Evaluation of Bagging Ensembles on Multimodal Data for Breast Cancer Diagnosis.- HF-Fed: Hierarchical based customized Federated Learning Framework for X-Ray Imaging.- DuEU-Net: Dual Encoder UNet with Modality-Agnostic Training for PET-CT Multi-Modal Organ and Lesion Segmentation.- One for All: UNET Training on Single-Sequence Masks for Multi-Sequence Breast MRI Segmentation.- Multimodal Breast MRI Language-Image Pretraining (MLIP): An Exploration of a Breast MRI Foundation Model.- Enhancing the Utility of Privacy-Preserving Cancer Classification using Synthetic Data.- Efficient Generation of Synthetic Breast CT Slices By Combining Generative and Super-Resolution Models.- Exploring Patient Data Requirements in Training Effective AI Models for MRI-based Breast Cancer Classification.

- Virtual dynamic contrast enhanced breast MRI using 2D U-Net.- Optimizing BI-RADS 4 Lesion Assessment using Lightweight Convolutional Neural Network with CBAM in Contrast Enhanced Mammography.- Mammographic Breast Positioning Assessment via Deep Learning.- Endpoint Detection in Breast Images for Automatic Classification of Breast Cancer Aesthetic Results.- Thick Slices for Optimal Digital Breast Tomosynthesis Classification with Deep-Learning.- Predicting Aesthetic Outcomes in Breast Cancer Surgery: a Multimodal Retrieval Approach.- Vision Mamba for Classification of Breast Ultrasound Images.- Breast Cancer Molecular Subtyping from H&E Whole Slide Images using Foundation Models and Transformers.

- Graph Neural Networks for modelling breast biomechanical compression.- A generative adversarial approach to remove Moiré artifacts in Dark-field and Phase-contrast x-ray images.- MRI Breast tissue segmentation using nnUNet for Biomechanical modeling.- Fat-Suppressed Breast MRI Synthesis for Domain Adaptation in Tumour Segmentation.- Guiding Breast Conservative Surgery by Augmented Reality from Preoperative MRI: Initial System Design and Retrospective Trials.- ELK: Enhanced Learning through cross-modal Knowledge transfer for lesion detection in limited-sample contrast-enhanced mammography datasets.- Safe Breast Cancer Diagnosis Resilient to Mammographic Adversarial Samples.