A New Three-stage Curriculum Learning Approach to Deep Network Based Liver Tumor Segmentation

TL;DR

This paper introduces a three-stage curriculum learning method for deep networks to improve liver tumor segmentation in medical images, effectively handling small tumor objects by progressively focusing on different features.

Contribution

It presents a novel three-stage curriculum learning framework that enhances deep network training for small object segmentation in medical imaging.

Findings

Significant improvement over cascaded methods.

Effective integration of global context and tumor features.

Single network approach simplifies the segmentation process.

Abstract

Automatic segmentation of liver tumors in medical images is crucial for the computer-aided diagnosis and therapy. It is a challenging task, since the tumors are notoriously small against the background voxels. This paper proposes a new three-stage curriculum learning approach for training deep networks to tackle this small object segmentation problem. The learning in the first stage is performed on the whole input to obtain an initial deep network for tumor segmenta-tion. Then the second stage of learning focuses the strength-ening of tumor specific features by continuing training the network on the tumor patches. Finally, we retrain the net-work on the whole input in the third stage, in order that the tumor specific features and the global context can be inte-grated ideally under the segmentation objective. Benefitting from the proposed learning approach, we only need to em-ploy one single network to segment the tumors directly. We evaluated our approach on the 2017 MICCAI Liver Tumor Segmentation challenge dataset. In the experiments, our approach exhibits significant improvement compared with the commonly used cascaded counterpart.