PEMBELAJARAN REPRESENTASI BERBASIS SELF-SUPERVISED UNTUK KLASIFIKASI PENYAKIT PARU PADA CITRA CHEST X-RAY DENGAN DATA BERLABEL TERBATAS

Authors

  • Nurhayati Universitas Mikroskil
  • Tioria Pasaribu STMIK Kaputama
  • Hernawati Gohzali Universitas Mikroskil
  • Fauzi Sekolah Tinggi Keguruan dan Ilmu Pendidikan Amal Bakti
  • Arisman Universitas Mikroskil
  • Suminar Ariwibowo Universitas Mikroskil

DOI:

https://doi.org/10.54314/jssr.v9i3.6482

Keywords:

Chest X-Ray, Self-Supervised Learning, Contrastive Learning, Deep Learning, Lung Disease Classification

Abstract

Abstract: Lung disease classification based on Chest X-Ray (CXR) images has become an important focus in the development of deep learning for medical imaging. However, most modern classification models still rely heavily on large amounts of labeled data, while medical image annotation requires radiology experts, high costs, and considerable time. This study aims to implement a self-supervised learning approach based on contrastive learning for lung disease classification on CXR images using the CheXpert dataset under limited labeled data conditions. The research stages include data preprocessing, image augmentation, self-supervised pretraining, fine-tuning, and model evaluation using accuracy, precision, recall, and F1-score metrics. The dataset was divided into 70% training data and 30% testing data. The experimental results showed that the model achieved an accuracy of 0.87, precision of 0.87, recall of 0.84, and F1-score of 0.85. These results indicate that the self-supervised learning approach is capable of utilizing unlabeled data to generate robust visual representations and improve lung disease classification performance under limited labeled data conditions. This study is expected to contribute to the development of more efficient deep learning-based medical image analysis systems with reduced dependency on medical annotations.

Keywords: Chest X-Ray, Self-Supervised Learning, Contrastive Learning, Deep Learning, Lung Disease Classification.

 

Abstrak: Klasifikasi penyakit paru berbasis citra CXR menjadi salah satu fokus penting dalam pengembangan deep learning pada bidang pencitraan medis. Namun, sebagian besar model klasifikasi modern masih bergantung pada data berlabel dalam jumlah besar, sedangkan proses anotasi citra medis membutuhkan tenaga ahli radiologi, biaya tinggi, dan waktu yang panjang. Penelitian ini bertujuan menerapkan pendekatan self-supervised learning berbasis contrastive learning untuk klasifikasi penyakit paru pada citra CXR menggunakan dataset CheXpert dengan kondisi data berlabel terbatas. Tahapan penelitian meliputi pra-pemrosesan data, augmentasi citra, self-supervised pretraining, fine-tuning, dan evaluasi model menggunakan metrik accuracy, precision, recall, dan F1-score. Dataset dibagi menggunakan rasio 70% data pelatihan dan 30% data pengujian. Hasil penelitian menunjukkan bahwa model mampu menghasilkan nilai accuracy sebesar 0.87, precision 0.87, recall 0.84, dan F1-score 0.85. Hasil tersebut menunjukkan bahwa pendekatan self-supervised learning mampu memanfaatkan data tidak berlabel untuk menghasilkan representasi visual yang robust dan meningkatkan performa klasifikasi penyakit paru pada kondisi data berlabel terbatas. Penelitian ini diharapkan dapat mendukung pengembangan sistem analisis citra medis berbasis deep learning yang lebih efisien terhadap kebutuhan anotasi medis.

Kata Kunci: Chest X-Ray, Self-Supervised Learning, Contrastive Learning, Deep Learning, Klasifikasi Penyakit Paru.

Downloads

Download data is not yet available.

References

M. Gazda and J. Gazda, “Self-Supervised Deep Convolutional Neural Network for Chest X-Ray Classification,” vol. 9, 2021, doi: 10.1109/ACCESS.2021.3125324.

H. Laçi and K. Sevrani, “Deep learning approaches for classification tasks in medical X-ray , MRI , and ultrasound images : a scoping review,” 2025.

C. X-ray, T. Rahman, M. E. H. Chowdhury, and A. Khandakar, “applied sciences Transfer Learning with Deep Convolutional Neural Network ( CNN ) for Pneumonia Detection Using”.

S. Azizi et al., “Big Self-Supervised Models Advance Medical Image Classification,” pp. 3478–3488.

J. Irvin et al., “CheXpert : A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison”.

B. Vanberlo, J. Hoey, and A. Wong, “A survey of the impact of self ‑ supervised pretraining for diagnostic tasks in medical X ‑ ray , CT , MRI , and ultrasound,” BMC Med. Imaging, pp. 1–24, 2024, doi: 10.1186/s12880-024-01253-0.

