An AI-powered self-driving microscope for low-cost acute leukemia detection
Abstract Current artificial intelligence systems for leukemia detection typically rely on costly whole-slide scanners, limiting accessibility in low-resource settings. We present ALLocate, a low-cost, artificial intelligence-powered microscope plugin that enables self-driving microscopy for leukemia detection. ALLocate attaches directly to conventional microscopes and provides automated analysis at a fraction of the cost of a whole-slide scanner. We evaluate its robustness at three levels: region-of-interest identification, cell detection, and end-to-end slide-level diagnosis. The system is trained and evaluated using more than 11,000 annotated regions and 130,000 annotated cells and is further validated using independent multi-institutional cohorts, including 165 physical bone marrow smear slides. ALLocate achieves an area under the receiver operating characteristic curve greater than 0.99 for region-of-interest identification, a mean average precision at 50% intersection over union of 0.90 for cell detection, and 88% accuracy for slide-level diagnosis on glass slides without requiring a whole-slide scanner. These results suggest that ALLocate provides an accurate, generalizable, and cost-effective approach for automated bone marrow smear screening, helping bridge the gap between AI innovation and practical deployment in resource-limited settings where access to specialist expertise may be limited.
Authors
- Aijazuddin Syed (ORCID: https://orcid.org/0009-0007-8702-7984)
- Sean D. Paulsen (ORCID: https://orcid.org/0000-0002-6625-2863)
- Özgür Can Eren (ORCID: https://orcid.org/0000-0001-9889-2702)
- Ahmet Doǧan (ORCID: https://orcid.org/0000-0001-6576-5256)
- Shenghuan Sun (ORCID: https://orcid.org/0000-0002-4339-2716)
- Jeeyeon Baik
- Maly Fenelus (ORCID: https://orcid.org/0000-0003-1959-4489)
- Gregory M. Goldgof (ORCID: https://orcid.org/0000-0001-8732-9834)
- Brenda Fried
- Deepika Dilip (ORCID: https://orcid.org/0000-0002-4961-1481)
- Orly Ardon (ORCID: https://orcid.org/0000-0001-8147-933X)
- Jamal K. Benhamida (ORCID: https://orcid.org/0000-0001-5542-9857)
- Allyne Manzo (ORCID: https://orcid.org/0009-0004-3056-1180)
- David Kim (ORCID: https://orcid.org/0000-0002-7593-6052)
- Chad Vanderbilt (ORCID: https://orcid.org/0000-0002-8114-0237)
- Siddharth Singi (ORCID: https://orcid.org/0009-0005-6184-5239)
- Ethan Yan (ORCID: https://orcid.org/0009-0005-6332-6803)
- Melissa Pulitzer
- Joanne K. Chun (ORCID: https://orcid.org/0009-0004-5677-0917)
- Mikhael Roshal
- Dianna Ng
- Khawaja H. Bilal
- Cesar Colorado-Jimenez
- Jacob Van Cleave
- Ali Kamali
- Anthony Cardillo
- Irem S. Isgor
- Zhanghan Yin
- Scott Drapeau
Institutions
- Memorial Sloan Kettering Cancer Center (US)
- University of California, San Francisco (US)
- New York Medical College (US)
- Cornell University (US)
- University of San Francisco (US)
- University of California, Berkeley (US)
Publication Details
- Journal
- Nature Communications
- Published
- 2026-08-27
- DOI
- https://doi.org/10.1038/s41467-026-77130-x
- Primary Topic
- Digital Imaging for Blood Diseases
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Warren Alpert Foundation
- Memorial Sloan-Kettering Cancer Center
- National Institutes of Health
- University of California, San Francisco
- National Cancer Institute