Segmentation and Detection of Red Blood Cells in Malaria Diagnostic Smears Using U-Net and Yolo V2
Keywords:
Red blood cells (RBCs), white blood cells (WBCs), deep learning, YOLOV2, connected components, semantic segmentation, U-Net.Abstract
Due to their increased precision and reproducibility as compared to manual segmentation and annotation, computer-assisted procedures have become a mainstay of biomedical applications. We present RBC-YOLONet, a novel pipeline for counting and identifying red blood cells in thin blood smear microscopy pictures. It employs a dual deep learning architecture. Two stages make up the RBC-YOLONet: a U-Net first stage for segmenting cell clusters and a YOLOV2 second stage for locating micro cell objects within connected component clusters. To locate tiny objects or fine-scale morphological traits in very large images, RBCNet employs cell clustering, which is robust to cell fragmentation and incredibly scalable. With greater accuracy than traditional and alternative deep learning techniques, the foreground cell-cluster masks from U-Net adaptively direct the detection step in the novel dual cascade RBC-YOLONet architecture. The RBC-YOLONet pipeline is a crucial step in automating malaria diagnosis.
References
- WHO, “World malaria report 2019,” World Health Organization, Geneva, Switzerland, Rep. 2019, 2019.
- WHO, “Malaria microscopy quality assurance manual-version 2,” World Health Organization, Geneva, Switzerland, Rep. no. 2016, 2016.
- A. Krizhevsky, I. Sutskever, and G. E Hinton, “Imagenet classification with deep convolutional neural networks,” in Proc. Adv. Neural Inf. Process. Syst., 2012, pp. 1097–1105.
- J. Schmidhuber, “Deep learning in neural networks: An overview,” Neural Netw., vol. 61, pp. 85–117, 2015.
- Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, 2015. 1746 IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, VOL. 25, NO. 5, MAY 2021.
- M. Poostchi, K. Silamut, R. J. Maude, S. Jaeger, and G. Thoma, “Image analysis and machine learning for detecting malaria,” Transl. Res., vol. 194, pp. 36–55, 2018.patients with 2019 novel coronavirus–infected pneumonia inWuhan, China." Jama (2020).
- D. Anggraini, A. S. Nugroho, C. Pratama, I. E. Rozi, V. Pragesjvara, and M. Gunawan, “Automated status identification of microscopic images obtained from malaria thin blood smears using bayes decision: A study case in plasmodium falciparum,” in Proc. Int. Conf. Adv. Comput. Sci. Inf. Syst., Dec. 2011, pp. 347–352.
- L. Malihi, K. Ansari-Asl, and A. Behbahani, “Malaria parasite detection in giemsa-stained blood cell images,” in Proc. Iranian Conf. Mach. Vis. Image Process., Sep. 2013, pp. 360–365.
- S. S. Savkare and S. P. Narote, “Automated system for malaria parasite identification,” in Proc. Int. Conf. Commun., Inf. Comput. Technol., Jan. 2015, pp. 1–4.
- S. S. Devi, A. Roy, M. Sharma, and R. H. Laskar, “knnNN classification-based erythrocyte separation in microscopic images of thin blood smear,” in Proc. Int. Conf. Comput. Intell. Netw., Jan. 2016, pp. 69–72.
- N. Abbas et al., “Microscopic rgb color images enhancement for blood cells segmentation in ycbcr color space for k-means clustering,” J. Theor. Appl. Inf. Technol., vol. 55, no. 1, pp. 117–125, 2013.
- A. S. Abdul-Nasir, M. Y. Mashor, and Z. Mohamed, “Colour image segmentation approach for detection of malaria parasites using variouscolour models and k-means clustering,” WSEAS Trans. Biol. Biomed., vol. 10, no. 1, pp. 41–55, 2013.
Downloads
Published
Issue
Section
License
Copyright (c) IJSRST
This work is licensed under a Creative Commons Attribution 4.0 International License.
