Deep Learning-Based Prediction of Future Extrahepatic Metastasis and Macrovascular Invasion in Hepatocellular Carcinoma

Sirui Fu,1,2,&ast; Meiqing Pan,2,3,&ast; Jie Zhang,4,&ast; Hui Zhang,2,3,5,&ast; Zhenchao Tang,2,3,5 Yong Li,1 Wei Mu,2,3,5 Jianwen Huang,1 Di Dong,3 Chongyang Duan,6 Xiaoqun Li,7 Shuo Wang,2,3 Xudong Chen,8 Xiaofeng He,9 Jianfeng Yan,10 Ligong Lu,1 Jie Tian2,3,5,11 1Zhuhai Interventional Medical Centre, Zhuhai People’s Hospital (Zhuhai Hospital Affiliated with Jinan University), Zhuhai, People’s Republic of China; 2Beijing Advanced Innovation Centre for Big Data-Based Precision Medicine, School of Engineering Medicine, Beihang University, Beijing, People’s Republic of China; 3CAS Key Laboratory of Molecular Imaging, Beijing Key Laboratory of Molecular Imaging, The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, People’s Republic of China; 4Department of Radiology, Zhuhai People’s Hospital (Zhuhai Hospital Affiliated with Jinan University), Zhuhai, People’s Republic of China; 5Key Laboratory of Big Data-Based Precision Medicine (Beihang University), Ministry of Industry and Information Technology, Beijing, People’s Republic of China; 6Department of Biostatistics, School of Public Health, Southern Medical University, Guangzhou, People’s Republic of China; 7Department of Interventional Treatment, Zhongshan City People’s Hospital, Zhongshan, People’s Republic of China; 8Department of Radiology, Shenzhen People’s Hospital, Shenzhen, People’s Republic of China; 9Interventional Diagnosis and Treatment Department, Nanfang Hospital, Southern Medical University, Guangzhou, People’s Republic of China; 10Department of Radiology, Yangjiang People’s Hospital, Yangjiang, People’s Republic of China; 11University of Chinese Academy of Sciences, Beijing, People’s Republic of China&ast;These authors contributed equally to this workCorrespondence: Jie TianBeijing Advanced Innovation Centre for Big Data-Based Precision Medicine, School of Engineering Medicine, Beihang University, Beijing, 100191, People’s Republic of ChinaEmail tian@ieee.orgLigong LuZhuhai Interventional Medical Centre, Zhuhai People’s Hospital (Zhuhai Hospital Affiliated with Jinan University), No. 79 Kangning Road, Zhuhai, 519000, Guangdong Province, People’s Republic of ChinaEmail llg0902@sina.comPurpose: For timely treatment of extrahepatic metastasis and macrovascular invasion (aggressive progressive disease [PD]) in hepatocellular carcinoma, models aimed at stratifying the risks of subsequent aggressive PD should be constructed.Patients and Methods: After dividing 332 patients from five hospitals into training (n = 236) and validation (n = 96) datasets, non-invasive models, including clinical/semantic factors (ModelCS), deep learning radiomics (ModelD), and both (ModelCSD), were constructed to stratify patients according to the risk of aggressive PD. We examined the discrimination and calibration; similarly, we plotted a decision curve and devised a nomogram. Furthermore, we performed analyses of subgroups who received different treatments or those in different disease stages and compared time to aggressive PD and overall survival in the high- and low-risk subgroups.Results: Among the constructed models, ModelCSD, combining clinical/semantic factors and deep learning radiomics, outperformed ModelCS and ModelD (areas under the curve [AUCs] for the training dataset: 0.741, 0.815, and 0.856; validation dataset: 0.780, 0.836, and 0.862), with statistical difference per the net reclassification improvement, the integrated discrimination improvement, and/or the DeLong test in both datasets. Besides, ModelCSD had the best calibration and decision curves. The performance of ModelCSD was not affected by treatment types (AUC: resection = 0.839; transarterial chemoembolization = 0.895; p = 0.183) or disease stages (AUC: BCLC [Barcelona Clinic Liver Cancer] stage 0 and A = 0.827; BCLC stage AB &B = 0.861; p = 0.537). Moreover, the high-risk group had a significantly shorter median time to aggressive PD than the low-risk group (training dataset hazard ratio [HR] = 0.108, p < 0.001; validation dataset HR = 0.058, p < 0.001) and poorer overall survival (training dataset HR = 0.357, p < 0.001; validation dataset HR = 0.204, p < 0.001).Conclusion: Our deep learning-based model successfully stratified the risks of aggressive PD. In the high-risk population, current guideline indicates that first-line treatments are insufficient to prevent extrahepatic metastasis and macrovascular invasion and ensure survival benefits, so more therapies may be explored for these patients.Keywords: aggressive disease progression, deep learning radiomics, clinical factors, high-risk, risk predictio