{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T16:05:59Z","timestamp":1791821159044,"version":"4.3.4"},"reference-count":28,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T00:00:00Z","timestamp":1745452800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>White blood cell (WBC) classification plays a crucial role in hematopathology and clinical diagnostics. However, traditional methods are constrained by limited receptive fields and insufficient utilization of contextual information, which hinders classification performance. To address these limitations, this paper proposes an enhanced WBC classification algorithm, CCE-YOLOv7, which is built upon the YOLOv7 framework. The proposed method introduces four key innovations to enhance detection accuracy and model efficiency: (1) A novel Conv2Former (Convolutional Transformer) backbone was designed to combine the local pattern extraction capability of convolutional neural networks (CNNs) with the global contextual reasoning of transformers, thereby improving the expressiveness of feature representation. (2) The CARAFE (Content-Aware ReAssembly of Features) upsampling operator was adopted to replace conventional interpolation methods, thereby enhancing the spatial resolution and semantic richness of feature maps. (3) An Efficient Multi-scale Attention (EMA) module was introduced to refine multi-scale feature fusion, enabling the model to better focus on spatially relevant features critical for WBC classification. (4) Soft-NMS (Soft Non-Maximum Suppression) was used instead of traditional NMS to better preserve true positives in densely packed or overlapping cell scenarios, thereby reducing false positives and false negatives. Experimental validation was conducted on a WBC image dataset acquired using the Fourier ptychographic microscopy (FPM) system. The proposed CCE-YOLOv7 achieved a detection accuracy of 89.3%, showing a 7.8% improvement over the baseline YOLOv7. Furthermore, CCE-YOLOv7 reduced the number of parameters by 2 million and lowered computational complexity by 5.7 GFLOPs, offering an efficient and lightweight model suitable for real-time clinical applications. To further evaluate model effectiveness, comparative experiments were conducted with YOLOv8 and YOLOv11. CCE-YOLOv7 achieved a 4.1% higher detection accuracy than YOLOv8 while reducing computational cost by 2.4 GFLOPs. Compared with the more advanced YOLOv11, CCE-YOLOv7 maintained competitive accuracy (only 0.6% lower) while using significantly fewer parameters and 4.3 GFLOPs less in computation, highlighting its superior trade-off between accuracy and efficiency. These results demonstrate that CCE-YOLOv7 provides a robust, accurate, and computationally efficient solution for automated WBC classification, with significant clinical applicability.<\/jats:p>","DOI":"10.3390\/s25092699","type":"journal-article","created":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T09:26:58Z","timestamp":1745486818000},"page":"2699","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Research and Optimization of White Blood Cell Classification Methods Based on Deep Learning and Fourier Ptychographic Microscopy"],"prefix":"10.3390","volume":"25","author":[{"given":"Mingjing","family":"Li","sequence":"first","affiliation":[{"name":"College of Electronic Information Engineering, Changchun University, Changchun 130022, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junshuai","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Electronic Information Engineering, Changchun University, Changchun 130022, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shu","family":"Fang","sequence":"additional","affiliation":[{"name":"College of Electronic Information Engineering, Changchun University, Changchun 130022, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Le","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Electronic Information Engineering, Changchun University, Changchun 130022, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyang","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Electronic Information Engineering, Changchun University, Changchun 130022, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haijiao","family":"Yun","sequence":"additional","affiliation":[{"name":"College of Electronic Information Engineering, Changchun University, Changchun 130022, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoli","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Electronic Information Engineering, Changchun University, Changchun 130022, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingyu","family":"Du","sequence":"additional","affiliation":[{"name":"College of Electronic Information Engineering, Changchun University, Changchun 130022, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziqing","family":"Han","sequence":"additional","affiliation":[{"name":"College of Electronic Information Engineering, Changchun University, Changchun 130022, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,4,24]]},"reference":[{"key":"ref_1","first-page":"118","article-title":"The value of blood smear analysis in routine blood test","volume":"16","author":"Chen","year":"2018","journal-title":"Chin. Med. Guidel."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Bochkovskiy, A., and Liao, H.Y.M. (2023, January 17\u201324). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"ref_3","first-page":"58","article-title":"Clinical comparative study between blood cell analyzer results and blood smear analysis in abnormal cases","volume":"13","author":"Yu","year":"2016","journal-title":"Chin. Med. Innov."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"739","DOI":"10.1038\/nphoton.2013.187","article-title":"Wide-field, high-resolution Fourier ptychographic microscopy","volume":"7","author":"Zheng","year":"2013","journal-title":"Nat. Photonics"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1016\/j.compmedimag.2014.11.005","article-title":"Digital pathology with Fourier ptychography","volume":"42","author":"Horstmeyer","year":"2015","journal-title":"Comput. Med. Imaging Graph."