Deeptech Learning for Breast Cancer

The only definitive way to diagnose breast cancer is by examining tissue samples collected from biopsy or surgery. The samples are commonly prepared with hematoxylin and eosin (H&E) staining to increase the contrast of structures in the tissue. Traditionally, pathologists examine the tissue on glass slides under a microscope to detect tumor tissue. Diagnosis takes time as pathologists must thoroughly inspect an entire slide at close magnification. Further, pathologists may not notice small tumors. Deep learning methods aim to automate the detection of tumor tissue, saving time and improving the detection rate of small tumors.

Deep learning methods for tumor classification rely on digital pathology, in which whole tissue slides are imaged and digitized. The resulting WSIs have extremely high resolution. WSIs are frequently stored in a multiresolution file to facilitate the display, navigation, and processing of the images.

Our Solution presents classification results as heatmaps that depict the probability that local tissue is tumorous. The localization of tumor regions enables medical pathologists to investigate specific regions and quickly identify tumors of any size in an image.

Paper on Deep Learning Network for Breast Cancer

Cancer is a global health burden which leads to increased morbidity and mortality across countries worldwide. Among many of the cancer types, breast cancers make up the highest proportion of cancers which lead to premature death among women of reproductive age group. It is the most prevalent cancer among women followed by lung cancers. Diagnosing cancer in its early stages is of utmost importance owing to the fact that it significantly reduces morbidity and mortality and improve prognosis. Staging and grading of tumors are done to predict clinical outcome of cancers.

Histopathology is the process where slices of tissue are examined under microscope to visualise the tissue architecture. It is an important process in diagnosing and deciding further management. Histopathological procedures are done by pathologists by using stained specimens of glass slides and observing through microscopes. Deep learning architecture is inspired by hierarchial organization of human biological neural system. This paper is first in a series of papers which is intended to provide insight into possibility of Deep learning for classifying biopsy images for cancer diagnosis.

OBJECTIVES:
To analyze cancer statistics in India, Implement Deep Learning in classifying biopsy images for cancer diagnosis, Application of Deep Learning in cancer prognosis and diagnosis

Download Paper