White Blood Cell Detection Using Yolov8 Integration with DETR to Improve Accuracy
DOI:
10.33395/sinkron.v8i3.12811Keywords:
coco, DETR, Object Detection, Wbc, YoloAbstract
One of the body's most crucial blood cell kinds is the white blood cell. White blood cells, called leukocytes, are crucial for the body's defence mechanism and against hazardous foreign substances, tumour cells, and infectious bacteria. This paper suggests a computer-based automated system for detecting white blood cells using the YOLOV8 transformer and white blood cell analysis in digital images of blood cells. The Generate process uses Yolov8. In Generate, this will produce image processing in the form of annotation results on each type of white blood cell and dataset with COCO format. The DETR Model training conducted in this study is to increase the accuracy value of the white output of the blood cell picture formation. Test results using recall, precision, f1 score and object detection values. In the lymphocyte and basophil datasets, the number of white blood cell images used is only 10 images. Following the results of training from yolov8 using Roboflow, the results were increased relatively high, with an average increase of 0.68 in all five images of white blood cells. This test also gets an average improvement in detection results from Yolo to DETR, getting a fairly significant result of 68%, which is because YOLO cannot handle undetected objects (which are not in the training dataset; furthermore, DETR can handle multiple objects in a single image. Typically, detecting traditional objects such as YOLO requires repeatedly multiple object detection with a fixed batch size
Downloads
References
Ak, S. B., Analis, J., Poltekkes, K., & Makassar, K. (2018). ANALISIS JUMLAH LEUKOSIT DAN JENIS LEUKOSIT PADA INDIVIDU YANG TIDUR DENGAN LAMPU MENYALA DAN YANG DIPADAMKAN. Jurnal Media Analis Kesehatan, 1(1).
Aldi, F., Nozomi, I., Sentosa, R. B., & Junaidi, A. (2023). Machine Learning to Identify Monkey Pox Disease. Sinkron, 8(3), 1335–1347. https://doi.org/10.33395/sinkron.v8i3.12524
Caesar, H., Uijlings, J., & Ferrari, V. (n.d.). COCO-Stuff: Thing and Stuff Classes in Context. http://calvin.inf.ed.ac.uk/datasets/coco-stuff
Carion Nicolas, Massa Francisco, Synnaeve Gabriel, Usunier Nicolas, Kirillov Alexander, & Zagoruyko Sergey. (2020). End-to-End Object Detection with Transformers (A. Vedaldi, H. Bischof, T. Brox, & J.-M. Frahm, Eds.). Springer International Publishing. https://doi.org/10.1007/978-3-030-58452-8
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., & Houlsby, N. (2020). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. http://arxiv.org/abs/2010.11929
Espinoza Cinthia, & Femat Aurora. (2022). Comparison of Accuracy of Color Spaces in Cell Features Classification in Images of Leukemia types ALL and MM [Revista Mexicana de Ingeniería Biomédica]. https://doi.org/10.17488/RMIB.43.2.3
Fathi, E., Rezaee, M. J., Tavakkoli-Moghaddam, R., Alizadeh, A., & Montazer, A. (2020). Design of an integrated model for diagnosis and classification of pediatric acute leukemia using machine learning. Proceedings of the Institution of Mechanical Engineers, Part H: Journal of Engineering in Medicine, 234(10), 1051–1069. https://doi.org/10.1177/0954411920938567
Leng, B., Wang, C., Leng, M., Ge, M., & Dong, W. (2023). Deep learning detection network for peripheral blood leukocytes based on improved detection transformer. Biomedical Signal Processing and Control, 82. https://doi.org/10.1016/j.bspc.2022.104518
Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021). Swin Transformer: Hierarchical Vision Transformer using Shifted Windows. http://arxiv.org/abs/2103.14030
Meng, D., Chen, X., Fan, Z., Zeng, G., Li, H., Yuan, Y., Sun, L., & Wang, J. (n.d.). Conditional DETR for Fast Training Convergence.
Minarno, A. E., Aripa, L., Azhar, Y., & Munarko, Y. (n.d.). Classification of Malaria Cell Image Using Inception-V3 Architecture. www.joiv.org/index.php/joiv
Park, Y. H., & Jun, T. H. (2022). Classification of Soybean [Glycine max (L.) Merr.] Seed Based on Deep Learning Using the YOLOv5 Model. Plant Breeding and Biotechnology, 10(1), 75–80. https://doi.org/10.9787/PBB.2022.10.1.75
Rajeshwari, P., Abhishek, P., Srikanth, P., & Vinod, T. (2019). Object Detection: An Overview. In Published in International Journal of Trend in Scientific Research and Development (ijtsrd) (Issue 3). http://creativecommons.org/licenses/by/4.0
Reynaldo, D., & Lina, ). (2019). KAJIAN TENTANG PENDETEKSIAN SEL DARAH PUTIH DENGAN TEKNIK SEGMENTASI WATERSHED.
Sri Indrawanti, A., & Prakarsa Mandyartha, E. (2018). Deteksi Limfoblas pada Citra Sel Darah Menggunakan Fitur Geometri dan Local Binary Pattern. In JNTETI (Vol. 7, Issue 4).
Suherman, E., Rahman, B., Hindarto, D., & Santoso, H. (2023). Implementation of ResNet-50 on End-to-End Object Detection (DETR) on Objects. SinkrOn, 8(2), 1085–1096. https://doi.org/10.33395/sinkron.v8i2.12378
Terven, J., & Cordova-Esparza, D. (2023). A Comprehensive Review of YOLO: From YOLOv1 and Beyond. http://arxiv.org/abs/2304.00501
Downloads
|
How to Cite
Issue
Section
License
Copyright (c) 2023 Shinta Jitny Ayu Nugraha, Bayu Erfianto
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Muhammad Khoiruddin harahap
Google Scholar 
Moraref
PKP Index
Garuda Kemdikbud
Indonesia OneSearch
OCLC Worldcat
Dimensions
Index Copernicus
Scilit
