Semi-Supervised Biomedical Image Segmentation via Diffusion Models and Teacher-Student Co-Training

2025-04-02

AI Summary

To address the limited generalizability of supervised models in medical image segmentation due to scarce annotated data, this paper proposes a semi-supervised framework integrating denoising diffusion probabilistic models (DDPMs) with teacher–student collaborative training. Its key contributions are: (1) the first application of DDPMs to generate semantic segmentation masks, enabling structure-aware pseudo-label modeling; (2) a noise-reconstruction cycle-consistency pretraining mechanism to enhance the teacher model’s unsupervised representation learning capability; and (3) a multi-round iterative pseudo-label refinement pipeline incorporating confidence-based filtering and cross-modality consistency constraints. Evaluated on multiple cross-modality medical segmentation benchmarks, the method achieves over 96% of fully supervised performance using only 10% labeled data, significantly outperforming state-of-the-art semi-supervised approaches.

Technology Category

• Machine Learning: Semi-Supervised Learning
• Computer Vision: Diffusion Models for Vision
• Search and Optimization: Learning to Search

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Supervised deep learning for semantic segmentation has achieved excellent results in accurately identifying anatomical and pathological structures in medical images. However, it often requires large annotated training datasets, which limits its scalability in clinical settings. To address this challenge, semi-supervised learning is a well-established approach that leverages both labeled and unlabeled data. In this paper, we introduce a novel semi-supervised teacher-student framework for biomedical image segmentation, inspired by the recent success of generative models. Our approach leverages denoising diffusion probabilistic models (DDPMs) to generate segmentation masks by progressively refining noisy inputs conditioned on the corresponding images. The teacher model is first trained in an unsupervised manner using a cycle-consistency constraint based on noise-corrupted image reconstruction, enabling it to generate informative semantic masks. Subsequently, the teacher is integrated into a co-training process with a twin-student network. The student learns from ground-truth labels when available and from teacher-generated pseudo-labels otherwise, while the teacher continuously improves its pseudo-labeling capabilities. Finally, to further enhance performance, we introduce a multi-round pseudo-label generation strategy that iteratively improves the pseudo-labeling process. We evaluate our approach on multiple biomedical imaging benchmarks, spanning multiple imaging modalities and segmentation tasks. Experimental results show that our method consistently outperforms state-of-the-art semi-supervised techniques, highlighting its effectiveness in scenarios with limited annotated data. The code to replicate our experiments can be found at https://github.com/ciampluca/diffusion_semi_supervised_biomedical_image_segmentation

Problem

• Reducing reliance on large annotated medical image datasets
• Improving segmentation accuracy with limited labeled data
• Enhancing pseudo-label generation via diffusion models

Innovation

• Uses diffusion models for mask generation
• Implements teacher-student co-training framework
• Introduces multi-round pseudo-label refinement