A machine-learning-based algorithm for bone marrow cell differential counting

Ta-Chuan Yu; Cheng-Kun Yang; Wei-Han Hsu; Cheng-An Hsu; Hsiao-Chun Wang; Hsin-Jung Hsiao; Hsiao-Ling Chao; Han-Peng Hsieh; Jia-Rong Wu; Yen-Chun Tsai; Yi-Mei Chiang; Poshing Lee; Che-Pin Lin; Ling-Ping Chen; Yung-Chuan Sung; Ya-Yun Yang; Chin-Ling Yu; Chih-Kang Lin; Chia-Pin Kang; Che-Wei Chang; Hsiu-Lin Chang; Jung-Hsuan Chu; Kai-Ling Cathy Kao; Li Lin; Min-Sheng Wu; Pei-Chen Lin; Po-Hsu Yang; Qun-Yi Zhang; Ming-Kai Chuang; Sheng-Chieh Chou; Sheng-Chuan Huang; Chieh-Lung Cheng; Chi-Yuan Yao; Feng-Ming Tien; Chao-Yuan Yeh; Wen-Chien Chou

doi:10.1016/j.ijmedinf.2024.105692

A machine-learning-based algorithm for bone marrow cell differential counting

Int J Med Inform. 2024 Nov 7:194:105692. doi: 10.1016/j.ijmedinf.2024.105692. Online ahead of print.

Authors

Ta-Chuan Yu¹, Cheng-Kun Yang², Wei-Han Hsu², Cheng-An Hsu³, Hsiao-Chun Wang³, Hsin-Jung Hsiao³, Hsiao-Ling Chao³, Han-Peng Hsieh³, Jia-Rong Wu³, Yen-Chun Tsai³, Yi-Mei Chiang³, Poshing Lee⁴, Che-Pin Lin⁵, Ling-Ping Chen⁵, Yung-Chuan Sung⁵, Ya-Yun Yang⁵, Chin-Ling Yu¹, Chih-Kang Lin², Chia-Pin Kang², Che-Wei Chang², Hsiu-Lin Chang², Jung-Hsuan Chu², Kai-Ling Cathy Kao², Li Lin², Min-Sheng Wu², Pei-Chen Lin², Po-Hsu Yang², Qun-Yi Zhang², Ming-Kai Chuang⁶, Sheng-Chieh Chou⁷, Sheng-Chuan Huang⁸, Chieh-Lung Cheng⁷, Chi-Yuan Yao⁶, Feng-Ming Tien⁷, Chao-Yuan Yeh⁹, Wen-Chien Chou¹⁰

Affiliations

¹ Department of Internal Medicine, National Taiwan University Hospital Yunlin Branch, No. 579, Sec. 2, Yunlin Rd., Douliu City, Yunlin County 640203, Taiwan.
² aetherAI, Co., Ltd., 9F, No. 3-2, Park Street, Nangang District, Taipei 115, Taiwan.
³ Department of Laboratory Medicine, National Taiwan University Hospital, No. 7, Zhongshan S Rd, Zhongzheng District, Taipei City 100, Taiwan.
⁴ BioReference Labs, 481 Edward H. Ross Drive Elmwood Park, NJ 07407, United States.
⁵ Cathy General Hospital, No. 280, Section 4, Ren'ai Rd, Da'an District, Taipei City 106, Taiwan.
⁶ Department of Laboratory Medicine, National Taiwan University Hospital, No. 7, Zhongshan S Rd, Zhongzheng District, Taipei City 100, Taiwan; Division of Hematology, Department of Internal Medicine, National Taiwan University Hospital, No. 7, Zhongshan S Rd, Zhongzheng District, Taipei City 100, Taiwan.
⁷ Division of Hematology, Department of Internal Medicine, National Taiwan University Hospital, No. 7, Zhongshan S Rd, Zhongzheng District, Taipei City 100, Taiwan.
⁸ Department of Laboratory Medicine, National Taiwan University Hospital, No. 7, Zhongshan S Rd, Zhongzheng District, Taipei City 100, Taiwan; Division of Hematology, Department of Internal Medicine, National Taiwan University Hospital, No. 7, Zhongshan S Rd, Zhongzheng District, Taipei City 100, Taiwan; Department of Hematology and Oncology, Hualien Tzu Chi Hospital, No. 707, Sec. 3, Chung Yang Rd., Hualien City 970, Taiwan; Department of Clinical Pathology, Hualien Tzu Chi Hospital, No. 707, Sec. 3, Chung Yang Rd., Hualien City 970, Taiwan.
⁹ aetherAI, Co., Ltd., 9F, No. 3-2, Park Street, Nangang District, Taipei 115, Taiwan. Electronic address: joeyeh@aetherai.com.
¹⁰ Department of Laboratory Medicine, National Taiwan University Hospital, No. 7, Zhongshan S Rd, Zhongzheng District, Taipei City 100, Taiwan; Division of Hematology, Department of Internal Medicine, National Taiwan University Hospital, No. 7, Zhongshan S Rd, Zhongzheng District, Taipei City 100, Taiwan. Electronic address: wchou@ntu.edu.tw.

PMID: 39549389
DOI: 10.1016/j.ijmedinf.2024.105692

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.

Keywords: Artificial intelligence; Blood cell count; Bone marrow examination.