Xi'an University of Science and Technology, School of Communication and Information Engineering, Xi'an, China.
Xi'an Key Laboratory of Network Convergence Communication, Xi'an, China.
J Biomed Opt. 2023 Apr;28(4):045002. doi: 10.1117/1.JBO.28.4.045002. Epub 2023 Apr 12.
Leukocytes are mainly composed of neutrophils, basophils, eosinophils, monocytes, and lymphocytes. The number and proportion of different types of leukocytes correspond to different diseases, so an accurate segmentation of each type of leukocyte is important for the diagnosis of disease. However, the acquisition of blood cell images can be affected by external environmental factors, which can lead to variable light and darkness, complex backgrounds, and poorly characterized leukocytes.
To address the problem of complex blood cell images collected under different environments and the lack of obvious leukocyte features, a leukocyte segmentation method based on improved U-net is proposed.
First, adaptive histogram equalization-retinex correction was introduced for data enhancement to make the leukocyte features in the blood cell images clearer. Then, to address the problem of similarity between different types of leukocytes, convolutional block attention module is added to the four skip connections of U-net to focus the features from spatial and channel aspects, so that the network can quickly locate the high-value information of features in different channels and spaces. It avoids the problem of large amount of repeated computation of low-value information, prevents overfitting, and improves the training efficiency and generalization ability of the network. Finally, to solve the problem of class imbalance in blood cell images and to better segment the cytoplasm of leukocytes, a loss function combining focal loss and Dice loss is proposed.
We use the BCISC public dataset to verify the effectiveness of the proposed method. The segmentation of multiple leukocytes using the method of this paper can achieve 99.53% accuracy and 91.89% mIoU.
The experimental results show that the method achieves good segmentation results for lymphocytes, basophils, neutrophils, eosinophils, and monocytes.
白细胞主要由中性粒细胞、嗜碱性粒细胞、嗜酸性粒细胞、单核细胞和淋巴细胞组成。不同类型白细胞的数量和比例对应着不同的疾病，因此准确地分割每种类型的白细胞对疾病的诊断很重要。然而，血细胞图像的获取可能会受到外部环境因素的影响，这可能导致光照和黑暗度变化、复杂的背景以及特征不明显的白细胞。
针对不同环境下采集的复杂血细胞图像以及白细胞特征不明显的问题，提出了一种基于改进 U-net 的白细胞分割方法。
首先，引入自适应直方图均衡化-反射率校正进行数据增强，以使血细胞图像中的白细胞特征更清晰。然后，针对不同类型白细胞之间的相似性问题，在 U-net 的四个 skip 连接中添加卷积块注意力模块，从空间和通道两个方面关注特征，使网络能够快速定位不同通道和空间中特征的高值信息。这避免了大量重复计算低值信息的问题，防止了过拟合，并提高了网络的训练效率和泛化能力。最后，为了解决血细胞图像中类不平衡的问题，并更好地分割白细胞的细胞质，提出了一种结合焦点损失和 Dice 损失的损失函数。
我们使用 BCISC 公共数据集验证了所提出方法的有效性。使用本文方法对多种白细胞的分割可以达到 99.53%的准确率和 91.89%的 mIoU。
实验结果表明，该方法对淋巴细胞、嗜碱性粒细胞、中性粒细胞、嗜酸性粒细胞和单核细胞的分割效果较好。
