Department of Clinical Hematology, Key Laboratory of Laboratory Medical Diagnostics Designated by the Ministry of Education, School of Laboratory Medicine, Chongqing Medical University, No. 1, Yixueyuan Road, Chongqing, 400016, China.
Department of Hematology, The First Affiliated Hospital of Chongqing Medical University, No. 1, Youyi Road, Chongqing, 400016, China.
J Cancer Res Clin Oncol. 2023 Dec;149(19):16971-16981. doi: 10.1007/s00432-023-05384-9. Epub 2023 Sep 23.
The morphology of bone marrow cells is essential in identifying malignant hematological disorders. The automatic classification model of bone marrow cell morphology based on convolutional neural networks shows considerable promise in terms of diagnostic efficiency and accuracy. However, due to the lack of acceptable accuracy in bone marrow cell classification algorithms, automatic classification of bone marrow cells is now infrequently used in clinical facilities. To address the issue of precision, in this paper, we propose a Dual Attention Gates DenseNet (DAGDNet) to construct a novel efficient, and high-precision bone marrow cell classification model for enhancing the classification model's performance even further.
DAGDNet is constructed by embedding a novel dual attention gates (DAGs) mechanism in the architecture of DenseNet. DAGs are used to filter and highlight the position-related features in DenseNet to improve the precision and recall of neural network-based cell classifiers. We have constructed a dataset of bone marrow cell morphology from the First Affiliated Hospital of Chongqing Medical University, which mainly consists of leukemia samples, to train and test our proposed DAGDNet together with the bone marrow cell classification dataset.
When evaluated on a multi-center dataset, experimental results show that our proposed DAGDNet outperforms image classification models such as DenseNet and ResNeXt in bone marrow cell classification performance. The mean precision of DAGDNet on the Munich Leukemia Laboratory dataset is 88.1%, achieving state-of-the-art performance while still maintaining high efficiency.
Our data demonstrate that the DAGDNet can improve the efficacy of automatic bone marrow cell classification and can be exploited as an assisting diagnosis tool in clinical applications. Moreover, the DAGDNet is also an efficient model that can swiftly inspect a large number of bone marrow cells and offers the benefit of reducing the probability of an incorrect diagnosis.
骨髓细胞形态学在识别恶性血液病方面至关重要。基于卷积神经网络的骨髓细胞形态自动分类模型在诊断效率和准确性方面具有很大的潜力。然而，由于骨髓细胞分类算法缺乏可接受的准确性，自动分类在临床设施中很少使用。为了解决精度问题，本文提出了一种双注意力门密集网络（DAGDNet），构建了一种新的高效、高精度的骨髓细胞分类模型，以进一步提高分类模型的性能。
DAGDNet 通过在 DenseNet 架构中嵌入一种新的双注意力门（DAGs）机制来构建。DAGs 用于过滤和突出 DenseNet 中的位置相关特征，以提高基于神经网络的细胞分类器的精度和召回率。我们从重庆医科大学第一附属医院的骨髓细胞形态学数据集构建了一个数据集，该数据集主要由白血病样本组成，与骨髓细胞分类数据集一起训练和测试我们提出的 DAGDNet。
在多中心数据集上进行评估时，实验结果表明，我们提出的 DAGDNet 在骨髓细胞分类性能方面优于 DenseNet 和 ResNeXt 等图像分类模型。在慕尼黑白血病实验室数据集上，DAGDNet 的平均精度为 88.1%，实现了最先进的性能，同时仍保持高效。
我们的数据表明，DAGDNet 可以提高自动骨髓细胞分类的效果，并可以作为临床应用中的辅助诊断工具。此外，DAGDNet 也是一种高效的模型，可以快速检查大量的骨髓细胞，并有助于减少误诊的概率。
