Metadata-independent classification of MRI sequences using convolutional neural networks: Successful application to prostate MRI.

PURPOSE: The ever-increasing volume of medical imaging data and interest in Big Data research brings challenges to data organization, categorization, and retrieval. Although the radiological value chain is almost entirely digital, data structuring has been widely performed pragmatically, but with insufficient naming and metadata standards for the stringent needs of image analysis. To enable automated data management independent of naming and metadata, this study focused on developing a convolutional neural network (CNN) that classifies medical images based solely on voxel data. METHOD: A 3D CNN (3D-ResNet18) was trained using a dataset of 31,602 prostate MRI volumes with 10 different sequence types of 1243 patients. A five-fold cross-validation approach with patient-based splits was chosen for training and testing. Training was repeated with a gradual reduction in training data assessing classification accuracies to determine the minimum training data required for sufficient performance. The trained model and developed method were tested on three external datasets. RESULTS: The model achieved an overall accuracy of 99.88 % ± 0.13 % in classifying typical prostate MRI sequence types. When being trained with approximately 10 % of the original cohort (112 patients), the CNN still achieved an accuracy of 97.43 % ± 2.10 %. In external testing the model achieved sensitivities of > 90 % for 10/15 tested sequence types. CONCLUSIONS: The herein developed CNN enabled automatic and reliable sequence identification in prostate MRI. Ultimately, such CNN models for voxel-based sequence identification could substantially enhance the management of medical imaging data, improve workflow efficiency and data quality, and allow for robust clinical AI workflows.

Interactive Explainable Deep Learning Model Informs Prostate Cancer Diagnosis at MRI.

Background Clinically significant prostate cancer (PCa) diagnosis at MRI requires accurate and efficient radiologic interpretation. Although artificial intelligence may assist in this task, lack of transparency has limited clinical translation. Purpose To develop an explainable artificial intelligence (XAI) model for clinically significant PCa diagnosis at biparametric MRI using Prostate Imaging Reporting and Data System (PI-RADS) features for classification justification. Materials and Methods This retrospective study included consecutive patients with histopathologic analysis-proven prostatic lesions who underwent biparametric MRI and biopsy between January 2012 and December 2017. After image annotation by two radiologists, a deep learning model was trained to detect the index lesion; classify PCa, clinically significant PCa (Gleason score ≥ 7), and benign lesions (eg, prostatitis); and justify classifications using PI-RADS features. Lesion- and patient-based performance were assessed using fivefold cross validation and areas under the receiver operating characteristic curve. Clinical feasibility was tested in a multireader study and by using the external PROSTATEx data set. Statistical evaluation of the multireader study included Mann-Whitney U and exact Fisher-Yates test. Results Overall, 1224 men (median age, 67 years; IQR, 62-73 years) had 3260 prostatic lesions (372 lesions with Gleason score of 6; 743 lesions with Gleason score of ≥ 7; 2145 benign lesions). XAI reliably detected clinically significant PCa in internal (area under the receiver operating characteristic curve, 0.89) and external test sets (area under the receiver operating characteristic curve, 0.87) with a sensitivity of 93% (95% CI: 87, 98) and an average of one false-positive finding per patient. Accuracy of the visual and textual explanations of XAI classifications was 80% (1080 of 1352), confirmed by experts. XAI-assisted readings improved the confidence (4.1 vs 3.4 on a five-point Likert scale; P = .007) of nonexperts in assessing PI-RADS 3 lesions, reducing reading time by 58 seconds (P = .009). Conclusion The explainable AI model reliably detected and classified clinically significant prostate cancer and improved the confidence and reading time of nonexperts while providing visual and textual explanations using well-established imaging features. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Chapiro in this issue.

MRI-targeted biopsy cores from prostate index lesions: assessment and prediction of the number needed.

