The AIM Lab (AI for Medical Imaging Lab) focused on using artificial intelligence for medical image recognition.
To drive these advancements, the lab leveraged key technical AI components, focusing primarily on:
With a commitment to explainable, and responsible AI systems.
The AIM Lab (AI for Medical Imaging Lab) was dedicated to bridging the gap between cutting-edge AI image recognition and real-world clinical medicine.
The lab’s mission and vision were to adapt and advance deep learning algorithms beyond everyday images, building the fundamental tools and human capacities needed to extract deeper, highly reliable diagnostic insights from complex medical imagery.
The impact of the lab was focused on accelerating a smarter, faster approach to healthcare, bringing together seven PhD researchers over five years to tackle critical challenges like rapid Alzheimer’s diagnosis, cardiac rhythm modeling, and automated X-ray reporting, while embedding fundamental, generalizable AI models to improve accuracy and efficiency across the medical ecosystem.
Quicker diagnosis of Alzheimer’s disease – Developing deep learning algorithms to detect subtle pattern shifts in neuroimaging, enabling earlier and faster identification of Alzheimer’s disease indicators before significant clinical progression.
Modeling cardiac rhythms – Applying image recognition and predictive AI to map electrical activity and dynamic movement patterns in the heart to better diagnose and monitor arrhythmias.
Automated report generation from x-ray images – Creating multimodal AI models that analyze X-ray scans (such as chest X-rays) and automatically generate structured, text-based clinical reports to assist radiologists.
Fundamental AI models and algorithms – Building generalizable machine learning, meta-learning, and vision-language architectures that can adapt image recognition techniques from natural images to the specific nuances of complex medical data across different diseases.
ProtoDiff: Learning to Learn Prototypical Networks by Task-Guided Diffusion Proceedings Article
In: Advances in Neural Information Processing Systems (NeurIPS), 2023.
Episodic Multi-Task Learning with Heterogeneous Neural Processes Proceedings Article
In: Advances in Neural Information Processing Systems (NeurIPS), 2023.
Bayesian Prompt Learning for Image-Language Model Generalization Proceedings Article
In: IEEE/CVF International Conference on Computer Vision (ICCV), 2023.
Open-Ended Medical Visual Question Answering Through Prefix Tuning of Language Models Proceedings Article
In: Medical Image Computing and Computer Assisted Intervention (MICCAI), 2023.
EMO: Episodic Memory Optimization for Few-Shot Meta-Learning Proceedings Article
In: Conference on Lifelong Learning Agents (CoLLAs), 2023.
MetaModulation: Learning Variational Feature Hierarchies for Few-Shot Learning with Fewer Tasks Proceedings Article
In: International Conference on Machine Learning (ICML), 2023.
SuperDisco: Super-Class Discovery Improves Visual Recognition for the Long-Tail Proceedings Article
In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023.
Meta Learning To Bridge Vision and Language Models for Multimodal Few-Shot Learning Proceedings Article
In: International Conference on Learning Representations (ICLR), 2023.
Energy-Based Test Sample Adaptation for Domain Generalization Proceedings Article
In: International Conference on Learning Representations (ICLR), 2023.
Probabilistic Integration of Object Level Annotations in Chest X-Ray Classification Proceedings Article
In: IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2023.
Association Graph Learning for Multi-Task Classification with Category Shifts Proceedings Article
In: Advances in Neural Information Processing Systems (NeurIPS), 2022.
LifeLonger: A Benchmark for Continual Disease Classification Proceedings Article
In: Medical Image Computing and Computer Assisted Intervention (MICCAI), 2022.
Uncertainty-Aware Report Generation for Chest X-Rays by Variational Topic Inference Journal Article
In: Medical Image Analysis, 2022.
Audio-Adaptive Activity Recognition Across Video Domains Proceedings Article
In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
MetaKernel: Learning Variational Random Features with Limited Labels Journal Article
In: IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022.
Hierarchical Variational Memory for Few-Shot Learning Across Domains Proceedings Article
In: International Conference on Learning Representations (ICLR), 2022.
Learning to Generalize Across Domains on Single Test Samples Proceedings Article
In: International Conference on Learning Representations (ICLR), 2022.
MetaNorm: Learning to Normalize Few-Shot Batches Across Domains Proceedings Article
In: International Conference on Learning Representations (ICLR), 2021.
Variational Multi-Task Learning with Gumbel-Softmax Priors Proceedings Article
In: Advances in Neural Information Processing Systems (NeurIPS), 2021.
Variational Knowledge Distillation for Disease Classification in Chest X-Rays Proceedings Article
In: Information Processing in Medical Imaging (IPMI), 2021.
Variational Topic Inference for Chest X-Ray Report Generation Proceedings Article
In: Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2021.
Meta-Learning with Variational Semantic Memory for Word Sense Disambiguation Proceedings Article
In: Findings of the Association for Computational Linguistics (ACL), 2021.
Kernel Continual Learning Proceedings Article
In: International Conference on Machine Learning (ICML), 2021.
A Bit More Bayesian: Domain-Invariant Learning with Uncertainty Proceedings Article
In: International Conference on Machine Learning (ICML), 2021.
Variational Prototype Inference for Few-Shot Semantic Segmentation Proceedings Article
In: IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2021.
NFormer: Robust Person Re-identification with Neighbor Transformer Proceedings Article
In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
Variational Abnormal Behavior Detection With Motion Consistency Journal Article
In: IEEE Transactions on Image Processing (TIP), 2021.
Learning to Adapt With Memory for Probabilistic Few-Shot Learning Journal Article
In: IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2021.
Spherical Zero-Shot Learning Journal Article
In: IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2021.
Learning to Automatically Generate Accurate ECG Captions Proceedings Article
In: Medical Imaging with Deep Learning (MIDL), 2021.
Learning to Learn Kernels with Variational Random Features Proceedings Article
In: International Conference on Machine Learning (ICML), 2020.
Learning to Learn Variational Semantic Memory Proceedings Article
In: Advances in Neural Information Processing Systems (NeurIPS), 2020.
Learning to Learn with Variational Information Bottleneck for Domain Generalization Proceedings Article
In: European Conference on Computer Vision (ECCV), 2020.
Variational Image Deraining Proceedings Article
In: IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2020.
Variational Image Deraining Journal Article
In: IEEE Transactions on Image Processing (TIP), 2020.
Inception Institute of Artificial Intelligence drives excellence and leadership of AI research in the UAE and the wider world with the aim of promoting economic growth, fostering innovation and improving healthcare and people’s lives.
University of Amsterdam (UvA) is the Netherlands’ largest university, offering the widest range of academic programmes.
