Research map / Vision-language and multimodal / Human and embodied modeling
MMTN: Multi-Modal Memory Transformer Network for Image-Report Consistent Medical Report Generation
Yiming Cao, Lizhen Cui, Lei Zhang, Fuqiang Yu, Zhen Li, Yonghui Xu
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 |
|---|---|---|---|
| Add the terminology encoder, memory augmentation, and multi-modal fusion to the report generator | MMTN · GE | BLEU-4: 0.579 -> 0.589 | Improved |
| Add the terminology encoder, memory augmentation, and multi-modal fusion to the report generator | MMTN · IU-CX | BLEU-4: 0.170 -> 0.175 | Improved |
| Add the terminology encoder, memory augmentation, and multi-modal fusion to the report generator | MMTN · MIMIC-CXR | BLEU-4: 0.106 -> 0.116 | Improved |
| Add medical terminology features instead of using only image grid features (ablation) | MMTN encoder · GE, IU-CX, and MIMIC-CXR | BLEU-1 | Improved |
| Add memory augmentation to associate and memorize image–terminology relationships (ablation) | MMTN encoder · GE, IU-CX, and MIMIC-CXR | BLEU-1 | Improved |
| Add the multi-modal fusion layer to combine visual and linguistic features (ablation) | MMTN decoder · GE, IU-CX, and MIMIC-CXR | BLEU-1 | Improved |
| Add the full MMTN model instead of AlignTransformer | medical report generation · MIMIC-CXR | ROUGE-L: 0.283 -> 0.283 | No clear effect |
Closest papers by meaning
- Automatic Radiology Reports Generation via Memory Alignment Network (AAAI 2024 · similarity 0.84)
- MEPNet: Medical Entity-Balanced Prompting Network for Brain CT Report Generation (AAAI 2025 · similarity 0.84)
- MedUnifier: Unifying Vision-and-Language Pre-training on Medical Data with Vision Generation Task using Discrete Visual Representations (CVPR 2025 · similarity 0.84)
- PromptMRG: Diagnosis-Driven Prompts for Medical Report Generation (AAAI 2024 · similarity 0.84)
- DAMPER: A Dual-Stage Medical Report Generation Framework with Coarse-Grained MeSH Alignment and Fine-Grained Hypergraph Matching (AAAI 2025 · similarity 0.84)
- Unlocking the Power of Spatial and Temporal Information in Medical Multimodal Pre-training (ICML 2024 · similarity 0.84)
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.