M. M. Afzal and M. O. Khan, “A Comprehensive Benchmark of Supervised and Self-supervised Pre-training on Multi-view Chest X-ray Classification,” pp. 1–16, 2024.

E. Eldele, M. Ragab, Z. Chen, M. Wu, C. Kwoh, and X. Li, “Self-supervised Contrastive Representation Learning for Semi-supervised Time-Series Classification,” pp. 1–17.

S. Langer, J. Ritter, R. Braren, D. Rueckert, and P. Hager, “Radiograph Anatomical Region Classification – How Clean Is Your Real-World Data ?”.

J. Yao, X. Wang, W. Liu, B. Wang, and Y. Chen, “EVA-X : a foundation model for general chest x-ray analysis with self-supervised learning,” pp. 1–10, 2025.

Y. Gao, Y. Jiang, Y. Peng, F. Yuan, X. Zhang, and J. Wang, “Medical Image Segmentation : A Comprehensive Review of Deep Learning-Based Methods,” 2025.

K. He, X. Chen, S. Xie, Y. Li, P. Doll, and R. Girshick, “Masked Autoencoders Are Scalable Vision Learners,” pp. 16000–16009.

X. Chen and F. Ai, “An Empirical Study of Training Self-Supervised Vision Transformers,” pp. 9640–9649.

R. Wang, A. K. Nandi, T. Lei, R. Cui, B. Zhang, and H. Meng, “Medical image segmentation using deep learning : A survey,” no. September 2021, pp. 1243–1267, 2022, doi: 10.1049/ipr2.12419.

Q. Guan, Y. Huang, Z. Zhong, Z. Zheng, L. Zheng, and Y. Yang, “Diagnose like a Radiologist : Attention Guided Convolutional Neural Network for Thorax Disease,” vol. 1, pp. 1–10.

C. Randieri, A. Perrotta, A. Puglisi, M. Grazia Bocci, and C. Napoli, “CNN-Based Framework for Classifying COVID-19, Pneumonia, and Normal Chest X-Rays,” Big Data Cogn. Comput., vol. 9, no. 7, pp. 1–18, 2025, doi: 10.3390/bdcc9070186.

M. Mann, R. P. Badoni, H. Soni, M. Al-Shehri, A. C. Kaushik, and D. Q. Wei, “Utilization of Deep Convolutional Neural Networks for Accurate Chest X-Ray Diagnosis and Disease Detection,” Interdiscip. Sci. – Comput. Life Sci., vol. 15, no. 3, pp. 374–392, 2023, doi: 10.1007/s12539-023-00562-2.

W. You, N. To, and K. About, “Interpreting a chest X-ray,” vol. 80, no. 5, pp. 75–79, 2019.

M. Benchoufi, E. Matzner-lober, N. Molinari, A. Jannot, and P. Soyer, “Interobserver agreement issues in radiology,” Diagn. Interv. Imaging, vol. 101, no. 10, pp. 639–641, 2020, doi: 10.1016/j.diii.2020.09.001.

M. Adnan and Q. Muhammad, “Medical Image Analysis using Convolutional Neural Networks: A Review”.

C. Albuquerque, R. Henriques, and M. Castelli, “Heliyon Deep learning-based object detection algorithms in medical imaging : Systematic review,” Heliyon, vol. 11, no. 1, p. e41137, 2025, doi: 10.1016/j.heliyon.2024.e41137.

T. Rahman, M. E. H. Chowdhury, and A. Khandakar, “applied sciences Transfer Learning with Deep Convolutional Neural Network ( CNN ) for Pneumonia Detection Using,” MDPI, J. app Sci., vol. 3233, pp. 1–17, 2020.

Y. Lecun, Y. Bengio, G. Hinton, Y. Lecun, Y. Bengio, and G. Hinton, “Deep learning To cite this version :,” 2023.

P. Conze et al., “with deep learning To cite this version : Current and emerging trends in medical image segmentation with deep learning,” 2023.

M. A. Abdou, “Literature review : efficient deep neural networks techniques for medical image analysis,” vol. 9, pp. 5791–5812, 2022.

O. Iparraguirre-villanueva, V. Guevara-ponce, O. R. Paredes, F. Sierra-liñan, J. Zapata-paulini, and M. Cabanillas-carbonell, “Convolutional Neural Networks with Transfer Learning for Pneumonia Detection,” vol. 13, no. 9, pp. 544–551, 2022.

C. Ma, H. Wang, and S. C. H. Hoi, “Multi-label Thoracic Disease Image Classification with Cross-Attention Networks,” pp. 1–9.

