Deteksi Penyakit Malaria Menggunakan Convolutional Neural Network Berbasis Saliency
Abstract
Malaria adalah penyakit mematikan yang menjadi masalah di berbagai negara. Metode yang paling umum untuk mendeteksi malaria adalah dengan memeriksanya secara manual, yang memakan waktu. Convolutional Neural Network (CNN) adalah salah satu solusi untuk deteksi malaria. CNN telah terbukti memberikan hasil yang sangat baik dalam klasifikasi gambar dan telah banyak digunakan dalam penelitian sebelumnya dan memiliki hasil yang baik. Sebelum proses klasifikasi, pra-pemrosesan gambar dapat digunakan untuk mendapatkan hasil klasifikasi yang lebih baik. Salah satu metode dalam pra-pemrosesan adalah arti-penting. Saliency adalah metode yang dapat mengambil bagian penting dari suatu gambar. Pada penelitian ini dilakukanlah pengujian terhadap metode saliency dan CNN untuk masalah pendeteksian penyakit malaria. Skenario pengujian dilakukan dengan membandingkan metode saliency, yaitu Region Contrast Saliency, Frequency-tuned saliency, Spectral Residual, dan Histogram Contrast. Metode saliency terbaik dalam mendeteksi penyakit malaria didapatkan oleh metode frequency-tuned saliency dengan akurasi sebesar 90,32% dibandingkan dengan metode saliency yang lain, yaitu 62,67% untuk region contrast saliency, 50% untuk spectral residual saliency, dan 79,06% untuk histogram contrast saliency.
Kata-kata kunci: Klasifikasi; CNN; Malaria; Saliency
Keywords
References
[1] L. Hakim, “Malaria Epidemiology and Diagnostic,” Aspirator J. Vector Borne Dis. Stud., vol. 3, no. 2, hal. 107–116, 2011, doi: 10.22435/aspirator.v3i2.2965.
[2] D. R. Anamisa, “Rancang Bangun Metode OTSU Untuk Deteksi Hemoglobin,” S@Cies, vol. 5, no. 2, hal. 106–110, 2015, doi: 10.31598/sacies.v5i2.64.
[3] C. Mehanian dkk., “Computer-Automated Malaria Diagnosis and Quantitation Using Convolutional Neural Networks,” Proc. - 2017 IEEE Int. Conf. Comput. Vis. Work. ICCVW 2017, hal. 116–125, 2017, doi: 10.1109/ICCVW.2017.22.
[4] I. R. Dave, “Image Analysis For Malaria Parasite Detection From Microscopic Images of Thick Blood Smear,” Proc. 2017 Int. Conf. Wirel. Commun. Signal Process. Networking, WiSPNET 2017, hal. 1303–1307, 2018, doi: 10.1109/WiSPNET.2017.8299974.
[5] A. Nanoti, S. Jain, C. Gupta, dan G. Vyas, “Detection of Malaria Parasite Species and Life Cycle Stages Using MicroscopicImages of Thin Blood Smear,” Proc. Int. Conf. Inven. Comput. Technol. ICICT 2016, vol. 1, 2016, doi: 10.1109/INVENTIVE.2016.7823258.
[6] F. Z. Rahmanti, H. A. Santoso, P. wahyu Adi, ketut E. Purnama, dan M. H. Purnomo, “LVQ (Learning Vector Quantization) Method for Identification of Plasmodium Vivax in Thick Blood Film,” ICBETA, 2014.
[7] S. C. Kalkan dan O. K. Sahingoz, “Deep Learning Based Classification of Malaria From Slide Images,” 2019 Sci. Meet. Electr. Biomed. Eng. Comput. Sci. EBBT 2019, hal. 1–4, 2019, doi: 10.1109/EBBT.2019.8741702.
[8] M. Zufar dan B. Setiyono, “Convolutional Neural Networks Untuk Pengenalan Wajah Secara Real-Time,” J. Sains dan Seni ITS, vol. 5, no. 2, hal. 72–77, 2016, doi: 10.12962/j23373520.v5i2.18854.
