Abstract：The number and structural characteristics of leukocytes contain important information about human health, and the counting of different types of leukocytes can provide important basis for the early treatment of many diseases. However, the high cost of collecting and labeling leukocyte data integration and the small number of available leukocyte datasets currently pose challenges for automatic computer-aided leukocyte classification. To address these challenges, an active iterative optimization leukocyte image classification model incorporating attention was proposed in this paper. By attaching a LossNet network for active learning to the ResNet18 backbone network, the most representative samples were selected from a large number of unlabeled samples for labeling, reducing the amount of samples that need to be manually labeled. Meanwhile, to cope with the impact of inter-class imbalance in the leukocyte dataset on active learning, this paper added an active iterative augmentation module to select difficult samples in the training process for data augmentation containing random factors, which formed a two-way information interaction from the bottom up and enhanced the adaptability of the model to imbalanced datasets. Finally, after comparing three attention modules, this paper chose to incorporate the CBAM attention module to enhance the model′s focus on the leukocyte feature regions and improve the model′s performance. In this study, the Raabin-WBC dataset containing 14514 leukocyte microscopy images was used for method validation, and the experimental results showed that the classification accuracy of the model proposed in this paper reached 92.35%, 93.64%, and 94.86% when using 28%, 37%, and 52% samples of the training set, respectively, which was 5.14%, 9.24%, and 2.37% higher than the original ResNet18, respectively, and the model greatly reduced the labeling cost of leukocyte dataset, showing wide application prospectives in medical datasets that was lack of labelling.
蒋舒颖, 李志明, 莫贤, 孙昂, 张俊然. 融合注意力的主动迭代优化白细胞图像分类模型[J]. 中国生物医学工程学报, 2024, 43(4): 408-418.
Jiang Shuying, Li Zhiming, Mo Xian, Sun Ang, Zhang Junran. Active Iterative Optimization of Leukocyte Image Classification Model with Fused Attention. Chinese Journal of Biomedical Engineering, 2024, 43(4): 408-418.
[1] Khaled A, Sertan S. Improved classification of white blood cells with the generative adversarial network and deep convolutional neural network.[J].Comput Intell Neurosci,2020, 2020:6490479. [2] Saade P, El Jammal R, El Hayek S, et al. Computer-aided detection of white blood cells using geometric features and color[C]// 2018 9th Cairo International Biomedical Engineering Conference (CIBEC). Piscataway: IEEE, 2018: 142-145. [3] Ghosh S, Majumder M, Kudeshia A. Leukox: leukocyte classification using least entropy combiner (lec) for ensemble learning[J]. IEEE Transactions on Circuits and Systems II: Express Briefs, 2021, 68(8): 2977-2981. [4] Karthikeyan MP, Venkatesan R. Interpolative leishman-stained transformation invariant deep pattern classification for white blood cells[J]. Soft Computing, 2020, 24(16): 12215-12225. [5] Özyurt F. A fused CNN model for WBC detection with MRMR feature selection and extreme learning machine[J]. Soft Computing, 2020, 24(11): 8163-8172. [6] Baby D, Devaraj SJ, Hemanth J. Leukocyte classification based on feature selection using extra trees classifier: a transfer learning approach[J]. Turkish Journal of Electrical Engineering and Computer Sciences, 2021, 29(8): 2742-2757. [7] Hegde RB, Prasad K, Hebbar H, et al. Feature extraction using traditional image processing and convolutional neural network methods to classify white blood cells: a study[J]. Australasian Physical & Engineering Sciences in Medicine, 2019, 42: 627-638. [8] Wijesinghe CB, Wickramarachchi DN, Kalupahana IN, et al. Fully automated detection and classification of white blood cells[C]// 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). Piscataway: IEEE, 2020: 1816-1819. [9] Ryabchykov O, Ramoji A, Bocklitz T, et al. Leukocyte subtypes classification by means of image processing[C]//2016 Federated conference on computer science and information systems (FedCSIS). Piscataway: IEEE, 2016: 309-316. [10] Chhabra G. Automated hematology analyzers: recent trends and applications[J]. Journal of Laboratory Physicians, 2018, 10(1): 15-16. [11] Bigorra L, Larriba I, Gutiérrez-Gallego R. Machine learning algorithms for the detection of spurious white blood cell differentials due to erythrocyte lysis resistance[J]. Journal of Clinical Pathology, 2019, 72(6): 431-437. [12] Dhieb N, Ghazzai H, Besbes H, et al. An automated blood cells counting and classification framework using mask R-CNN deep learning model[C]//2019 31st International Conference on Microelectronics (ICM). Piscataway: IEEE, 2019: 300-303. [13] El Achi H, Khoury JD. Artificial intelligence and digital microscopy applications in diagnostic hematopathology[J]. Cancers, 2020, 12(4): 797. [14] 王亚品,曹益平,付光凯等. 