Prediction of clinically significant prostate cancer using radiomics models in real-world clinical practice: a retrospective multicenter study.

PURPOSE: To develop and evaluate machine learning models based on MRI to predict clinically significant prostate cancer (csPCa) and International Society of Urological Pathology (ISUP) grade group as well as explore the potential value of radiomics models for improving the performance of radiologists for Prostate Imaging Reporting and Data System (PI-RADS) assessment. MATERIAL AND METHODS: A total of 1616 patients from 4 tertiary care medical centers were retrospectively enrolled. PI-RADS assessments were performed by junior, senior, and expert-level radiologists. The radiomics models for predicting csPCa were built using 4 machine-learning algorithms. The PI-RADS were adjusted by the radiomics model. The relationship between the Rad-score and ISUP was evaluated by Spearman analysis. RESULTS: The radiomics models made using the random forest algorithm yielded areas under the receiver operating characteristic curves (AUCs) of 0.874, 0.876, and 0.893 in an internal testing cohort and external testing cohorts, respectively. The AUC of the adjusted_PI-RADS was improved, and the specificity was improved at a slight sacrifice of sensitivity. The participant-level correlation showed that the Rad-score was positively correlated with ISUP in all testing cohorts (r > 0.600 and p < 0.0001). CONCLUSIONS: This radiomics model resulted as a powerful, non-invasive auxiliary tool for accurately predicting prostate cancer aggressiveness. The radiomics model could reduce unnecessary biopsies and help improve the diagnostic performance of radiologists' PI-RADS. Yet, prospective studies are still needed to validate the radiomics models further. CRITICAL RELEVANCE STATEMENT: The radiomics model with MRI may help to accurately screen out clinically significant prostate cancer, thereby assisting physicians in making individualized treatment plans. KEY POINTS: • The diagnostic performance of the radiomics model using the Random Forest algorithm is comparable to the Prostate Imaging Reporting and Data System (PI-RADS) obtained by radiologists. • The performance of the adjusted Prostate Imaging Reporting and Data System (PI-RADS) was improved, which implied that the radiomics model could be a potential radiological assessment tool. • The radiomics model lowered the percentage of equivocal cases. Moreover, the Rad-scores can be used to characterize prostate cancer aggressiveness.

Detecting Adverse Pathology of Prostate Cancer With a Deep Learning Approach Based on a 3D Swin-Transformer Model and Biparametric MRI: A Multicenter Retrospective Study.

BACKGROUND: Accurately detecting adverse pathology (AP) presence in prostate cancer patients is important for personalized clinical decision-making. Radiologists' assessment based on clinical characteristics showed poor performance for detecting AP presence. PURPOSE: To develop deep learning models for detecting AP presence, and to compare the performance of these models with those of a clinical model (CM) and radiologists' interpretation (RI). STUDY TYPE: Retrospective. POPULATION: Totally, 616 men from six institutions who underwent radical prostatectomy, were divided into a training cohort (508 patients from five institutions) and an external validation cohort (108 patients from one institution). FIELD STRENGTH/SEQUENCES: T2-weighted imaging with a turbo spin echo sequence and diffusion-weighted imaging with a single-shot echo plane-imaging sequence at 3.0 T. ASSESSMENT: The reference standard for AP was histopathological extracapsular extension, seminal vesicle invasion, or positive surgical margins. A deep learning model based on the Swin-Transformer network (TransNet) was developed for detecting AP. An integrated model was also developed, which combined TransNet signature with clinical characteristics (TransCL). The clinical characteristics included biopsy Gleason grade group, Prostate Imaging Reporting and Data System scores, prostate-specific antigen, ADC value, and the lesion maximum cross-sectional diameter. STATISTICAL TESTS: Model and radiologists' performance were assessed using area under the receiver operating characteristic curve (AUC), sensitivity, and specificity. The Delong test was used to evaluate difference in AUC. P < 0.05 was considered significant. RESULTS: The AUC of TransCL for detecting AP presence was 0.813 (95% CI, 0.726-0.882), which was higher than that of TransNet (0.791 [95% CI, 0.702-0.863], P = 0.429), and significantly higher than those of CM (0.749 [95% CI, 0.656-0.827]) and RI (0.664 [95% CI, 0.566-0.752]). DATA CONCLUSION: TransNet and TransCL have potential to aid in detecting the presence of AP and some single adverse pathologic features. LEVEL OF EVIDENCE: 4 TECHNICAL EFFICACY: Stage 4.

Predicting clinically significant prostate cancer with a deep learning approach: a multicentre retrospective study.

PURPOSE: This study aimed to develop deep learning (DL) models based on multicentre biparametric magnetic resonance imaging (bpMRI) for the diagnosis of clinically significant prostate cancer (csPCa) and compare the performance of these models with that of the Prostate Imaging and Reporting and Data System (PI-RADS) assessment by expert radiologists based on multiparametric MRI (mpMRI). METHODS: We included 1861 consecutive male patients who underwent radical prostatectomy or biopsy at seven hospitals with mpMRI. These patients were divided into the training (1216 patients in three hospitals) and external validation cohorts (645 patients in four hospitals). PI-RADS assessment was performed by expert radiologists. We developed DL models for the classification between benign and malignant lesions (DL-BM) and that between csPCa and non-csPCa (DL-CS). An integrated model combining PI-RADS and the DL-CS model, abbreviated as PIDL-CS, was developed. The performances of the DL models and PIDL-CS were compared with that of PI-RADS. RESULTS: In each external validation cohort, the area under the receiver operating characteristic curve (AUC) values of the DL-BM and DL-CS models were not significantly different from that of PI-RADS (P > 0.05), whereas the AUC of PIDL-CS was superior to that of PI-RADS (P < 0.05), except for one external validation cohort (P > 0.05). The specificity of PIDL-CS for the detection of csPCa was much higher than that of PI-RADS (P < 0.05). CONCLUSION: Our proposed DL models can be a potential non-invasive auxiliary tool for predicting csPCa. Furthermore, PIDL-CS greatly increased the specificity of csPCa detection compared with PI-RADS assessment by expert radiologists, greatly reducing unnecessary biopsies and helping radiologists achieve a precise diagnosis of csPCa.

