Singh Dharmesh, Kumar Virendra, Das Chandan J, Singh Anup, Mehndiratta Amit
Centre for Biomedical Engineering, Indian Institute of Technology Delhi, New Delhi, India.
Department of Nuclear Magnetic Resonance (NMR), All India Institute of Medical Sciences, New Delhi, India.
Front Oncol. 2022 Nov 24;12:961985. doi: 10.3389/fonc.2022.961985. eCollection 2022.
Prostate Imaging-Reporting and Data System version 2.1 (PI-RADS v2.1) was developed to standardize the interpretation of multiparametric MRI (mpMRI) for prostate cancer (PCa) detection. However, a significant inter-reader variability among radiologists has been found in the PI-RADS assessment. The purpose of this study was to evaluate the diagnostic performance of an in-house developed semi-automated model for PI-RADS v2.1 scoring using machine learning methods.
The study cohort included an MRI dataset of 59 patients (PI-RADS v2.1 score 2 = 18, score 3 = 10, score 4 = 16, and score 5 = 15). The proposed semi-automated model involved prostate gland and zonal segmentation, 3D co-registration, lesion region of interest marking, and lesion measurement. PI-RADS v2.1 scores were assessed based on lesion measurements and compared with the radiologist PI-RADS assessment. Machine learning methods were used to evaluate the diagnostic accuracy of the proposed model by classification of PI-RADS v2.1 scores.
The semi-automated PI-RADS assessment based on the proposed model correctly classified 50 out of 59 patients and showed a significant correlation ( = 0.94, p < 0.05) with the radiologist assessment. The proposed model achieved an accuracy of 88.00% ± 0.98% and an area under the receiver-operating characteristic curve (AUC) of 0.94 for score 2 vs. score 3 vs. score 4 vs. score 5 classification and accuracy of 93.20 ± 2.10% and AUC of 0.99 for low score vs. high score classification using fivefold cross-validation.
The proposed semi-automated PI-RADS v2.1 assessment system could minimize the inter-reader variability among radiologists and improve the objectivity of scoring.
前列腺影像报告和数据系统第2.1版（PI-RADS v2.1）旨在规范多参数磁共振成像（mpMRI）对前列腺癌（PCa）检测的解读。然而，在PI-RADS评估中发现放射科医生之间存在显著的阅片者间差异。本研究的目的是使用机器学习方法评估一种内部开发的用于PI-RADS v2.1评分的半自动模型的诊断性能。
研究队列包括59例患者的MRI数据集（PI-RADS v2.1评分2 = 18例，评分3 = 10例，评分4 = 16例，评分5 = 15例）。所提出的半自动模型包括前列腺腺体和分区分割、三维配准、病变感兴趣区域标记以及病变测量。基于病变测量评估PI-RADS v2.1评分，并与放射科医生的PI-RADS评估进行比较。使用机器学习方法通过对PI-RADS v2.1评分进行分类来评估所提出模型的诊断准确性。
基于所提出模型的半自动PI-RADS评估正确分类了59例患者中的50例，并且与放射科医生的评估显示出显著相关性（ = 0.94，p < 0.05）。所提出的模型在2分与3分与4分与5分分类中的准确率为88.00% ± 0.98%，受试者操作特征曲线（AUC）下面积为0.94，在低分与高分分类中使用五重交叉验证的准确率为93.20 ± 2.10%，AUC为0.99。
所提出的半自动PI-RADS v2.1评估系统可以最大限度地减少放射科医生之间的阅片者间差异，并提高评分的客观性。
