loading page

Treatment Planning CT Radiomics for Predicting Treatment outcomes and Hematologic Toxicities to Intensity-modulated Radiation Therapy in Locally Advanced Cervical Cancer
  • +9
  • Kang Ren,
  • Lin Shen,
  • Jianfeng Qiu,
  • Kui Sun,
  • Tingyin Chen,
  • Long Xuan,
  • Minwu Yang,
  • Hao-Yuan She,
  • Liangfang Shen,
  • Lan Deng,
  • Di Jing,
  • Liting Shi
Kang Ren
Xiangya Hospital Central South University

Corresponding Author:[email protected]

Author Profile
Lin Shen
Xiangya Hospital Central South University
Author Profile
Jianfeng Qiu
Shandong First Medical University
Author Profile
Kui Sun
Shandong First Medical University
Author Profile
Tingyin Chen
Xiangya Hospital Central South University
Author Profile
Long Xuan
Central South University Xiangya School of Medicine
Author Profile
Minwu Yang
Central South University Xiangya School of Stomatology
Author Profile
Hao-Yuan She
Central South University School of Life Sciences
Author Profile
Liangfang Shen
Xiangya Hospital Central South University
Author Profile
Lan Deng
Hunan University of Technology
Author Profile
Di Jing
Xiangya Hospital Central South University
Author Profile
Liting Shi
Shandong First Medical University
Author Profile

Abstract

Objectives: We evaluated radiotherapy planning CT-based radiomics for predicting clinical endpoints [tumor complete response (CR), 5-year overall survival (OS), hypohemoglobin, and leucopenia] after intensity-modulated radiation therapy (IMRT) in locally advanced cervical cancer (LACC). Methods: This study retrospectively collected 257 LACC patients treated with IMRT from 2014 to 2017. Patients were allocated into the training/validation sets (3:1 ratio) using proportional random sampling, resulting in the same proportion of groups in the two sets. We extracted 254 radiomic features from each of the gross target volume (GTV), pelvis, and sacral vertebrae in planning CT images. The sequentially backward elimination support vector machine algorithm was used for feature selection and endpoint prediction. Model performance was evaluated using area under the curve (AUC). Results: A combination of 10 clinicopathological parameters and 34 radiomic features achieved the best performance for predicting CR [validation balanced accuracy: 80.79%]. For OS, 54 radiomic features showed good prediction accuracy [validation balanced accuracy: 85.75%], and the threshold value of their scores can stratify patients into the low-risk and high-risk groups (P<0.001). The clinical and radiomic models were also predictive of hypohemoglobin and severe leucopenia [validation balanced accuracies: 70.96% and 69.93%]. Conclusion: This study demonstrated that combining clinicopathological parameters with CT-based radiomics had good predictive value for treatment outcomes and hematologic toxicities to radiotherapy in LACC. The prediction of clinical endpoints prior to radiotherapy may assist the radiation therapists to select the optimal therapeutic strategy with the minimal toxicity and best curative effect.
14 Feb 2022Submitted to BJOG: An International Journal of Obstetrics and Gynaecology
22 Feb 2022Submission Checks Completed
22 Feb 2022Assigned to Editor
02 Mar 2022Reviewer(s) Assigned
13 Jun 2022Review(s) Completed, Editorial Evaluation Pending
25 Jun 2022Editorial Decision: Revise Major
22 Jul 20221st Revision Received
29 Jul 2022Submission Checks Completed
29 Jul 2022Assigned to Editor
29 Jul 2022Review(s) Completed, Editorial Evaluation Pending
05 Aug 2022Editorial Decision: Revise Minor
08 Aug 20222nd Revision Received
10 Aug 2022Submission Checks Completed
10 Aug 2022Assigned to Editor
10 Aug 2022Review(s) Completed, Editorial Evaluation Pending
22 Aug 2022Editorial Decision: Accept