Xiaobin Liu1, Miaomiao Long1, Chuanqi Sun2, Yining Yang3, Peng Lin4, Zhiwei Shen5, Shuang Xia6, Wen Shen7. 1. Department of Radiology, Tianjin Medical Imaging Institute, Tianjin First Central Hospital, School of Medicine, Nankai University, Fukang Road No. 24, Nankai District, 300192, Tianjin, China. 2. Department of Biomedical Engineering, Guangzhou Medical University, Xinzao Road No. 1, Panyu District, Guangzhou, 511436, China. 3. Department of Radiotherapy, Tianjin First Central Hospital, School of Medicine, Nankai University, Fukang Road No. 24, Nankai District, Tianjin, 300192, China. 4. Department of Otorhinolaryngology Head and Neck Surgery, Tianjin First Central Hospital, School of Medicine, Nankai University, Fukang Road No. 24, Nankai District, Tianjin, 300192, China. 5. Philips Healthcare, World Profit Centre, 100125, Tianze Road No. 16, Chaoyang District, Beijing, China. 6. Department of Radiology, Tianjin Medical Imaging Institute, Tianjin First Central Hospital, School of Medicine, Nankai University, Fukang Road No. 24, Nankai District, 300192, Tianjin, China. xiashuang77@163.com. 7. Department of Radiology, Tianjin Medical Imaging Institute, Tianjin First Central Hospital, School of Medicine, Nankai University, Fukang Road No. 24, Nankai District, 300192, Tianjin, China. shen_hos@163.com.
Abstract
OBJECTIVES: To establish and validate a CT radiomics model for prediction of induction chemotherapy (IC) response and progression-free survival (PFS) among patients with locally advanced hypopharyngeal carcinoma (LAHC). METHODS: One hundred twelve patients with LAHC (78 in training cohort and 34 in validation cohort) who underwent contrast-enhanced CT (CECT) scans prior to IC were enrolled. Least absolute shrinkage and selection operator (LASSO) was used to select the crucial radiomic features in the training cohort. Radiomics signature and clinical data were used to build a radiomics nomogram to predict individual response to IC. Kaplan-Meier analysis and log-rank test were used to evaluate ability of radiomics signature in progression-free survival risk stratification. RESULTS: The radiomics signature consisted of 6 selected features from the arterial and venous phases of CECT images and demonstrated good performance in predicting the IC response in both two cohorts. The radiomics nomogram showed good discriminative performance, and the C-index of nomogram was 0.899 (95% confidence interval (CI), 0.831-0.967) and 0.775 (95% CI, 0.591-0.959) in the training and validation cohorts, respectively. Survival analysis indicated that low-risk and high-risk groups defined by the value of radiomics signature had significant difference in PFS (3-year PFS 66.4% vs 29.7%, p < 0.001). CONCLUSIONS: Multiparametric CT-based radiomics model could be useful for predicting treatment response and PFS in patients with LAHC who underwent IC. KEY POINTS: • CT radiomics can predict IC response and progression-free survival in hypopharyngeal carcinoma. • We combined significant radiomics signature with clinical predictors to establish a nomogram to predict individual response to IC. • Radiomics signature could divide patients into the high-risk and low-risk groups based on the PFS.
OBJECTIVES: To establish and validate a CT radiomics model for prediction of induction chemotherapy (IC) response and progression-free survival (PFS) among patients with locally advanced hypopharyngeal carcinoma (LAHC). METHODS: One hundred twelve patients with LAHC (78 in training cohort and 34 in validation cohort) who underwent contrast-enhanced CT (CECT) scans prior to IC were enrolled. Least absolute shrinkage and selection operator (LASSO) was used to select the crucial radiomic features in the training cohort. Radiomics signature and clinical data were used to build a radiomics nomogram to predict individual response to IC. Kaplan-Meier analysis and log-rank test were used to evaluate ability of radiomics signature in progression-free survival risk stratification. RESULTS: The radiomics signature consisted of 6 selected features from the arterial and venous phases of CECT images and demonstrated good performance in predicting the IC response in both two cohorts. The radiomics nomogram showed good discriminative performance, and the C-index of nomogram was 0.899 (95% confidence interval (CI), 0.831-0.967) and 0.775 (95% CI, 0.591-0.959) in the training and validation cohorts, respectively. Survival analysis indicated that low-risk and high-risk groups defined by the value of radiomics signature had significant difference in PFS (3-year PFS 66.4% vs 29.7%, p < 0.001). CONCLUSIONS: Multiparametric CT-based radiomics model could be useful for predicting treatment response and PFS in patients with LAHC who underwent IC. KEY POINTS: • CT radiomics can predict IC response and progression-free survival in hypopharyngeal carcinoma. • We combined significant radiomics signature with clinical predictors to establish a nomogram to predict individual response to IC. • Radiomics signature could divide patients into the high-risk and low-risk groups based on the PFS.
Authors: Devadhas Devakumar; Goutham Sunny; Balu Krishna Sasidharan; Stephen R Bowen; Ambily Nadaraj; L Jeyseelan; Manu Mathew; Aparna Irodi; Rajesh Isiah; Simon Pavamani; Subhashini John; Hannah Mary T Thomas Journal: J Med Phys Date: 2021-09-08