Breast cancer detection and classification via a robust deep learning approach

Abstract This work presents a leakage-controlled deep-learning framework for breast cancer classification using the CBIS-DDSM mammography archive. The proposed pipeline combines patient-level data partitioning before augmentation, a two-stage transfer-learning strategy based on ResNet50, and an Inte...

Popoln opis

Bibliografske podrobnosti

Principais autores:	Magy Makram, Alber S. Aziz, Mary Monir Saeid, Mostafa Thabet Mohamed
Format:	Artigo
Jezik:	Inglês
Izdano:	Nature Portfolio 2026-07-01
Serija:	Scientific Reports
Teme:	Breast cancer classification Mammography CBIS-DDSM ResNet50 Inter-view attention fusion Transfer learning
Online dostop:	https://doi.org/10.1038/s41598-026-62255-2
Oznake:	Označite Brez oznak, prvi označite!