Morphogo: An Automatic Bone Marrow Cell Classification System on Digital Images Analyzed by Artificial Intelligence

Abstract

Introduction: The nucleated-cell differential count on the bone marrow aspirate smears is required for the clinical diagnosis of hematological malignancy. Manual bone marrow differential count is time consuming and lacks consistency. In this study, a novel artificial intelligence (AI)-based system was developed to perform cell automatic classification of bone marrow cells and determine its potential clinical applications. Materials and Methods: Bone marrow aspirate smears were collected from the Xinqiao Hospital of Army Medical University. First, an automated analysis system (Morphogo) scanned and generated whole digital images of bone marrow smears. Then, the nucleated marrow cells in the selected areas of the smears at a magnification of ×1,000 were analyzed by the software utilizing an AI-based platform. The cell classification results were further reviewed and confirmed independently by 2 experienced pathologists. The automatic cell classification performance of the system was evaluated using 3 categories: accuracy, sensitivity, and specificity. Correlation coefficients and linear regression equations between automatic cell classification by the AI-based system and concurrent manual differential count were calculated. Results: In 230 cases, the classification accuracy was above 85.7% for hematopoietic lineage cells. Averages of sensitivity and specificity of the system were found to be 69.4 and 97.2%, respectively. The differential cell percentage of the automated count based on 200–500 cell counts was correlated with differential cell percentage provided by the pathologists for granulocytes, erythrocytes, and lymphocytes (r ≥ 0.762, p < 0.001). Discussion/Conclusion: This pilot study confirmed that the Morphogo system is a reliable tool for automatic bone marrow cell differential count analysis and has potential for clinical applications. Current ongoing large-scale multicenter validation studies will provide more information to further confirm the clinical utility of the system.

A Machine Learning Tool Using Digital Microscopy (Morphogo) for the Identification of Abnormal Lymphocytes in the Bone Marrow

“…It is proved to be a useful screening tool to discriminate abnormal nucleated cells from normal hematopoietic cells, it has the potential to optimize the work flow of pathologists in the daily practice of hematopathology. Plasma cells and mature lymphocytes also displayed a good correlation [2].…”

“…The Morphogo system was validated to recognize lymphocytes in the differential from other lineages of bone marrow hematopoietic cells; the results have already been published in our previous studies [2]. The accuracy of recognition of lymphocytes in bone marrow aspirate smears by the instrument was 87.8% (sensitivity 85.5% and specificity 88.3%).…”

“…Recently, the validation study has been published. It demonstrated a recognition rate of 85.7% of nucleated cells in bone marrow and a high agreement between the percentage of cell series by the automatic system and those by manual count under the light microscope [2]. This system is still in the early phase of clinical diagnostic implementation and is currently more used for telepathology consultation and research projects.…”

“…A representative digital morphology microscopy system is "Morphogo" [2], which allows batch automated analysis of bone marrow smears, scanning the smear (20 mm × 40 mm) and generating a whole slide image (0.17 ± 0.02 μm/pixel) of the bone marrow smear, then automatically acquire, segment and identify nucleated cells in the digital image at a magnification of ×1,000 (×100 oil, 0.018 ± 0.005 μm/pixel) [3], finally generate an auxiliary report of the bone marrow smear. The system has established a digital analysis process required for the morphological analysis of bone marrow smears.…”

Investigation of modifications of the basic computer algorithm of artificial immune system

“…Алгоритм искусственной иммунной системы получил широкое применение в системах принятия решений и анализа данных в медицине и физике [3,5]. Поэтому снижение затрат машинного времени, энергоресурсов, а также увеличение сходимости данного алгоритма -актуальные задачи инженерии информационных системх [6].…”