基于人工智能技术的骨髓细胞形态学辅助诊断研究进展

doi:10.3969/j.issn.1673-8640.2025.01.002

摘要/Abstract

摘要：

血液系统肿瘤的诊断需要综合考虑临床表现和骨髓细胞形态学、遗传学免疫表型相关检查检测结果，其中骨髓细胞形态学检查结果是部分血液系统疾病形态学诊断的“金标准”。随着组织图像分析和人工智能（AI）技术在临床的广泛应用，基于AI开发的自动图像处理系统在骨髓细胞形态学检查中表现出极大的优势，可以在提高形态学诊断效率和质量的同时大大降低人力成本，并进一步使检测结果具有一致性和可比性。文章综述AI在骨髓细胞形态学识别及其应用于血液系统疾病诊断的最新进展，并探讨AI在未来临床试验和血液系统肿瘤诊断中的重要价值，以及面临的挑战。

关键词: 人工智能, 骨髓, 细胞形态学, 血液系统肿瘤

Abstract:

The diagnosis of hematologic neoplasms requires comprehensive consideration of clinical manifestations，bone marrow cell morphology，genetics and immune phenotypes. However，bone marrow cell morphology examination is regarded as the gold standard for morphological diagnosis of most hematologic diseases. With the widespread application of tissue image analysis and artificial intelligence （AI） in clinical practice，the automatic image processing system developed using AI demonstrates significant advantages in the bone marrow cell morphology，which can improve the efficiency and quality of morphological diagnosis，reduce labor costs，and enhance the consistency and comparability of determination results. This review focuses on the latest progress in AI's identification of bone marrow cell morphology and its application in the diagnosis of hematologic neoplasms，as well as discusses the challenges and value that AI faces in the future clinical trials and diagnostics.

Key words: Artificial intelligence, Bone marrow, Cell morphology, Hematologic neoplasm

中图分类号:

R446.19

王驰, 刘邵梅, 李绵洋. 基于人工智能技术的骨髓细胞形态学辅助诊断研究进展[J]. 检验医学, 2025, 40(1): 8-14.

WANG Chi, LIU Shaomei, LI Mianyang. Research progress on artificial intelligence in assisting diagnosis of bone marrow cell morphology[J]. Laboratory Medicine, 2025, 40(1): 8-14.