K. Saini and R. Devi, “Review Article A systematic scoping review of the analysis of COVID-19 disease using chest X-ray images with deep learning models,” vol. 7, no. 2, pp. 1–19, 2024, doi: 10.32629/jai.v7i2.928.

L. Quinn, K. Tryposkiadis, J. O. N. Deeks, and H. C. W. D. E. Vet, “Interobserver variability studies in diagnostic imaging : a methodological systematic review,” no. April, 2023.

A. Singh, D. Mandal, and D. Mishra, “Self-Supervised Contextual Representations of Chest X-Ray Images,” vol. 32, pp. 2728–2732, 2025.

F. C. Ghesu et al., “Contrastive self-supervised learning from 100 million medical images with optional supervision,” vol. 9, no. 6, pp. 1–20, 2022, doi: 10.1117/1.JMI.9.6.064503.

L. Jing and Y. Tian, “Self-supervised Visual Feature Learning with Deep Neural Networks : A Survey,” pp. 1–24.

K. He and F. Ai, “Momentum Contrast for Unsupervised Visual Representation Learning,” pp. 9729–9738.

D. Karimi, H. Dou, S. K. Warfield, and A. Gholipour, HHS Public Access. 2021. doi: 10.1016/j.media.2020.101759.Deep.

B. Vanberlo, B. Li, A. Wong, J. Hoey, and R. Arntfield, “Exploring the Utility of Self-Supervised Pretraining Strategies for the Detection of Absent Lung Sliding in M-Mode Lung Ultrasound,” pp. 3077–3086.

T. Chen, S. Kornblith, M. Norouzi, and G. Hinton, “A Simple Framework for Contrastive Learning of Visual Representations,” no. Figure 1, 2019.

X. Chen and F. Ai, “Exploring Simple Siamese Representation Learning,” no. Figure 1, pp. 15750–15758.

K. Imagawa and K. Shiomoto, “Evaluation of Effectiveness of Self ‑ Supervised Learning in Chest X ‑ Ray Imaging to Reduce Annotated Images,” J. Imaging Informatics Med., vol. 37, no. 4, pp. 1618–1624, 2024, doi: 10.1007/s10278-024-00975-5.

T. Ahmed, A. Ahmed, A. L. I. S. Imran, M. Ullah, A. Manaf, and A. Soylu, “Exploring the Impact of Self-Supervised Learning and Swin-B Transformer on Saliency Maps and Performance in Multi-Label Chest X-Ray Classification,” IEEE Access, vol. 14, no. January, pp. 21833–21857, 2026, doi: 10.1109/ACCESS.2026.3655022.

B. Vanberlo, J. Hoey, and A. Wong, “A S Urvey Of The I Mpact Of S Elf -S Upervised P Retraining For D Iagnostic T Asks With R Adiological I Mages,” no. Frn 186945, pp. 1–32.

A. Taleb, W. Loetzsch, N. Danz, J. Severin, and T. Gaertner, “3D Self-

Supervised Methods for Medical Imaging,” no. NeurIPS, pp. 1–15, 2020.

K. Chaitanya, “Contrastive learning of global and local features for medical image segmentation with limited annotations,” no. NeurIPS, 2020.

A. L. Simpson et al., “arXiv : 1902 . 09063v1 [ cs . CV ] 25 Feb 2019 A large annotated medical image dataset for the development and evaluation of segmentation algorithms,” 2019.

M. Benchoufi, E. Matzner-Lober, N. Molinari, A. S. Jannot, and P. Soyer, “Interobserver agreement issues in radiology,” Diagn. Interv. Imaging, vol. 101, no. 10, pp. 639–641, 2020, doi: 10.1016/j.diii.2020.09.001.

J. Irvin et al., “CheXpert: A large chest radiograph dataset with uncertainty labels and expert comparison,” 33rd AAAI Conf. Artif. Intell. AAAI 2019, 31st Innov. Appl. Artif. Intell. Conf. IAAI 2019 9th AAAI Symp. Educ. Adv. Artif. Intell. EAAI 2019, pp. 590–597, 2019, doi: 10.1609/aaai.v33i01.3301590.

J. Wang, S. Wang, and Y. Zhang, “Deep learning on medical image analysis,” CAAI Trans. Intell. Technol., vol. 10, no. 1, pp. 1–35, 2025, doi: 10.1049/cit2.12356.

Downloads

Published

2026-06-14

Issue

Vol. 9 No. 3 (2026): June 2026

Section

Artikel

License

Copyright (c) 2026 Nurhayati, Tioria Pasaribu, Hernawati Gohzali, Fauzi, Arisman, Suminar Ariwibowo

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.