Liver Fibrosis and NAS scoring from CT images using self-supervised learning and texture encoding

TL;DR

This paper introduces a self-supervised learning approach combined with texture encoding to accurately predict liver fibrosis and NAS scores from CT images, reducing reliance on large annotated datasets and transfer learning.

Contribution

It presents a novel self-supervised method for liver disease scoring from CT images that performs well with limited data and incorporates texture encoding for improved accuracy.

Findings

Self-supervised model outperforms transfer learning methods.

Texture encoding enhances prediction accuracy.

Effective with small datasets of 30 patients.

Abstract

Non-alcoholic fatty liver disease (NAFLD) is one of the most common causes of chronic liver diseases (CLD) which can progress to liver cancer. The severity and treatment of NAFLD is determined by NAFLD Activity Scores (NAS)and liver fibrosis stage, which are usually obtained from liver biopsy. However, biopsy is invasive in nature and involves risk of procedural complications. Current methods to predict the fibrosis and NAS scores from noninvasive CT images rely heavily on either a large annotated dataset or transfer learning using pretrained networks. However, the availability of a large annotated dataset cannot be always ensured andthere can be domain shifts when using transfer learning. In this work, we propose a self-supervised learning method to address both problems. As the NAFLD causes changes in the liver texture, we also propose to use texture encoded inputs to improve the performance of the model. Given a relatively small dataset with 30 patients, we employ a self-supervised network which achieves better performance than a network trained via transfer learning. The code is publicly available at https://github.com/ananyajana/fibrosis_code.