基于深度卷积神经网络的人体外周血白细胞显微图像分类[J]. 光电子· 激光, 2019, 30(5): 546-555. [15] Chen H, Liu J, Hua C, et al. Accurate classification of white blood cells by coupling pre-trained ResNet and DenseNet with SCAM mechanism[J]. BMC Bioinformatics, 2022, 23(1): 1-20. [16] Perez L, Wang J. The effectiveness of data augmentation in image classification using deep learning[EB/OL]. arXiv preprint arXiv:1712.04621, 2017-12-03/2023-02-23. [17] 马力,帅仁俊,刘文佳,李文煜.基于改进的残差神经网络的白细胞分类[J].计算机工程与设计,2020,41(10):2982-2987. [18] Ren P, Xiao Y, Chang X, et al. A survey of deep active learning[J]. ACM Computing Surveys, 2021, 54(9): 1-40. [19] Singh A, Chakraborty S. Deep active learning with relative label feedback: An application to facial age estimation[C]//2021 International Joint Conference on Neural Networks (IJCNN). Piscataway: IEEE, 2021: 1-8. [20] Alahmari SS, Goldgof D, Hall LO, et al. Automatic cell counting using active deep learning and unbiased stereology[C]//2019 IEEE International Conference on Systems, Man and Cybernetics (SMC). Piscataway: IEEE, 2019: 1708-1713. [21] Wen S, Kurc TM, Hou L, et al. Comparison of different classifiers with active learning to support quality control in nucleus segmentation in pathology images[J]. AMIA Summits on Translational Science Proceedings, 2018, 2018: 227. [22] Yang L, Zhang Y, Chen J, et al. Suggestive annotation: A deep active learning framework for biomedical image segmentation[C]// Proceedings of MICCAI 2017: 20th International Conference on Medical Image Computing and Computer Assisted Intervention. Quebec City: Springer International Publishing, 2017: 399-407. [23] 鞠孟汐,李欣蔚,李章勇.基于深度主动学习的白带白细胞智能检测方法研究[J].生物医学工程学杂志,2020,37(3):519-526. [24] Beluch WH, Genewein T, Nürnberger A, et al. The power of ensembles for active learning in image classification[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 9368-9377. [25] Geifman Y, El-Yaniv R .Deep active learning with a neural architecture search[C]// Proceedings of the Advances in Neural Information Processing Svstems 32: Annual Conference on Neural Information Processing Systems. San Diego: NIPS,2019.5974-5984. [26] Shui C, Zhou F, Gagné C, et al. Deep active learning: unified and principled method for query and training[C]//International Conference on Artificial Intelligence and Statistics. New York: PMLR, 2020: 1308-1318. [27] Yoo D, Kweon I S. Learning loss for active learning[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2019: 93-102. [28] He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE,2016: 770-778. [29] Fifty C, Amid E, Zhao Z, et al. Efficiently identifying task groupings for multi-task learning[J]. Advances in Neural Information Processing Systems, 2021, 34: 27503-27516. [30] 怀听听,赵建伟,曹飞龙,等.基于综合特征和随机森林的白细胞分类算法[J].中国计量学院学报,2015,26(4):474-479. [31] Settles B. Active learning literature survey[J]. Science, 1995, 10(3): 237-304. [32] Aggarwal U, Popescu A, Hudelot C. Active learning for imbalanced datasets[C]//Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. Piscataway:IEEE,2020: 1428-1437. [33] Lin TY, Goyal P, Girshick R, et al. Focal loss for dense object detection[C]//Proceedings of the IEEE International Conference on Computer Vision. Piscataway:IEEE,2017: 2980-2988. [34] Wang Q, Wu B, Zhu P, et al. ECA-Net: Efficient channel attention for deep convolutional neural networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2020: 11534-11542. [35] Lee HJ, Kim HE, Nam H. Srm: a style-based recalibration module for convolutional neural networks[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. Piscataway:IEEE,2019: 1854-1862. [36] Woo S, Park J, Lee JY, et al. Cbam: convolutional block attention module[C]//.Proceedings of the European Conference on Computer Vision (ECCV).Berlin: Springer, 2018: 3-19. [37] Kouzehkanan Z M, Saghari S, Tavakoli E, et al. Raabin-WBC: a large free access dataset of white blood cells from normal peripheral blood[EB/OL]. bioRxiv, 2021: 2021.05. 02.442287, 2021-05-29/2023-02-23. [38] Standley T, Zamir A, Chen D, et al.Which tasks should be learned together in multi-task learning?[C]//International Conference on Machine Learning. New York: PMLR, 2020:9120-9132. [39] Zhao Yan, Wang Xiuying, Che Tongtong, et al. Multi-task deep learning for medical image computing and analysis: a review[J].Comput Biol Med, 2023, 153:106496. [40] Guo Menghao. Attention mechanisms in computer vision: a survey[J]. Computational Visual Media, 2022, 8(3) : 331-368.
