A machine-learning-based algorithm for bone marrow cell differential counting.
Journal
International journal of medical informatics
Journal Volume
194
Pages
105692
ISSN
1872-8243
Date Issued
2025-02
Author(s)
Yu, Ta-Chuan
Yang, Cheng-Kun
Hsu, Wei-Han
Hsu, Cheng-An
Wang, Hsiao-Chun
Hsiao, Hsin-Jung
Chao, Hsiao-Ling
Hsieh, Han-Peng
Wu, Jia-Rong
Tsai, Yen-Chun
Chiang, Yi-Mei
Lee, Poshing
Lin, Che-Pin
Chen, Ling-Ping
Sung, Yung-Chuan
Yang, Ya-Yun
Yu, Chin-Ling
Lin, Chih-Kang
Kang, Chia-Pin
Chang, Che-Wei
Chang, Hsiu-Lin
Chu, Jung-Hsuan
Cathy Kao, Kai-Ling
Lin, Li
Wu, Min-Sheng
Lin, Pei-Chen
Yang, Po-Hsu
Zhang, Qun-Yi
Huang, Sheng-Chuan
Yeh, Chao-Yuan
Abstract
Background: Differential counting (DC) of different cell types in bone marrow (BM) aspiration smears is crucial for diagnosing hematological diseases. However, a clinically applicable method for automatic DC has yet to be developed. Objective: This study developed and validated an artificial intelligence (AI)-based algorithm for identifying and classifying nucleated cells in BM smears. Methods: In the development phase, a mask region–based convolutional neural network (Mask R-CNN)-based AI model was trained to detect and classify individual BM cells. We used a large data set of expert-annotated images representing a variety of disease categories. The BM slides were stained with Liu's stain or Wright–Giemsa stain. Consensus meetings were held to ensure experts from different institutes applied consistent criteria in classifying cells. Subsequently, the performance of the AI algorithm in identifying cell images and determining cell ratios was evaluated using a multinational clinical dataset. Results: The AI model was trained on 542 slides (85.1 % stained with Liu's stain and 14.9 % with Wright–Giemsa stain) containing 597,222 annotated cells. It achieved an accuracy of 0.94 for the testing dataset containing 26,170 cells. The performance of the AI model was further validated using another multinational real-world dataset (data obtained from three centers in Taiwan and one in the United States) comprising 200,639 cells. The AI model achieved an accuracy of 0.881 in classifying individual cells and demonstrated high precision in classifying blasts (0.927), bands and polymorphonuclear neutrophils (0.955), plasma cells (0.930), and lymphocytes (0.789). When the differential counting percentage of each cell type was assessed, a strong correlation (ρ > 0.8) between the AI and manual methods was observed for most cell categories. Conclusions: In this study, an AI algorithm was developed and clinically validated using large, multinational datasets. Our algorithm can locate and classify BM cells simultaneously and has potential clinical applicability for automating BM differential counting.
Subjects
Artificial intelligence
Blood cell count
Bone marrow examination
Publisher
Elsevier Ireland Ltd
Description
Article number 105692
Type
journal article