André Anjos
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
André Anjos has a total of 1000 co-authors. Here are the top co-authors by number of shared publications:
P. Werner
17 shared publicationsC. Meessen
14 shared publicationsA. Di Mattia
13 shared publicationsF. Touchard
13 shared publicationsS. Sivoklokov
13 shared publicationsA. Negri
University of California Irvine
12 shared publications
Latest Publications
- Top Cited PapersOpen Access
- 17 March 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Computing for Healthcare
- Vol. 7 (2) , 1-24
Fair Foundation Models for Medical Image Analysis: Challenges and Perspectives
Ensuring equitable Artificial Intelligence (AI) in healthcare demands systems that make unbiased decisions across all demographic groups, bridging technical innovation with ethical principles. Foundation Models (FMs), trained on vast datasets through self-supervised learning, enable efficient adaptation across medical imaging tasks while reducing dependency on labeled data. These models demonstrate potential for enhancing fairness, though significant challenges remain in achieving consistent performance across demographic groups. Our review indicates that effective bias mitigation in FMs requires systematic interventions throughout all stages of development. While previous approaches focused primarily on model-level bias mitigation, our analysis reveals that fairness in FMs requires integrated interventions throughout the development pipeline, from data documentation to deployment protocols. This comprehensive framework advances current knowledge by demonstrating how systematic bias mitigation, combined with policy engagement, can effectively address both technical and institutional barriers to equitable AI in healthcare. The development of equitable FMs represents a critical step toward democratizing advanced healthcare technologies, particularly for underserved populations and regions with limited medical infrastructure and computational resources.
- 17 March 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Computing for Healthcare
- Vol. 7 (2) , 1-24
Top Cited PapersOpen AccessFair Foundation Models for Medical Image Analysis: Challenges and Perspectives
Ensuring equitable Artificial Intelligence (AI) in healthcare demands systems that make unbiased decisions across all demographic groups, bridging technical innovation with ethical principles. Foundation Models (FMs), trained on vast datasets through self-supervised learning, enable efficient adaptation across medical imaging tasks while reducing dependency on labeled data. These models demonstrate potential for enhancing fairness, though significant challenges remain in achieving consistent performance across demographic groups. Our review indicates that effective bias mitigation in FMs requires systematic interventions throughout all stages of development. While previous approaches focused primarily on model-level bias mitigation, our analysis reveals that fairness in FMs requires integrated interventions throughout the development pipeline, from data documentation to deployment protocols. This comprehensive framework advances current knowledge by demonstrating how systematic bias mitigation, combined with policy engagement, can effectively address both technical and institutional barriers to equitable AI in healthcare. The development of equitable FMs represents a critical step toward democratizing advanced healthcare technologies, particularly for underserved populations and regions with limited medical infrastructure and computational resources.
- Open Access
- 21 August 2025
- Published by Machine Learning for Biomedical Imaging in Machine Learning for Biomedical Imaging
- Vol. 3 (Special on) , 938-957
A Multi-Objective Evaluation Framework for Analyzing Utility-Fairness Trade-Offs in Machine Learning Systems
The evaluation of fairness models in Machine Learning involves complex challenges, such as defining appropriate metrics, balancing trade-offs between utility and fairness, and there are still gaps in this stage. This work presents a novel multi-objective evaluation framework that enables the analysis of utility-fairness trade-offs in Machine Learning systems. The framework was developed using criteria from Multi-Objective Optimization that collect comprehensive information regarding this complex evaluation task. The assessment of multiple Machine Learning systems is summarized, both quantitatively and qualitatively, in a straightforward manner through a radar chart and a measurement table encompassing various aspects such as convergence, system capacity, and diversity. The framework’s compact representation of performance facilitates the comparative analysis of different Machine Learning strategies for decision-makers, in real-world applications, with single or multiple fairness requirements. In particular, this study focuses on the medical imaging domain, where fairness considerations are crucial due to the potential impact of biased diagnostic systems on patient outcomes. The proposed framework enables a systematic evaluation of multiple fairness constraints helping to identify and mitigate disparities among demographic groups while maintaining diagnostic performance. The framework is model-agnostic and flexible to be adapted to any kind of Machine Learning systems, that is, black- or white-box, any kind and quantity of evaluation metrics, including multidimensional fairness criteria. The functionality and effectiveness of the proposed framework is shown with different simulations, and an empirical study conducted on three real-world medical imaging datasets with various Machine Learning systems. Our evaluation framework is publicly available at https://pypi.org/project/fairical
