Precise Location Matching Improves Dense Contrastive Learning in Digital Pathology
Precise Location Matching Improves Dense Contrastive Learning in Digital Pathology
复制标题
DOI：
10.48550/arxiv.2212.12105
复制
发表时间：
2022-12
期刊：
影响因子：
--
通讯作者：
Jingwei Zhang;S. Kapse;Ke Ma;P. Prasanna;M. Vakalopoulou;J. Saltz;D. Samaras
中科院分区：
文献类型：
--
作者：
Jingwei Zhang;S. Kapse;Ke Ma;P. Prasanna;M. Vakalopoulou;J. Saltz;D. Samaras
密集预测任务，如病理实体的分割和检测，在计算病理学工作流程中具有至关重要的临床价值。然而，在大型队列上获得密集注释通常是繁琐且昂贵的。因此，对比学习（CL）通常用于利用大量未标记的数据来预训练骨干网络。为了提高密集预测的CL，一些研究提出了预训练中密集匹配目标的变化。然而，我们的分析表明，采用现有的密集匹配策略的组织病理学图像之间的不正确的密集功能对强制执行不变性，因此，是不精确的。为了解决这个问题，我们提出了一个精确的基于位置的匹配机制，利用几何变换之间的重叠信息，以精确地匹配两个增强区域。在两个预训练数据集（TCGA-BRCA，NCT-CRC-HE）和三个下游数据集（GlaS，CRAG，BCSS）上的大量实验突出了我们的方法在语义和实例分割任务中的优越性。我们的方法优于以前的密集匹配方法高达7.2%的平均精度检测和5.6%的平均精度实例分割任务。此外，通过在三个流行的对比学习框架MoCo-v2，VICRegL和ConCL中使用我们的匹配机制，检测的平均精度提高了0.7%到5.2%，分割的平均精度提高了0.7%到4.0%，具有推广性。我们的代码可在https://github.com/cvlab-stonybrook/PLM_SSL上获得。
Dense prediction tasks such as segmentation and detection of pathological entities hold crucial clinical value in computational pathology workflows. However, obtaining dense annotations on large cohorts is usually tedious and expensive. Contrastive learning (CL) is thus often employed to leverage large volumes of unlabeled data to pre-train the backbone network. To boost CL for dense prediction, some studies have proposed variations of dense matching objectives in pre-training. However, our analysis shows that employing existing dense matching strategies on histopathology images enforces invariance among incorrect pairs of dense features and, thus, is imprecise. To address this, we propose a precise location-based matching mechanism that utilizes the overlapping information between geometric transformations to precisely match regions in two augmentations. Extensive experiments on two pretraining datasets (TCGA-BRCA, NCT-CRC-HE) and three downstream datasets (GlaS, CRAG, BCSS) highlight the superiority of our method in semantic and instance segmentation tasks. Our method outperforms previous dense matching methods by up to 7.2% in average precision for detection and 5.6% in average precision for instance segmentation tasks. Additionally, by using our matching mechanism in the three popular contrastive learning frameworks, MoCo-v2, VICRegL, and ConCL, the average precision in detection is improved by 0.7% to 5.2%, and the average precision in segmentation is improved by 0.7% to 4.0%, demonstrating generalizability. Our code is available at https://github.com/cvlab-stonybrook/PLM_SSL.