MRI-based intratumoral and peritumoral radiomics on prediction of lymph-vascular space invasion in cervical cancer: A multi-center study. (February 2022)

• Record Type: Journal Article
• Authors: Shi, Jiaxin; Cui, Linpeng; Wang, Hongbo; Dong, Yue; Yu, Tao; Yang, Huazhe; Wang, Xingling; Liu, Guanyu; Jiang, Wenyan; Luo, Yahong; Yang, Zhiguang; Jiang, Xiran
• Is Part Of: Biomedical signal processing and control. Volume 72(2022)Part B
• Publication Date: 2022-02
• Subjects: Cervical cancer -- Lymph-vascular space invasion -- Radiomics; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2021.103373
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: This multicenter report highlighted intra- and peritumoral radiomics of LVSI status. Handcrafted- and deep learning-based radiomics models were developed and compared. Prediction power of the whole tumor, intra-subregions and peri-regions were assessed. A multi-regional clinical-radiomics nomogram was constructed and validated. Abstract: Purpose: To explore and externally validate intratumoral and peritumoral radiomics on predicting lymph-vascular space invasion (LVSI) in cervical cancer. Methods: A primary cohort (160 patients) was used to develop radiomics models. A consecutively enrolled internal validation cohort (44 patients) and an external validation cohort (36 patients) were used to test the models. The tumor was partitioned into two intratumoral subregions (S1 and S2) based on patient- and population-level clustering. Handcrafted and deep learning-based features were extracted and selected based on each subregion and the whole tumor, and used to build the multi-regional radiomics signature. Prediction capabilities of various machine learning classifiers were compared. A clinical-radiomics nomogram was constructed integrating the multi-regional radiomics signature and the most important clinical predictor. Receiver operating characteristic (ROC), calibration and decision curves were plotted to assess the radiomics models on the time-independent internal and external validation cohorts. Results: Predictive performance of S1 and S2 both outperformed the whole tumor. The peritumoral region with 6 mm outside the tumor (Peri-6) showed good predictive capability. The multi-regional radiomics signature integrating S1, S2 and Peri-6 yielded AUCs of 0.841, 0.795, 0.817 and 0.815 in the training, test, internal validation and external validation cohort. The nomogram integrating the multi-regional radiomics signature and degree of differentiation achieved the highest AUCs of 0.859, 0.832, 0.835 and 0.825 in the training, test, internal validation and external validation cohort. Conclusions: The proposed radiomics models combined intratumoral and peritumoral can effectively predict the LVSI in cervical cancer, and may help to improve clinical decision-making.