Signature maps for automatic identification of prostate cancer from colorimetric analysis of H&E- and IHC-stained histopathological specimens

Abstract

Prostate cancer (PCa) is a major cause of cancer death among men. The histopathological examination of post-surgical prostate specimens and manual annotation of PCa not only allow for detailed assessment of disease characteristics and extent, but also supply the ground truth for developing of computer-aided diagnosis (CAD) systems for PCa detection before definitive treatment. As manual cancer annotation is tedious and subjective, there have been a number of publications describing methods for automating the procedure via the analysis of digitized whole-slide images (WSIs). However, these studies have focused only on the analysis of WSIs stained with hematoxylin and eosin (H&E), even though there is additional information that could be obtained from immunohistochemical (IHC) staining. In this work, we propose a framework for automating the annotation of PCa that is based on automated colorimetric analysis of both H&E and IHC WSIs stained with a triple-antibody cocktail against high-molecular weight cytokeratin (HMWCK), p63, and α-methylacyl CoA racemase (AMACR). The analysis outputs were then used to train a regression model to estimate the distribution of cancerous epithelium within slides. The approach yielded an AUC of 0.951, sensitivity of 87.1%, and specificity of 90.7% as compared to slide-level annotations, and generalized well to cancers of all grades.

Radiomics-Based Machine Learning Models for Predicting P504s/P63 Immunohistochemical Expression: A Noninvasive Diagnostic Tool for Prostate Cancer

“…While P63, expressed by the basal cells, could be regarded as a kind of negative marker of PCa. On the other hand, P504s, an enzyme involved in fatty acid metabolism, have been proved expression upregulated in 97–100% of PCa ( 5 , 6 ). Therefore, P504s can function as a positive biomarker for diagnosis of prostate cancer.…”

AI-based Carcinoma Detection and Classification Using Histopathological Images: A Systematic Review

“…The Kappa value, which represents classifier's overall grading agreement with the pathologists, was reported as 0.51. Leng et al [87] designed a regression model to estimate cancerous regions in WSI and achieved AUC of 0.951. They reported the use of colorimetric analysis of H&E and IHC stained histopathological specimens.…”

“…Color Deconvolution [87,88], Gaussian filtering [92,95], Reinhard color [89] Watershed [84,86,96], Thresholding [85,88,92,95] Morphological features [84,86,87,95], Various texture features [85], Wavelet features [85], SURF descriptors [86], Topological features [89],…”

“…Epithelial layer architecture features [96] Machine learning algorithms [84,86,88,95,96], Ensemble classifier [85,87], Ensemble CNN [87], Transfer learning models [92,94], Hierarchical Ward clustering [89], Custom CNN [93] Lung…”

“…ConvNet features [108] Machine learning algorithms [82,108] [18], [20], [21], [45] [22], [73], [27] -- [45] (25K) High magnification (20X, 40X, 45X, 50X, 60X) [61], [72], [94], [19], [57], [56], [95] [29], [25] [23], [83], [63], [58] [14], [31] [77] (1lakh), [105] (5256), [44] High magnification (20X, 40X, 45X, 50X, 60X) [28], [34], [35], [67], [70], [89], [87], [96], [100], [26], [32], [40], [69], [65], [80], [85] [82]…”