Xiaomei Wu1, Yajun Li2, Xin Chen3, Yanqi Huang4, Lan He4, Ke Zhao1, Xiaomei Huang5, Wen Zhang6, Yucun Huang6, Yexing Li7, Mengyi Dong5, Jia Huang7, Ting Xia1, Changhong Liang8, Zaiyi Liu9. 1. School of Medicine, South China University of Technology, Guangzhou, Guangdong Province, China; Department of Radiology, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, 106 Zhongshan Er Road, Guangzhou, Guangdong Province, China. 2. School of Computer Science Engineering, South China University of Technology, Guangzhou, Guangdong Province, China. 3. Department of Radiology, Guangzhou First People's Hospital, Guangzhou, Guangdong Province, China. 4. Department of Radiology, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, 106 Zhongshan Er Road, Guangzhou, Guangdong Province, China. 5. Department of Radiology, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, 106 Zhongshan Er Road, Guangzhou, Guangdong Province, China; Southern Medical University, Guangzhou, Guangdong Province, PR China. 6. Southern Medical University, Guangzhou, Guangdong Province, PR China. 7. Department of Radiology, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, 106 Zhongshan Er Road, Guangzhou, Guangdong Province, China; Shantou University, Shantou, Guangdong Province, PR China. 8. Department of Radiology, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, 106 Zhongshan Er Road, Guangzhou, Guangdong Province, China. Electronic address: cjr.lchh@vip.163.com. 9. Department of Radiology, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, 106 Zhongshan Er Road, Guangzhou, Guangdong Province, China. Electronic address: zyliu@163.com.
Abstract
RATIONALE AND OBJECTIVES: We assess the performance of a model combining a deep convolutional neural network and a hand-crafted radiomics signature for predicting KRAS status in patients with colorectal cancer (CRC). MATERIALS AND METHODS: The primary cohort consisted of 279 patients with clinicopathologically confirmed CRC between April 2011 and April 2015. Portal venous phase computed tomographic images were analyzed to extract traditional hand-crafted radiomics features as well as deep learning features. A Wilcoxon rank sum test, the minimum redundancy maximum relevance algorithm, and multivariable logistic regression analysis were used to select features and build a radiomics signature. A combined model was then developed using multivariable logistic regression analysis. An independent validation cohort of 119 patients from May 2015 to April 2016 was used to confirm the combined model's predictive performance. RESULTS: The C-index of hand-crafted radiomics signature's discriminative ability was 0.719 (95% confidence interval, CI: 0.658-0.776) for the primary cohort and 0.720 (95% CI: 0.625-0.813) for the validation cohort. The C-index of the deep radiomics signature's discriminative ability was 0.754 (95% CI: 0.696-0.813) for the primary cohort and 0.786 (95% CI: 0.702-0.863) for the validation cohort. The combined model, which merged the hand-crafted radiomics features and deep radiomics features, achieve a C-index of 0.815 (95% CI: 0.766-0.868) for the primary cohort and 0.832 (95% CI: 0.762-0.905) for the validation cohort. CONCLUSION: This study presents a model that incorporates the hand-crafted and deep radiomics signature, which can be used for individualized preoperative prediction of KRAS mutations in patients with CRC.
RATIONALE AND OBJECTIVES: We assess the performance of a model combining a deep convolutional neural network and a hand-crafted radiomics signature for predicting KRAS status in patients with colorectal cancer (CRC). MATERIALS AND METHODS: The primary cohort consisted of 279 patients with clinicopathologically confirmed CRC between April 2011 and April 2015. Portal venous phase computed tomographic images were analyzed to extract traditional hand-crafted radiomics features as well as deep learning features. A Wilcoxon rank sum test, the minimum redundancy maximum relevance algorithm, and multivariable logistic regression analysis were used to select features and build a radiomics signature. A combined model was then developed using multivariable logistic regression analysis. An independent validation cohort of 119 patients from May 2015 to April 2016 was used to confirm the combined model's predictive performance. RESULTS: The C-index of hand-crafted radiomics signature's discriminative ability was 0.719 (95% confidence interval, CI: 0.658-0.776) for the primary cohort and 0.720 (95% CI: 0.625-0.813) for the validation cohort. The C-index of the deep radiomics signature's discriminative ability was 0.754 (95% CI: 0.696-0.813) for the primary cohort and 0.786 (95% CI: 0.702-0.863) for the validation cohort. The combined model, which merged the hand-crafted radiomics features and deep radiomics features, achieve a C-index of 0.815 (95% CI: 0.766-0.868) for the primary cohort and 0.832 (95% CI: 0.762-0.905) for the validation cohort. CONCLUSION: This study presents a model that incorporates the hand-crafted and deep radiomics signature, which can be used for individualized preoperative prediction of KRAS mutations in patients with CRC.
Authors: Wei Zhang; Hongkun Yin; Zixing Huang; Jian Zhao; Haoyu Zheng; Du He; Mou Li; Weixiong Tan; Song Tian; Bin Song Journal: Cancer Med Date: 2021-05-08 Impact factor: 4.452
Authors: Ning Zhao; Yinghao Cao; Jia Yang; Hang Li; Ke Wu; Jiliang Wang; Tao Peng; Kailin Cai Journal: Front Oncol Date: 2021-06-17 Impact factor: 6.244