• Raksha G Rao
• Dr. P M Shivamurthy
• Basavaraj Hadimani
• Navya P
• Deeksha K T

Deep learning-based computer-aided diagnosis (CAD) is gaining prominence, for interpreting histopathology pictures. However, there has been little research into reliably classifying breast biopsy tissue into different histological categories with hematoxylin and eosin stained images. Researchers and professionals aim to create a computer-aided diagnosis method for diagnosing breast cancer histopathology pictures. Using eosin stained and hematoxylin images, CAD has helped improve the diagnosis accuracy of biopsy tissue. Traditional methods for extracting handcrafted features have been employed by most CAD systems, which are inaccurate in diagnosis and are time-consuming. Both CAD and computational diagnostics are utilized to help pathologists work more efficiently and accurately. Different techniques that divide breast cancer histology images into benign and malignant categories have been proposed in this research. A custom CNN model and three pre-trained models for classification of histopathological images have been used with Resnet50 model yielding an accuracy of 96 percent.

CAD, Histopathology, Classification, CNN

"Classification Of Histopathological Images Using Deep Learning Approach", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.8, Issue 6, page no.e168-e173, June-2021, Available :http://www.jetir.org/papers/JETIR2106581.pdf

"Classification Of Histopathological Images Using Deep Learning Approach", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.8, Issue 6, page no. ppe168-e173, June-2021, Available at : http://www.jetir.org/papers/JETIR2106581.pdf