Radiomics prediction model for the improved diagnosis of clinically significant prostate cancer on biparametric MRI.

BACKGROUND: To evaluate the potential of clinical-based model, a biparametric MRI-based radiomics model and a clinical-radiomics combined model for predicting clinically significant prostate cancer (PCa). METHODS: In total, 381 patients with clinically suspicious PCa were included in this retrospective study; of those, 199 patients did not have PCa upon biopsy, while 182 patients had PCa. All patients underwent 3.0-T MRI examinations with the same acquisition parameters, and clinical risk factors associated with PCa (age, prostate volume, serum PSA, etc.) were collected. We randomly stratified the training and test sets using a 6:4 ratio. The radiomic features included gradient-based histogram features, grey-level co-occurrence matrix (GLCM), run-length matrix (RLM), and grey-level size zone matrix (GLSZM). Three models were developed using multivariate logistic regression analysis to predict clinically significant PCa: a clinical model, a radiomics model and a clinical-radiomics combined model. The diagnostic performance and clinical net benefit of each model were compared via receiver operating characteristic (ROC) curve analysis and decision curves, respectively. RESULTS: Both the radiomics model (AUC: 0.98) and the clinical-radiomics combined model (AUC: 0.98) achieved greater predictive efficacy than the clinical model (AUC: 0.79). The decision curve analysis also showed that the radiomics model and combined model had higher net benefits than the clinical model. CONCLUSIONS: Compared with the evaluation of clinical risk factors associated with PCa only, the radiomics-based machine learning model can improve the predictive accuracy for clinically significant PCa, in terms of both diagnostic performance and clinical net benefit.

Differentiating Transition Zone Cancers From Benign Prostatic Hyperplasia by Histogram Analysis of Apparent Diffusion Coefficient Maps With Standard and Ultrahigh b-value Diffusion-weighted MR Imaging.

OBJECTIVE: To compare the diagnostic performance of standard and ultrahigh b-value Diffusion-weighted Imaging (DWI) using volumetric histogram analysis in differentiating transition zone (TZ) cancer from benign prostatic hyperplasia (BPH). METHODS: 57 TZ cancer and 61 BPH patients received standard (1000 s/mm) and ultrahigh b-value (2000 s/mm) DWI. The diagnostic ability of ADC histogram parameters derived from two DWI for differentiating TZ cancer from BPH was determined by receiver operating characteristic curve. RESULTS: Median, minimum, the 10th, 25th percentile ADC in both ADC1000 and ADC2000 and skewness in ADC2000 had significant differences between TZ cancer and BPH (for all, P < 0.05).The 10th percentile ADC showed highest area under the ROC curve (AUC) in both ADC1000 and ADC2000.The 10th percentile ADC of ADC2000 showed significantly higher AUC than did ADC1000 (P = 0.0385). CONCLUSIONS: The 10th percentile ADC obtained from ultrahigh b-value DWI performed better for differentiating TZ cancer from BPH.

[Associations of apparent diffusion coefficient value from MR diffusion-weighted imaging with Ki-67 expression and differentiation grade in gastric cancer].

OBJECTIVE: To examine the associations of apparent diffusion coefficient (ADC) value from MR diffusion-weighted imaging (DWI) with Ki-67 expression and differentiation grade in gastric cancer. METHODS: Images and pathologic data of 68 gastric cancer patients between September 2013 and February 2015 in Affiliated Changshu Hospital of Soochow University were analyzed retrospectively. The expression of Ki-67 antigen in cancer tissue sample was determined by immunohistochemistry. Ki-67 labeling index(LI) was calculated to divide the cases into low Ki-67 group(Ki-67 LI <50%) and high Ki-67 group (Ki-67 LI ≥ 50%). Associations of ADC value with differentiation grade and Ki-67 LI were examined. RESULTS: Mean ADC value of low Ki-67 LI group was significantly higher than that of high Ki-67 LI group [(0.977 ± 0.100) × 10(-3) mm(2)/s vs. (0.859 ± 0.064) × 10(-3) mm(2)/s, P=0.000]. The ADC value was negatively correlated with Ki-67 LI (r=-0.685, P=0.000). Mean ADC value of well differentiated adenocarcinoma, moderately differentiated adenocarcinoma, poorly differentiated adenocarcinoma, and signet-ring cell carcinoma was (1.124 ± 0.080) × 10(-3) mm(2)/s, (0.950 ± 0.064) × 10(-3) mm(2)/s, (0.899 ± 0.091) × 10(-3) mm(2)/s, and (0.894 ± 0.081) × 10(-3) mm(2)/s respectively. Difference of ADC value among differentiation grades was significantly different (F=11.405, P=0.000). Difference of ADC value between well differentiated adenocarcinoma and non-well differentiated adenocarcinoma was significantly different(P=0.000). CONCLUSION: ADC value is associated with differentiation grade and Ki-67 LI of gastric cancer, which may be used as a noninvasive predictor for evaluating the proliferation and differentiation grade of gastric cancer.