12 papers published at MICCAI 2026

Dear colleagues,

We’re pleased to share that Bagci Lab in the Department of Radiology at Northwestern University will have 12 papers published at MICCAI 2026 and its associated workshops.

MICCAI is one of the premier international conferences in medical image computing and computer-assisted intervention. This year’s record submissions and reported 27% main-conference acceptance rate make the lab’s two main-conference publications especially noteworthy.

Our research spans CT, MRI, ultrasound, mammography, and medical visual question answering, with studies on segmentation, model robustness, generalization, diagnosis, and risk stratification.

Select a paper title to open its preprint, OpenReview paper, or project page.

Main conference

Anatomy-Aware Prediction of Bronchoscopic Accessibility from 3D CT

Using anatomical information from 3D CT to predict bronchoscopic accessibility.

SRMA-Mamba: Spatial Reverse Mamba Attention Network for Pathological Liver Segmentation in MRI Volumes

A spatial reverse Mamba attention network for segmenting pathological liver anatomy in MRI volumes.

Workshop publications

CLIMEM workshop

How Resilient are Foundation Segmentation Models to Noisy Ultrasound Artifacts? A Multi-Dataset Benchmark Across Prompts, Noise Types, and Severity Levels

DEEP-BREA3TH workshop

BreastMammo and DenseMammo: Benchmarks for Mammography Domain Generalization

ELAMI workshop

Contrastive Answer Calibration for Medical Visual Question Answering

LISA workshop

Asymmetric Paired-Annotation Learning for Multi-Structure ULF Pediatric Brain MRI Segmentation

MIRASOL workshop

TRIUNE-Net: Harmonizing Scale, Shape, and Efficiency in Pancreatic Tumor Segmentation

MLMI workshop

Hierarchical MoE for Multi-Modal ILD Diagnosis

Distributional Mutual Correction for Semi-Supervised Pancreas Segmentation

Gaussian Meta-Space Augmentation for Stacking Ensembles in Multimodal IPMN Risk Stratification

SliceLift: Slice-to-Volume Feature Lifting for Volumetric Pancreatic Cyst MRI Segmentation

GazeRefine: Expert Gaze as a Test-Time Prompt for Training-Free Medical Image Segmentation

Congratulations to all authors and collaborators whose work made these publications possible. We look forward to sharing our research with the MICCAI community.