Boldú Laura, Merino Anna, Acevedo Andrea, Molina Angel, Rodellar José
Hospital Clínic de Barcelona-IDIBAPS, Haematology and Cytology Unit, CORE Laboratory, Biomedical Diagnostic Centre, Spain.
Hospital Clínic de Barcelona-IDIBAPS, Haematology and Cytology Unit, CORE Laboratory, Biomedical Diagnostic Centre, Spain.
Comput Methods Programs Biomed. 2021 Apr;202:105999. doi: 10.1016/j.cmpb.2021.105999. Epub 2021 Feb 12.
Morphological differentiation among blasts circulating in blood in acute leukaemia is challenging. Artificial intelligence decision support systems hold substantial promise as part of clinical practise in detecting haematological malignancy. This study aims to develop a deep learning-based system to predict the diagnosis of acute leukaemia using blood cell images.
A set of 731 blood smears containing 16,450 single-cell images was analysed from 100 healthy controls, 191 patients with viral infections and 148 with acute leukaemia. Training and testing sets were arranged with 85% and 15% of these smears, respectively. To find the best architecture for acute leukaemia classification VGG16, ResNet101, DenseNet121 and SENet154 were evaluated. Fine-tuning was implemented to these pre-trained CNNs to adapt their layers to our data. Once the best architecture was chosen, a system with two modules working sequentially was configured (ALNet). The first module recognised abnormal promyelocytes among other mononuclear blood cell images, such as lymphocytes, monocytes, reactive lymphocytes and blasts. The second distinguished if blasts were myeloid or lymphoid lineage. The final strategy was to predict patients' initial diagnosis of acute leukaemia lineage using the blood smear review. ALNet was assessed with smears of the testing set.
ALNet provided the correct diagnostic prediction of all patients with promyelocytic and myeloid leukaemia. Sensitivity, specificity and precision values of 100%, 92.3% and 93.7%, respectively, were obtained for myeloid leukaemia. Regarding lymphoid leukaemia, a sensitivity of 89% and specificity and precision values of 100% were obtained.
ALNet is a predictive model designed with two serially connected convolutional networks. It is proposed to assist clinical pathologists in the diagnosis of acute leukaemia during the blood smear review. It has been proved to distinguish neoplastic (leukaemia) and non-neoplastic (infections) diseases, as well as recognise the leukaemia lineage.
急性白血病患者血液中循环的原始细胞的形态学鉴别具有挑战性。人工智能决策支持系统作为临床实践的一部分，在检测血液系统恶性肿瘤方面具有巨大潜力。本研究旨在开发一种基于深度学习的系统，利用血细胞图像预测急性白血病的诊断。
分析了来自100名健康对照者、191名病毒感染患者和148名急性白血病患者的731份血涂片，共包含16450张单细胞图像。训练集和测试集分别由这些血涂片的85%和15%组成。为了找到用于急性白血病分类的最佳架构，对VGG16、ResNet101、DenseNet121和SENet154进行了评估。对这些预训练的卷积神经网络进行微调，使其各层适应我们的数据。一旦选择了最佳架构，就配置了一个由两个模块顺序工作的系统（ALNet）。第一个模块在其他单核血细胞图像（如淋巴细胞、单核细胞、反应性淋巴细胞和原始细胞）中识别异常早幼粒细胞。第二个模块区分原始细胞是髓系还是淋巴系。最终策略是通过血涂片检查预测患者急性白血病谱系的初始诊断。使用测试集的血涂片对ALNet进行评估。
ALNet对所有早幼粒细胞白血病和髓系白血病患者都提供了正确的诊断预测。髓系白血病的敏感性、特异性和精确率分别为100%、92.3%和93.7%。对于淋巴系白血病，敏感性为89%，特异性和精确率为100%。
ALNet是一个由两个串联连接的卷积网络设计的预测模型。建议在血涂片检查期间协助临床病理学家诊断急性白血病。它已被证明能够区分肿瘤性（白血病）和非肿瘤性（感染）疾病，以及识别白血病谱系。
