Adversarial Multi-Task Learning for Liver Tumor Segmentation, Dynamic Enhancement Regression, and Classification

TL;DR

This paper introduces MTI-Net, an end-to-end multi-task learning framework that simultaneously performs liver tumor segmentation, dynamic enhancement regression, and classification, leveraging novel modules for inter-task interaction and dynamic MRI feature extraction.

Contribution

The paper presents a novel integrated framework with a task interaction module and a task-driven discriminator, effectively capturing inter-task relevance and dynamic MRI information for multiple liver tumor tasks.

Findings

High performance across all tasks on a 238-subject dataset

Effective integration of frequency and spectral domain features

Enhanced inter-task synergy improves overall accuracy

Abstract

Liver tumor segmentation, dynamic enhancement regression, and classification are critical for clinical assessment and diagnosis. However, no prior work has attempted to achieve these tasks simultaneously in an end-to-end framework, primarily due to the lack of an effective framework that captures inter-task relevance for mutual improvement and the absence of a mechanism to extract dynamic MRI information effectively. To address these challenges, we propose the Multi-Task Interaction adversarial learning Network (MTI-Net), a novel integrated framework designed to tackle these tasks simultaneously. MTI-Net incorporates Multi-domain Information Entropy Fusion (MdIEF), which utilizes entropy-aware, high-frequency spectral information to effectively integrate features from both frequency and spectral domains, enhancing the extraction and utilization of dynamic MRI data. The network also introduces a task interaction module that establishes higher-order consistency between segmentation and regression, thus fostering inter-task synergy and improving overall performance. Additionally, we designed a novel task-driven discriminator (TDD) to capture internal high-order relationships between tasks. For dynamic MRI information extraction, we employ a shallow Transformer network to perform positional encoding, which captures the relationships within dynamic MRI sequences. In experiments on a dataset of 238 subjects, MTI-Net demonstrates high performance across multiple tasks, indicating its strong potential for assisting in the clinical assessment of liver tumors. The code is available at: https://github.com/xiaojiao929/MTI-Net.