图/表 1

参考文献 52

[1]	ALAGGIO R, AMADOR C, ANAGNOSTOPOULOS I, et al. The 5th edition of the World Health Organization Classification of Haematolymphoid Tumours:lymphoid neoplasms[J]. Leukemia, 2022, 36(7):1720-1748.
[2]	KHOURY J D, SOLARY E, ABLA O, et al. The 5th edition of the World Health Organization Classification of Haematolymphoid Tumours:myeloid and histiocytic/dendritic neoplasms[J]. Leukemia, 2022, 36(7):1703-1719.
[3]	刘水清, 彭贤贵, 张杨. 《人工智能辅助血细胞形态学检查的技术要求及其临床应用中国专家共识(2024版)》解读[J]. 临床血液学杂志, 2024, 37(5):298-300.
[4]	刘贵建, 庞博. 应促进和拓展人工智能辅助血细胞形态学检查的临床应用[J]. 中华检验医学杂志, 2023, 46(3):231-237.
[5]	卢兴国. 血液病形态学检查和整合诊断思路[J]. 中华检验医学杂志, 2023, 46(3):238-242.
[6]	杨军霞, 连荷清, 庞博. 人工智能血细胞形态学检查的关键技术进展[J]. 中华检验医学杂志, 2023, 46(3):326-330.
[7]	FU X, FU M, LI Q, et al. Morphogo:an automatic bone marrow cell classification system on digital images analyzed by artificial intelligence[J]. Acta Cytol, 2020, 64(6):588-596.
[8]	VAN EEKELEN L, LITJENS G, HEBEDA K M. Artificial intelligence in bone marrow histological diagnostics:potential applications and challenges[J]. Pathobiology, 2024, 91(1):8-17.
[9]	YASNITSKY L N. Artificial intelligence and medicine:history,current state,and forecasts for the future[J]. Curr Hypertens Rev, 2020, 16(3):210-215.
[10]	SRINIDHI C L, CIGA O, MARTEL A L. Deep neural network models for computational histopathology:a survey[J]. Med Image Anal, 2021, 67:101813.
[11]	BEN BARUCH S, ROTMAN-NATIV N, BARAM A, et al. Cancer-cell deep-learning classification by integrating quantitative-phase spatial and temporal fluctuations[J]. Cells, 2021, 10(12):3353.
[12]	李文静, 白静, 彭斌, 等. 图卷积神经网络及其在图像识别领域的应用综述[J]. 计算机工程与应用, 2023, 59(22):15-35. DOI
[13]	LEWIS J E, POZDNYAKOVA O. Digital assessment of peripheral blood and bone marrow aspirate smears[J]. Int J Lab Hematol, 2023, 45(2):50-58.
[14]	LV Z, CAO X, JIN X, et al. High-accuracy morphological identification of bone marrow cells using deep learning-based Morphogo system[J]. Sci Rep, 2023, 13(1):13364. DOI PMID
[15]	LIN Y, CHEN Q, CHEN T. Recent advancements in machine learning for bone marrow cell morphology analysis[J]. Front Med(Lausanne), 2024, 11:1402768.
[16]	ZHENG X, WANG Y, WANG G, et al. Fast and robust segmentation of white blood cell images by self-supervised learning[J]. Micron, 2018, 107:55-71. DOI PMID
[17]	TARIMO S A, JANG M A, NGASA E E, et al. WBC YOLO-ViT:2 Way - 2 stage white blood cell detection and classification with a combination of YOLOv5 and vision transformer[J]. Comput Biol Med, 2024, 169:107875.
[18]	REHMAN A, ABBAS N, SABA T, et al. Classification of acute lymphoblastic leukemia using deep learning[J]. Microsc Res Tech, 2018, 81(11):1310-1317.
[19]	HEGDE R B, PRASAD K, HEBBAR H, et al. Feature extraction using traditional image processing and convolutional neural network methods to classify white blood cells:a study[J]. Australas Phys Eng Sci Med, 2019, 42(2):627-638.
[20]	NANAA A, AKKUS Z, LEE W Y, et al. Machine learning and augmented human intelligence use in histomorphology for haematolymphoid disorders[J]. Pathology, 2021, 53(3):400-407.
[21]	CHOI J W, KU Y, YOO B W, et al. White blood cell differential count of maturation stages in bone marrow smear using dual-stage convolutional neural networks[J]. PLoS One, 2017, 12(12):e0189259.
[22]	MATEK C, KRAPPE S, MUNZENMAYER C, et al. Highly accurate differentiation of bone marrow cell morphologies using deep neural networks on a large image data set[J]. Blood, 2021, 138(20):1917-1927. DOI PMID
[23]	GLÜGE S, BALABANOV S, KOELZER V H, et al. Evaluation of deep learning training strategies for the classification of bone marrow cell images[J]. Comput Methods Programs Biomed, 2024, 243:107924.
[24]	NAKAMURA I, IDA H, YABUTA M, et al. Evaluation of two semi-supervised learning methods and their combination for automatic classification of bone marrow cells[J]. Sci Rep, 2022, 12(1):16736. DOI PMID
[25]	WANG D, HWANG M, JIANG W C, et al. A deep learning method for counting white blood cells in bone marrow images[J]. BMC Bioinformatics, 2021, 22(5):94.
[26]	CHANDRADEVAN R, ALJUDI A A, DRUMHELLER B R, et al. Machine-based detection and classification for bone marrow aspirate differential counts:initial development focusing on nonneoplastic cells[J]. Lab Invest, 2020, 100(1):98-109.
[27]	LIU J, YUAN R, LI Y, et al. A deep learning method and device for bone marrow imaging cell detection[J]. Ann Transl Med, 2022, 10(4):208. DOI PMID
