Localized Protein Quantification of Blood Brain Barrier Vasculature in Brightfield IHC Images

In this paper, we present an objective method for locally quantifying proteins in blood brain barrier (BBB) vasculature using standard immunohistochemistry (IHC) techniques and bright-field microscopy. Images from the hippocampal region at the BBB are acquired using bright-field microscopy and subjected to our immunohistochemistry quantification (IQ) algorithm which is designed to automatically identify and segment microvessels containing the protein glucose transporter 1 (GLUT1). Gabor filtering and k-means clustering are employed to isolate potential vascular structures within cryopsectioned slabs of the hippocampus, which are subsequently subjected to feature extraction followed by classification via decision forest. The false positive rate (FPR) of microvessel classification is characterized using synthetic and non-synthetic IHC image data for image entropies ranging between 3 and 8 bits. The average FPR for synthetic and non-synthetic IHC image data was found to be 5.48% and 5.04%, respectively.

本研究提出一种基于标准免疫组织化学（immunohistochemistry, IHC）技术与明场显微镜（bright-field microscopy）的客观方法，可对血脑屏障（blood brain barrier, BBB）脉管中的蛋白质进行原位定量分析。本研究通过明场显微镜采集血脑屏障相关海马区的图像，将其输入自研的免疫组化定量（immunohistochemistry quantification, IQ）算法，该算法旨在自动识别并分割表达葡萄糖转运蛋白1（glucose transporter 1, GLUT1）的微血管。研究采用Gabor滤波（Gabor filtering）与k-means聚类（k-means clustering）算法，从海马冷冻切片标本中分离出潜在的脉管结构，随后对其进行特征提取，并通过决策森林（decision forest）完成分类。本研究针对图像熵（image entropy）介于3至8比特的合成与非合成免疫组化图像数据，对微血管分类的假阳性率（false positive rate, FPR）进行了表征分析。实验结果显示，合成与非合成免疫组化图像数据的平均假阳性率分别为5.48%与5.04%。