Joint Liver Lesion Segmentation and Classification via Transfer Learning

TL;DR

This paper explores combining transfer learning and joint learning for improved liver lesion segmentation and classification in CT images, demonstrating significant performance gains over existing methods.

Contribution

It introduces a simple joint learning framework that outperforms Y-Net, enhancing both segmentation and classification accuracy in liver lesion analysis.

Findings

Joint learning improves segmentation and classification results.

The proposed framework achieves 10% higher classification accuracy than Y-Net.

Transfer learning from MICCAI 2017 LiTS dataset benefits small medical imaging datasets.

Abstract

Transfer learning and joint learning approaches are extensively used to improve the performance of Convolutional Neural Networks (CNNs). In medical imaging applications in which the target dataset is typically very small, transfer learning improves feature learning while joint learning has shown effectiveness in improving the network's generalization and robustness. In this work, we study the combination of these two approaches for the problem of liver lesion segmentation and classification. For this purpose, 332 abdominal CT slices containing lesion segmentation and classification of three lesion types are evaluated. For feature learning, the dataset of MICCAI 2017 Liver Tumor Segmentation (LiTS) Challenge is used. Joint learning shows improvement in both segmentation and classification results. We show that a simple joint framework outperforms the commonly used multi-task architecture (Y-Net), achieving an improvement of 10% in classification accuracy, compared to a 3% improvement with Y-Net.