This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
TASC-SwinMT: Task-Adaptive Synergistic Cross-Task Swin Multi-Task Framework for CT and MRI Image Interpolation and Segmentation
School of Biomedical Engineering, Northeastern University, Shenyang 110004, China
*
Author to whom correspondence should be addressed.
Tomography 2026, 12(6), 80; https://doi.org/10.3390/tomography12060080 (registering DOI)
Submission received: 11 April 2026
/
Revised: 23 May 2026
/
Accepted: 28 May 2026
/
Published: 30 May 2026
(This article belongs to the Special Issue Cutting-Edge Applications: Artificial Intelligence and Deep Learning Revolutionizing CT and MRI)
Simple Summary
Medical CT and MRI image interpolation and segmentation are essential for clinical thoracic disease diagnosis and anatomical analysis, yet most existing methods handle these two tasks separately with redundant computation and insufficient cross-task feature mining. This study proposes TASC-SwinMT, a unified task-adaptive synergistic cross-task Swin multi-task framework for joint interpolation and segmentation. Three dedicated collaborative modules and a learnable dynamic loss are designed to enable adaptive feature modulation, fine-grained cross-task interaction, and balanced joint optimization. Evaluated on public heart MRI and lung CT datasets, TASC-SwinMT outperforms mainstream baseline and state-of-the-art models in both interpolation reconstruction and lesion segmentation, while substantially reducing computational overhead. The proposed framework provides an efficient, generalizable solution for synchronous medical image interpolation and segmentation, holding practical application potential in routine clinical thoracic imaging analysis.
Abstract
Background: Computed Tomography(CT) and Magnetic Resonance Imaging(MRI) interpolation and segmentation are critical for clinical diagnosis, anatomical quantification and personalized treatment. Most existing methods perform these two tasks separately, leading to computational redundancy and insufficient mining of shared spatial features. This study aims to construct an integrated multi-task learning framework for the synchronous processing of medical image interpolation and segmentation. Methods: We propose a unified multi-task framework named TASC-SwinMT for joint interpolation and multi-frame segmentation of CT and MRI images. It employs a shared SwinUNet encoder to extract general spatial features, matched with two task-specific decoders for frame prediction and mask generation. Three functional modules are designed for cross-task synergistic learning, and a dynamic multi-task loss function is used to balance objective optimization. Experiments are performed on Medical Segmentation Decathlon Task02_Heart and Task06_Lung datasets. Results: Our method outperforms baseline models and ablation variants in both tasks with outstanding accuracy and significantly reduced computational overhead. It exhibits superior performance in lesion boundary depiction, small object segmentation and inter-slice consistency, and anatomical prior constraints with frequency-domain modeling further enhance prediction quality. Conclusions: The cross-task feature sharing and joint optimization strategy are validated effective. The proposed TASC-SwinMT framework has favorable stability and generalization ability, providing a reliable solution for clinical medical image analysis.
