Multimodal Deep Learning with Attention-Based Fusion for Skin Cancer Diagnosis
Wiem Abdelbaki, Hend Alshaya, Inzamam Mashood Nasir, Sara Tehsin, Wided Bouchelligua · 2026
Read Multimodal Deep Learning with Attention-Based Fusion for Skin Cancer Diagnosis by Wiem Abdelbaki, Hend Alshaya, Inzamam Mashood Nasir, Sara Tehsin, Wided Bouchelligua (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13203454.txt.
Description
Wiem Abdelbaki and co-authors published a research paper in 2026 on a deep learning system that diagnoses skin cancer from both lesion photos and clinical notes. Skin lesions vary widely and photos vary in quality, so image-only tools miss context. Their design fuses dermoscopic image features with structured patient information through an attention mechanism.
Across three large public data sets, accuracy ran between about eighty-nine and ninety-two percent. The fused model beat two strong image-only baselines on standard scores by clear margins. Removing the attention or fusion parts cost measurable accuracy, confirming both help. The system is compact enough, the authors say, for real clinic deployment.
Catalog record
| CREATOR | Wiem Abdelbaki, Hend Alshaya, Inzamam Mashood Nasir, Sara Tehsin, Wided Bouchelligua |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 88 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |