Multi-task deep learning network to predict future macrovascular invasion in hepatocellular carcinoma

Sirui Fu; Haoran Lai; Meiyan Huang; Qiyang Li; Yao Liu; Jiawei Zhang; Jianwen Huang; Xiumei Chen; Chongyang Duan; Xiaoqun Li; Tao Wang; Xiaofeng He; Jianfeng Yan; Ligong Lu

doi:10.1016/j.eclinm.2021.101201

Multi-task deep learning network to predict future macrovascular invasion in hepatocellular carcinoma

EClinicalMedicine. 2021 Dec 9:42:101201. doi: 10.1016/j.eclinm.2021.101201. eCollection 2021 Dec.

Authors

Sirui Fu¹, Haoran Lai², Meiyan Huang^{2

3

4}, Qiyang Li⁵, Yao Liu¹, Jiawei Zhang², Jianwen Huang¹, Xiumei Chen², Chongyang Duan⁶, Xiaoqun Li⁷, Tao Wang², Xiaofeng He⁸, Jianfeng Yan⁹, Ligong Lu^{1

2}

Affiliations

¹ Zhuhai Interventional Medical Centre, Zhuhai People's Hospital (Zhuhai hospital affiliated to Jinan University), Zhuhai, China.
² School of Biomedical Engineering, Southern Medical University, Guangzhou, China.
³ Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, Guangzhou, China.
⁴ Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology, Southern Medical University, Guangzhou, China.
⁵ Department of Radiology, Shenzhen People's Hospital, Shenzhen, China.
⁶ Department of Biostatistics, School of Public Health, Southern Medical University, Guangzhou, China.
⁷ Department of Interventional Treatment, Zhongshan City People's Hospital, Zhongshan, China.
⁸ Interventional Diagnosis and Treatment Department, Nanfang Hospital, Southern Medical University, Guangzhou, China.
⁹ Department of Radiology, Yangjiang People's hospital, Yangjiang, China.

Abstract

Background: Models predicting future macrovascular invasion in hepatocellular carcinoma are constructed to assist timely interventions.

Methods: A total of 366 HCC cases were retrospectively collected from five Chinese hospitals between April 2007 and November 2016: the training dataset comprised 281 patients from four hospitals; the external validation dataset comprised 85 patients from another hospital. Multi-task deep learning network-based models were constructed to predict future macrovascular invasion. The discrimination, calibration, and decision curves were compared to identify the best model. We compared the time to macrovascular invasion and overall survival using the best model and related image heterogeneity scores (H-score). Then, we determined the need for a segmentation subnet or the replacement deep learning algorithm by logistic regression in screening clinical/radiological factors. Finally, an applet was constructed for future application.

Findings: The best model combined clinical/radiological factors and radiomic features. It achieved best discrimination (areas under the curve: 0·877 in the training dataset and 0·836 in the validation dataset), calibration, and decision curve. Its performance was not affected by the treatments and disease stages. The subgroups had statistical significance for time to macrovascular invasion (training: hazard ratio [HR] = 0·073, 95% confidence interval [CI]: 0·032-0·167, p < 0·001 and validation: HR = 0·090, 95%CI: 0·022-0·366, p < 0·001) and overall survival (training: HR = 0·344, 95%CI: 0·246-0·547, p < 0·001 and validation: HR = 0·489, 95%CI: 0·279 - 0·859, p = 0·003). Similar results were achieved when the patients were subdivided by the H-score. The subnet for segmentation and end-to-end deep learning algorithms improved the performance of the model.

Interpretation: Our multi-task deep learning network-based model successfully predicted future macrovascular invasion. In high-risk populations, besides the current first-line treatments, more therapies may be explored for macrovascular invasion.

Keywords: AUC, AUC areas under curve; BCLC, Barcelona Clinic Liver Cancer; CI, confidence interval; CT, computed tomography; Clinical factors; HCC, hepatocellular carcinoma; HR, hazard ratio; Hepatocellular carcinoma; IDI, integrated discrimination improvement; MTnet, multi-task deep learning neural network; Macrovascular invasion; Multi-task deep learning; NRI, net reclassification improvement; OS, overall survival; PD, disease progression; ROC, receiver operating characteristic; Radiological characteristics; TACE, transarterial chemoembolization.