clinically significant cancers on a voxel-level, and classifying entire lesions into Prostate Imaging Reporting and Data System categories/Gleason scores. Multiple studies in all these areas have shown many promising results approximating accuracies of radiologists. Despite this flourishing research, more prospective multicenter studies are needed to uncover the full impact and utility of AI on improving radiologist performance and clinical management of prostate cancer. In this narrative review, we aim to introduce emerging medical imaging AI paper quality metrics such as the Checklist for Artificial Intelligence in Medical Imaging (CLAIM) and Field-Weighted Citation Impact (FWCI), dive into some of the top AI models for segmentation, detection, and classification.