Weixiao Liu1, Yulin Cheng2, Zaiyi Liu3, Chunling Liu3, Renee Cattell4, Xinyan Xie2, Yingyi Wang3, Xiaojun Yang3, Weitao Ye3, Cuishan Liang5, Jiao Li3, Ying Gao2, Chuan Huang6, Changhong Liang7. 1. Department of Radiology, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, No.106, Zhongshan 2nd road, Guangzhou 510080 Guangdong, PR China; Graduate College, Shantou University Medical College, Shantou, Guangdong, PR China. 2. The School of Computer Science and Engineering, South China University of Technology, Guangzhou, Guangdong, PR China. 3. Department of Radiology, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, No.106, Zhongshan 2nd road, Guangzhou 510080 Guangdong, PR China. 4. Department of Biomedical Engineering, Stony Brook University, Stony Brook, New York. 5. Department of Radiology, Foshan Fetal Medicine Institute, Foshan Maternity and Children's Healthcare Hospital Affiliated to Southern Medical University, Foshan Guangdong, PR China. 6. Department of Biomedical Engineering, Stony Brook University, Stony Brook, New York; Department of Radiology, Stony Brook Medicine, Stony Brook, New York; Department of Psychiatry, Stony Brook Medicine, Stony Brook, New York. 7. Department of Radiology, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, No.106, Zhongshan 2nd road, Guangzhou 510080 Guangdong, PR China. Electronic address: cjr.lchh@vip.163.com.
Abstract
RATIONALE AND OBJECTIVES: Ki-67 is one of the most important biomarkers of breast cancer traditionally measured invasively via immunohistochemistry. In this study, deep learning based radiomics models were established for preoperative prediction of Ki-67 status using multiparametric magnetic resonance imaging (mp-MRI). MATERIALS AND METHODS: Total of 328 eligible patients were retrospectively reviewed [training dataset (n = 230) and a temporal validation dataset (n = 98)]. Deep learning imaging features were extracted from T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), and contrast enhanced T1-weighted imaging (T1+C). Transfer learning techniques constructed four feature sets based on the individual three MR sequences and their combination (i.e., mp-MRI). Multilayer perceptron classifiers were trained for final prediction of Ki-67 status. Mann-Whitney U test compared the predictive performance of individual models. RESULTS: The area under curve (AUC) of models based on T2WI,T1+C,DWI and mp-MRI were 0.727, 0.873, 0.674, and 0.888 in the training dataset, respectively, and 0.706, 0.829, 0.643, and 0.875 in the validation dataset, respectively. The predictive performance of mp-MRI classification model in the AUC value was significantly better than that of the individual sequence model (all p< 0.01). CONCLUSION: In clinical practice, a noninvasive approach to improve the performance of radiomics in preoperative prediction of Ki-67 status can be provided by extracting breast cancer specific structural and functional features from mp-MRI images obtained from conventional scanning sequences using the advanced deep learning methods. This could further personalize medicine and computer aided diagnosis.
RATIONALE AND OBJECTIVES: Ki-67 is one of the most important biomarkers of breast cancer traditionally measured invasively via immunohistochemistry. In this study, deep learning based radiomics models were established for preoperative prediction of Ki-67 status using multiparametric magnetic resonance imaging (mp-MRI). MATERIALS AND METHODS: Total of 328 eligible patients were retrospectively reviewed [training dataset (n = 230) and a temporal validation dataset (n = 98)]. Deep learning imaging features were extracted from T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), and contrast enhanced T1-weighted imaging (T1+C). Transfer learning techniques constructed four feature sets based on the individual three MR sequences and their combination (i.e., mp-MRI). Multilayer perceptron classifiers were trained for final prediction of Ki-67 status. Mann-Whitney U test compared the predictive performance of individual models. RESULTS: The area under curve (AUC) of models based on T2WI,T1+C,DWI and mp-MRI were 0.727, 0.873, 0.674, and 0.888 in the training dataset, respectively, and 0.706, 0.829, 0.643, and 0.875 in the validation dataset, respectively. The predictive performance of mp-MRI classification model in the AUC value was significantly better than that of the individual sequence model (all p< 0.01). CONCLUSION: In clinical practice, a noninvasive approach to improve the performance of radiomics in preoperative prediction of Ki-67 status can be provided by extracting breast cancer specific structural and functional features from mp-MRI images obtained from conventional scanning sequences using the advanced deep learning methods. This could further personalize medicine and computer aided diagnosis.
Authors: Ashley M Mendez; Lauren K Fang; Claire H Meriwether; Summer J Batasin; Stéphane Loubrie; Ana E Rodríguez-Soto; Rebecca A Rakow-Penner Journal: Front Oncol Date: 2022-07-08 Impact factor: 5.738
Authors: Melissa M Chen; Admir Terzic; Anton S Becker; Jason M Johnson; Carol C Wu; Max Wintermark; Christoph Wald; Jia Wu Journal: Eur J Radiol Open Date: 2022-09-29