BREAST CANCER DETECTION USING DEEP LEARNING AND COMPARING DIFFERENT ALGORITHMS

Main Article Content

Prof. Gajanan Kale
Prof. Parag Dounde
Prof. Milan Shetake

Abstract

Accurate diagnosis of breast cancer in histopathology images is challenging due to the heterogeneity of cancer cell growth as well as of a variety of benign breast tissue proliferative lesions. In this work, we propose a practical and self-interpretable invasive cancer diagnosis solution. With minimum annotation information, the proposed method mines contrast patterns between normal and malignant images in unsupervised manner and generates a probability map of abnormalities to verify its reasoning. Particularly, a fully convolutional auto encoder is used to learn the dominant structural patterns among normal image patches. Patches that do not share the characteristics of this normal population are detected and analyzed by one- class support vector machine and 1-layer neural network. We apply the proposed method to a public breast cancer image set. Our results, in consultation with a senior pathologist, demonstrate that the proposed method outperforms existing methods. The obtained probability map could benefit the pathology practice by providing visualized verification data and potentially leads to a better understanding of data-driven diagnosis solutions. And comparing the different algorithms and find out the accurate result

Article Details

How to Cite
Prof. Gajanan Kale, Prof. Parag Dounde, & Prof. Milan Shetake. (2022). BREAST CANCER DETECTION USING DEEP LEARNING AND COMPARING DIFFERENT ALGORITHMS. International Journal of Innovations in Engineering Research and Technology. Retrieved from https://repo.ijiert.org/index.php/ijiert/article/view/3245
Section
Articles