BACKGROUND: Magnetic resonance imaging (MRI) is used to detect the prostate index lesion before targeted biopsy. However, the number of biopsy cores that should be obtained from the index lesion is unclear. The aim of this study is to analyze how many MRI-targeted biopsy cores are needed to establish the most relevant histopathologic diagnosis of the index lesion and to build a prediction model. METHODS: We retrospectively included 451 patients who underwent 10-core systematic prostate biopsy and MRI-targeted biopsy with sampling of at least three cores from the index lesion. A total of 1587 biopsy cores were analyzed. The core sampling sequence was recorded, and the first biopsy core detecting the most relevant histopathologic diagnosis was identified. In a subgroup of 261 patients in whom exactly three MRI-targeted biopsy cores were obtained from the index lesion, we generated a prediction model. A nonparametric Bayes classifier was trained using the PI-RADS score, prostate-specific antigen (PSA) density, lesion size, zone, and location as covariates. RESULTS: The most relevant histopathologic diagnosis of the index lesion was detected by the first biopsy core in 331 cases (73%), by the second in 66 cases (15%), and by the third in 39 cases (9%), by the fourth in 13 cases (3%), and by the fifth in two cases (<1%). The Bayes classifier correctly predicted which biopsy core yielded the most relevant histopathologic diagnosis in 79% of the subjects. PI-RADS score, PSA density, lesion size, zone, and location did not independently influence the prediction model. CONCLUSION: The most relevant histopathologic diagnosis of the index lesion was made on the basis of three MRI-targeted biopsy cores in 97% of patients. Our classifier can help in predicting the first MRI-targeted biopsy core revealing the most relevant histopathologic diagnosis; however, at least three MRI-targeted biopsy cores should be obtained regardless of the preinterventionally assessed covariates.

Inter-Reader Variability Using PI-RADS v2 Versus PI-RADS v2.1: Most New Disagreement Stems from Scores 1 and 2.

PURPOSE: To analyze possible differences in the inter-reader variability between PI-RADS version 2 (v2) and version 2.1 (v2.1) for the classification of prostate lesions using multiparametric MRI (mpMRI) of the prostate. METHODS: In this retrospective and randomized study, 239 annotated and histopathologically correlated prostate lesions (104 positive and 135 negative for prostate cancer) were rated twice by three experienced uroradiologists using PI-RADS v2 and v2.1 with an interval of at least two months between readings. Results were tabulated across readers and reading timepoints and inter-reader variability was determined using Fleiss' kappa (κ). Thereafter, an additional analysis of the data was performed in which PI-RADS scores 1 and 2 were combined, as they have the same clinical consequences. RESULTS: PI-PI-RADS v2.1 showed better inter-reader agreement in the peripheral zone (PZ), but poorer inter-reader agreement in the transition zone (TZ) (PZ: κ = 0.63 vs. κ = 0.58; TZ: κ = 0.47 vs. κ = 0.57). When PI-RADS scores 1 and 2 were combined, the use of PI-RADS v2.1 resulted in almost perfect inter-reader agreement in the PZ and substantial agreement in the TZ (PZ: κ = 0.81; TZ: κ = 0.80). CONCLUSION: PI-RADS v2.1 improves inter-reader agreement in the PZ. New differences in inter-reader agreement were mainly the result of the assignment of PI-RADS v2.1 scores 1 and 2 to lesions in the TZ. Combining scores 1 and 2 improved inter-reader agreement both in the TZ and in the PZ, indicating that refined definitions may be warranted for these PI-RADS scores. KEY POINTS: · PI-RADSv2.1 improves inter-reader agreement in the PZ but not in the TZ.. · New differences derived from PI-RADSv2.1 scores 1 and 2 in the TZ.. · Combined PI-RADSv2.1 scores of 1 and 2 yielded better inter-reader agreement.. · PI-RADSv2.1 appears to provide more precise description of lesions in the PZ.. · Improved inter-reader agreement in the PZ stresses the importance of appropriate lexicon description.. CITATION FORMAT: · Beetz N, Haas M, Baur A et al. Inter-Reader Variability Using PI-RADS v2 Versus PI-RADS v2.1: Most New Disagreement Stems from Scores 1 and 2. Fortschr Röntgenstr 2022; 194: 852 - 861.

Diagnostic performance of PI-RADS version 2.1 compared to version 2.0 for detection of peripheral and transition zone prostate cancer.

The purpose of this study is to compare diagnostic performance of Prostate Imaging Reporting and Data System (PI-RADS) version (v) 2.1 and 2.0 for detection of Gleason Score (GS) ≥ 7 prostate cancer on MRI. Three experienced radiologists provided PI-RADS v2.0 scores and at least 12 months later v2.1 scores on lesions in 333 prostate MRI examinations acquired between 2012 and 2015. Diagnostic performance was assessed retrospectively by using MRI/transrectal ultrasound fusion biopsy and 10-core systematic biopsy as the reference. From a total of 359 lesions, GS ≥ 7 tumor was present in 135 lesions (37.60%). Area under the ROC curve (AUC) revealed slightly lower values for peripheral zone (PZ) and transition zone (TZ) scoring in v2.1, but these differences did not reach statistical significance. A significant number of score 2 lesions in the TZ were downgraded to score 1 in v2.1 showing 0% GS ≥ 7 tumor (0/11). The newly introduced diffusion-weighted imaging (DWI) upgrading rule in v2.1 was applied in 6 lesions from a total of 143 TZ lesions (4.2%). In summary, PI-RADS v2.1 showed no statistically significant differences in overall diagnostic performance of TZ and PZ scoring compared to v2.0. Downgraded BPH nodules showed favorable cancer frequencies. The new DWI upgrading rule for TZ lesions was applied in only few cases.

