Xiao-Li Song1, Jia-Liang Ren2, Ting-Yu Yao3, Dan Zhao3, Jinliang Niu4. 1. Radiology Department, Shanxi Medical University Second Affiliated Hospital, Taiyuan, 030001, Shanxi, China. 2. GE Healthcare, Beijing, China. 3. Shanxi Medical University, Taiyuan, Shanxi, China. 4. Radiology Department, Shanxi Medical University Second Affiliated Hospital, Taiyuan, 030001, Shanxi, China. sxlscjy@163.com.
Abstract
OBJECTIVES: To develop a radiomics signature based on multisequence magnetic resonance imaging (MRI) to preoperatively predict peritoneal metastasis (PM) in ovarian cancer (OC). METHODS: Eighty-nine patients with OC were divided into a training cohort including patients (n = 54) with a single lesion and a validation cohort including patients (n = 35) with bilateral lesions. Radiomics features were extracted from the T2-weighted images (T2WIs), fat-suppressed T2WIs, multi-b-value diffusion-weighted images (DWIs), and corresponding parametric maps. A radiomics signature and nomogram incorporating the radiomics signature and clinical predictors were developed and validated on the training and validation cohorts, respectively. RESULTS: The radiomics signature generated by 6 selected features showed a favorable discriminatory ability to predict PM in OC with an area under the curve (AUC) of 0.963 in the training cohort and an AUC of 0.928 in the validation cohort. The nomogram, comprising the radiomics signature, pelvic fluid, and CA-125 level, showed more favorable discrimination with an AUC of 0.969 in the training cohort and 0.944 in the validation cohort. Net reclassification index with values of 0.548 in the training cohort and 0.500 in the validation cohort. CONCLUSION: Radiomics signature based on multisequence MRI serves as an effective quantitative approach to predict PM in OC patients. A nomogram of radiomics signature and clinical predictors could further improve the prediction ability of PM in patients with OC. KEY POINTS: • Multisequence MRI-based radiomics showed a favorable discriminatory ability to predict PM in OC. • The nomogram incorporating the radiomics signature and clinical predictors was clinically useful to preoperatively predict PM in patients with OC.
OBJECTIVES: To develop a radiomics signature based on multisequence magnetic resonance imaging (MRI) to preoperatively predict peritoneal metastasis (PM) in ovarian cancer (OC). METHODS: Eighty-nine patients with OC were divided into a training cohort including patients (n = 54) with a single lesion and a validation cohort including patients (n = 35) with bilateral lesions. Radiomics features were extracted from the T2-weighted images (T2WIs), fat-suppressed T2WIs, multi-b-value diffusion-weighted images (DWIs), and corresponding parametric maps. A radiomics signature and nomogram incorporating the radiomics signature and clinical predictors were developed and validated on the training and validation cohorts, respectively. RESULTS: The radiomics signature generated by 6 selected features showed a favorable discriminatory ability to predict PM in OC with an area under the curve (AUC) of 0.963 in the training cohort and an AUC of 0.928 in the validation cohort. The nomogram, comprising the radiomics signature, pelvic fluid, and CA-125 level, showed more favorable discrimination with an AUC of 0.969 in the training cohort and 0.944 in the validation cohort. Net reclassification index with values of 0.548 in the training cohort and 0.500 in the validation cohort. CONCLUSION: Radiomics signature based on multisequence MRI serves as an effective quantitative approach to predict PM in OC patients. A nomogram of radiomics signature and clinical predictors could further improve the prediction ability of PM in patients with OC. KEY POINTS: • Multisequence MRI-based radiomics showed a favorable discriminatory ability to predict PM in OC. • The nomogram incorporating the radiomics signature and clinical predictors was clinically useful to preoperatively predict PM in patients with OC.
Entities:
Keywords:
Magnetic resonance imaging; Ovarian neoplasms; Peritoneal carcinomatosis; Radiomics
Authors: Ignace Vergote; Corneel Coens; Matthew Nankivell; Gunnar B Kristensen; Mahesh K B Parmar; Tom Ehlen; Gordon C Jayson; Nick Johnson; Ann Marie Swart; René Verheijen; W Glenn McCluggage; Tim Perren; Pierluigi Benedetti Panici; Gemma Kenter; Antonio Casado; Cesar Mendiola; Gavin Stuart; Nick S Reed; Sean Kehoe Journal: Lancet Oncol Date: 2018-11-06 Impact factor: 41.316