[9] Z. Liang dkk., “CNN-based Image Analysis For Malaria Diagnosis,” Proc. - 2016 IEEE Int. Conf. Bioinforma. Biomed. BIBM 2016, hal. 493–496, 2017, doi: 10.1109/BIBM.2016.7822567.
[10] W. D. Pan, Y. Dong, dan D. Wu, “Classification of Malaria-Infected Cells Using Deep Convolutional Neural Networks,” Mach. Learn. - Adv. Tech. Emerg. Appl., 2018, doi: 10.5772/intechopen.72426.
[11] N. Jmour, S. Zayen, dan A. Abdelkrim, “Convolutional Neural Networks For Image Classification,” 2018 Int. Conf. Adv. Syst. Electr. Technol. IC_ASET 2018, hal. 397–402, 2018, doi: 10.1109/ASET.2018.8379889.
[12] M. M. Cheng, N. J. Mitra, X. Huang, P. H. S. Torr, dan S. M. Hu, “Global Contrast Based Salient Region Detection,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 37, no. 3, hal. 569–582, 2015, doi: 10.1109/TPAMI.2014.2345401.
[13] G. Zeng, “Fruit and Vegetables Classification System Using Image Saliency and Convolutional Neural Network,” Proc. 2017 IEEE 3rd Inf. Technol. Mechatronics Eng. Conf. ITOEC 2017, hal. 613–617, 2017, doi: 10.1109/ITOEC.2017.8122370.
[14] D. S. Ferreira dkk., “Saliency-driven System Models For Cell Analysis With Deep Learning,” Comput. Methods Programs Biomed., vol. 182, hal. 1–13, 2019, doi: 10.1016/j.cmpb.2019.105053.
[15] A. M. Obeso, J. Benois-Pineau, K. Guissous, V. Gouet-Brunet, M. S. Garcia Vazquez, dan A. A. Ramirez Acosta, “Comparative Study of Visual Saliency Maps in the Problem of Classification of Architectural Images With Deep CNNs,” 2018 8th Int. Conf. Image Process. Theory, Tools Appl. IPTA 2018 - Proc., 2019, doi: 10.1109/IPTA.2018.8608125.
[16] S. Rajaraman dkk., “Pre-trained convolutional neural networks as feature extractors toward improved malaria parasite detection in thin blood smear images,” PeerJ, hal. 1–17, 2018, doi: 10.7717/peerj.4568.
[17] X. Hou dan L. Zhang, “Saliency Detection: A Spectral Residual Approach,” IEEE Conf. Comput. Vis. Pattern Recognit., hal. 1063–6919, 2007, doi: 10.1109/CVPR.2007.383267.
[18] R. Achanta, S. Hemami, F. Estrada, dan S. S¨usstrunk, “Frequency-tuned Salient Region Detection,” IEEE Conf. Comput. Vis. Pattern Recognit., hal. 1063–6919, 2009, doi: 10.1109/CVPR.2009.5206596.
[19] A. Trask, Grokking Deep Learning. Shelter Island, New York, United States: Manning Publications, 2019.
[20] J. P. Mueller dan L. Massaron, Deep Learning For Dummies. United States: For Dummies, 2019.
[21] I. Vasilev, D. Slater, G. Spacagna, P. Roelants, dan V. Zocca, Python Deep Learning: Exploring Deep Learning Techniques and Neural Network Architectures With PyTorch, Keras, and TensorFlow. Birmingham, United Kingdom: Packt Publishing, 2019.
[22] Suyanto, Machine Learning: Tingkat Dasar dan Lanjut. Bandung: Informatika, 2018.
DOI: 10.30595/juita.v8i1.6671
Refbacks
- There are currently no refbacks.
This work is licensed under a Creative Commons Attribution 4.0 International License.
ISSN: 2579-8901
- Visitor Stats
View JUITA Stats
Email this article (Login required)
Email the author (Login required)
 |
 |
 |
 |
 |
 |
 |
 |
