AI Breast cancer detection using InBreast, CBIS-DDSM, MIAS mammography image datasets

Multi-modal deep learning with attention mechanism

Detection of tumors on mammography images

Stack of REST APIs built on Flask for serving requests to MAMMORY (App), deployed on Azure with GitHub Actions (CI/CD)

MICCAI 2024: Ordinal Learning: Longitudinal Attention Alignment Model for Predicting Time to Future Breast Cancer Events from Mammograms

Restore low-dose DBT projections using VCT software

Code for "Radio-opaque artefacts in digital mammography: Automatic detection and analysis of downstream effects" - ISBI 2025 paper

Independent evaluation of a multi-view multi-task convolutional neural network breast cancer classification model using Finnish mammography screening data

This repository contains the training and testing codes for the paper "Imposing noise correlation fidelity on digital breast tomosynthesis restoration through deep learning techniques", submitted to the IWBI 2022 conference.

1st-place-solution of SPR Screening Mammography Recall

Official repository of "Enhancing the Utility of Privacy-Preserving Cancer Classification using Synthetic Data"

Mammo Lingua is a GUI application for Name Entity Recognition (NER) and BIRADS Classification. The application is built using Python with PyQt5 for the GUI and SpaCy for NER. The goal is to provide a tool that can analyze medical texts, identify named entities, and classify BIRADS categories.

基于深度学习的乳腺X光片良恶性分类诊断系统，采用多模型集成（EfficientNet-B3/B4、ResNet50、DenseNet121）结合SWA随机权重平均、Focal Loss和MixUp数据增强，针对CBIS-DDSM数据集实现高精度三分类

Python tool for keyboard-driven breast density classification on mammography DICOM studies.

This is the implementation of the MVCM model mentioned in our paper 'Validation of artificial intelligence contrast mammography in diagnosis of breast cancer: Relationship to histopathological results'.

Progressive generation of mammography images using Generative Adversarial Networks (ProGAN). Developed as a Final Degree Project in UEX.

Python tool for mammography DICOM review: browse studies by metadata, highlight target-positive cases, capture 128×128 ROIs, and keep a timestamped PNG audit trail.

ViT approach to find the abnormal parts of mammograms, and recalibrate with Explainable AI

Vision Transformer (ViT) based Context Embedding Network for multi-view breast cancer detection in mammograms.

Mammography experimentation repo delivering reproducible preprocessing, feature engineering, and modeling steps. Run ResNet50 or EfficientNet B0 extractors for full training loops and density classifiers.