Research map / Detection and segmentation / Open-set and few-shot detection
Multivariate Mixture Model for Myocardial Segmentation Combining Multi-Source Images
Xiahai Zhuang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| segment LGE jointly with T2 and bSSFP (MvMM) instead of Atlas alone | Atlas · LGE CMR | Dice myocardium: 0.4950 -> 0.7169 | Improved |
| segment jointly (MvMM) instead of GMM alone | GMM · LGE CMR | Dice myocardium: 0.5163 -> 0.7169 | Improved |
| use bSSFP to assist atlas registration (ablation) | Atlas · LGE CMR | Dice myocardium: 0.4950 -> 0.6203 | Improved |
| use bSSFP to assist initial registration (ablation) | GMM · LGE CMR | Dice myocardium: 0.5163 -> 0.6352 | Improved |
| joint MvMM beats best separate scheme GMM+bSSFP | GMM+bSSFP · LGE CMR | Dice myocardium: 0.6352 -> 0.7169 | Improved |
| add shift correction (SC) for motion-shifted slices (ablation) | MvMM without registration · LGE CMR | Dice myocardium: 0.6971 -> 0.7168 | Improved |
| add FFD atlas registration correction (ablation) | MvMM without registration · LGE CMR | Dice myocardium: 0.6971 -> 0.7008 | Improved |
| add FFD to MvMM with shift correction (ablation) | MvMM + SC · LGE CMR | Dice myocardium: 0.7168 -> 0.7169 | No clear effect |
| add follow-up GMM on MvMM result (ablation) | MvMM · T2 CMR | Dice myocardium: 0.717 -> 0.744 | Improved |
| add follow-up GMM on MvMM result (ablation) | MvMM · T2 CMR | Dice endocardium: 0.794 -> 0.827 | Improved |
| add follow-up GMM on MvMM result (ablation) | MvMM · T2 CMR | Dice epicardium: 0.908 -> 0.878 | Hurt |
| increase number of images from 1 to 2 (UvMM1 to MvMM2) (ablation) | UvMM · Simulated BrainWeb MR | Dice | Improved |
Closest papers by meaning
- Fourier Contour Learning for Efficient and Traceable Cardiac MRI Quantification (NeurIPS 2026 · similarity 0.83)
- beta-FFT: Nonlinear Interpolation and Differentiated Training Strategies for Semi-Supervised Medical Image Segmentation (CVPR 2025 · similarity 0.81)
- EchoONE: Segmenting Multiple Echocardiography Planes in One Model (CVPR 2025 · similarity 0.81)
- Versatile Medical Image Segmentation Learned from Multi-Source Datasets via Model Self-Disambiguation (CVPR 2024 · similarity 0.81)
- FAMNet: Frequency-aware Matching Network for Cross-domain Few-shot Medical Image Segmentation (AAAI 2025 · similarity 0.81)
- MemSAM: Taming Segment Anything Model for Echocardiography Video Segmentation (CVPR 2024 · similarity 0.81)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
