IMPLEMENTASI METODE TRANSFER LEARNING UNTUK KLASIFIKASI MALARIA MENGGUNAKAN RESNET 50
DOI:
https://doi.org/10.70248/jrsit.v3i2.3138Keywords:
Malaria, Deep Learning, CNN, ResNet-50, Transfer Learning, plasmodiumAbstract
Malaria merupakan penyakit menular yang disebabkan oleh parasit Plasmodium dan masih menjadi masalah kesehatan serius di Indonesia, khususnya di wilayah timur. Diagnosis malaria yang cepat dan akurat sangat penting untuk mencegah komplikasi serta memutus rantai penularan. Penelitian ini bertujuan untuk mengimplementasikan metode transfer learning menggunakan arsitektur Convolutional Neural Network (CNN) ResNet-50 dalam mendeteksi sel darah yang terinfeksi malaria pada citra mikroskopis. Dataset yang digunakan terdiri dari dua kelas, yaitu Parasitized (terinfeksi) dan Uninfected (tidak terinfeksi). Tahapan penelitian meliputi preprocessing data, augmentasi citra, pemanfaatan model pretrained ResNet-50, penambahan lapisan klasifikasi, pelatihan model, serta evaluasi performa menggunakan metrik akurasi, presisi, recall, F1-score, dan AUC. Hasil penelitian menunjukkan bahwa model ResNet-50 mencapai akurasi sebesar 93,00%, dengan presisi 96,00%, recall 97,00%, F1-score 93,00%, dan AUC 98,00%. Dengan performa tersebut, pendekatan ini berpotensi menjadi solusi pendukung diagnosis malaria yang cepat, objektif, dan efisien, serta dapat diintegrasikan dalam sistem skrining laboratorium dan mendukung pengambilan keputusan medis berbasis kecerdasan buatan.
References
Adoma, A. F., Henry, N. M. dan Chen, W. (2020) “Comparative Analyses of Bert, Roberta, Distilbert, and Xlnet for Text-Based Emotion Recognition,” 2020 17th International Computer Conference on Wavelet Active Media Technology and Information Processing, ICCWAMTIP 2020, hal. 117–121. doi: 10.1109/ICCWAMTIP51612.2020.9317379.
Aisyah, D. N. et al. (2024) “The Changing Incidence of Malaria in Indonesia: A 9-Year Analysis of Surveillance Data,” Advances in Public Health, 2024(1). doi: 10.1155/adph/2703477.
Alarcón-Soto, Y. et al. (2019) “Data Science in Biomedicine,” hal. 1–20. Tersedia pada: http://arxiv.org/abs/1909.04486.
Chollet, F. (2018). Deep Learning with Python. In 2018 21st International Conference on Information Fusion, FUSION 2018. https://doi.org/10.23919/ICIF.2018.845553
Fransisca, L. et al. (2025) “Enhanced data quality to improve malaria surveillance in Papua, Indonesia,” Malaria Journal , 24(1). doi: 10.1186/s12936-025-05358-x.
Gao, Y. et al. (2023) “Distinguishing infectivity in patients with pulmonary tuberculosis using deep learning,” Frontiers in Public Health, 11(1). doi: 10.3389/fpubh.2023.1247141.
Hemachandran, K. et al. (2023) “Performance Analysis of Deep Learning Algorithms in Diagnosis of Malaria Disease,” Diagnostics, 13(3). doi: 10.3390/diagnostics13030534.
Maeda-Gutiérrez, V. et al. (2020) “Comparison of convolutional neural network architectures for classification of tomato plant diseases,” Applied Sciences (Switzerland), 10(4). doi: 10.3390/app10041245.
Millar, S. B. dan Cox-Singh, J. (2015) “Human infections with Plasmodium knowlesi-zoonotic malaria,” Clinical Microbiology and Infection, 21(7), hal. 640–648. doi: 10.1016/j.cmi.2015.03.017.
Nagendra, S. et al. (2024) “Techniques Versus Standard Microscopy in a Reference Laboratory,” (December).
Opoku Afriyie, S. et al. (2023) “Accuracy of diagnosis among clinical malaria patients: comparing microscopy, RDT and a highly sensitive quantitative PCR looking at the implications for submicroscopic infections,” Malaria Journal, 22(1), hal. 1–11. doi: 10.1186/s12936-023-04506-5.
Ramadhan, F. M. dan Riwurohi, J. E. (2024) “Perbandingan Optimizer, Batch Size Dan Epoch Pada Metode Convolution Neural Network,” JSiI (Jurnal Sistem Informasi), 11(2), hal. 134–138. doi: 10.30656/jsii.v11i2.9249.
Rajaraman, S., Antani, S. K., Poostchi, M., Silamut, K., Hossain, M. A., Maude, R. J., Jaeger, S., & Thoma, G. R. (2018). Pre-trained convolutional neural networks as feature extractors toward improved malaria parasite detection in thin blood smear images. PeerJ, 2018(4), 1–17. https://doi.org/10.7717/peerj.456
Ruicun Liu, Tuoyu Liu, Tingting Dan, ..., Xianchao Zhang, H. C. dan Teng, Y. (2023) “AIDMAN: An AI-based object detection system for malaria diagnosis from smartphone thin-bloodsmear images.”
Sinha, S. dan Gupta, N. (2023) “Computer-aided Diagnosis of Malaria through Transfer Learning using the ResNet50 Backbone,” 36, hal. 1–9.
Sutarto dan Cania, E. (2017) “Faktor Lingkungan , Perilaku dan Penyakit Malaria Environmental Factors , Behavior and Malaria Disease,” Jurnal AgromedUnila, 4(1), hal. 173–184.
Tegegne, B. et al. (2025) “Performance of BIOCREDIT Pf/Pv lactate dehydrogenase-based malaria rapid diagnostic test among pregnant women with suspected malaria infection in Bahir Dar City Administration, northwest Ethiopia,” PLoS ONE, 20(5 May), hal. 1–13. doi: 10.1371/journal.pone.0322362.
Wantini, S., & Huda, M. (2021). Pengaruh konsentrasi dan waktu pengecatan giemsa pada pemeriksaan mikroskopik malaria. Jurnal Analis Kesehatan, 10(1), 8-13.
WHO (2020) “The 2023 WHO World malaria report,” The Lancet Microbe, 5(3), hal. e214. doi: 10.1016/s2666-5247(24)00016-8.
WHO (2021) Word Malaria Report 2021, Word Malaria report Geneva: World Health Organization. (2021). Licence: CC BY-NC-SA 3.0 IGO. Tersedia pada: https://www.who.int/teams/global-malaria-programme/reports/world-malaria-report-2021
Zhuang, Q. et al. (2021) “Zero-shot Event Extraction via Transfer Learning: Challenges and Insights,” ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the Conference, 2, hal. 322–332. doi: 10.18653/v1/2021.acl-short.42