[28]	TAYEBI R M, MU Y, DEHKHARGHANIAN T, et al. Automated bone marrow cytology using deep learning to generate a histogram of cell types[J]. Commun Med (Lond), 2022, 2:45.
[29]	OUYANG N, WANG W, MA L, et al. Diagnosing acute promyelocytic leukemia by using convolutional neural network[J]. Clinica Chimica Acta, 2021, 512:1-6. DOI PMID
[30]	ECKARDT J N, SCHMITTMANN T, RIECHERT S, et al. Deep learning identifies acute promyelocytic leukemia in bone marrow smears[J]. BMC Cancer, 2022, 22(1):201.
[31]	XIAO Y, HUANG Z, WU J, et al. Rapid screening of acute promyelocytic leukaemia in daily batch specimens:a novel artificial intelligence-enabled approach to bone marrow morphology[J]. Clin Transl Med, 2024, 14(7):e1783.
[32]	MANESCU P, NARAYANAN P, BENDKOWSKI C, et al. Detection of acute promyelocytic leukemia in peripheral blood and bone marrow with annotation-free deep learning[J]. Sci Rep, 2023, 13(1):2562. DOI PMID
[33]	REZAYI S, MOHAMMADZADEH N, BOURAGHI H, et al. Timely diagnosis of acute lymphoblastic leukemia using artificial intelligence-oriented deep learning methods[J]. Comput Intell Neurosci, 2021, 2021:5478157.
[34]	ATTEIA G, ALHUSSAN A A, SAMEE N A. BO-ALLCNN:bayesian-based optimized CNN for acute lymphoblastic leukemia detection in microscopic blood smear images[J]. Sensors(Basel), 2022, 22(15):5520.
[35]	SHAFIQUE S, TEHSIN S. Acute lymphoblastic leukemia detection and classification of its subtypes using pretrained deep convolutional neural networks[J]. Technol Cancer Res Treat, 2018, 17:1533033818802789.
[36]	KIMURA K, TABE Y, AI T, et al. A novel automated image analysis system using deep convolutional neural networks can assist to differentiate MDS and AA[J]. Sci Rep, 2019, 9(1):13385. DOI PMID
[37]	MORI J, KAJI S, KAWAI H, et al. Assessment of dysplasia in bone marrow smear with convolutional neural network[J]. Sci Rep, 2020, 10(1):14734. DOI PMID
[38]	LEE N, JEONG S, PARK M J, et al. Deep learning application of the discrimination of bone marrow aspiration cells in patients with myelodysplastic syndromes[J]. Sci Rep, 2022, 12(1):18677. DOI PMID
[39]	ARBER D A, ORAZI A, HASSERJIAN R P, et al. International consensus classification of myeloid neoplasms and acute leukemias:integrating morphologic,clinical,and genomic data[J]. Blood, 2022, 140(11):1200-1228.
[40]	NAGATA Y, ZHAO R, AWADA H, et al. Machine learning demonstrates that somatic mutations imprint invariant morphologic features in myelodysplastic syndromes[J]. Blood, 2020, 136(20):2249-2262. DOI PMID
[41]	HUANG F, GUANG P, LI F, et al. AML,ALL,and CML classification and diagnosis based on bone marrow cell morphology combined with convolutional neural network:a STARD compliant diagnosis research[J]. Medicine(Baltimore), 2020, 99(45):e23154.
[42]	YU Z, LI J, WEN X, et al. AMLnet,a deep-learning pipeline for the differential diagnosis of acute myeloid leukemia from bone marrow smears[J]. J Hematol Oncol, 2023, 16(1):27.
[43]	AHMED N, YIGIT A, ISIK Z, et al. Identification of leukemia subtypes from microscopic images using convolutional neural network[J]. Diagnostics(Basel), 2019, 9(3):104.
[44]	杜忠华, 张福明, 吴波, 等. 人工智能技术Morphogo系统在骨髓细胞形态学检查的临床应用[J]. 中国实验诊断学, 2021, 25(7):958-961.
[45]	MOHLMAN J S, LEVENTHAL S D, HANSEN T, et al. Improving augmented human intelligence to distinguish burkitt lymphoma from diffuse large B-cell lymphoma cases[J]. Am J Clin Pathol, 2020, 153(6):743-759. DOI PMID
[46]	TANG G, FU X, WANG Z, et al. A machine learning tool using digital microscopy (Morphogo)for the identification of abnormal lymphocytes in the bone marrow[J]. Acta Cytol, 2021, 65(4):354-357.
[47]	CHEN P, CHEN XU R, CHEN N, et al. Detection of metastatic tumor cells in the bone marrow aspirate smears by artificial intelligence (AI)-based Morphogo system[J]. Front Oncol, 2021, 11:742395.
[48]	刘思恒, 李佳, 杨武晨, 等. 人工智能识别骨髓细胞可应用于诊断急性白血病微小残留病[J]. 中华检验医学杂志, 2023, 46(3):280-285.
[49]	刘思恒, 李佳, 彭贤贵, 等. 探索Morphogo在多发性骨髓瘤MRD检测中的应用[J]. 重庆医科大学学报, 2022, 47(8):948-952.
[50]	CHEN P, ZHANG L, CAO X, et al. Detection of circulating plasma cells in peripheral blood using deep learning‐based morphological analysis[J]. Cancer, 2024, 130(10):1884-1893.
[51]	BRÜCK O E, LALLUKKA-BRÜCK S E, HOHTARI H R, et al. Machine learning of bone marrow histopathology identifies genetic and clinical determinants in patients with MDS[J]. Blood Cancer Discov, 2021, 2(3):238-249.
[52]	XING Y, LIU X, DAI J, et al. Artificial intelligence of digital morphology analyzers improves the efficiency of manual leukocyte differentiation of peripheral blood[J]. BMC Med Inform Decis Mak, 2023, 23(1):50.

