I-Cheng Lee1,2, Jo-Yu Huang3, Ting-Chun Chen3, Chia-Heng Yen3,4, Nai-Chi Chiu5, Hsuen-En Hwang5, Jia-Guan Huang6, Chien-An Liu5, Gar-Yang Chau7, Rheun-Chuan Lee5, Yi-Ping Hung8, Yee Chao8, Shinn-Ying Ho3,9,10,11, Yi-Hsiang Huang1,2,12. 1. Division of Gastroenterology and Hepatology, Department of Medicine, Taipei Veterans General Hospital, Taipei, Taiwan. 2. Faculty of Medicine, National Yang Ming Chiao Tung University School of Medicine, Taipei, Taiwan. 3. Institute of Bioinformatics and Systems Biology, National Yang Ming Chiao Tung University, Hsinchu, Taiwan. 4. Institute of Computer Science and Engineering, National Yang Ming Chiao Tung University, Hsinchu, Taiwan. 5. Department of Radiology, Taipei Veterans General Hospital, Taipei, Taiwan. 6. National Taiwan University School of Medicine, Taipei, Taiwan. 7. Department of Surgery, Taipei Veterans General Hospital, Taipei, Taiwan. 8. Cancer Center, Taipei Veterans General Hospital, Taipei, Taiwan. 9. Department of Biological Science and Technology, National Yang Ming Chiao Tung University, Hsinchu, Taiwan. 10. Center for Intelligent Drug Systems and Smart Bio-Devices (IDS2B), National Yang Ming Chiao Tung University, Hsinchu, Taiwan. 11. College of Health Sciences, Kaohsiung Medical University, Kaohsiung, Taiwan. 12. Institute of Clinical Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan.
Abstract
BACKGROUND AND AIMS: Current prediction models for early recurrence of hepatocellular carcinoma (HCC) after surgical resection remain unsatisfactory. The aim of this study was to develop evolutionary learning-derived prediction models with interpretability using both clinical and radiomic features to predict early recurrence of HCC after surgical resection. METHODS: Consecutive 517 HCC patients receiving surgical resection with available contrast-enhanced computed tomography (CECT) images before resection were retrospectively enrolled. Patients were randomly assigned to a training set (n = 362) and a test set (n = 155) in a ratio of 7:3. Tumor segmentation of all CECT images including noncontrast phase, arterial phase, and portal venous phase was manually performed for radiomic feature extraction. A novel evolutionary learning-derived method called genetic algorithm for predicting recurrence after surgery of liver cancer (GARSL) was proposed to design prediction models for early recurrence of HCC within 2 years after surgery. RESULTS: A total of 143 features, including 26 preoperative clinical features, 5 postoperative pathological features, and 112 radiomic features were used to develop GARSL preoperative and postoperative models. The area under the receiver operating characteristic curves (AUCs) for early recurrence of HCC within 2 years were 0.781 and 0.767, respectively, in the training set, and 0.739 and 0.741, respectively, in the test set. The accuracy of GARSL models derived from the evolutionary learning method was significantly better than models derived from other well-known machine learning methods or the early recurrence after surgery for liver tumor (ERASL) preoperative (AUC = 0.687, p < 0.001 vs. GARSL preoperative) and ERASL postoperative (AUC = 0.688, p < 0.001 vs. GARSL postoperative) models using clinical features only. CONCLUSION: The GARSL models using both clinical and radiomic features significantly improved the accuracy to predict early recurrence of HCC after surgical resection, which was significantly better than other well-known machine learning-derived models and currently available clinical models.
BACKGROUND AND AIMS: Current prediction models for early recurrence of hepatocellular carcinoma (HCC) after surgical resection remain unsatisfactory. The aim of this study was to develop evolutionary learning-derived prediction models with interpretability using both clinical and radiomic features to predict early recurrence of HCC after surgical resection. METHODS: Consecutive 517 HCC patients receiving surgical resection with available contrast-enhanced computed tomography (CECT) images before resection were retrospectively enrolled. Patients were randomly assigned to a training set (n = 362) and a test set (n = 155) in a ratio of 7:3. Tumor segmentation of all CECT images including noncontrast phase, arterial phase, and portal venous phase was manually performed for radiomic feature extraction. A novel evolutionary learning-derived method called genetic algorithm for predicting recurrence after surgery of liver cancer (GARSL) was proposed to design prediction models for early recurrence of HCC within 2 years after surgery. RESULTS: A total of 143 features, including 26 preoperative clinical features, 5 postoperative pathological features, and 112 radiomic features were used to develop GARSL preoperative and postoperative models. The area under the receiver operating characteristic curves (AUCs) for early recurrence of HCC within 2 years were 0.781 and 0.767, respectively, in the training set, and 0.739 and 0.741, respectively, in the test set. The accuracy of GARSL models derived from the evolutionary learning method was significantly better than models derived from other well-known machine learning methods or the early recurrence after surgery for liver tumor (ERASL) preoperative (AUC = 0.687, p < 0.001 vs. GARSL preoperative) and ERASL postoperative (AUC = 0.688, p < 0.001 vs. GARSL postoperative) models using clinical features only. CONCLUSION: The GARSL models using both clinical and radiomic features significantly improved the accuracy to predict early recurrence of HCC after surgical resection, which was significantly better than other well-known machine learning-derived models and currently available clinical models.
Authors: Nazario Portolani; Arianna Coniglio; Sara Ghidoni; Mara Giovanelli; Anna Benetti; Guido Alberto Massimo Tiberio; Stefano Maria Giulini Journal: Ann Surg Date: 2006-02 Impact factor: 12.969