• Honglin Bai, Wei Xia, Xuefu Ji, Dong He, Xingyu Zhao, Jie Bao, Jian Zhou, Xuedong Wei, Yuhua Huang, Qiong Li, and Xin Gao.
• School of Biomedical Engineering (Suzhou), Division of Life Science and Medicine, University of Science and Technology of China, Hefei, 230026, China.
• J Magn Reson Imaging. 2021 Oct 1; 54 (4): 1222-1230.

BackgroundPreoperative prediction of extracapsular extension (ECE) of prostate cancer (PCa) is important to guide clinical decision-making and improve patient prognosis.PurposeTo investigate the value of multiparametric magnetic resonance imaging (mpMRI)-based peritumoral radiomics for preoperative prediction of the presence of ECE.Study TypeRetrospective.PopulationTwo hundred eighty-four patients with PCa from two centers (center 1: 226 patients; center 2: 58 patients). Cases from center 1 were randomly divided into training (158 patients) and internal validation (68 patients) sets. Cases from center 2 were assigned to the external validation set.Field Strength/SequenceA 3.0 T MRI scanners (three vendors). Sequence: Pelvic T2-weighted turbo/fast spin echo sequence and diffusion weighted echo planar imaging sequence.AssessmentThe peritumoral region (PTR) was obtained by 3-12 mm (half of the tumor length) 3D dilatation of the intratumoral region (ITR). Single-MRI radiomics signatures, mpMRI radiomics signatures, and integrated models, which combined clinical characteristics with the radiomics signatures were built. The discrimination ability was assessed by area under the receiver operating characteristic curve (AUC) in the internal and external validation sets.Statistical TestsFisher's exact test, Mann-Whitney U-test, DeLong test.ResultsThe PTR radiomics signatures demonstrated significantly better performance than the corresponding ITR radiomics signatures (AUC: 0.674 vs. 0.554, P < 0.05 on T2-weighted, 0.652 vs. 0.546, P < 0.05 on apparent diffusion coefficient, 0.682 vs. 0.556 on mpMRI in the external validation set). The integrated models combining the PTR radiomics signature with clinical characteristics performed better than corresponding radiomics signatures in the internal validation set (eg. AUC: 0.718 vs. 0.671, P < 0.05 on mpMRI) but performed similar in the external validation set (eg. AUC: 0.684, vs. 0.682, P = 0.45 on mpMRI).Data ConclusionThe peritumoral radiomics can better predict the presence of ECE preoperatively compared with the intratumoral radiomics and may have better generalization than clinical characteristics. EVIDENCE LEVEL: 4 TECHNICAL EFFICACY: 2.© 2021 International Society for Magnetic Resonance in Medicine.

14 keywords...

hide…