YOLOv5 untuk Menghitung Sel Darah Merah dan Sel Darah Putih
DOI:
Abstract Views:
1079 times
PDF Downloads:
561 times
Abstract
Abstract—Health practitioners use hemocytometer to manually counting the blood cells, and it is considered time-consuming, arduous, and expert-dependent. Automated methods are costly, require meticulous maintenance, can lead to misidentify abnormal cells. This research proposed an application that swiftly, precisely, and easily count red and white blood cells. YOLOv5 is used to detect red and white blood cells in digital images. The model is trained on BCCD dataset and BCCD+ALL-IDB1 using YOLOv5s configuration and 736x736 image input size, and achieve 89.9% mAP50 value for red blood cell, 99.4% for white blood cell, and 93.8% for all classes using BCCD dataset. About 17.7% mean absolute percentage error (MAPE) is obtained using YOLO5x configuration with 416x416 image input size tested on BCCD dataset. The YOLOv5s configuration setup with 736x736 image input size gives 10.9% error rate against ALL-IDB1 dataset. The system is developed using Laravel and Flask, and it proficiently detects and counts red and white blood cells.
Keywords: YOLOv5, computer vision, blood count, red blood cell, white blood cell
Abstrak—Metode perhitungan sel darah merah secara manual menggunakan hemositometer membutuhkan waktu yang lama serta melelahkan dan sangat bergantung kepada tenaga ahli di bidang medis, sedangkan perhitungan otomatis menggunakan alat membutuhkan biaya yang mahal dan perawatan ekstra untuk menjaga hasil yang akurat serta apabila dihadapkan dengan sel berukuran abnormal maka alat akan salah mengidentifikasi, maka dibutuhkan suatu sistem yang dapat menghitung jumlah sel darah merah dengan cepat, akurat, dan mudah untuk dioperasikan. YOLOv5 digunakan untuk mendeteksi sel darah merah melalui citra digital. Model dilatih menggunakan BCCD Dataset dan BCCD + ALL-IDB1. Berdasarkan nilai mAP50 didapatkan model terbaik dengan konfigurasi YOLOv5s dengan ukuran masukan 736x736 dengan data latih yaitu BCCD sebesar 89.9% untuk sel darah merah, 99,4% untuk sel darah putih dan 93,8% untuk semua kelas. Berdasarkan mean absolute percentage error (MAPE) didapatkan sebesar 17.7% untuk konfigurasi YOLOv5x dengan ukuran citra masukan 416x416 jika diuji menggunakan data BCCD, namun konfigurasi YOLOv5s dengan ukuran citra masukan 736x736 memiliki nilai lebih rendah yaitu 10.9% jika dihadapkan dengan data uji ALL-IDB1. Sistem dibuat dengan menggunakan Laravel dan Flask. Secara keseluruhan, sistem dapat dengan baik mendeteksi serta menghitung sel darah merah maupun sel darah putih.
Kata kunci: YOLOv5, visi computer, hitung sel darah, sel darah merah, sel darah putih
Downloads
References
Alam, M. M., & Islam, M. T. (2019). Machine learning approach of automatic identification and counting of blood cells. Healthcare Technology Letters, 6(4), 103–108. https://doi.org/10.1049/htl.2018.5098
Bramantya, A. A., Fatichah, C., & Suciati, N. (2022). Bramantya, Fatichah, and Suciati-Detection and Classification of Red Blood Cells Abnormality using Faster R-CNN and Graph Convolutional Networks. Jurnal Ilmiah Teknologi Informasi, vol. 20, no. 1, 31 Jan. 2022, pp. 23-44, doi: 10.12962/j24068535.v19i3.a1118
Lee, S.-J., Chen, P.-Y., & Lin, J.-W. (2022). Complete Blood Cell Detection and Counting Based on Deep Neural Networks. Applied Sciences, 12(16), 8140. MDPI AG. http://dx.doi.org/10.3390/app12168140
Mayo Clinic Staff. (2020, December 22). Complete blood count (CBC). Mayo Clinic. Diakses tanggal 19 September 2022, dari https://www.mayoclinic.org/tests-procedures/complete-blood-count/about/pac-20384919
National Library of Medicine. (2021, October 4). Red Blood Cell (RBC) Count: MedlinePlus Medical Test. Diakses tanggal 19 September, 2022, from https://medlineplus.gov/lab-tests/red-blood-cell-rbc-count/
Tran, T., Binh Minh, L., Lee, S., & Kwon, K. (2019). Blood Cell Count Using Deep Learning Semantic Segmentation. Preprints 2019, 2019090075. https://doi.org/10.20944/preprints201909.0075.v1
BIBLIOGRAFI
Acharya, V., & Kumar, P. (2017). Identification and red blood cell automated counting from blood smear images using computer-aided system. Medical &Amp; Biological Engineering &Amp; Computing, 56(3), 483–489. https://doi.org/10.1007/s11517-017-1708-9
Alam, M. (2019). Complete-Blood-Cell-Count-Dataset. Diakses tanggal 6 Januari 2023, dari https://github.com/MahmudulAlam/Complete-Blood-Cell-Count-Dataset
Barbedo, J. G. A. (2013). Automatic Object Counting In Neubauer Chambers. In Anais de XXXI Simpósio Brasileiro de Telecomunicações. https://doi.org/10.14209/sbrt.2013.224
Batrah, S. (2018, April 6). Total RBC count using hemocytometer / Neubauer's Chamber (Microdilution & Macrodilution Method): Hematology practicals. Paramedics World. Diakses tanggal 6 Januari 2023, dari https://paramedicsworld.com/hematology-practicals/total-red-blood-cell-rbc-count-using-hemocytometer-neubauer-chamber-microdilution-macrodilution/medical-paramedical-studynotes
