Semi-supervised Medical Image Segmentation through Dual-task Consistency

TL;DR

This paper introduces a dual-task consistency framework for semi-supervised medical image segmentation, leveraging joint prediction of segmentation and geometry-aware representations to improve accuracy with unlabeled data.

Contribution

It proposes the first dual-task consistency approach that explicitly regularizes at the task level, enhancing semi-supervised segmentation performance.

Findings

Significant performance improvement over existing methods.

Outperforms state-of-the-art semi-supervised segmentation techniques.

Effective use of unlabeled data in medical image segmentation.

Abstract

Deep learning-based semi-supervised learning (SSL) algorithms have led to promising results in medical images segmentation and can alleviate doctors' expensive annotations by leveraging unlabeled data. However, most of the existing SSL algorithms in literature tend to regularize the model training by perturbing networks and/or data. Observing that multi/dual-task learning attends to various levels of information which have inherent prediction perturbation, we ask the question in this work: can we explicitly build task-level regularization rather than implicitly constructing networks- and/or data-level perturbation-and-transformation for SSL? To answer this question, we propose a novel dual-task-consistency semi-supervised framework for the first time. Concretely, we use a dual-task deep network that jointly predicts a pixel-wise segmentation map and a geometry-aware level set representation of the target. The level set representation is converted to an approximated segmentation map through a differentiable task transform layer. Simultaneously, we introduce a dual-task consistency regularization between the level set-derived segmentation maps and directly predicted segmentation maps for both labeled and unlabeled data. Extensive experiments on two public datasets show that our method can largely improve the performance by incorporating the unlabeled data. Meanwhile, our framework outperforms the state-of-the-art semi-supervised medical image segmentation methods. Code is available at: https://github.com/Luoxd1996/DTC