Guiding the classification of hepatocellular carcinoma on 3D CT-scans using deep and handcrafted radiological features

TL;DR

This paper introduces a hybrid approach combining deep learning and handcrafted radiological features to improve the classification of hepatocellular carcinoma in 3D CT scans, outperforming standard deep learning methods and matching expert radiologists.

Contribution

The study presents a novel two-step method inspired by LI-RADS that enhances HCC classification accuracy over standard deep learning models.

Findings

Improved AUC scores by 6 to 18 points over baseline deep learning models.

Outperforms non-expert radiologists in clinical validation.

Achieves results comparable to expert radiologists.

Abstract

Hepatocellular carcinoma is the most spread primary liver cancer across the world ($\sim$80\% of the liver tumors). The gold standard for HCC diagnosis is liver biopsy. However, in the clinical routine, expert radiologists provide a visual diagnosis by interpreting hepatic CT-scans according to a standardized protocol, the LI-RADS, which uses five radiological criteria with an associated decision tree. In this paper, we propose an automatic approach to predict histology-proven HCC from CT images in order to reduce radiologists' inter-variability. We first show that standard deep learning methods fail to accurately predict HCC from CT-scans on a challenging database, and propose a two-step approach inspired by the LI-RADS system to improve the performance. We achieve improvements from 6 to 18 points of AUC with respect to deep learning baselines trained with different architectures. We also provide clinical validation of our method, achieving results that outperform non-expert radiologists and are on par with expert ones.