Deteksi Malaria Semi-Supervised: Eksplorasi Convolutional Autoencoder dengan SSIM Loss dan Youden J Thresholding
DOI:
https://doi.org/10.29407/zq98rv70Abstract
Sebuah convolutional autoencoder diterapkan dalam kerangka deteksi anomali semi-supervised untuk mengidentifikasi sel darah merah yang terinfeksi malaria. Model dilatih secara eksklusif menggunakan citra sel normal guna menangkap ciri struktural alaminya, sehingga memungkinkan deteksi anomali berdasarkan perbedaan rekonstruksi yang diukur menggunakan Structural Similarity Index Measure (SSIM). Threshold optimal ditentukan melalui analisis ROC dan statistik Youden’s J. Evaluasi pada dataset uji yang seimbang menghasilkan akurasi sebesar 76%, dengan presisi 76,5% dan recall 76%, yang menyoroti tantangan dalam mendeteksi variasi patologis yang halus. Hasil menunjukkan potensi unsupervised representation learning dalam deteksi malaria, sekaligus menyarankan bahwa penelitian di masa depan sebaiknya difokuskan pada peningkatan sensitivitas dan robustnes melalui ekstraksi fitur yang lebih canggih dan teknik hybrid supervised-unsupervised.
Keywords:
convolutional autoencoder, deteksi anomali, deteksi malaria, semi-supervised, SSIM##plugins.themes.default.displayStats.downloads##
References
[1] 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, doi: 10.1016/j.trsl.2017.12.004.
[2] M. H. D. Alnussairi and A. A. İbrahim, “Malaria parasite detection using deep learning algorithms based on (CNNs) technique,” Computers and Electrical Engineering, vol. 103, p. 108316, Oct. 2022, doi: 10.1016/J.COMPELECENG.2022.108316.
[3] J. T. Bandzuh et al., “Knowledge, attitudes, and practices of Anopheles mosquito control through insecticide treated nets and community-based health programs to prevent malaria in East Sumba Island, Indonesia,” PLOS Global Public Health, vol. 2, no. 9, pp. e0000241-, Sep. 2022, [Online]. Available: https://doi.org/10.1371/journal.pgph.0000241
[4] N. Shvetsova, B. Bakker, I. Fedulova, H. Schulz, and D. V Dylov, “Anomaly Detection in Medical Imaging With Deep Perceptual Autoencoders,” IEEE Access, vol. 9, pp. 118571–118583, 2021, doi: 10.1109/access.2021.3107163.
[5] M.-I. Georgescu, “Masked Autoencoders for Unsupervised Anomaly Detection in Medical Images,” 2023. [Online]. Available: https://arxiv.org/abs/2307.07534
[6] Y. Tian et al., “Unsupervised Anomaly Detection in Medical Images with a Memory-augmented Multi-level Cross-attentional Masked Autoencoder,” 2023. [Online]. Available: https://arxiv.org/abs/2203.11725
[7] C. Baur, S. Denner, B. Wiestler, S. Albarqouni, and N. Navab, “Autoencoders for Unsupervised Anomaly Segmentation in Brain MR Images: A Comparative Study,” 2020. [Online]. Available: https://arxiv.org/abs/2004.03271
[8] Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli, “Image quality assessment: from error visibility to structural similarity,” IEEE Transactions on Image Processing, vol. 13, no. 4, pp. 600–612, 2004, doi: 10.1109/TIP.2003.819861.
[9] S. K. Zhou et al., “A Review of Deep Learning in Medical Imaging: Imaging Traits, Technology Trends, Case Studies With Progress Highlights, and Future Promises,” Proceedings of the IEEE, vol. 109, no. 5, pp. 820–838, 2021, doi: 10.1109/JPROC.2021.3054390.
[10] K. M. F. Fuhad, J. F. Tuba, M. R. A. Sarker, S. Momen, N. Mohammed, and T. Rahman, “Deep Learning Based Automatic Malaria Parasite Detection from Blood Smear and its Smartphone Based Application,” Diagnostics (Basel), vol. 10, no. 5, p. 329, 2020, [Online]. Available: https://doi.org/10.3390/diagnostics10050329
[11] M. Bhuiyan and M. S. Islam, “A new ensemble learning approach to detect malaria from microscopic red blood cell images,” Sensors International, vol. 4, p. 100209, 2023, doi: https://doi.org/10.1016/j.sintl.2022.100209.
[12] A. Huq, M. T. Reza, S. Hossain, and S. M. Dipto, “AnoMalNet: Outlier Detection based Malaria Cell Image Classification Method Leveraging Deep Autoencoder,” 2024. [Online]. Available: https://arxiv.org/abs/2303.05789
[13] P. Bergmann, S. Löwe, M. Fauser, D. Sattlegger, and C. Steger, “Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoders,” Nov. 2019, pp. 372–380. doi: 10.5220/0007364503720380.
[14] S. Rajaraman, S. Jaeger, and S. K. Antani, “Performance evaluation of deep neural ensembles toward malaria parasite detection in thin-blood smear images,” PeerJ, vol. 7, p. e6977, 2019, [Online]. Available: https://doi.org/10.7717/peerj.6977
[15] H. Torabi, S. L. Mirtaheri, and S. Greco, “Practical autoencoder based anomaly detection by using vector reconstruction error,” Cybersecurity, vol. 6, no. 1, p. 1, 2023, doi: 10.1186/s42400-022-00134-9.
[16] J. Chen, S. Sathe, C. Aggarwal, and D. Turaga, “Outlier Detection with Autoencoder Ensembles,” in Proceedings of the 2017 SIAM International Conference on Data Mining (SDM), pp. 90–98. doi: 10.1137/1.9781611974973.11.
[17] V. Chandola, A. Banerjee, and V. Kumar, “Anomaly detection: A survey,” ACM Comput. Surv., vol. 41, no. 3, Jul. 2009, doi: 10.1145/1541880.1541882.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Danuar Aditya Anardha, Resty Wulanningrum, Julian Sahertian
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Copyright on any article is retained by the author(s).
- The author grants the journal, right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work’s authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal’s published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
- The article and any associated published material is distributed under the Creative Commons Attribution-ShareAlike 4.0 International License
