Prediction of early recurrence of hepatocellular carcinoma after resection using digital pathology images assessed by machine learning

Abstract

Hepatocellular carcinoma (HCC) is a representative primary liver cancer caused by long-term and repetitive liver injury. Surgical resection is generally selected as the radical cure treatment. Because the early recurrence of HCC after resection is associated with low overall survival, the prediction of recurrence after resection is clinically important. However, the pathological characteristics of the early recurrence of HCC have not yet been elucidated. We attempted to predict the early recurrence of HCC after resection based on digital pathologic images of hematoxylin and eosin-stained specimens and machine learning applying a support vector machine (SVM). The 158 HCC patients meeting the Milan criteria who underwent surgical resection were included in this study. The patients were categorized into three groups: Group I, patients with HCC recurrence within 1 year after resection (16 for training and 23 for test); Group II, patients with HCC recurrence between 1 and 2 years after resection (22 and 28); and Group III, patients with no HCC recurrence within 4 years after resection (31 and 38). The SVM-based prediction method separated the three groups with 89.9% (80/89) accuracy. Prediction of Groups I was consistent for all cases, while Group II was predicted to be Group III in one case, and Group III was predicted to be Group II in 8 cases. The use of digital pathology and machine learning could be used for highly accurate prediction of HCC recurrence after surgical resection, especially that for early recurrence. Currently, in most cases after HCC resection, regular blood tests and diagnostic imaging are used for follow-up observation; however, the use of digital pathology coupled with machine learning offers potential as a method for objective postoprative follow-up observation.

Development of Models to Predict Postoperative Complications for Hepatitis B Virus-Related Hepatocellular Carcinoma

“…However, associations between these predictors were detected as well. A high HBV DNA level was an independent risk factor of microvascular invasion, and HBcAb-positive HCC was much bigger, more often involved with vascular invasion and elevated AFP ( 50 , 56 ). In this case, if all possible clinical variables are not included in the candidates, it is impossible to determine the truly independent predictors.…”

“…Although the prediction models for early recurrence after liver resection of HCC had been built a lot ( 48 – 50 ), they are seldom derived from comprehensive candidate variables potentially relevant to HBV-related HCC. In our study, the third model for prediction of early recurrence of HCC was constructed by incorporating eight parameters from HBV-related marks, surgical conditions, pathological examination, preoperative and postoperative laboratory results.…”

Experimental Models of Hepatocellular Carcinoma—A Preclinical Perspective

“…Additionally, the authors constructed a risk heat map which offers visual insight into the HCC recurrence risk in different years [190]. Saito et al designed a model for predicting the early recurrence of HCC based on images of hematoxylin-eosin (HE)-stained specimens and ML using a support vector machine, which offered a 89.9% accuracy rate [191].…”

Current updates in machine learning in the prediction of therapeutic outcome of hepatocellular carcinoma: what should we know?

“…The predictive variables within the BN model are based on the clinician's experience and knowledge, and the associated relationship between variables and outcome is not always clear; therefore, the performance of the BN model is generally confusing. Unlike ANN and BN, RF and SVM can be used to either select variables or develop models [48][49][50][51][52][53][54]. Wang et al [52] used the RF algorithm to select 30 radiomic features from 3144 MR texture features and developed a predictive RSF model for the 5-year survival of HCC following surgical resection with an area under curve (AUC) of 0.980.…”