Exploring automatic prostate histopathology image gleason grading via local structure modeling

Abstract

Gleason-grading of prostate cancer pathology specimens reveal the malignancy of the cancer tissues, thus provides critical guidance for prostate cancer diagnoses and treatment. Computer-aided automatic grading methods have been providing efficient and result-consistent alternative to traditional manually slide reading approach, through statistical and structural feature analysis of the digitized pathology slides. In this paper, we propose a novel automatic Gleason grading algorithm through local structure model learning and classification. We use attributed graph to represent the tissue glandular structures in histopathology images; representative sub-graphs features were learned as bags-of-words features from labeled samples of each grades. Then structural similarity between sub-graphs in the unlabeled images and the representative sub-graphs were obtained using the learned codebook. Gleason grade was given based on an overall similarity score. We validated the proposed algorithm on 300 prostate histopathology images from the TCGA dataset, and the algorithm achieved average grading accuracy of 91.25%, 76.36% and 64.75% on images with Gleason grade 3, 4 and 5 respectively.

Machine Learning Methods for Histopathological Image Analysis

“…Other diagnosis-related tasks include detection or segmentation of Region of Interest (ROI) such as tumor region in WSI [16,17], scoring of immunostaining [11,18], cancer staging [15,19], mitosis detection [20,21], gland segmentation [22][23][24], and detection and quantification of vascular invasion [25].…”

“…In some applications such as IHC scoring, staging of lymph node metastasis of specimens or patients, and staging of prostate cancer diagnosed by Glisson score of multiple regions within one slide, more sophisticated algorithms to integrate patch-level or object-level decisions are required [14,17,18,40,41,76]. For example, for pN-staging of metastatic breast cancer, which was one of the tasks in Camelyon 17, multiple participating teams including us applied random forest classifiers of pixel or patch-level probabilities estimated by deep learning using various features such as estimated tumor size [41].…”

Reimagining T Staging Through Artificial Intelligence and Machine Learning Image Processing Approaches in Digital Pathology

“…Like the textons approach, each image in the bag-of-words approach is defined by a cluster signature (or bag of words) that is then used to compare its similarity with other images. Textons and bag-of-words approaches have been used to prognosticate survival in gliomas, predict Gleason grading in prostate cancer, 21,22 and classify medulloblastomas. 23 Cellular shape.…”

Software-defined environments for science and engineering

“…In order to demonstrate the concepts proposed in this article, we containerized a synthesized workflow based on a histopathology image analysis application and used it as a driver to evaluate our approach. Specifically, the application is an automatic Gleason-grading workflow of prostate malignancy using pathology specimens of prostate tissues, which provides critical guidance for prostate cancer diagnoses and further treatment (Wang et al, 2015). This workflow is composed of two stages: (1) region segmentation, which extracts image patches from whole slide imaging of the sample slides and locates regions of interest (ROI) and (2) grade classification, which gives a Gleason grade for each segmented ROI by a three-level classifier.…”