Automatic pathology of prostate cancer in whole mount slides incorporating individual gland classification

This paper presents an automatic pathology (AutoPath) approach to detect prostatic adenocarcinoma based on morphological analysis of high resolution whole mount (WM) histopathology images of the prostate. In the first stage of the cancer detection algorithm, a pre-screening of cancerous regions is performed at low magnification (5x) based on regional features. In the second stage, we propose a novel technique of labelling individual glands as benign or malignant using gland specific features at high magnification (20x). Two new features, Number of Nuclei Layers and Epithelial Layer Density, are proposed to label individual glands. We validate the approach on 70 WM slides, obtained from 30 patients, and achieve average sensitivity of 90%, specificity of 93% and accuracy of 93%. The main advantage of the approach is that detection of individual malignant gland units, irrespective of neighbouring histology and/or the spatial extent of the cancer, allows a finer annotation of cancer. The AutoPath method performs well on slides with low Gleason grades (3 and 4), but is currently limited in its ability to detect cancer in higher Gleason grades.