SS-CTML: Self-Supervised Cross-Task Mutual Learning for CT Image Reconstruction

2024-12-31

AI Summary

To address the scarcity of paired training data in clinical CT reconstruction—hindering the practical deployment of supervised learning—this paper proposes a self-supervised, three-task collaborative reconstruction framework that requires no ground-truth labels. Methodologically, it introduces a novel cross-task mutual learning mechanism: leveraging the same raw scan data, it formulates three complementary reconstruction tasks—full-view, sparse-view, and limited-view CT—and jointly models them via a three-branch network. The framework integrates sinogram-domain decomposition, inter-task feature consistency constraints, and gradient-coupled optimization to enable shared semantic prior learning, thereby eliminating reliance on annotated data. Evaluated on real clinical datasets, the method substantially suppresses visual artifacts and achieves superior PSNR and SSIM compared to state-of-the-art unsupervised approaches. Both qualitative and quantitative results demonstrate new state-of-the-art performance.

Technology Category

• Machine Learning: Unsupervised & Self-Supervised Learning
• Computer Vision: Learning & Optimization for CV
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

Supervised deep-learning (SDL) techniques with paired training datasets have been widely studied for X-ray computed tomography (CT) image reconstruction. However, due to the difficulties of obtaining paired training datasets in clinical routine, the SDL methods are still away from common uses in clinical practices. In recent years, self-supervised deep-learning (SSDL) techniques have shown great potential for the studies of CT image reconstruction. In this work, we propose a self-supervised cross-task mutual learning (SS-CTML) framework for CT image reconstruction. Specifically, a sparse-view scanned and a limited-view scanned sinogram data are first extracted from a full-view scanned sinogram data, which results in three individual reconstruction tasks, i.e., the full-view CT (FVCT) reconstruction, the sparse-view CT (SVCT) reconstruction, and limited-view CT (LVCT) reconstruction. Then, three neural networks are constructed for the three reconstruction tasks. Considering that the ultimate goals of the three tasks are all to reconstruct high-quality CT images, we therefore construct a set of cross-task mutual learning objectives for the three tasks, in which way, the three neural networks can be self-supervised optimized by learning from each other. Clinical datasets are adopted to evaluate the effectiveness of the proposed framework. Experimental results demonstrate that the SS-CTML framework can obtain promising CT image reconstruction performance in terms of both quantitative and qualitative measurements.

Problem

• CT image reconstruction
• unsupervised learning
• data scarcity

Innovation

• SS-CTML
• Self-supervised Cross-task Mutual Learning
• CT Image Reconstruction