Deep neural architecture empowered by explainable artificial intelligence for accurate and early diagnosis of gynaecological cancer using medical images
Sabah Abdullah Al-Somali, Zenah Mahmoud AlKubaisy, Muhyaddin Rawa, Khalid H. Allehaibi, Rania M. Alhazmi, Mahmoud Ragab · 2026
Read Deep neural architecture empowered by explainable artificial intelligence for accurate and early diagnosis of gynaecological cancer using medical images by Sabah Abdullah Al-Somali, Zenah Mahmoud AlKubaisy, Muhyaddin Rawa, Khalid H. Allehaibi, Rania M. Alhazmi, Mahmoud Ragab (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/PMC13493927.txt.
Description
Sabah Abdullah Al-Somali leads a six-author team presenting in 2026 an explainable deep learning system for diagnosing gynecological cancers from medical images. Cancers of the cervix, ovaries, and uterus kill partly because image reading is slow and error-prone. The pipeline first cleans scans with a two-stage filter, then extracts features with a mobile-grade neural network built for speed.
A hybrid classifier combining graph convolutions with recurrent memory then separates cancerous from healthy tissue. On the benchmark dataset used, the system reported accuracy near ninety-eight percent, ahead of the comparison methods. Crucially, heat map overlays show clinicians exactly which image regions drove each verdict, answering the trust problem that keeps black box tools out of clinics. Earlier, more transparent diagnosis is the stated goal.
Catalog record
| CREATOR | Sabah Abdullah Al-Somali, Zenah Mahmoud AlKubaisy, Muhyaddin Rawa, Khalid H. Allehaibi, Rania M. Alhazmi, Mahmoud Ragab |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 119991 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |