Network Reduction Strategy and Deep Ensemble Learning for Blood Cell Detection
Abstract
Identifying and characterizing blood cells are vital for diagnosing diseases and evaluating a patient's health. Blood, consisting of plasma and cells, offers valuable insights through its biochemical and ecological features. Plasma constitutes the liquid component containing water, protein, and salt, while platelets, red blood cells (RBCs), and white blood cells (WBCs) form the solid portion. Due to diverse cell characteristics and data complexity, achieving reliable and precise cell detection remains a significant challenge. This study presents a network reduction strategy and deep ensemble learning approaches to detect blood cell types based on the YOLOv8 model. Our proposed methods aim to optimize the YOLOv8 model by reducing network depth while preserving performance and leveraging deep ensemble learning to enhance model accuracy. Based on the experiments, the NRS strategy can reduce the complexity of the YOLO model by reducing the depth and width of the YOLO network while maintaining model performance by 4%, outperforming the baseline YOLOv8 model.
Downloads
Download data is not yet available.
References
[1] D. R. Loh, W. X. Yong, J. Yapeter, K. Subburaj, dan R. Chandramohanadas, “A deep learning approach to the screening of malaria infection: Automated and rapid cell counting, object detection, and instance segmentation using Mask R-CNN,” Computerized Medical Imaging and Graphics, vol. 88, hlm. 101845, 2021, doi: 10.1016/j.compmedimag.2020.101845.
[2] L. Vogado., “Diagnosis of Leukaemia in Blood Slides Based on a Fine-Tuned and Highly Generalisable Deep Learning Model,” Sensors 2021, Vol. 21, Page 2989, vol. 21, no. 9, hlm. 2989, Apr 2021, doi: 10.3390/S21092989.
[3] D. Ananta, H. A1, A. Jamal, A. S. Nugroho, A. A. Septiandri, dan B. Wiweko, “Embryo Grading after In Vitro Fertilization using YOLO,” Lontar Komputer : Jurnal Ilmiah Teknologi Informasi, vol. 13, no. 3, hlm. 137–149, Nov 2022, doi: 10.24843/LKJITI.2022.V13.I03.P01.
[4] I. Gusti dkk., “Optimization Strategy on Deep Learning Model to Improve Fruit Freshness Recognition,” Lontar Komputer : Jurnal Ilmiah Teknologi Informasi, vol. 14, no. 1, hlm. 1–11, Agu 2023, doi: 10.24843/LKJITI.2023.V14.I01.P01.
[5] I. W. A. S. Darma, N. Suciati, dan D. Siahaan, “GFF-CARVING: Graph Feature Fusion for the Recognition of Highly Varying and Complex Balinese Carving Motifs,” IEEE Access, 2022, doi: 10.1109/ACCESS.2022.3228382.
[6] I. W. A. S. Darma, N. Suciati, dan D. Siahaan, “Neural Style Transfer and Geometric Transformations for Data Augmentation on Balinese Carving Recognition using MobileNet,” vol. 13, no. 6, hlm. 349–363, 2020, doi: 10.22266/ijies2020.1231.31.
[7] I. W. A. S. Darma, N. Suciati, dan D. Siahaan, “Balinese Carving Recognition using Pre-Trained Convolutional Neural Network,” 2020 4th International Conference on Informatics and Computational Sciences (ICICoS), 2020, hlm. 1–5. doi: 10.1109/ICICoS51170.2020.9299021.
[8] I. W. A. S. Darma, N. Suciati, dan D. Siahaan, “A Performance Comparison of Balinese Carving Motif Detection and Recognition using YOLOv5 and Mask R-CNN,” hlm. 52–57, Des 2021, doi: 10.1109/ICICOS53627.2021.9651855.
[9] S. Du, P. Zhang, B. Zhang, dan H. Xu, “Weak and Occluded Vehicle Detection in Complex Infrared Environment Based on Improved YOLOv4,” IEEE Access, vol. 9, hlm. 25671–25680, Okt 2021, doi: 10.1109/ACCESS.2021.3057723.
[10] X. Han dan J. Chang, “Real-time object object detection detection based based on on YOLO-v2 for for tiny tiny vehicle vehicle object object,” Procedia Computer Science, vol. 183, hlm. 61–72, 2021, doi: 10.1016/j.procs.2021.02.031.
[11] G. Zhou, W. Zhang, A. Chen, M. He, dan X. Ma, “Rapid Detection of Rice Disease Based on FCM-KM and Faster R-CNN Fusion,” IEEE Access, vol. 7, hlm. 143190–143206, 2019, doi: 10.1109/ACCESS.2019.2943454.
[12] Y. S. Devi dan S. P. Kumar, “A deep transfer learning approach for identification of diabetic retinopathy using data augmentation,” IAES International Journal of Artificial Intelligence (IJ-AI), vol. 11, no. 4, hlm. 1287, Des 2022, doi: 10.11591/ijai.v11.i4.pp1287-1296.
[13] R. F. Rahmat dkk., “Astrocytoma, ependymoma, and oligodendroglioma classification with deep convolutional neural network,” IAES International Journal of Artificial Intelligence (IJ-AI), vol. 11, no. 4, hlm. 1306, Des 2022, doi: 10.11591/ijai.v11.i4.pp1306-1313.
[14] Z. Xu, H. Ren, W. Zhou, dan Z. Liu, “ISANET: Non-small cell lung cancer classification and detection based on CNN and attention mechanism,” Biomedical Signal Processing and Control, vol. 77, hlm. 103773, 2022, doi: https://doi.org/10.1016/j.bspc.2022.103773.
[15] E. Ratnasari Putri, A. Zarkasi, P. Prajitno, dan D. Soeharso Soejoko, “Artificial neural network for cervical abnormalities detection on computed tomography images,” IAES International Journal of Artificial Intelligence (IJ-AI), vol. 12, no. 1, hlm. 171, Mar 2023, doi: 10.11591/ijai.v12.i1.pp171-179.
[16] G. H. Aly, M. Marey, S. A. El-Sayed, dan M. F. Tolba, “YOLO Based Breast Masses Detection and Classification in Full-Field Digital Mammograms,” Computer Methods and Programs in Biomedicine, vol. 200, hlm. 105823, 2021, doi: https://doi.org/10.1016/j.cmpb.2020.105823.
[17] T. Ozturk, M. Talo, E. A. Yildirim, U. B. Baloglu, O. Yildirim, dan U. Rajendra Acharya, “Automated detection of COVID-19 cases using deep neural networks with X-ray images,” Computers in Biology and Medicine, vol. 121, hlm. 103792, Jun 2020, doi: 10.1016/J.COMPBIOMED.2020.103792.
[18] S. Albahli, N. Nida, A. Irtaza, M. H. Yousaf, dan M. T. Mahmood, “Melanoma Lesion Detection and Segmentation Using YOLOv4-DarkNet and Active Contour,” IEEE Access, vol. 8, hlm. 198403–198414, 2020, doi: 10.1109/ACCESS.2020.3035345.
[19] L. Wang, K. Zhou, A. Chu, G. Wang, dan L. Wang, “An Improved Light-Weight Traffic Sign Recognition Algorithm Based on YOLOv4-Tiny,” IEEE Access, vol. 9, hlm. 124963–124971, 2021, doi: 10.1109/ACCESS.2021.3109798.
[20] Q. Xu, R. Lin, H. Yue, H. Huang, Y. Yang, dan Z. Yao, “Research on Small Target Detection in Driving Scenarios Based on Improved Yolo Network,” IEEE Access, vol. 8, hlm. 27574–27583, 2020, doi: 10.1109/ACCESS.2020.2966328.
[21] A. Casado-García dkk., “LabelStoma: A tool for stomata detection based on the YOLO algorithm,” Computers and Electronics in Agriculture, vol. 178, hlm. 105751, 2020, doi: https://doi.org/10.1016/j.compag.2020.105751.
[22] A. Fadl, “MSR-YOLO : Method Method to Enhance Fish Detection Detection and Tracking Tracking in Fish Farms in Fish Farms,” Procedia Computer Science, vol. 170, no. 2019, hlm. 539–546, 2020, doi: 10.1016/j.procs.2020.03.123.
[23] I. W. A. S. Darma, N. Suciati, dan D. Siahaan, “CARVING-DETC: A network scaling and NMS ensemble for Balinese carving motif detection method,” Visual Informatics, Jun 2023, doi: 10.1016/j.visinf.2023.05.004.
[24] L. Nanni, S. Ghidoni, dan S. Brahnam, “Ensemble of convolutional neural networks for bioimage classification,” Applied Computing and Informatics, vol. 17, no. 1, hlm. 19–35, 2021, doi: 10.1016/j.aci.2018.06.002.
[25] H. Kusetogullari, A. Yavariabdi, J. Hall, dan N. Lavesson, “DIGITNET: A Deep Handwritten Digit Detection and Recognition Method Using a New Historical Handwritten Digit Dataset,” Big Data Research, vol. 23, hlm. 100182, 2021, doi: 10.1016/j.bdr.2020.100182.
[26] H. A. Qadir, Y. Shin, J. Solhusvik, J. Bergsland, L. Aabakken, dan I. Balasingham, “Polyp Detection and Segmentation using Mask R-CNN: Does a Deeper Feature Extractor CNN Always Perform Better?,” International Symposium on Medical Information and Communication Technology, ISMICT, vol. 2019-May, hlm. 1–6, 2019, doi: 10.1109/ISMICT.2019.8743694.
[27] M. Sharif dkk., “Recognition of Different Types of Leukocytes Using YOLOv2 and Optimized Bag-of-Features,” IEEE Access, vol. 8, hlm. 167448–167459, 2020, doi: 10.1109/ACCESS.2020.3021660.
[28] G. Fang, Y. suhua, dan J. shaofeng, “Detection of white blood cells using YOLOV3 network,” dalam 2019 14th IEEE International Conference on Electronic Measurement & Instruments (ICEMI), IEEE, Nov 2019, hlm. 1683–1688. doi: 10.1109/ICEMI46757.2019.9101709.
[29] S. Banerjee dan S. S. Chaudhuri, “Total contribution score and fuzzy entropy based two-stage selection of FC, ReLU and inverseReLU features of multiple convolution neural networks for erythrocytes detection,” IET Computer Vision, vol. 13, no. 7, hlm. 640–650, 2019, doi: 10.1049/iet-cvi.2018.5545.
[30] S. Cheng, Y. Suhua, dan J. Shaofeng, “Improved faster RCNN for white blood cells detection in blood smear image,” 2019 14th IEEE International Conference on Electronic Measurement and Instruments, ICEMI 2019, hlm. 1677–1682, Nov 2019, doi: 10.1109/ICEMI46757.2019.9101445.
[31] L. Alzubaidi, M. A. Fadhel, O. Al‐shamma, J. Zhang, dan Y. Duan, “Deep learning models for classification of red blood cells in microscopy images to aid in sickle cell anemia diagnosis,” Electronics (Switzerland), vol. 9, no. 3, hlm. 427, 2020, doi: 10.3390/electronics9030427.
[32] M. A. Parab dan N. D. Mehendale, “Red Blood Cell Classification Using Image Processing and CNN,” SN Computer Science 2021 2:2, vol. 2, no. 2, hlm. 1–10, Feb 2021, doi: 10.1007/S42979-021-00458-2.
[33] M. M. Alam dan M. T. Islam, “Machine learning approach of automatic identification and counting of blood cells,” Healthcare Technology Letters, vol. 6, no. 4, hlm. 103–108, Aug 2019, doi: 10.1049/HTL.2018.5098.
[34] A. Dongre, “Blood Cell Detection Dataset.” MIT, 2021. Last access: November 28, 2023. [Online]. Available at: https://www.kaggle.com/datasets/adhoppin/blood-cell-detection-datatset
[2] L. Vogado., “Diagnosis of Leukaemia in Blood Slides Based on a Fine-Tuned and Highly Generalisable Deep Learning Model,” Sensors 2021, Vol. 21, Page 2989, vol. 21, no. 9, hlm. 2989, Apr 2021, doi: 10.3390/S21092989.
[3] D. Ananta, H. A1, A. Jamal, A. S. Nugroho, A. A. Septiandri, dan B. Wiweko, “Embryo Grading after In Vitro Fertilization using YOLO,” Lontar Komputer : Jurnal Ilmiah Teknologi Informasi, vol. 13, no. 3, hlm. 137–149, Nov 2022, doi: 10.24843/LKJITI.2022.V13.I03.P01.
[4] I. Gusti dkk., “Optimization Strategy on Deep Learning Model to Improve Fruit Freshness Recognition,” Lontar Komputer : Jurnal Ilmiah Teknologi Informasi, vol. 14, no. 1, hlm. 1–11, Agu 2023, doi: 10.24843/LKJITI.2023.V14.I01.P01.
[5] I. W. A. S. Darma, N. Suciati, dan D. Siahaan, “GFF-CARVING: Graph Feature Fusion for the Recognition of Highly Varying and Complex Balinese Carving Motifs,” IEEE Access, 2022, doi: 10.1109/ACCESS.2022.3228382.
[6] I. W. A. S. Darma, N. Suciati, dan D. Siahaan, “Neural Style Transfer and Geometric Transformations for Data Augmentation on Balinese Carving Recognition using MobileNet,” vol. 13, no. 6, hlm. 349–363, 2020, doi: 10.22266/ijies2020.1231.31.
[7] I. W. A. S. Darma, N. Suciati, dan D. Siahaan, “Balinese Carving Recognition using Pre-Trained Convolutional Neural Network,” 2020 4th International Conference on Informatics and Computational Sciences (ICICoS), 2020, hlm. 1–5. doi: 10.1109/ICICoS51170.2020.9299021.
[8] I. W. A. S. Darma, N. Suciati, dan D. Siahaan, “A Performance Comparison of Balinese Carving Motif Detection and Recognition using YOLOv5 and Mask R-CNN,” hlm. 52–57, Des 2021, doi: 10.1109/ICICOS53627.2021.9651855.
[9] S. Du, P. Zhang, B. Zhang, dan H. Xu, “Weak and Occluded Vehicle Detection in Complex Infrared Environment Based on Improved YOLOv4,” IEEE Access, vol. 9, hlm. 25671–25680, Okt 2021, doi: 10.1109/ACCESS.2021.3057723.
[10] X. Han dan J. Chang, “Real-time object object detection detection based based on on YOLO-v2 for for tiny tiny vehicle vehicle object object,” Procedia Computer Science, vol. 183, hlm. 61–72, 2021, doi: 10.1016/j.procs.2021.02.031.
[11] G. Zhou, W. Zhang, A. Chen, M. He, dan X. Ma, “Rapid Detection of Rice Disease Based on FCM-KM and Faster R-CNN Fusion,” IEEE Access, vol. 7, hlm. 143190–143206, 2019, doi: 10.1109/ACCESS.2019.2943454.
[12] Y. S. Devi dan S. P. Kumar, “A deep transfer learning approach for identification of diabetic retinopathy using data augmentation,” IAES International Journal of Artificial Intelligence (IJ-AI), vol. 11, no. 4, hlm. 1287, Des 2022, doi: 10.11591/ijai.v11.i4.pp1287-1296.
[13] R. F. Rahmat dkk., “Astrocytoma, ependymoma, and oligodendroglioma classification with deep convolutional neural network,” IAES International Journal of Artificial Intelligence (IJ-AI), vol. 11, no. 4, hlm. 1306, Des 2022, doi: 10.11591/ijai.v11.i4.pp1306-1313.
[14] Z. Xu, H. Ren, W. Zhou, dan Z. Liu, “ISANET: Non-small cell lung cancer classification and detection based on CNN and attention mechanism,” Biomedical Signal Processing and Control, vol. 77, hlm. 103773, 2022, doi: https://doi.org/10.1016/j.bspc.2022.103773.
[15] E. Ratnasari Putri, A. Zarkasi, P. Prajitno, dan D. Soeharso Soejoko, “Artificial neural network for cervical abnormalities detection on computed tomography images,” IAES International Journal of Artificial Intelligence (IJ-AI), vol. 12, no. 1, hlm. 171, Mar 2023, doi: 10.11591/ijai.v12.i1.pp171-179.
[16] G. H. Aly, M. Marey, S. A. El-Sayed, dan M. F. Tolba, “YOLO Based Breast Masses Detection and Classification in Full-Field Digital Mammograms,” Computer Methods and Programs in Biomedicine, vol. 200, hlm. 105823, 2021, doi: https://doi.org/10.1016/j.cmpb.2020.105823.
[17] T. Ozturk, M. Talo, E. A. Yildirim, U. B. Baloglu, O. Yildirim, dan U. Rajendra Acharya, “Automated detection of COVID-19 cases using deep neural networks with X-ray images,” Computers in Biology and Medicine, vol. 121, hlm. 103792, Jun 2020, doi: 10.1016/J.COMPBIOMED.2020.103792.
[18] S. Albahli, N. Nida, A. Irtaza, M. H. Yousaf, dan M. T. Mahmood, “Melanoma Lesion Detection and Segmentation Using YOLOv4-DarkNet and Active Contour,” IEEE Access, vol. 8, hlm. 198403–198414, 2020, doi: 10.1109/ACCESS.2020.3035345.
[19] L. Wang, K. Zhou, A. Chu, G. Wang, dan L. Wang, “An Improved Light-Weight Traffic Sign Recognition Algorithm Based on YOLOv4-Tiny,” IEEE Access, vol. 9, hlm. 124963–124971, 2021, doi: 10.1109/ACCESS.2021.3109798.
[20] Q. Xu, R. Lin, H. Yue, H. Huang, Y. Yang, dan Z. Yao, “Research on Small Target Detection in Driving Scenarios Based on Improved Yolo Network,” IEEE Access, vol. 8, hlm. 27574–27583, 2020, doi: 10.1109/ACCESS.2020.2966328.
[21] A. Casado-García dkk., “LabelStoma: A tool for stomata detection based on the YOLO algorithm,” Computers and Electronics in Agriculture, vol. 178, hlm. 105751, 2020, doi: https://doi.org/10.1016/j.compag.2020.105751.
[22] A. Fadl, “MSR-YOLO : Method Method to Enhance Fish Detection Detection and Tracking Tracking in Fish Farms in Fish Farms,” Procedia Computer Science, vol. 170, no. 2019, hlm. 539–546, 2020, doi: 10.1016/j.procs.2020.03.123.
[23] I. W. A. S. Darma, N. Suciati, dan D. Siahaan, “CARVING-DETC: A network scaling and NMS ensemble for Balinese carving motif detection method,” Visual Informatics, Jun 2023, doi: 10.1016/j.visinf.2023.05.004.
[24] L. Nanni, S. Ghidoni, dan S. Brahnam, “Ensemble of convolutional neural networks for bioimage classification,” Applied Computing and Informatics, vol. 17, no. 1, hlm. 19–35, 2021, doi: 10.1016/j.aci.2018.06.002.
[25] H. Kusetogullari, A. Yavariabdi, J. Hall, dan N. Lavesson, “DIGITNET: A Deep Handwritten Digit Detection and Recognition Method Using a New Historical Handwritten Digit Dataset,” Big Data Research, vol. 23, hlm. 100182, 2021, doi: 10.1016/j.bdr.2020.100182.
[26] H. A. Qadir, Y. Shin, J. Solhusvik, J. Bergsland, L. Aabakken, dan I. Balasingham, “Polyp Detection and Segmentation using Mask R-CNN: Does a Deeper Feature Extractor CNN Always Perform Better?,” International Symposium on Medical Information and Communication Technology, ISMICT, vol. 2019-May, hlm. 1–6, 2019, doi: 10.1109/ISMICT.2019.8743694.
[27] M. Sharif dkk., “Recognition of Different Types of Leukocytes Using YOLOv2 and Optimized Bag-of-Features,” IEEE Access, vol. 8, hlm. 167448–167459, 2020, doi: 10.1109/ACCESS.2020.3021660.
[28] G. Fang, Y. suhua, dan J. shaofeng, “Detection of white blood cells using YOLOV3 network,” dalam 2019 14th IEEE International Conference on Electronic Measurement & Instruments (ICEMI), IEEE, Nov 2019, hlm. 1683–1688. doi: 10.1109/ICEMI46757.2019.9101709.
[29] S. Banerjee dan S. S. Chaudhuri, “Total contribution score and fuzzy entropy based two-stage selection of FC, ReLU and inverseReLU features of multiple convolution neural networks for erythrocytes detection,” IET Computer Vision, vol. 13, no. 7, hlm. 640–650, 2019, doi: 10.1049/iet-cvi.2018.5545.
[30] S. Cheng, Y. Suhua, dan J. Shaofeng, “Improved faster RCNN for white blood cells detection in blood smear image,” 2019 14th IEEE International Conference on Electronic Measurement and Instruments, ICEMI 2019, hlm. 1677–1682, Nov 2019, doi: 10.1109/ICEMI46757.2019.9101445.
[31] L. Alzubaidi, M. A. Fadhel, O. Al‐shamma, J. Zhang, dan Y. Duan, “Deep learning models for classification of red blood cells in microscopy images to aid in sickle cell anemia diagnosis,” Electronics (Switzerland), vol. 9, no. 3, hlm. 427, 2020, doi: 10.3390/electronics9030427.
[32] M. A. Parab dan N. D. Mehendale, “Red Blood Cell Classification Using Image Processing and CNN,” SN Computer Science 2021 2:2, vol. 2, no. 2, hlm. 1–10, Feb 2021, doi: 10.1007/S42979-021-00458-2.
[33] M. M. Alam dan M. T. Islam, “Machine learning approach of automatic identification and counting of blood cells,” Healthcare Technology Letters, vol. 6, no. 4, hlm. 103–108, Aug 2019, doi: 10.1049/HTL.2018.5098.
[34] A. Dongre, “Blood Cell Detection Dataset.” MIT, 2021. Last access: November 28, 2023. [Online]. Available at: https://www.kaggle.com/datasets/adhoppin/blood-cell-detection-datatset
Published
2023-12-05
How to Cite
PIARSA, I Nyoman; SUTRAMIANI, Ni Putu; SURYA DARMA, I Wayan Agus.
Network Reduction Strategy and Deep Ensemble Learning for Blood Cell Detection.
Lontar Komputer : Jurnal Ilmiah Teknologi Informasi, [S.l.], v. 14, n. 3, p. 161-171, dec. 2023.
ISSN 2541-5832.
Available at: <https://ojs.unud.ac.id/index.php/lontar/article/view/108906>. Date accessed: 28 apr. 2024.
doi: https://doi.org/10.24843/LKJITI.2023.v14.i03.p04.
Section
Articles
This work is licensed under a Creative Commons Attribution 4.0 International License.
The Authors submitting a manuscript do so on the understanding that if accepted for publication, the copyright of the article shall be assigned to Jurnal Lontar Komputer as the publisher of the journal. Copyright encompasses exclusive rights to reproduce and deliver the article in all forms and media, as well as translations. The reproduction of any part of this journal (printed or online) will be allowed only with written permission from Jurnal Lontar Komputer. The Editorial Board of Jurnal Lontar Komputer makes every effort to ensure that no wrong or misleading data, opinions, or statements be published in the journal.
This work is licensed under a Creative Commons Attribution 4.0 International License.
