使用 Rein 微调视觉基础模型进行跨器官和跨扫描仪腺癌分割
Cross-Organ and Cross-Scanner Adenocarcinoma Segmentation using Rein to Fine-tune Vision Foundation Models
AI总结：
本文提出使用 Rein 微调方法高效微调 ConvNeXt 和 DINOv2 等视觉基础模型，以解决跨器官和跨扫描仪腺癌分割中的领域差异问题，并在 COSAS2024 挑战赛中取得优异分数。
摘要：
近年来，数字病理学领域的肿瘤分割取得了显著进展。然而，器官、组织制备方法和图像采集过程的差异可能导致数字病理图像之间出现领域差异。为了解决这一问题，本文使用 Rein 这一微调方法，以参数化且高效的方式微调多种视觉基础模型（VFMs），用于 MICCAI 2024 跨器官和跨扫描仪腺癌分割挑战赛（COSAS2024）。Rein 的核心由一组可学习的 token 组成，这些 token 直接与实例相关联，在每一层中提升实例级别的功能。在 COSAS2024 挑战赛的数据环境下，大量实验表明，经过 Rein 微调的视觉基础模型取得了令人满意的结果。具体而言，我们使用 Rein 微调了 ConvNeXt 和 DINOv2。我们的团队使用前者在任务1的初步测试阶段和最终测试阶段分别获得了 0.7719 和 0.7557 的分数，而后者在任务2的初步测试阶段和最终测试阶段分别获得了 0.8848 和 0.8192 的分数。代码可在 GitHub 上获取。
英文摘要：
In recent years, significant progress has been made in tumor segmentation within the field of digital pathology. However, variations in organs, tissue preparation methods, and image acquisition processes can lead to domain discrepancies among digital pathology images. To address this problem, in this paper, we use Rein, a fine-tuning method, to parametrically and efficiently fine-tune various vision foundation models (VFMs) for MICCAI 2024 Cross-Organ and Cross-Scanner Adenocarcinoma Segmentation (COSAS2024). The core of Rein consists of a set of learnable tokens, which are directly linked to instances, improving functionality at the instance level in each layer. In the data environment of the COSAS2024 Challenge, extensive experiments demonstrate that Rein fine-tuned the VFMs to achieve satisfactory results. Specifically, we used Rein to fine-tune ConvNeXt and DINOv2. Our team used the former to achieve scores of 0.7719 and 0.7557 on the preliminary test phase and final test phase in task1, respectively, while the latter achieved scores of 0.8848 and 0.8192 on the preliminary test phase and final test phase in task2. Code is available at GitHub.
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。