BIT, H. A. (2019, October 15). Semantic Segmentation. Diakses tanggal 6 Januari 2023, dari https://medium.com/hackabit/semantic-segmentation-8f2900eff5c8
Britannica, T. Editors of Encyclopaedia (2022, October 23). Red Blood Cell. Encyclopedia Britannica. Diakses tanggal 6 Januari 2023, dari https://www.britannica.com/science/red-blood-cell
Friebe, M. (2017). International Healthcare Vision 2037 - new technologies, educational goals and entrepreneurial challenges ; proceedings + summary of the 5th BME-IDEA EU Conference ; 11 - 13 June 2017, Magdeburg, Germany. doi:10.25673/4992
Hemalatha, B., Karthik, B., Krishna Reddy, C., & Latha, A. (2022). Deep learning approach for segmentation and classification of blood cells using enhanced CNN. Measurement: Sensors, 24, 100582. https://doi.org/10.1016/j.measen.2022.100582
Katsamenis, I., Karolou, E. E., Davradou, A., Protopapadakis, E., Doulamis, A., Doulamis, A., & Kalogeras, D. (2022). TraCon: A Novel Dataset for Real-Time Traffic Cones Detection Using Deep Learning. In: Krouska, A., Troussas, C., Caro, J. (eds) Novel & Intelligent Digital Systems: Proceedings of the 2nd International Conference (NiDS 2022). NiDS 2022. Lecture Notes in Networks and Systems, vol 556. Springer, Cham. https://doi.org/10.1007/978-3-031-17601-2_37
Madan, P., Samaya , S. (2020, March 2). An introduction to deep learning. IBM developer. Diakses tanggal 6 Januari 2023, dari https://developer.ibm.com/articles/an-introduction-to-deep-learning/?mhsrc=ibmsearch_a&mhq=+deep+learning
Medline plus. (2021). Red Blood Cell (RBC) Count: MedlinePlus Medical Test. Diakses tanggal 6 Januari 2023, dari https://medlineplus.gov/lab-tests/red-blood-cell-rbc-count/
Microyn Improved Neubauer Hemocytometer, Cell Counting Chamber with Bright Line. (n.d.). Diakses tanggal 6 Januari 2023, dari https://www.amazon.com/Microyn-Improved-Neubauer-Hemocytometer-Counting/dp/B01M8KKCT3
Mount Sinai. (n.d.). Mount Sinai Health System. Diakses tanggal 6 Januari 2023, dari https://www.mountsinai.org/health-library/tests/rbc-count
Overton, T., & Tucker, A. (2020). DO-U-Net for Segmentation and Counting. In M. R. Berthold, A. Feelders, & G. Krempl (Eds.), Advances in Intelligent Data Analysis XVIII (pp. 391–403). Cham: Springer International Publishing.
Publications, M. (2019, August 18). The Computer Vision Pipeline, part 3: Image preprocessing. Manning. Diakses tanggal 6 Januari 2023, dari https://freecontent.manning.com/the-computer-vision-pipeline-part-3-image-preprocessing/
Rais, M. D. A., Arif, F., Arifuddin, M. F., Muhammad, M., Kaswar, A. B., & Prima Putra, K. (2022). Metode Otomatis untuk Menghitung Sel Darah Merah Menggunakan Image Processing. Journal of Embedded Systems, Security and Intelligent Systems, 3(2), 102. https://doi.org/10.26858/jessi.v3i2.38250
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You Only Look Once: Unified, Real-Time Object Detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 779-788).
Ronneberger, O., Fischer, P., Brox, T. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. In: Navab, N., Hornegger, J., Wells, W., Frangi, A. (eds) Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015. MICCAI 2015. Lecture Notes in Computer Science(), vol 9351. Springer, Cham. https://doi.org/10.1007/978-3-319-24574-4_28
Vasković, J. (2022, July 6). Erythrocytes. Kenhub. Diakses tanggal 6 Januari 2023, dari https://www.kenhub.com/en/library/anatomy/erythrocytes
Vlab, A. (2011, January 14). Hemocytometer - Counting of cells - Amrita University. Retrieved January 6, 2023, from https://www.youtube.com/watch?v=MKS0KM3lr90
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
- Articles published in Keluwih: Jurnal Sains dan Teknologi are licensed under a Creative Commons Attribution-ShareAlike 4.0 International license. You are free to copy, transform, or redistribute articles for any lawful purpose in any medium, provided you give appropriate credit to the original author(s) and the journal, link to the license, indicate if changes were made, and redistribute any derivative work under the same license.
- Copyright on articles is retained by the respective author(s), without restrictions. A non-exclusive license is granted to Keluwih: Jurnal Sains dan Teknologi to publish the article and identify itself as its original publisher, along with the commercial right to include the article in a hardcopy issue for sale to libraries and individuals.
- By publishing in Keluwih: Jurnal Sains dan Teknologi, authors grant any third party the right to use their article to the extent provided by the Creative Commons Attribution-ShareAlike 4.0 International license.
