Classification of breast cancer stroma as a tool for prognosis

Abstract

It has been shown that the tumour microenvironment plays a crucial role in regulating tumour progression by a number of different mechanisms, including the remodelling of collagen fibres in tumour-associated stroma. It is still unclear, however, if these stromal changes are of benefit to the host or the tumour. We hypothesise that stromal maturity is an important reflection of tumour biology, and thus can be used to predict prognosis. The aim of this study is to develop a texture analysis methodology which will automatically classify stromal regions from images of hematoxylin and eosin-stained (H&E) sections into two categories: mature and immature. Subsequently we will investigate whether stromal maturity could be used as a predictor of survival and also as a means to better understand the relationship between the radiological imaging signal and the underlying tissue microstructure. We present initial results for 118 regions-of-interest from a dataset of 39 patients diagnosed with invasive breast cancer.

Automated Classification of Breast Cancer Stroma Maturity From Histological Images

“…2) Combining BIFs with local binary patterns a) Light-lines DtG filter Consultation with a experienced breast pathologist (SEP) concluded that one of the primary features for defining stroma maturity is its alignment and linear coherence, and we infered that the use of only one of the categories from the BIFs classification -the light lines filter response -was sufficient for describing stroma maturity, as per our previous findings [21]. A representative image can be seen in Figure 4.…”

“…In previous work [21], we proposed an algorithm based on a support vector machine (SVM) classifier applied to a set of quantitative texture features to automatically classify stromal regions from images of H&E sections according to their maturity. Derivative-of-Gaussians (DtG) have been used for many applications, such as edge detection, retinal blood vessels extraction or texture analysis [22]- [24].…”

Micro Calcification Detection in Mammogram Images Using Contiguous Convolutional Neural Network Algorithm

“…The next stages of processing evaluate the BC stages using Convolutional Neural Network (CNN). Micro calcifications (MC) were diagnosed with breast cancer's surrounding tissue Fanizzi et al 2020, Reis et al 2016 breast X-ray photographs. The ability to recognize each feature Wavelet transform using benign and malignant tissues is a set of recognition using probabilistic neural networks.…”