Ensemble learning based on efficient features combination can predict the outcome of recurrence-free survival in patients with hepatocellular carcinoma within three years after surgery

Wang, Liyang1; Wu, Meilong2,3; Zhu, Chengzhan4; Li, Rui4; Bao, Shiyun2,3; Yang, Shizhong5; Dong, Jiahong1

2022-11-10

10.3389/fonc.2022.1019009

Frontiers in Oncology   Impact Factor & Quartile

2234-943X

Preoperative prediction of recurrence outcome in hepatocellular carcinoma (HCC) facilitates physicians' clinical decision-making. Preoperative imaging and related clinical baseline data of patients are valuable for evaluating prognosis. With the widespread application of machine learning techniques, the present study proposed the ensemble learning method based on efficient feature representations to predict recurrence outcomes within three years after surgery. Radiomics features during arterial phase (AP) and clinical data were selected for training the ensemble models. In order to improve the efficiency of the process, the lesion area was automatically segmented by 3D U-Net. It was found that the mIoU of the segmentation model was 0.8874, and the Light Gradient Boosting Machine (LightGBM) was the most superior, with an average accuracy of 0.7600, a recall of 0.7673, a F-1 score of 0.7553, and an AUC of 0.8338 when inputting radiomics features during AP and clinical baseline indicators. Studies have shown that the proposed strategy can relatively accurately predict the recurrence outcome within three years, which is helpful for physicians to evaluate individual patients before surgery.

recurrence prediction efficient features ensemble learning hepatocellular carcinoma surgery

SCI

English

Others

[82090052] ; [82090050] ; [81930119] ; [2019-I2M-5-056]

Oncology

Oncology

WOS:000889501000001

FRONTIERS MEDIA SA

Web of Science

1.Tsinghua Univ, Sch Clin Med, Beijing, Peoples R China
2.Jinan Univ, Shenzhen Peoples Hosp, Dept Gen Surg, Div Hepatobiliary & Pancreas Surg,Clin Med Coll 2, Shenzhen, Guangdong, Peoples R China
3.Southern Univ Sci & Technol, Affiliated Hosp 1, Shenzhen, Guangdong, Peoples R China
4.Affiliated Hosp Qingdao Univ, Dept Pediat Surg, Qingdao, Peoples R China
5.Tsinghua Univ, Beijing Tsinghua Changgung Hosp, Hepatopancreatobiliary Ctr, Sch Clin Med, Beijing, Peoples R China

Wang, Liyang,Wu, Meilong,Zhu, Chengzhan,et al. Ensemble learning based on efficient features combination can predict the outcome of recurrence-free survival in patients with hepatocellular carcinoma within three years after surgery[J]. Frontiers in Oncology,2022,12.

Wang, Liyang.,Wu, Meilong.,Zhu, Chengzhan.,Li, Rui.,Bao, Shiyun.,...&Dong, Jiahong.(2022).Ensemble learning based on efficient features combination can predict the outcome of recurrence-free survival in patients with hepatocellular carcinoma within three years after surgery.Frontiers in Oncology,12.

Wang, Liyang,et al."Ensemble learning based on efficient features combination can predict the outcome of recurrence-free survival in patients with hepatocellular carcinoma within three years after surgery".Frontiers in Oncology 12(2022).