Domain adaptation, Explainability & Fairness in AI for Medical Image Analysis: Diagnosis of COVID-19 based on 3-D Chest CT-scans
Dimitrios Kollias, Anastasios Arsenos, Stefanos Kollias
TL;DR
The paper reports the 4th COV19D Competition under the DEF-AI-MIA workshop at CVPR 2024, focusing on COVID-19 detection and domain adaptation using 3-D chest CT data from the COV19-CT-DB. It presents a CNN-RNN baseline and a Monte Carlo Dropout–based domain adaptation strategy, with dataset splits and anchor-based explainability cues, evaluated via macro F1 on validation sets. The results show macro F1 scores of 0.78 for detection and 0.73 for domain adaptation, establishing competitive baselines and highlighting challenges in cross-center generalization and uncertainty estimation. The work underscores the importance of diverse, anonymized 3-D CT datasets and robust, interpretable AI methods for reliable medical imaging analyses across different clinical settings.
Abstract
The paper presents the DEF-AI-MIA COV19D Competition, which is organized in the framework of the 'Domain adaptation, Explainability, Fairness in AI for Medical Image Analysis (DEF-AI-MIA)' Workshop of the 2024 Computer Vision and Pattern Recognition (CVPR) Conference. The Competition is the 4th in the series, following the first three Competitions held in the framework of ICCV 2021, ECCV 2022 and ICASSP 2023 International Conferences respectively. It includes two Challenges on: i) Covid-19 Detection and ii) Covid-19 Domain Adaptation. The Competition use data from COV19-CT-DB database, which is described in the paper and includes a large number of chest CT scan series. Each chest CT scan series consists of a sequence of 2-D CT slices, the number of which is between 50 and 700. Training, validation and test datasets have been extracted from COV19-CT-DB and provided to the participants in both Challenges. The paper presents the baseline models used in the Challenges and the performance which was obtained respectively.