arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2504.01547cs.CV
收藏

半监督生物医学图像分割:通过扩散模型和教师-学生协同训练

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

Luca Ciampi, Gabriele Lagani, Giuseppe Amato, Fabrizio Falchi

AI总结:

本文提出了一种基于扩散模型的半监督生物医学图像分割框架,通过教师-学生协同训练和多轮伪标签生成策略,在有限标注数据下提升分割性能。

摘要:

监督深度学习在准确识别医学图像中的解剖和病理结构方面取得了优异成果。然而,它通常需要大量的标注训练数据集,这限制了其在临床环境中的可扩展性。为了解决这一挑战,半监督学习是一种已建立的方法,它利用了标记和未标记的数据。在本文中,我们介绍了一种新的半监督教师-学生框架,用于生物医学图像分割,灵感来自于生成模型最近的成功。我们的方法利用去噪扩散概率模型(DDPMs)通过逐步细化嘈杂输入并根据相应的图像进行条件生成来生成分割掩码。教师模型首先通过基于噪声损坏图像重建的循环一致性约束以无监督的方式进行训练,使其能够生成信息丰富的语义掩码。随后,教师被整合到双学生网络的协同训练过程中。学生在有可用的地面真实标签时学习,否则从教师生成的伪标签中学习,而教师不断改进其伪标签能力。最后,为了进一步提高性能,我们引入了一种多轮伪标签生成策略,该策略通过迭代改进伪标签过程。我们在多个生物医学成像基准上评估了我们的方法,涵盖了多种成像模态和分割任务。实验结果表明,我们的方法在标注数据有限的情况下始终优于最先进的半监督技术,突显了其有效性。复制我们实验的代码可在https://github.com/ciampluca/diffusion_semi_supervised_biomedical_image_segmentation找到。

英文摘要:

Supervised deep learning achieves strong performance in biomedical image segmentation but relies on costly pixel-wise annotations, motivating semi-supervised approaches that exploit unlabeled data. We introduce a diffusion-based teacher--student framework in which segmentation predictions are used to condition image denoising, encouraging the production of more informative pseudo-labels. The teacher is first pretrained through an unsupervised reconstruction task using diffusion-style corruption, timestep conditioning, and denoising. Starting from a corrupted empty mask, the model predicts an intermediate segmentation that conditions image denoising, encouraging the predicted mask to capture structural information useful for recovering the original image. The resulting teacher is then co-trained with a student using supervised segmentation on labeled samples and cross pseudo-supervision on unlabeled data. We further introduce a multi-round extension during co-training, in which the teacher generates multiple stochastic image reconstructions and corresponding segmentation predictions, providing additional reconstruction and alignment signals to improve its pseudo-labels. We evaluate the proposed framework on three public 2D biomedical segmentation datasets and a 3D left atrial segmentation benchmark. Across several labeling regimes, our method achieves competitive or superior performance compared with state-of-the-art semi-supervised approaches, with the largest gains observed under severe label scarcity.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