ALLocate: Auto Ai Live Localization and Classification of Myeloid Leukemia in Bone Marrow

Overview

The accurate leukemia detection in current clinical practice still remains challenging due to limitations in cost, time, and medical experience. To address this issue, this study aims to develop the first integrated low-cost automatic artificial intelligence system for the real-time detection of acute myeloid leukemia in marrow smears, named ALLocate. This system consists of an automatic microscope scanner system, an image sampling system, and a deep learning-based detection system. A low-cost automatic microscope scanner system was developed using 3D-printed pieces controlled by stepper motors and a programmed RAMPS control board. A region classifier using a convolutional neural network model was developed to select usable regions. For real-time cell detection, the YOLOv8 model was developed and optimized. The key variables for optimization include the number of epochs, learning rate, and network architecture. These models show high performance with CNN accuracy of 96%, and YOLOv8 mAP of 91%. When the ALLocate was applied to a marrow smear, its leukemia detection results are similar to the results from a doctor but it is much faster. This is the first report to integrate the deep learning system with a low-cost microscope automatic scanner system for leukemia detection. For small community practices or clinics in underserved areas, ALLocate can significantly improve the efficiency of leukemia detection and bring accessible and affordable healthcare to underserved communities.

Competition history

• AJAS 2025 Category not listed

Related projects

Closest projects by meaning, across every fair and year in the corpus.

Browse more like this

• AJAS None projects
• Every AJAS 2025 project