AI
Multimodal Fusion: A Review of Breast Cancer Advanced and Traditional Modalities
Publication: cs.AI updates on arXiv.org
Author: Jawaher Al-Tuweity, Jo\~ao Paulo Papa
Source published: 17/11/2026, 05:00:00 UTC
Briefing created: 17/11/2026, 08:50:09 UTC
Based on a feed excerpt; full article content has not been acquired. Source evidence retrieved 17/11/2026, 08:33:24 UTC.
Briefings
This review analyzes over 15 imaging modalities for breast cancer detection, identifying mammography, ultrasound, and MRI as the most widely used. Recent AI advances enable fusion at data, feature, and decision levels, integrating imaging with clinical and genomic data. Key challenges include limited diverse datasets, protocol variations, and the need for interpretable AI models. The study concludes that multimodal fusion offers promising opportunities but requires robust strategies and standardized datasets for reliable clinical translation.
Key points
- Mammography, ultrasound, and MRI remain the most widely used modalities for breast cancer detection, providing complementary structural and functional information.
- Recent AI advances enable fusion at the data, feature, and decision levels, integrating imaging data with clinical, histopathological, and genomic information.
Context
Multimodal medical imaging fusion (MMIF) is an increasingly important approach to breast cancer detection, as different imaging modalities rely on different physical principles and provide complementary information. No single modality can capture all the structural, functional, and biological information needed for accurate diagnosis and characterization.
Limitations
The review covers more than 15 imaging modalities but lacks data on specific regional adoption rates, long-term clinical outcomes, or the impact of specific fusion strategies on patient survival rates. The evidence is limited to the review of existing modalities and AI capabilities, with no external validation data provided.
Generated by Bittrees-hosted qwen35-2b sha256:aaf42c8b7c3c on 17/11/2026, 08:50:09 UTC. Based on publisher-provided feed evidence; may not cover the full original article. Check the source for details.
View archived briefing on IPFS
bafybeih2jz5hykqcyotmo3efjawfjxxb3wdnjp2tyxrlmqfyui2jeqibc4