# Modality-AGnostic Image Cascade (MAGIC) for Multi-Modality Cardiac Substructure Segmentation

arXiv: https://arxiv.org/abs/2506.10797 · HTML: https://mlsanity.com/paper/2506.10797/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 54 references that are in the map.
- First posted on arXiv 12 Jun 2025.

## Builds on (most cited first, 18 of 18)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [TotalSegmentator: robust segmentation of 104 anatomical structures in CT images](https://mlsanity.com/paper/2208.05868/) (2022)
- [MONAI: An open-source framework for deep learning in healthcare](https://mlsanity.com/paper/2211.02701/) (2022)
- [clDice -- A Novel Topology-Preserving Loss Function for Tubular Structure Segmentation](https://mlsanity.com/paper/2003.07311/) (2020)
- [Metrics reloaded: Recommendations for image analysis validation](https://mlsanity.com/paper/2206.01653/) (2022)
- [Deep learning for cardiac image segmentation: A review](https://mlsanity.com/paper/1911.03723/) (2019)
- [HeMIS: Hetero-Modal Image Segmentation](https://mlsanity.com/paper/1607.05194/) (2016)
- [Evaluation of Algorithms for Multi-Modality Whole Heart Segmentation: An Open-Access Grand Challenge](https://mlsanity.com/paper/1902.07880/) (2019)
- [mmFormer: Multimodal Medical Transformer for Incomplete Multimodal Learning of Brain Tumor Segmentation](https://mlsanity.com/paper/2206.02425/) (2022)
- [Unpaired Multi-modal Segmentation via Knowledge Distillation](https://mlsanity.com/paper/2001.03111/) (2020)
- [No New-Net](https://mlsanity.com/paper/1809.10483/) (2018)
- [Learning Topological Interactions for Multi-Class Medical Image Segmentation](https://mlsanity.com/paper/2207.09654/) (2022)
- [Multimodal Machine Learning in Image-Based and Clinical Biomedicine: Survey and Prospects](https://mlsanity.com/paper/2311.02332/) (2023)
- [A persistent homology-based topological loss function for multi-class CNN segmentation of cardiac MRI](https://mlsanity.com/paper/2008.09585/) (2020)
- [On Image Segmentation With Noisy Labels: Characterization and Volume Properties of the Optimal Solutions to Accuracy and Dice](https://mlsanity.com/paper/2206.06484/) (2022)
- [Volumetric medical image segmentation through dual self-distillation in U-shaped networks](https://mlsanity.com/paper/2306.03271/) (2023)
- [Modality-Agnostic Learning for Medical Image Segmentation Using Multi-modality Self-distillation](https://mlsanity.com/paper/2306.03730/) (2023)
- [Contour Dice loss for structures with Fuzzy and Complex Boundaries in Fetal MRI](https://mlsanity.com/paper/2209.12232/) (2022)

## Abstract (arXiv)

Cardiac substructure delineation is emerging in treatment planning to minimize the risk of radiation-induced heart disease. Deep learning offers efficient methods to reduce contouring burden but currently lacks generalizability across different modalities and overlapping structures. This work introduces and validates a Modality-AGnostic Image Cascade (MAGIC) deep-learning pipeline for comprehensive and multi-modal cardiac substructure segmentation. MAGIC is implemented through replicated encoding and decoding branches of an nnU-Net backbone to handle multi-modality inputs and overlapping labels. First benchmarked on the multi-modality whole-heart segmentation (MMWHS) dataset including cardiac CT-angiography (CCTA) and MR modalities, twenty cardiac substructures (heart, chambers, great vessels (GVs), valves, coronary arteries (CAs), and conduction nodes) from clinical simulation CT (Sim-CT), low-field MR-Linac, and cardiac CT-angiography (CCTA) modalities were delineated to train semi-supervised (n=151), validate (n=15), and test (n=30) MAGIC. For comparison, fourteen single-modality comparison models (two MMWHS modalities and four subgroups across three clinical modalities) were trained. Methods were evaluated for efficiency and against reference contours through the Dice similarity coefficient (DSC) and two-tailed Wilcoxon Signed-Rank test (p<0.05). Average MMWHS DSC scores across CCTA and MR inputs were 0.88(0.08) and 0.87(0.04) respectively with significant improvement over unimodal baselines. Average 20-structure DSC scores were 0.75(0.16) for Sim-CT, 0.68(0.21) for MR-Linac, and 0.80(0.16) for CCTA. Furthermore, >80% and >70% reductions in training time and parameters were achieved, respectively. MAGIC offers an efficient, lightweight solution capable of segmenting multiple image modalities and overlapping structures in a single model without compromising segmentation accuracy.