Hamid Abdollahi1, Seied Rabi Mahdavi1,2, Bahram Mofid3, Mohsen Bakhshandeh4, Abolfazl Razzaghdoust5, Afshin Saadipoor3, Kiarash Tanha6. 1. a Department of Medical Physics, School of Medicine , Iran University of Medical Sciences , Tehran , Iran. 2. b Radiation Biology Research Center, Iran University of Medical Sciences , Tehran , Iran. 3. c Department of Radiation Oncology , Shohada Tajrish Medical Center, Shahid Beheshti University of Medical Sciences , Tehran , Iran. 4. d Radiology Technology Department, Allied Medical Faculty , Shahid Beheshti University of Medical Sciences , Tehran , Iran. 5. e Urology and Nephrology Research Center, Student Research Committee, Shahid Beheshti University of Medical Sciences , Tehran , Iran. 6. f Department of Biostatistics, School of Public Health , Iran University of Medical Sciences , Tehran , Iran.
Abstract
PURPOSE: To investigate MRI radiomic analysis to assess IMRT associated rectal wall changes and also for predicting radiotherapy induced rectal toxicity. MATERIAL AND METHODS: At first, a machine learning radiomic analysis was applied on T2-weighted (T2W) and apparent diffusion coefficient (ADC) rectal wall MR images of prostate cancer patients' pre- and post-IMRT to predict rectal toxicity. Next, Wilcoxon singed ranked test was performed to find radiomic features with significant changes pre- and post-IMRT. A logistic regression classifier was used to find correlation between features with significant changes and radiation toxicity. Area under the curve (AUC) of receiver operating characteristic (ROC) curve was used in two levels of study for finding performances. RESULTS: AUCmean, 0.68 ± 0.086 and 0.61 ± 0.065 were obtained for pre- and post-IMRT T2 radiomic models, respectively. For ADC radiomic models, AUCmean was 0.58 ± 0.034 for pre-IMRT and was 0.56 ± 0.038 for post-IMRT. Wilcoxon-signed rank test revealed that 9 T2 radiomic features vary significantly post-IMRT. The AUC of logistic-regression was in the range of 0.46-0.58 for single significant features and was 0.81 when all significant features were combined. CONCLUSIONS: Pre-IMRT MR image radiomic features could predict rectal toxicity in prostate cancer patients. Radiotherapy associated complications may be assessed by studying the changes in the MR radiomic features.
PURPOSE: To investigate MRI radiomic analysis to assess IMRT associated rectal wall changes and also for predicting radiotherapy induced rectal toxicity. MATERIAL AND METHODS: At first, a machine learning radiomic analysis was applied on T2-weighted (T2W) and apparent diffusion coefficient (ADC) rectal wall MR images of prostate cancerpatients' pre- and post-IMRT to predict rectal toxicity. Next, Wilcoxon singed ranked test was performed to find radiomic features with significant changes pre- and post-IMRT. A logistic regression classifier was used to find correlation between features with significant changes and radiation toxicity. Area under the curve (AUC) of receiver operating characteristic (ROC) curve was used in two levels of study for finding performances. RESULTS: AUCmean, 0.68 ± 0.086 and 0.61 ± 0.065 were obtained for pre- and post-IMRT T2 radiomic models, respectively. For ADC radiomic models, AUCmean was 0.58 ± 0.034 for pre-IMRT and was 0.56 ± 0.038 for post-IMRT. Wilcoxon-signed rank test revealed that 9 T2 radiomic features vary significantly post-IMRT. The AUC of logistic-regression was in the range of 0.46-0.58 for single significant features and was 0.81 when all significant features were combined. CONCLUSIONS: Pre-IMRT MR image radiomic features could predict rectal toxicity in prostate cancerpatients. Radiotherapy associated complications may be assessed by studying the changes in the MR radiomic features.
Authors: Ivan Zhovannik; Johan Bussink; Alberto Traverso; Zhenwei Shi; Petros Kalendralis; Leonard Wee; Andre Dekker; Rianne Fijten; René Monshouwer Journal: Clin Transl Radiat Oncol Date: 2019-07-16
Authors: Simon K B Spohn; Alisa S Bettermann; Fabian Bamberg; Matthias Benndorf; Michael Mix; Nils H Nicolay; Tobias Fechter; Tobias Hölscher; Radu Grosu; Arturo Chiti; Anca L Grosu; Constantinos Zamboglou Journal: Theranostics Date: 2021-07-06 Impact factor: 11.556