OBJECTIVE: The tumor microenvironment plays a crucial role in regulating tumor progression by a number of different mechanisms, in particular, the remodeling of collagen fibers in tumor-associated stroma, which has been reported to be related to patient survival. The underlying motivation of this work is that remodeling of collagen fibers gives rise to observable patterns in hematoxylin and eosin (H&E) stained slides from clinical cases of invasive breast carcinoma that the pathologist can label as mature or immature stroma. The aim of this paper is to categorise and automatically classify stromal regions according to their maturity and show that this classification agrees with that of skilled observers, hence providing a repeatable and quantitative measure for prognostic studies. METHODS: We use multiscale basic image features and local binary patterns, in combination with a random decision trees classifier for classification of breast cancer stroma regions-of-interest (ROI). RESULTS: We present results from a cohort of 55 patients with analysis of 169 ROI. Our multiscale approach achieved a classification accuracy of 84%. CONCLUSION: This work demonstrates the ability of texture-based image analysis to differentiate breast cancer stroma maturity in clinically acquired H&E-stained slides at least as well as skilled observers.
OBJECTIVE: The tumor microenvironment plays a crucial role in regulating tumor progression by a number of different mechanisms, in particular, the remodeling of collagen fibers in tumor-associated stroma, which has been reported to be related to patient survival. The underlying motivation of this work is that remodeling of collagen fibers gives rise to observable patterns in hematoxylin and eosin (H&E) stained slides from clinical cases of invasive breast carcinoma that the pathologist can label as mature or immature stroma. The aim of this paper is to categorise and automatically classify stromal regions according to their maturity and show that this classification agrees with that of skilled observers, hence providing a repeatable and quantitative measure for prognostic studies. METHODS: We use multiscale basic image features and local binary patterns, in combination with a random decision trees classifier for classification of breast cancer stroma regions-of-interest (ROI). RESULTS: We present results from a cohort of 55 patients with analysis of 169 ROI. Our multiscale approach achieved a classification accuracy of 84%. CONCLUSION: This work demonstrates the ability of texture-based image analysis to differentiate breast cancer stroma maturity in clinically acquired H&E-stained slides at least as well as skilled observers.
Authors: Yue Du; Roy Zhang; Abolfazl Zargari; Theresa C Thai; Camille C Gunderson; Katherine M Moxley; Hong Liu; Bin Zheng; Yuchen Qiu Journal: Ann Biomed Eng Date: 2018-07-26 Impact factor: 3.934