- 21 August 2025
- Published by Machine Learning for Biomedical Imaging in Machine Learning for Biomedical Imaging
- Vol. 3 (Special on) , 938-957
Open AccessA Multi-Objective Evaluation Framework for Analyzing Utility-Fairness Trade-Offs in Machine Learning Systems
The evaluation of fairness models in Machine Learning involves complex challenges, such as defining appropriate metrics, balancing trade-offs between utility and fairness, and there are still gaps in this stage. This work presents a novel multi-objective evaluation framework that enables the analysis of utility-fairness trade-offs in Machine Learning systems. The framework was developed using criteria from Multi-Objective Optimization that collect comprehensive information regarding this complex evaluation task. The assessment of multiple Machine Learning systems is summarized, both quantitatively and qualitatively, in a straightforward manner through a radar chart and a measurement table encompassing various aspects such as convergence, system capacity, and diversity. The framework’s compact representation of performance facilitates the comparative analysis of different Machine Learning strategies for decision-makers, in real-world applications, with single or multiple fairness requirements. In particular, this study focuses on the medical imaging domain, where fairness considerations are crucial due to the potential impact of biased diagnostic systems on patient outcomes. The proposed framework enables a systematic evaluation of multiple fairness constraints helping to identify and mitigate disparities among demographic groups while maintaining diagnostic performance. The framework is model-agnostic and flexible to be adapted to any kind of Machine Learning systems, that is, black- or white-box, any kind and quantity of evaluation metrics, including multidimensional fairness criteria. The functionality and effectiveness of the proposed framework is shown with different simulations, and an empirical study conducted on three real-world medical imaging datasets with various Machine Learning systems. Our evaluation framework is publicly available at https://pypi.org/project/fairical
- 2 July 2025
- Published by Elsevier in Applied Soft Computing
- Vol. 181
Optimizing fairness and utility in healthcare machine learning models
- 2 July 2025
- Published by Elsevier in Applied Soft Computing
- Vol. 181
Optimizing fairness and utility in healthcare machine learning models
- Open Access
STM-GNN: Space-Time-and-Memory Graph Neural Networks for Predicting Multi-Drug Resistance Risks in Dynamic Patient Networks
Hospital-acquired infections (HAIs), particularly those caused by multidrug-resistant (MDR) bacteria, pose significant risks to vulnerable patients. Accurate predictive models are important for assessing infection dynamics and informing infection prediction and control (IPC) programmes. Graph-based methods, including graph neural networks (GNNs), offer a powerful approach to model complex relationships between patients and environments but often struggle with data sparsity, irregularity, and heterogeneity. We propose the space-time-and-memory (STM)-GNN, a temporal GNN enhanced with recurrent connectivity designed to capture spatiotemporal infection dynamics. STM-GNN effectively integrates sparse, heterogeneous data combining network information from patient-environment interactions and internal memory from historical colonization and contact patterns. Using a unique IPC dataset containing clinical and environmental colonization information collected from a long-term healthcare unit, we show that STM-GNN effectively addresses the challenges of limited and irregular data in an MDR prediction task. Our model reaches 0.84 AUROC, and achieves the most balanced performance overall compared to classic machine learning algorithms, as well as temporal GNN approaches.
Open AccessSTM-GNN: Space-Time-and-Memory Graph Neural Networks for Predicting Multi-Drug Resistance Risks in Dynamic Patient Networks
Hospital-acquired infections (HAIs), particularly those caused by multidrug-resistant (MDR) bacteria, pose significant risks to vulnerable patients. Accurate predictive models are important for assessing infection dynamics and informing infection prediction and control (IPC) programmes. Graph-based methods, including graph neural networks (GNNs), offer a powerful approach to model complex relationships between patients and environments but often struggle with data sparsity, irregularity, and heterogeneity. We propose the space-time-and-memory (STM)-GNN, a temporal GNN enhanced with recurrent connectivity designed to capture spatiotemporal infection dynamics. STM-GNN effectively integrates sparse, heterogeneous data combining network information from patient-environment interactions and internal memory from historical colonization and contact patterns. Using a unique IPC dataset containing clinical and environmental colonization information collected from a long-term healthcare unit, we show that STM-GNN effectively addresses the challenges of limited and irregular data in an MDR prediction task. Our model reaches 0.84 AUROC, and achieves the most balanced performance overall compared to classic machine learning algorithms, as well as temporal GNN approaches.
