arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新，休息一下吧，周末愉快~~
arXiv 2309.04312cs.CV

AMLP：可调掩码病变块用于自监督医学图像分割

AMLP: Adjustable Masking Lesion Patches for Self-Supervised Medical Image Segmentation

State Key Laboratory of Reliability and Intelligence of Electrical Equipment, School of Health Sciences and Biomedical Engineering, Hebei University of Technology, Tianjin, China（河北工业大学可靠性与智能电气设备国家重点实验室，健康科学与生物医学工程学院，中国天津）；Department of Computer Science, University of Oxford, Oxford, United Kingdom（英国牛津大学计算机科学系）；institute of Logic and Computation, Vienna University of Technology, Vienna, Austria（奥地利技术大学逻辑与计算研究所）

Xiangtao Wang, Ruizhi Wang, Thomas Lukasiewicz, Zhenghua Xu

备注：
© 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

AMLP通过可调掩码策略和改进的损失函数，提升医学图像分割的自监督建模性能。

摘要：

自监督掩码图像建模（MIM）方法在分析自然图像上表现出了有希望的性能。然而，直接将此类方法应用于医学图像分割任务仍然无法取得满意的成果。挑战来自于以下事实：（i）医学图像本质上比自然图像更复杂，医学图像中的主体往往表现出更明显的轮廓特征；（ii）此外，MIM中传统的高且固定的掩码比例可能遮蔽背景，限制了可学习信息的范围。为了解决这些问题，我们提出了一种新的自监督医学图像分割框架，称为可调掩码病变块（AMLP），它采用掩码块选择（MPS）策略来识别高概率包含病变的块，以帮助模型实现精确的病变重建。为了提高MPS中块的分类，我们进一步引入相对重建损失（RRL）以更好地学习难以重建的病变块。然后，类别一致性损失（CCL）被提出，以基于重建难度对块分类进行细化，增强病变与背景之间的差异。此外，还提出了一种可调掩码比例（AMR）策略，以在训练过程中逐渐增加掩码比例，以扩大可学习的互信息范围。在两个医学分割数据集上的大量实验表明，所提出的AMLP在与最先进的自监督方法相比时表现出优越的性能；结果证明，AMLP有效解决了将掩码建模应用于医学图像和捕捉准确病变细节以用于分割任务的挑战。

英文摘要：

Self-supervised masked image modeling (MIM) methods have shown promising performances on analyzing natural images. However, directly applying such methods to medical image segmentation tasks still cannot achieve satisfactory results. The challenges arise from the facts that (i) medical images are inherently more complex compared to natural images, and the subjects in medical images often exhibit more distinct contour features; (ii) moreover, the conventional high and fixed masking ratio in MIM is likely to mask the background, limiting the scope of learnable information. To address these problems, we propose a new self-supervised medical image segmentation framework, called Adjustable Masking Lesion Patches (AMLP), which employs Masked Patch Selection~(MPS) strategy to identify patches with high probabilities of containing lesions to help model achieve precise lesion reconstruction. To improve the categorization of patches in MPS, we further introduce Relative Reconstruction Loss (RRL) to better learn hard-to-reconstruct lesion patches. Then, Category Consistency Loss (CCL) is proposed to refine patch categorization based on reconstruction difficulty, enhancing difference between lesions and backgrounds. Moreover, an Adjustable Masking Ratio (AMR) strategy is proposed to gradually increase the masking ratio over training to expand~the scope of learnable mutual information. Extensive~experiments on two medical segmentation datasets demonstrate the superior performances of the proposed AMLP w.r.t. the SOTA self-supervised methods; the results prove that AMLP effectively addresses the challenges of applying masked modeling to medical images and capturing accurate lesion details that are crucial for segmentation tasks.

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。

↑