Thorsted Bjarne, Bjerregaard Lisette, Jensen Pia S, Rasmussen Lars M, Lindholt Jes S, Bloksgaard Maria
Department of Cardiothoracic and Vascular Surgery, Odense University Hospital, Odense, Denmark.
Department of Clinical Biochemistry and Pharmacology, Odense University Hospital, Odense, Denmark.
Front Physiol. 2022 Aug 22;13:840965. doi: 10.3389/fphys.2022.840965. eCollection 2022.
Quantification of histological information from excised human abdominal aortic aneurysm (AAA) specimens may provide essential information on the degree of infiltration of inflammatory cells in different regions of the AAA. Such information will support mechanistic insight in AAA pathology and can be linked to clinical measures for further development of AAA treatment regimens. We hypothesize that artificial intelligence can support high throughput analyses of histological sections of excised human AAA. We present an analysis framework based on supervised machine learning. We used TensorFlow and QuPath to determine the overall architecture of the AAA: thrombus, arterial wall, and adventitial loose connective tissue. Within the wall and adventitial zones, the content of collagen, elastin, and specific inflammatory cells was quantified. A deep neural network (DNN) was trained on manually annotated, Weigert stained, tissue sections (14 patients) and validated on images from two other patients. Finally, we applied the method on 95 new patient samples. The DNN was able to segment the sections according to the overall wall architecture with Jaccard coefficients after 65 epocs of 92% for the training and 88% for the validation data set, respectively. Precision and recall both reached 92%. The zone areas were highly variable between patients, as were the outputs on total cell count and elastin/collagen fiber content. The number of specific cells or stained area per zone was deterministically determined. However, combining the masks based on the Weigert stainings, with images of immunostained serial sections requires addition of landmark recognition to the analysis path. The combination of digital pathology, the DNN we developed, and landmark registration will provide a strong tool for future analyses of the histology of excised human AAA. In combination with biomechanical testing and microstructurally motivated mathematical models of AAA remodeling, the method has the potential to be a strong tool to provide mechanistic insight in the disease. In combination with each patients' demographic and clinical profile, the method can be an interesting tool to in supportof a better treatment regime for the patients.
对切除的人腹主动脉瘤（AAA）标本的组织学信息进行量化，可能会提供有关AAA不同区域炎症细胞浸润程度的重要信息。此类信息将有助于深入了解AAA的发病机制，并可与临床措施相关联，以进一步开发AAA治疗方案。我们假设人工智能可以支持对切除的人AAA组织切片进行高通量分析。我们提出了一个基于监督机器学习的分析框架。我们使用TensorFlow和QuPath来确定AAA的整体结构：血栓、动脉壁和外膜疏松结缔组织。在壁区和外膜区内，对胶原蛋白、弹性蛋白和特定炎症细胞的含量进行了量化。在手动标注的、魏格特染色的组织切片（14例患者）上训练深度神经网络（DNN），并在另外两名患者的图像上进行验证。最后，我们将该方法应用于95个新的患者样本。经过65个轮次的训练，DNN能够根据整体壁结构对切片进行分割，训练数据集的杰卡德系数为92%，验证数据集的杰卡德系数为88%。精确率和召回率均达到92%。患者之间的区域面积差异很大，总细胞计数和弹性蛋白/胶原纤维含量的输出也是如此。每个区域的特定细胞数量或染色面积是可以确定的。然而，将基于魏格特染色的掩码与免疫染色连续切片的图像相结合，需要在分析路径中添加地标识别。数字病理学、我们开发的DNN和地标配准的结合将为未来切除的人AAA组织学分析提供一个强大的工具。与生物力学测试和AAA重塑的微观结构驱动数学模型相结合，该方法有可能成为深入了解该疾病发病机制的有力工具。与每个患者的人口统计学和临床特征相结合，该方法可以成为支持为患者制定更好治疗方案的有趣工具。
