Invasive ductal breast carcinoma detector that is robust to image magnification in whole digital slides

Abstract

., "Invasive ductal breast carcinoma detector that is robust to image magnification in whole digital slides," J. Abstract. Invasive ductal breast carcinomas (IDBCs) are the most frequent and aggressive subtypes of breast cancer, affecting a large number of Canadian women every year. Part of the diagnostic process includes grading the cancerous tissue at the microscopic level according to the Nottingham modification of the Scarff-BloomRichardson system. Although reliable, there exists a growing interest in automating the grading process, which will provide consistent care for all patients. This paper presents a solution for automatically detecting regions expressing IDBC in images of microscopic tissue, or whole digital slides. This represents the first stage in a larger solution designed to automatically grade IDBC. The detector first tessellated whole digital slides, and image features were extracted, such as color information, local binary patterns, and histograms of oriented gradients. These were presented to a random forest classifier, which was trained and tested using a database of 66 cases diagnosed with IDBC. When properly tuned, the detector balanced accuracy, F1 score, and Dice's similarity coefficient were 88.7%, 79.5%, and 0.69, respectively. Overall, the results seemed strong enough to integrate our detector into a larger solution equipped with components that analyze the cancerous tissue at higher magnification, automatically producing the histopathological grade.

A Fast and Refined Cancer Regions Segmentation Framework in Whole-slide Breast Pathological Images

“…Balazsi et al . 6 realized a system to detect invasive ductal breast carcinoma. They firstly segmented the WSI by superpixel method in low resolution and then classified every superpixel region into health or cancer tissue using random forest classifier.…”

Análise comparativa da influência dos espaços de cores na segmentação multi-classe de Whole Slide Imaging do câncer de mama utilizando deep learning

“…Os métodos baseados em extração de recursos buscam representar uma imagem em características significativas para o problema. Neste contexto, o trabalho de [Balazsi et al 2016] segmenta regiões de imagens histopatológicas e extrai características, como padrões binários locais e histogramas de gradientes orientados, para identificar carcinoma ductal invasivo utilizando Random Forest. Outra forma de representar uma imagem histológica do câncer de mamá e com a utilização descritores wavelet de cores [Issac Niwas et al 2012].…”

A Novel method for IDC Prediction in Breast Cancer Histopathology images using Deep Residual Neural Networks

“…Similarly, M. S. Reza and J. Ma [18] employ different sampling techniques along with convolutional neural networks for histopathology image classification in class-imbalanced data. M. Balazsi et al [19] proposed a system for detecting regions expressing IDC in images of microscopic tissues or whole digital slides. A. C. Roa et al [20] proposed a CNN architecture for detection and analysis of IDC tissue regions in whole slide images (WSIs) of breast cancer.…”