Decoding Histopathology: Deep Learning Advancements in Early Breast Cancer Detection

View at publisher Summarise with VIRAT
Authors: Zarina begum M, V Gowthami, Monish Sai. R
Cited by: 0
References: 14

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Breast cancer remains a major health challenge for women, yet recent technological advancements have significantly improved the prospects of early detection. Deep Learning approaches have emerged as highly effective in medical image analysis, providing accurate and dependable solutions for cancer classification and detection. The BreakHis dataset is used to test the latest Convolutional Neural Network (CNN) architectures, including ResNet-50, MobileNet, DenseNet201, InceptionV3, NASNetLarge, InceptionResNetV2, and NASNetMobile, for the classification of histological pictures. These mod- els show remarkable success in deriving meaningful features to increase the diagnostic power. The findings indicate that the use of DL-based approaches has a lot of potential to assist healthcare professionals and help them make faster diagnoses, more accurate classifications, and achieve better outcomes when taking care of a patient.

Fields of Study & Subjects

AI in cancer detection Digital Imaging for Blood Diseases Radiomics and Machine Learning in Medical Imaging

Publication details

Journal / source
International Conference on Computing, Communication, Control and Cyber-Physical Systems (I5CPS)
Pages
1–6
Publication date
26 February 2026
Language
EN