Tag Archives: MICCAI

IML at MICCAI 2026: Best Paper Award and two contributions at EMERGE workshop

The Interactive Machine Learning (IML) department was represented at the 29th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2026) in Strasbourg, France. MICCAI is widely recognized as a leading international venue for medical image computing, computer-assisted intervention, and AI in medicine. 

At the MICCAI Student Board EMERGE Workshop – Empowering Medical Information Computing and Research through Early-career Guidance and Expertise, IML contributed two oral presentations addressing important challenges in multimodal medical AI and medical image analysis. 

Hasan Md Tusfiqur Alam presented “MedHyperGraph: EHR-Integrated Multimodal Hyperedges for Clinical VQA”, which received the Best Paper Award at the EMERGE Workshop. It introduces a multimodal hypergraph approach for clinical visual question answering that integrates imaging studies with structured and longitudinal information from electronic health records. Rather than simply increasing the amount of retrieved clinical text, the approach preserves temporal and higher-order relationships between clinical events. The results demonstrate the importance of structured clinical context for reasoning across longitudinal patient data.

Abdulrahman M. Selim and Hasan Md Tusfiqur Alam with the Best Paper Award

Hasan Md Tusfiqur Alam at the conference

Abdulrahman M. Selim presented “LocSAM3: Box-Supervised Adaptation of SAM3 for Text-Only Chest X-Ray Segmentation”, which investigates whether dense pixel-level annotations are necessary to adapt foundation segmentation models to medical imaging. LocSAM3 uses only bounding boxes and concept names during training and requires only an image and a textual concept at inference. The results show that coarse localization supervision can effectively support text-driven pixel-level segmentation of anatomical structures and pathological findings in chest X-rays. 

Together, the two contributions reflect IML’s ongoing research on multimodal medical AI, structured clinical reasoning, and data-efficient adaptation of foundation models, with the goal of developing medical AI systems that can make better use of heterogeneous clinical information while reducing costly annotation requirements. 

Congratulations to everyone involved, and especially to the MedHyperGraph team on receiving the Best Paper Award! 

Paper accepted at MICCAI 2023

The MICCAI Society is a professional organization dedicated to the fields of Medical Image Computing and Computer Assisted Interventions. It brings together researchers from various scientific disciplines such as computer science, robotics, physics, and medicine. The society is renowned for its annual MICCAI Conference, which allows for the presentation and publication of original research related to medical imaging. It has an acceptance rate of ~30%. Additionally, the society endorses and sponsors several scientific events each year.

This year, a paper titled “EdgeAL: An Edge Estimation Based Active Learning Approach for OCT Segmentation” was presented by Md Abdul Kadir Hasan, Md Tusfiqur Alam, and Daniel Sonntag. The paper focuses on the use of active learning algorithms for training models with limited data. The authors propose EdgeAL, a method that uses the edge information of unseen images as a priori information to measure uncertainty. This uncertainty is quantified by analyzing the divergence and entropy in model predictions across edges. The measure is then used to select superpixels for annotation. The effectiveness of EdgeAL was demonstrated on multi-class Optical Coherence Tomography (OCT) segmentation tasks. The method achieved a 99% dice score while reducing the annotation label cost to 12%, 2.3%, and 3% on three publicly available datasets (Duke, AROI, and UMN). The source code for this method is available online.

Diagram from the paper “EdgeAL: An Edge Estimation Based Active Learning Approach for OCT Segmentation”

Md Abdul Kadir from IML at the MICCAI 2023 conference in Vancouver, Canada

Poster presenting IML’s work (on the left) at MICCAI 2023

References

Kadir, M.A., Alam, H.M.T., Sonntag, D. (2023). EdgeAL: An Edge Estimation Based Active Learning Approach for OCT Segmentation. In: Greenspan, H., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2023. MICCAI 2023. Lecture Notes in Computer Science, vol 14221. Springer, Cham. https://doi.org/10.1007/978-3-031-43895-0_8