Machine learning-based radiomics model to predict benign and malignant PI-RADS v2.1 category 3 lesions - a retrospective multi-center study

Sep 24, 2026

Purpose: Develop machine learning-based radiomics models using different MRI sequences to distinguish benign and malignant PI-RADS 3 lesions before intervention, and cross-institutionally validate model generalization. Methods: Retrospective multi-center pre-biopsy MRI data from 463 PI-RADS 3 patients were used to extract 2347 radiomics features from T2WI, DWI, and ADC VOIs. ANOVA feature ranking and support vector machines built three single-sequence models plus one integrated model. Performance was assessed with AUC, calibration via Hosmer–Lemeshow tests, and generalization using a non-inferiority test.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages13

Reading Time33 min

AccessFree to download

Abstract

Purpose

Methods

Results

Conclusions

Introduction

Prostate cancer background

PI-RADS v2.1 and PI-RADS 3 variability

Jin et al. BMC Medical Imaging (2023) 23:47 [https://doi.org/10.1186/s12880-023-01002-9](https://doi.org/10.1186/s12880-023-01002-9) BMC Medical Imaging RESEARCH Open Access Machine learning-based radiomics model to predict benign and malignant PI-RADS v2.1 category 3 lesions: a retrospective multi-center study Pengfei Jin1, Junkang Shen2, Liqin Yang3, Ji Zhang4, Ao Shen5, Jie Bao3 and Ximing Wang3* Abstract Purpose To develop machine learning-based radiomics models derive from different MRI sequences for distinction between benign and malignant PI-RADS 3 lesions before intervention, and to cross-institution validate the generalization ability of the models. Methods The pre-biopsy MRI datas of 463 patients classified as PI-RADS 3 lesions were collected from 4 medical institutions retrospectively. 2347 radiomics features were extracted from the VOI ofT2WI, DWI and ADC images. The ANOVA feature ranking method and support vector machine classifier were used to construct 3 single-sequence models and 1 integrated model combined with the features of three sequences. All the models were established in the training set and independently verified in the internal test and external validation set. The AUC was used to compared the predictive performance of PSAD with each model. Hosmer–lemeshow test was used to evaluate the degree of fitting between prediction probability and pathological results. Non-inferiority test was used to check generalization performance of the integrated model. Results The difference of PSAD between PCa and benign lesions was statistically significant (P = 0 . 006), with the mean AUC of 0.701 for predicting clinically significant prostate cancer (internal test AUC = 0.709 vs. external validation AUC = 0 . 692, P = 0 . 013) and 0.630 for predicting all cancer (internal test AUC = 0.637 vs. external validation AUC = 0 . 623, P = 0 . 036) . T2WI-model with the mean AUC of 0.717 for predicting csPCa (internal test AUC = 0.738 vs. external validation AUC = 0 . 695, P = 0 . 264) and 0.634 for predicting all cancer (internal test AUC = 0.678 vs. external validation AUC = 0 . 589, P = 0 . 547) . DWI-model with the mean AUC of 0.658 for predicting csPCa (internal test AUC = 0.635 vs. external validation AUC = 0 . 681, P = 0 . 086) and 0.655 for predicting all cancer (internal test AUC = 0.712 vs. external validation AUC = 0 . 598, P = 0 .437) . ADC-model with the mean AUC of 0.746 for predicting csPCa (internal test AUC = 0.767 vs. external validation AUC = 0 . 724, P = 0 . 269) and 0.645 for predicting all cancer (internal test AUC = 0.650 vs. external validation AUC = 0 . 640, P = 0 . 848) . Integrated model with the mean AUC of 0.803 for predicting csPCa (internal test AUC = 0.804 vs. external validation AUC = 0 . 801, P = 0 . 019) and 0.778 for predicting all cancer (internal test AUC = 0.801 vs. external validation AUC = 0 . 754, P = 0 . 047) . *Correspondence: Ximing Wang [wangximing1998@163.com](wangximing1998@163.com) Full list of author information is available at the end of the article © The Author(s) 2023. Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit [http://creativecommons.org/licenses/by/4.0/](http://creativecommons.org/licenses/by/4.0

FAQs

What is the study’s main purpose?

To build machine learning-based radiomics models from different MRI sequences to differentiate benign from malignant PI-RADS 3 lesions before intervention, and to validate generalization across institutions.

How were the radiomics models constructed?

Pre-biopsy MRI data from 463 patients were used to extract 2347 features from T2WI, DWI, and ADC VOIs. ANOVA feature ranking and a support vector machine were used to create three single-sequence models and one integrated multi-sequence model.

How was predictive performance and generalization evaluated?

Predictive performance used AUC. Calibration between predicted probabilities and pathology used Hosmer–Lemeshow testing, and generalization for the integrated model was assessed with a non-inferiority test.

Sep 24, 2026

Upload by Lucas Martin