},{"key":"ref_6","unstructured":"Konda, P.C., Taylor, J.M., and Harvey, A.R. (2018). Parallelized aperture synthesis using multi-aperture Fourier ptychographic microscopy. arXiv."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"050802","DOI":"10.1063\/1.5090552","article-title":"Full-field Fourier ptychography (FFP): Spatially varying pupil modeling and its application for rapid field-dependent aberration metrology","volume":"4","author":"Song","year":"2019","journal-title":"APL Photonics"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Wei, H., Du, J., Liu, L., He, Y., Yang, Y., Hu, S., and Tang, Y. (2021). Accurate and stable two-step LED position calibration method for Fourier ptychographic microscopy. J. Biomed. Opt., 26.","DOI":"10.1117\/1.JBO.26.10.106502"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"128163","DOI":"10.1016\/j.optcom.2022.128163","article-title":"Space-based correction method for LED array misalignment in Fourier ptychographic microscopy","volume":"514","author":"Zhu","year":"2022","journal-title":"Opt. Commun."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"976","DOI":"10.1364\/OPTICA.5.000976","article-title":"Single-shot phase retrieval via Fourier ptychographic microscopy","volume":"5","author":"Lee","year":"2018","journal-title":"Optica"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Wu, J., Bian, Z., Suo, J., Zheng, G., and Dai, Q. (2017). Fourier ptychographic microscopy using wavelength multiplexing. J. Biomed. Opt., 22.","DOI":"10.1117\/1.JBO.22.6.066006"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"3365","DOI":"10.1364\/OL.43.003365","article-title":"Single-shot quantitative phase microscopy based on color multiplexed Fourier ptychography","volume":"43","author":"Sun","year":"2018","journal-title":"Opt. Lett."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1186\/s43074-022-00071-3","article-title":"Adaptive optical quantitative phase imaging based on annular illumination Fourier ptychographic microscopy","volume":"3","author":"Shu","year":"2022","journal-title":"PhotoniX"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1016\/j.patcog.2018.01.027","article-title":"Integrating multi-level deep learning and concept ontology for large-scale visual recognition","volume":"78","author":"Kuang","year":"2018","journal-title":"Pattern Recognit."},{"key":"ref_15","first-page":"166","article-title":"The value of routine blood tests in infection determination","volume":"3","author":"Ju","year":"2020","journal-title":"Chin. J. Pediatr. Emerg. Med."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"137392","DOI":"10.1155\/2013\/137392","article-title":"An improved computer vision method for white blood cells detection","volume":"2013","author":"Cuevas","year":"2013","journal-title":"Comput. Math. Methods Med."},{"key":"ref_17","first-page":"95","article-title":"Detection and classification of leukocyte cells from smear image","volume":"30","author":"Kasim","year":"2015","journal-title":"J. Fac. Eng. Archit. Gazi Univ."},{"key":"ref_18","unstructured":"Cheng, K. (2006). Fuzzy Morphology Technology and Its Application in Image Processing, Nanjing University of Science and Technology."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1748301818813322","DOI":"10.1177\/1748301818813322","article-title":"Leukocyte recognition with convolutional neural network","volume":"13","author":"Lin","year":"2018","journal-title":"J. Algorithms Comput. Technol."},{"key":"ref_20","unstructured":"Wang, X. (2023). Research on White Blood Cell Classification Algorithm Based on Deep Learning. [Master\u2019s Thesis, Huazhong Agricultural University]."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Siddique, M.A.I., Aziz, A.Z.B., and Matin, A. (2020, January 17\u201319). An improved deep learning based classification of human white blood cell images. Proceedings of the 2020 11th International Conference on Electrical and Computer Engineering (ICECE), Dhaka, Bangladesh.","DOI":"10.1109\/ICECE51571.2020.9393156"},{"key":"ref_22","first-page":"1482","article-title":"Peripheral blood white blood cell detection based on YOLOv5","volume":"12","author":"Gan","year":"2022","journal-title":"Comput. Sci. Appl."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Chen, Y., Chen, Z., An, Y., Lu, C., and Qiao, X. (2024). DAFFNet: A Dual Attention Feature Fusion Network for Classification of White Blood Cells. arXiv.","DOI":"10.1016\/j.bspc.2025.107699"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Khan, R., and Mir, J. (2022, January 3\u20134). White blood cells segmentation and classification using U-Net CNN and hand-crafted features. Proceedings of the 2022 International Conference on IT and Industrial Technologies (ICIT), Chiniot, Pakistan.","DOI":"10.1109\/ICIT56493.2022.9988955"},{"key":"ref_25","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2020). An Image is Worth 16 \u00d7 16 Words: Transformers for Image Recognition at Scale. arXiv."},{"key":"ref_26","unstructured":"Hou, Q., Lu, C.Z., Cheng, M.M., and Feng, J.S. (2022). Conv2Former: A simple transformer-style ConvNet for visual recognition. arXiv."},{"key":"ref_27","unstructured":"Wang, J., Chen, K., Xu, R., Liu, Z., Loy, C.C., and Lin, D. (November, January 27). CARAFE: Content-Aware Reassembly of Features. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Seoul, Republic of Korea."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Bodla, N., Singh, B., Chellappa, R., and Davis, L.S. (2017, January 22\u201329). Soft-NMS\u2014Improving object detection with one line of code. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.593"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/9\/2699\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:20:55Z","timestamp":1760030455000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/9\/2699"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,24]]},"references-count":28,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2025,5]]}},"alternative-id":["s25092699"],"URL":"https:\/\/doi.org\/10.3390\/s25092699","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,24]]}}}