系统名称	公司	应用范围
DCS-1600细胞医学图像分析仪、DSS-8200玻片扫描影像系统	深圳深析智能有限公司	利用计算机软件对涂片的细胞进行分类标记和分析，快速生成细胞形态和计数报告
Morphogo系统	杭州智微信息科技有限公司	对骨髓有核细胞进行图像采集、定位、预分类和数量统计，可通过内置模板形成图文报告
Aether AI Hema骨髓涂片数位形态分析软件	中国台湾云象科技公司	自动分类计数骨髓细胞，可在5 min之内完成判读，可识别15种骨髓血液细胞
Cellsee骨髓细胞形态分析仪	无锡瑄立智能科技有限公司	基于高倍镜下高清细胞图像，采用辅助图像识别算法计数骨髓和外周血样本中的各类细胞并分类，人工审核后修改内置模板，出具图文报告；部分医院已试用于浆膜腔积液、脑脊液图像识别等

系统名称	公司	应用范围
DCS-1600细胞医学图像分析仪、DSS-8200玻片扫描影像系统	深圳深析智能有限公司	利用计算机软件对涂片的细胞进行分类标记和分析，快速生成细胞形态和计数报告
Morphogo系统	杭州智微信息科技有限公司	对骨髓有核细胞进行图像采集、定位、预分类和数量统计，可通过内置模板形成图文报告
Aether AI Hema骨髓涂片数位形态分析软件	中国台湾云象科技公司	自动分类计数骨髓细胞，可在5 min之内完成判读，可识别15种骨髓血液细胞
Cellsee骨髓细胞形态分析仪	无锡瑄立智能科技有限公司	基于高倍镜下高清细胞图像，采用辅助图像识别算法计数骨髓和外周血样本中的各类细胞并分类，人工审核后修改内置模板，出具图文报告；部分医院已试用于浆膜腔积液、脑脊液图像识别等