Optimizing size thresholds for detection of clinically significant prostate cancer on MRI: Peripheral zone cancers are smaller and more predictable than transition zone tumors.

PURPOSE: To evaluate if size-based cut-offs based on MR imaging can successfully assess clinically significant prostate cancer (csPCA). The goal was to improve the currently applied size-based differentiation criterion in PI-RADS. METHODS AND MATERIALS: MRIs of 293 patients who had undergone 3 T MR imaging with subsequent confirmation of prostate cancer on systematic and targeted MRI/TRUS-fusion biopsy were re-read by three radiologists. All identifiable tumors were measured on T2WI for lesions originating in the transition zone (TZ) and on DWI for lesions from the peripheral zone (PZ) and tabulated against their Gleason grade. RESULTS: 309 lesions were analyzed, 213 (68.9 %) in the PZ and 96 (31.1 %) in the TZ. ROC-Analysis showed a stronger correlation between lesion size and clinically significant (defined as Gleason Grade Group ≥ 2) prostate cancer (PCa) for the PZ (AUC = 0.73) compared to the TZ (AUC = 0.63). The calculated Youden index resulted in size cut-offs of 14 mm for PZ and 21 mm for TZ tumors. CONCLUSION: Size cut-offs can be used to stratify prostate cancer with different optimal size thresholds in the peripheral zone and transition zone. There was a clearer separation of clinically significant tumors in peripheral zone cancers compared to transition zone cancers. Future iterations of PI-RADS could therefore take different size-based cut-offs for peripheral zone and transition zone cancers into account.

Validation of the PI-RADS language: predictive values of PI-RADS lexicon descriptors for detection of prostate cancer.

OBJECTIVES: To assess the discriminatory power of lexicon terms used in PI-RADS version 2 to describe MRI features of prostate lesions. METHODS: Four hundred fifty-four patients were included in this retrospective, institutional review board-approved study. Patients received multiparametric (mp) MRI and subsequent prostate biopsy including MRI/transrectal ultrasound fusion biopsy and 10-core systematic biopsy. PI-RADS lexicon terms describing lesion characteristics on mpMRI were assigned to lesions by experienced readers. Positive and negative predictive values (PPV, NPV) of each lexicon term were assessed using biopsy results as a reference standard. RESULTS: From a total of 501 lesions, clinically significant prostate cancer (csPCa) was present in 175 lesions (34.9%). Terms related to findings of restricted diffusion showed PPVs of up to 52.0%/43.9% and NPV of up to 91.8%/89.7% (peripheral zone or PZ/transition zone or TZ). T2-weighted imaging (T2W)-related terms showed a wide range of predictive values. For PZ lesions, high PPVs were found for "markedly hypointense," "lenticular," "lobulated," and "spiculated" (PPVs between 67.2 and 56.7%). For TZ lesions, high PPVs were found for "water-drop-shaped" and "erased charcoal sign" (78.6% and 61.0%). The terms "encapsulated," "organized chaos," and "linear" showed to be good predictors for benignity with distinctively low PPVs between 5.4 and 6.9%. Most T2WI-related terms showed improved predictive values for TZ lesions when combined with DWI-related findings. CONCLUSIONS: Lexicon terms with high discriminatory power were identified (e.g., "markedly hypointense," "water-drop-shaped," "organized chaos"). DWI-related terms can be useful for excluding TZ cancer. Combining T2WI- with DWI findings in TZ lesions markedly improved predictive values. KEY POINTS: • Lexicon terms describing morphological and functional features of prostate lesions on MRI show a wide range of predictive values for prostate cancer. • Some T2-related terms have favorable PPVs, e.g., "water-drop-shaped" and "organized chaos" while others show less distinctive predictive values. DWI-related terms have noticeable negative predictive values in TZ lesions making DWI feature a useful tool for exclusion of TZ cancer. • Combining DWI- and T2-related lexicon terms for assessment of TZ lesions markedly improves PPVs. Most T2-related lexicon terms showed a significant decrease in PPV when combined with negative findings for "DW hyperintensity."