- Open Access
- 20 May 2025
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 193, 110327
Automatic transformer-based grading of multiple retinal inflammatory signs in uveitis on fluorescein angiography
- 20 May 2025
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 193, 110327
Open AccessAutomatic transformer-based grading of multiple retinal inflammatory signs in uveitis on fluorescein angiography
- 27 July 2022
- Published by Elsevier in Computer Speech & Language
- Vol. 77
Towards lifelong human assisted speaker diarization
- 27 July 2022
- Published by Elsevier in Computer Speech & Language
- Vol. 77
Towards lifelong human assisted speaker diarization
- Open Access
On the Evaluation and Real-World Usage Scenarios of Deep Vessel Segmentation for Retinography
We identify and address three research gaps in the field of vessel segmentation for funduscopy. The first focuses on the task of inference on high-resolution fundus images for which only a limited set of ground-truth data is publicly available. Notably, we highlight that simple rescaling and padding or cropping of lower resolution datasets is surprisingly effective. Additionally we explore the effectiveness of semi-supervised learning for better domain adaptation. Our results show competitive performance on a set of common public retinal vessel datasets using a small and light-weight neural network. For HRF, the only very high-resolution dataset currently available, we reach new state-of-the-art performance by solely relying on training images from lower-resolution datasets. The second topic concerns evaluation metrics. We investigate the variability of the F1-score on the existing datasets and report results for recent SOTA architectures. Our evaluation show that most SOTA results are actually comparable to each other in performance. Last, we address the issue of reproducibility by open-sourcing our complete pipeline.
Open AccessOn the Evaluation and Real-World Usage Scenarios of Deep Vessel Segmentation for Retinography
We identify and address three research gaps in the field of vessel segmentation for funduscopy. The first focuses on the task of inference on high-resolution fundus images for which only a limited set of ground-truth data is publicly available. Notably, we highlight that simple rescaling and padding or cropping of lower resolution datasets is surprisingly effective. Additionally we explore the effectiveness of semi-supervised learning for better domain adaptation. Our results show competitive performance on a set of common public retinal vessel datasets using a small and light-weight neural network. For HRF, the only very high-resolution dataset currently available, we reach new state-of-the-art performance by solely relying on training images from lower-resolution datasets. The second topic concerns evaluation metrics. We investigate the variability of the F1-score on the existing datasets and report results for recent SOTA architectures. Our evaluation show that most SOTA results are actually comparable to each other in performance. Last, we address the issue of reproducibility by open-sourcing our complete pipeline.
- Top Cited Papers
- 14 May 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 15 (15566013) , 42-55
Biometric Face Presentation Attack Detection With Multi-Channel Convolutional Neural Network
Face recognition is a mainstream biometric authentication method. However, vulnerability to presentation attacks (a.k.a spoofing) limits its usability in unsupervised applications. Even though there are many methods available for tackling presentation attacks (PA), most of them fail to detect sophisticated attacks such as silicone masks. As the quality of presentation attack instruments improves over time, achieving reliable PA detection with visual spectra alone remains very challenging. We argue that analysis in multiple channels might help to address this issue. In this context, we propose a multi-channel Convolutional Neural Network based approach for presentation attack detection (PAD). We also introduce the new Wide Multi-Channel presentation Attack (WMCA) database for face PAD which contains a wide variety of 2D and 3D presentation attacks for both impersonation and obfuscation attacks. Data from different channels such as color, depth, near-infrared and thermal are available to advance the research in face PAD. The proposed method was compared with feature-based approaches and found to outperform the baselines achieving an ACER of 0.3% on the introduced dataset. The database and the software to reproduce the results are made available publicly.
- 14 May 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 15 (15566013) , 42-55
Top Cited PapersBiometric Face Presentation Attack Detection With Multi-Channel Convolutional Neural Network
Face recognition is a mainstream biometric authentication method. However, vulnerability to presentation attacks (a.k.a spoofing) limits its usability in unsupervised applications. Even though there are many methods available for tackling presentation attacks (PA), most of them fail to detect sophisticated attacks such as silicone masks. As the quality of presentation attack instruments improves over time, achieving reliable PA detection with visual spectra alone remains very challenging. We argue that analysis in multiple channels might help to address this issue. In this context, we propose a multi-channel Convolutional Neural Network based approach for presentation attack detection (PAD). We also introduce the new Wide Multi-Channel presentation Attack (WMCA) database for face PAD which contains a wide variety of 2D and 3D presentation attacks for both impersonation and obfuscation attacks. Data from different channels such as color, depth, near-infrared and thermal are available to advance the research in face PAD. The proposed method was compared with feature-based approaches and found to outperform the baselines achieving an ACER of 0.3% on the introduced dataset. The database and the software to reproduce the results are made available publicly.
- 2 January 2019
- Published by Springer Nature
- p. 207-228
Recent Advances in Face Presentation Attack Detection
- 2 January 2019
- Published by Springer Nature
- p. 207-228
Recent Advances in Face Presentation Attack Detection
- 2 January 2019
- Published by Springer Nature
- p. 419-438
An Introduction to Vein Presentation Attacks and Detection
- 2 January 2019
- Published by Springer Nature
- p. 419-438
An Introduction to Vein Presentation Attacks and Detection