Liver imaging features by convolutional neural network to predict the metachronous liver metastasis in stage I-III colorectal cancer patients based on preoperative abdominal CT scan

BMC Bioinformatics

So Yeon Kim¹  Dokyoon Kim²  Hua Sun Kim³  Kyu Joo Park⁴  Eun Kyung Choe⁵  Sangwoo Lee⁶ 

[1] Department of Biostatistics, Epidemiology & Informatics, Perelman School of Medicine, University of Pennsylvania, B304 Richards Building, 3700 Hamilton Walk, 19104-6116, Philadelphia, PA, USA;Department of Software and Computer Engineering, Ajou University, 16499, Suwon, South Korea;Department of Biostatistics, Epidemiology & Informatics, Perelman School of Medicine, University of Pennsylvania, B304 Richards Building, 3700 Hamilton Walk, 19104-6116, Philadelphia, PA, USA;Institute for Biomedical Informatics, University of Pennsylvania, 19104, Philadelphia, PA, USA;Department of Radiology, Seoul National University College of Medicine, 03080, Seoul, South Korea;Department of Surgery, Seoul National University College of Medicine, 03080, Seoul, South Korea;Department of Surgery, Seoul National University Hospital Healthcare System Gangnam Center, 06236, Seoul, South Korea;Department of Biostatistics, Epidemiology & Informatics, Perelman School of Medicine, University of Pennsylvania, B304 Richards Building, 3700 Hamilton Walk, 19104-6116, Philadelphia, PA, USA;Division of Future Convergent, The Cyber University of Korea, 03051, Seoul, South Korea;

关键词: Radiomics;    Colorectal cancer;    Convolutional neural network;    Artificial intelligence;   

DOI  :  10.1186/s12859-020-03686-0

来源: Springer

【 摘 要 】

BackgroundIntroducing deep learning approach to medical images has rendered a large amount of un-decoded information into usage in clinical research. But mostly, it has been focusing on the performance of the prediction modeling for disease-related entity, but not on the clinical implication of the feature itself. Here we analyzed liver imaging features of abdominal CT images collected from 2019 patients with stage I – III colorectal cancer (CRC) using convolutional neural network (CNN) to elucidate its clinical implication in oncological perspectives.ResultsCNN generated imaging features from the liver parenchyma. Dimension reduction was done for the features by principal component analysis. We designed multiple prediction models for 5-year metachronous liver metastasis (5YLM) using combinations of clinical variables (age, sex, T stage, N stage) and top principal components (PCs), with logistic regression classification. The model using “1st PC (PC1) + clinical information” had the highest performance (mean AUC = 0.747) to predict 5YLM, compared to the model with clinical features alone (mean AUC = 0.709). The PC1 was independently associated with 5YLM in multivariate analysis (beta = − 3.831, P < 0.001). For the 5-year mortality rate, PC1 did not contribute to an improvement to the model with clinical features alone. For the PC1, Kaplan-Meier plots showed a significant difference between PC1 low vs. high group. The 5YLM-free survival of low PC1 was 89.6% and the high PC1 was 95.9%. In addition, PC1 had a significant correlation with sex, body mass index, alcohol consumption, and fatty liver status.ConclusionThe imaging features combined with clinical information improved the performance compared to the standardized prediction model using only clinical information. The liver imaging features generated by CNN may have the potential to predict liver metastasis. These results suggest that even though there were no liver metastasis during the primary colectomy, the features of liver imaging can impose characteristics that could be predictive for metachronous liver metastasis.

【 授权许可】

CC BY