AML, ALL, and CML classification and diagnosis based on bone marrow cell morphology combined with convolutional neural network: A STARD compliant diagnosis research.
机构：[a]Department of Opto-Electronic Engineering, Jinan University[b]Department of Gastroenterology, Integrated Hospital of Traditional Chinese Medicine, Southern Medical University, Guangzhou[c]Department of Pharmacy, Maoming People’s Hospital, Maoming, Guangdong, China
Leukemia diagnosis based on bone marrow cell morphology primarily relies on the manual microscopy of bone marrow smears. However, this method is greatly affected by subjective factors and tends to lead to misdiagnosis. This study proposes using bone marrow cell microscopy images and employs convolutional neural network (CNN) combined with transfer learning to establish an objective, rapid, and accurate method for classification and diagnosis of LKA (AML, ALL, and CML). We collected cell microscopy images of 104 bone marrow smears (including 18 healthy subjects, 53 AML patients, 23 ALL patients, and 18 CML patients). The perfect reflection algorithm and a self-adaptive filter algorithm were first used for preprocessing of bone marrow cell images collected from experiments. Subsequently, 3 CNN frameworks (Inception-V3, ResNet50, and DenseNet121) were used to construct classification models for the raw dataset and preprocessed dataset. Transfer learning was used to improve the prediction accuracy of the model. Results showed that the DenseNet121 model based on the preprocessed dataset provided the best classification results, with a prediction accuracy of 74.8%. The prediction accuracy of the DenseNet121 model that was obtained by transfer learning optimization was 95.3%, which was increased by 20.5%. In this model, the prediction accuracies of the normal groups, AML, ALL, and CML were 90%, 99%, 97%, and 95%, respectively. The results showed that the leukemic cell morphology classification and diagnosis based on CNN combined with transfer learning is feasible. Compared with conventional manual microscopy, this method is more rapid, accurate, and objective.
基金：
This work was supported by the National Natural Science Foundation of China (61975069); Natural Science Foundation of Guangdong Province, China(2018A0303131000).
语种：
外文
PubmedID：
中科院(CAS)分区：
出版当年[2019]版：
大类|4 区医学
小类|3 区医学：内科
最新[2025]版：
大类|4 区医学
小类|4 区医学：内科
第一作者：
第一作者机构：[a]Department of Opto-Electronic Engineering, Jinan University
通讯作者：
通讯机构：[b]Department of Gastroenterology, Integrated Hospital of Traditional Chinese Medicine, Southern Medical University, Guangzhou[c]Department of Pharmacy, Maoming People’s Hospital, Maoming, Guangdong, China[*1]Department of Gastroenterology, Integrated Hospital of Traditional Chinese Medicine, Southern Medical University, Guangdong, Guangzhou, 510315, China[*2]Department of Pharmacy, Maoming People’s Hospital, Maoming, Guangdong, 525000, China
推荐引用方式(GB/T 7714)：
Huang Furong,Guang Peiwen,Li Fucui,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.2020,99(45):e23154.doi:10.1097/MD.0000000000023154.
APA：
Huang Furong,Guang Peiwen,Li Fucui,Liu Xuewen,Zhang Weimin&Huang Wendong.(2020).AML, ALL, and CML classification and diagnosis based on bone marrow cell morphology combined with convolutional neural network: A STARD compliant diagnosis research..Medicine,99,(45)
MLA：
Huang Furong,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.".Medicine 99..45(2020):e23154
