Duke Division of Artificial Intelligence and Computational Pathology, Duke University Medical Center, Durham NC, USA; Department of Anesthesiology, Duke University Medical Center, Durham NC, USA.
Department of Biostatistics and Bioinformatics, Duke School of Medicine, Durham NC, USA.
Cardiovasc Pathol. 2024 Sep-Oct;72:107646. doi: 10.1016/j.carpath.2024.107646. Epub 2024 Apr 26.
Pathologic antibody mediated rejection (pAMR) remains a major driver of graft failure in cardiac transplant patients. The endomyocardial biopsy remains the primary diagnostic tool but presents with challenges, particularly in distinguishing the histologic component (pAMR-H) defined by 1) intravascular macrophage accumulation in capillaries and 2) activated endothelial cells that expand the cytoplasm to narrow or occlude the vascular lumen. Frequently, pAMR-H is difficult to distinguish from acute cellular rejection (ACR) and healing injury. With the advent of digital slide scanning and advances in machine deep learning, artificial intelligence technology is widely under investigation in the areas of oncologic pathology, but in its infancy in transplant pathology. For the first time, we determined if a machine learning algorithm could distinguish pAMR-H from normal myocardium, healing injury and ACR.
A total of 4,212 annotations (1,053 regions of normal, 1,053 pAMR-H, 1,053 healing injury and 1,053 ACR) were completed from 300 hematoxylin and eosin slides scanned using a Leica Aperio GT450 digital whole slide scanner at 40X magnification. All regions of pAMR-H were annotated from patients confirmed with a previous diagnosis of pAMR2 (>50% positive C4d immunofluorescence and/or >10% CD68 positive intravascular macrophages). Annotations were imported into a Python 3.7 development environment using the OpenSlide™ package and a convolutional neural network approach utilizing transfer learning was performed.
The machine learning algorithm showed 98% overall validation accuracy and pAMR-H was correctly distinguished from specific categories with the following accuracies: normal myocardium (99.2%), healing injury (99.5%) and ACR (99.5%).
Our novel deep learning algorithm can reach acceptable, and possibly surpass, performance of current diagnostic standards of identifying pAMR-H. Such a tool may serve as an adjunct diagnostic aid for improving the pathologist's accuracy and reproducibility, especially in difficult cases with high inter-observer variability. This is one of the first studies that provides evidence that an artificial intelligence machine learning algorithm can be trained and validated to diagnose pAMR-H in cardiac transplant patients. Ongoing studies include multi-institutional verification testing to ensure generalizability.
病理性抗体介导的排斥反应（pAMR）仍然是心脏移植患者移植物衰竭的主要驱动因素。心内膜心肌活检仍然是主要的诊断工具，但存在挑战，特别是在区分组织学成分（pAMR-H）方面，其定义为 1）毛细血管内巨噬细胞积聚和 2）扩张细胞质以变窄或阻塞血管腔的活化内皮细胞。pAMR-H 通常难以与急性细胞排斥反应（ACR）和愈合损伤区分。随着数字幻灯片扫描的出现和机器深度学习的进步，人工智能技术在肿瘤病理学领域得到了广泛的研究，但在移植病理学领域仍处于起步阶段。我们首次确定机器学习算法是否可以区分 pAMR-H 与正常心肌、愈合损伤和 ACR。
共完成了 4212 个注释（1053 个正常区域、1053 个 pAMR-H 区域、1053 个愈合损伤区域和 1053 个 ACR 区域），这些注释来自 300 张苏木精和曙红染色的幻灯片，这些幻灯片使用 Leica Aperio GT450 数字全玻片扫描仪以 40X 放大倍数进行扫描。所有 pAMR-H 区域均来自先前诊断为 pAMR2（>50%阳性 C4d 免疫荧光和/或>10%CD68 阳性血管内巨噬细胞）的患者的注释。使用 OpenSlide™包将注释导入到 Python 3.7 开发环境中，并使用迁移学习进行卷积神经网络方法。
机器学习算法的总体验证准确率为 98%，pAMR-H 可以正确地区分以下特定类别：正常心肌（99.2%）、愈合损伤（99.5%）和 ACR（99.5%）。
我们的新型深度学习算法可以达到可接受的、甚至可能超过当前识别 pAMR-H 的诊断标准的性能。这样的工具可以作为辅助诊断工具，提高病理学家的准确性和可重复性，特别是在观察者间差异较大的困难情况下。这是第一项提供证据表明人工智能机器学习算法可以经过训练和验证来诊断心脏移植患者 pAMR-H 的研究之一。正在进行的研究包括多机构验证测试，以确保通用性。
