Fraunhofer Center for Assistive Information and Communication Solutions – AICOSDescription:
The goal of this project is to explore and combine Content-Based Image Retrieval techniques, and explainability methods using Deep Learning applied to diagnostic and CADx contexts. The expected outcome is a system capable of querying a database with an image for similar images within a specific diagnostic context and highlighting the structures in both images.
Outcome:
Explore an as of yet unexplored XAI approach in CADx for the TAMI (Transparent Artificial Medical Intelligence) project.
Author: Beatriz Barrocas
Type: MSc thesis
Partner: FCT NOVA – Faculdade de Ciências e Tecnologias da Universidade Nova de Lisboa
Year: 2021