arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2312.07489cs.CV
收藏

NearbyPatchCL:利用邻近补丁实现全玻片图像中自监督补丁级多类别分类

NearbyPatchCL: Leveraging Nearby Patches for Self-Supervised Patch-Level Multi-Class Classification in Whole-Slide Images

University of Science, VNU-HCM(越南胡志明市国家大学理学院);Vietnam National University, Ho Chi Minh City(越南胡志明市国家大学)

Gia-Bao Le, Van-Tien Nguyen, Trung-Nghia Le, Minh-Triet Tran

AI总结:

针对全玻片图像补丁级分类中类别不平衡导致的表征不稳定问题,提出NearbyPatchCL自监督方法,以邻近补丁为正样本结合解耦对比损失,仅用1%标注数据即可达到媲美全监督的效果,还构建了犬类皮肤癌组织学新基准数据集。

摘要:

全玻片图像(WSI)分析在癌症诊断与治疗中发挥着关键作用。为满足这一关键任务的需求,自监督学习(SSL)方法已成为一种宝贵的资源,其优势在于无需大量标注——部署监督方法所需的标注既昂贵又耗时。然而,补丁级表征的性能可能存在不稳定性,这主要源于WSI内补丁选择导致的类别不平衡问题。本文提出邻近补丁对比学习(NearbyPatchCL),这是一种新型自监督学习方法,它将邻近补丁作为正样本,并采用解耦对比损失实现鲁棒的表征学习。实验表明,该方法在补丁级多类别分类的下游任务中性能有切实提升。此外,我们基于犬类皮肤癌组织学(Canine Cutaneous Cancer Histology)来源的WSI整理了一个新数据集,为严格评估补丁级多类别分类方法建立了基准。大量实验显示,我们的方法以87.56%的top-1分类准确率,显著优于监督基线和当前最优的SSL方法。此外,该方法仅使用1%的标注数据就取得了相当的结果,与其他方法需要100%标注数据的要求形成鲜明对比。源代码:https://github.com/nvtien457/NearbyPatchCL

英文摘要:

Whole-slide image (WSI) analysis plays a crucial role in cancer diagnosis and treatment. In addressing the demands of this critical task, self-supervised learning (SSL) methods have emerged as a valuable resource, leveraging their efficiency in circumventing the need for a large number of annotations, which can be both costly and time-consuming to deploy supervised methods. Nevertheless, patch-wise representation may exhibit instability in performance, primarily due to class imbalances stemming from patch selection within WSIs. In this paper, we introduce Nearby Patch Contrastive Learning (NearbyPatchCL), a novel self-supervised learning method that leverages nearby patches as positive samples and a decoupled contrastive loss for robust representation learning. Our method demonstrates a tangible enhancement in performance for downstream tasks involving patch-level multi-class classification. Additionally, we curate a new dataset derived from WSIs sourced from the Canine Cutaneous Cancer Histology, thus establishing a benchmark for the rigorous evaluation of patch-level multi-class classification methodologies. Intensive experiments show that our method significantly outperforms the supervised baseline and state-of-the-art SSL methods with top-1 classification accuracy of 87.56%. Our method also achieves comparable results while utilizing a mere 1% of labeled data, a stark contrast to the 100% labeled data requirement of other approaches. Source code: https://github.com/nvtien457/NearbyPatchCL

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。

↑