Development and Validation of a Histological Method to Measure Microvessel Density in Whole-Slide Images of Cancer Tissue

Abstract

Despite all efforts made to develop predictive biomarkers for antiangiogenic therapies, no unambiguous markers have been identified so far. This is due to among others the lack of standardized tests. This study presents an improved microvessel density quantification method in tumor tissue based on stereological principles and using whole-slide images. Vessels in tissue sections of different cancer types were stained for CD31 by an automated and validated immunohistochemical staining method. The stained slides were digitized with a digital slide scanner. Systematic, uniform, random sampling of the regions of interest on the whole-slide images was performed semi-automatically with the previously published applications AutoTag and AutoSnap. Subsequently, an unbiased counting grid was combined with the images generated with these scripts. Up to six independent observers counted microvessels in up to four cancer types: colorectal carcinoma, glioblastoma multiforme, ovarian carcinoma and renal cell carcinoma. At first, inter-observer variability was found to be unacceptable. However, after a series of consensus training sessions and interim statistical analysis, counting rules were modified and inter-observer concordance improved considerably. Every CD31-positive object was counted, with exclusion of suspected CD31-positive monocytes, macrophages and tumor cells. Furthermore, if interconnected, stained objects were considered a single vessel. Ten regions of interest were sufficient for accurate microvessel density measurements. Intra-observer and inter-observer variability were low (intraclass correlation coefficient > 0.7) if the observers were adequately trained.

Automated multiparametric localization of prostate cancer based on B-mode, shear-wave elastography, and contrast-enhanced ultrasound radiomics

“…Despite the performance gains obtained using the proposed method, some malignant ROIs were still missed and some benign ROIs were wrongly classified as malignant by the algorithm. In the future, immunohistochemical techniques [50,51] might elucidate more on the nature of the false readings. There are indications that (co-occurring) prostatitis or BPH might be responsible for false positives, as these diseases are known to also promote angiogenesis [52,53].…”

Comparing the expression profiles of steroid hormone receptors and stromal cell markers in prostate cancer at different Gleason scores

“…A major methodological novelty in this study was the use of whole slide imaging and automated image analysis tools to characterize IHC. Compared to the generally used semi-quantitative and observer-dependent visual scoring systems of IHC, annotating the regions of interest to compartmentalise the quantitative analysis is a very time-consuming approach, but it has the major advantages to generate robust and reproducible quantitative data and to avoid the effects of human subjectivity in visual evaluation 32 , 35 – 38 . Recent developments in machine learning, and more specifically in deep learning, propose methods for automatically segmenting glandular epithelium in H&E slide images from non-tumor and tumor colorectal tissue samples 39 , 40 .…”

Consensus guidelines for the use and interpretation of angiogenesis assays

“…Individual microvessels are then counted at high power magnification in these regions. As an alternative, microvessels can be counted in regions defined by systematic uniform random sampling (SURS) [ 112 ]. These IHC staining assays are robust, fast, and easy to perform and to automate.…”