An integrated AI pipeline for automated cytogenetic analysis of bone marrow karyograms in hematological malignancies: A Pix2Pix enhancement and deep learning detection approach
Lamia Alsubaie, Sarah Alsobaie, Nawaf Alhammad, Luluh Aldhubayi, Yazeed Al-shaikh · 2026
Read An integrated AI pipeline for automated cytogenetic analysis of bone marrow karyograms in hematological malignancies: A Pix2Pix enhancement and deep learning detection approach by Lamia Alsubaie, Sarah Alsobaie, Nawaf Alhammad, Luluh Aldhubayi, Yazeed Al-shaikh (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-13273851.txt.
Description
Lamia Alsubaie and co-authors build an AI pipeline that helps read chromosome spreads from bone marrow in blood cancers, in a 2026 study. Human experts do this work by eye, slowly, with results that vary between readers and suffer when images are poor. Past AI tools each did one step, not the whole chain.
Their pipeline cleans the image with a generative model, finds chromosomes with a detector, and classifies a key structural swap. It then writes a report in the standard code that labs and accreditors use. On past clinical cases, image cleanup kept over 98 percent of structure, and case calls matched experts about 86 percent of the time. After fair wording disputes were settled, the rate rose to 92 percent. Every report still passes a human check, and the authors stress the tool supports, not replaces, experts.
Catalog record
| CREATOR | Lamia Alsubaie, Sarah Alsobaie, Nawaf Alhammad, Luluh Aldhubayi, Yazeed Al-shaikh |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 64 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |