Abstract
The identification of urine sediment in human urine samples through microscopic images is a critical part of in vitro testing. Currently, automatic urine sediment analyzers are used by doctors to supplement manual examinations. However, the conventional technique of artificial feature extraction used by most analyzers can be labor-intensive and subjectively dependent on the professional’s prior knowledge. To overcome these limitations, this work employs YoloV8, a recent version of the Yolo algorithm, to accurately detect and categorize urine particles. In addition, a data-centric strategy has been introduced to address difficulties with missing data, incorrect labeling, and class imbalance. This strategy aims to improve labeling reliability and remove noisy data points. Experimental findings on the dataset show that YOLOv8 has a greater detection accuracy than existing state-of-the-art techniques for detecting eleven different categories of urine sediments. The approach presented in this work outperforms other techniques, yielding a mean average precision (mAP) of 91%. Furthermore, the average detection time of the model is 0.6 microseconds.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Goswami, D., Aggrawal, H., Agarwal. V.: Cell detection and classification from urine sediment microscopic images (2020)
Aglibot, K.P., Angeles, J.A., Gecana, J.F., Germano, A.B., Macalindong, J.A., Tolentino, R.E.: Urine crystal classification using convolutional neural networks. In: 2022 International Visualization, Informatics and Technology Conference (IVIT), pp. 245–250. IEEE (2022)
Ji, Q., Li, X., Zhiyu, Q., Dai, C.: Research on urine sediment images recognition based on deep learning. IEEE Access 7, 166711–166720 (2019)
Uijlings, J.R.R., Van De Sande, K.E.A., Gevers, T., Smeulders, A.W.M.: Selective search for object recognition. Int. J. Comput. Vis. 104, 154–171 (2013)
Girshick. R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440–1448 (2015)
Wang, Q., Bi, S., Sun, M., Wang, Y., Wang, D., Yang, S.: Deep learning approach to peripheral leukocyte recognition. PLoS ONE 14(6), e0218808 (2019)
Redmon, I., Farhadi, A.: Yolov3: an incremental improvement. preprint. arXiv preprint arXiv:1804.02767, 4322 (2018)
Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779–788 (2016)
Redmon, J., Farhadi, A.: Yolo9000: better, faster, stronger. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7263–7271 (2017)
Li, Q., et al.: Inspection of visible components in urine based on deep learning. Med. Phys. 47(7), 2937–2949 (2020)
Lin, T-y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980–2988 (2017)
Liang, Y., Kang, R., Lian, C., Mao, Y.: An end-to-end system for automatic urinary particle recognition with convolutional neural network. J. Med. Syst. 42, 1–14 (2018)
Liang, Y., Tang, Z., Yan, M., Liu, J.: Object detection based on deep learning for urine sediment examination. Biocybernet. Biomed. Eng. 38(3), 661–670 (2018)
Wang, Q., Sun, Q., Wang. Y.: A two-stage urine sediment detection method. In: 2020 International Conference on Image, Video Processing and Artificial Intelligence, vol. 11584, pp. 15–21. SPIE (2020)
Dong, S., Zhang, S., Jiao, L., Wang. Q.: Automatic urinary sediments visible component detection based on improved yolo algorithm. In: 2020 International Conference on Computer Vision, Image and Deep Learning (CVIDL), pp. 485–490. IEEE (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Akhtar, S., Hanif, M., Malih, H. (2023). Automatic Urine Sediment Detection and Classification Based on YoloV8. In: Gervasi, O., et al. Computational Science and Its Applications – ICCSA 2023 Workshops. ICCSA 2023. Lecture Notes in Computer Science, vol 14112. Springer, Cham. https://doi.org/10.1007/978-3-031-37129-5_22
Download citation
DOI: https://doi.org/10.1007/978-3-031-37129-5_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-37128-8
Online ISBN: 978-3-031-37129-5
eBook Packages: Computer ScienceComputer Science (R0)