PULMONARY EDEMA CLASSIFICATION USING CLASSICAL AND QUANTUM CONVOLUTIONAL NEURAL NETWORKS
DOI:
https://doi.org/10.33480/jitk.v12i1.8446Keywords:
CNN, hyperparameters, pulmonary edema, QCNN, X-ray imageAbstract
This study develops a pulmonary edema detection model based on chest x-ray images using both classical Convolutional Neural Network (CNN) and Quantum Convolutional Neural Network (QCNN) approaches. The dataset consists of chest x-ray images labeled as positive and negative for pulmonary edema and is divided into training and testing sets with an 80:20 ratio. To obtain the best performance, both models were optimized through hyperparameter tuning. The classical CNN model employed 3×3 filters, four convolutional layers, and was trained for 10 epochs. The QCNN model was designed with a comparable architecture incorporating quantum gate modifications and was also trained for 10 epochs. The performances of these models were assessed based on accuracy, sensitivity, and precision in order to measure their classification capacities. The QCNN was developed under the same experimental conditions to enable a fair performance comparison with the optimized classical CNN model. The results show that the classical CNN achieved better performance than the QCNN. This lower QCNN performance is likely due to the current limitations of quantum architectures and hardware, which are not yet able to extract and process image features as effectively as classical CNNs. However, this study was conducted using low-resolution medical images and a preliminary QCNN framework under limited computational resources.
Downloads
References
[1] F. Campos-Rodríguez et al., “Respiratory Pathology and Cardiovascular Diseases: A Scoping Review,” Open Respir. Arch., vol. 7, no. 1, p. 100392, Jan. 2025, doi: 10.1016/j.opresp.2024.100392.
[2] C. Zanza et al., “Cardiogenic Pulmonary Edema in Emergency Medicine,” Adv. Respir. Med., vol. 91, no. 5, pp. 445–463, Oct. 2023, doi: 10.3390/arm91050034.
[3] W. Abbasi, A. Shahzadi, and A. Aljohani, "Enhanced detection of pulmonary edema in chest X-rays using deep learning ensembles with attention mechanism," J. Digit. Imaging. Inform. Med., vol. 39, no. 4, pp. 2876–2889, Aug. 2026, doi: 10.1007/s10278-025-01710-4.
[4] D. Schulz et al., "A deep learning model enables accurate prediction and quantification of pulmonary edema from chest X-rays," Crit. Care, vol. 27, no. 1, art. no. 201, Dec. 2023, doi: 10.1186/s13054-023-04426-5.
[5] V. V. Danilov, A. O. Makoveev, A. Proutski, I. Ryndova, A. Karpovsky, and Y. Gankin, "Explainable AI to identify radiographic features of pulmonary edema," Radiol. Adv., vol. 1, no. 1, Art. no. umae003, May 2024, doi: 10.1093/radadv/umae003.
[6] J. Kim, M. Hassan, L. Bijulisingh, and M. Paneru, “Atypical Presentation of Cardiogenic Pulmonary Edema: Multiple Subsolid Lung Nodules,” Am. J. Respir. Crit. Care Med., vol. 211, no. Abstracts, pp. A2195–A2195, May 2025, doi: 10.1164/ajrccm.2025.211.Abstracts.A2195.
[7] H. M. S. S. Herath, H. M. K. K. M. B. Herath, N. Madusanka, and B.-I. Lee, “A Systematic Review of Medical Image Quality Assessment,” J. Imaging, vol. 11, no. 4, p. 100, Apr. 2025, doi: 10.3390/jimaging11040100.
[8] H. Matsuo et al., “Artificial intelligence for chest radiography: an overview of techniques, challenges, and future directions,” Npj Health Syst., vol. 3, no. 1, p. 41, Jun. 2026, doi: 10.1038/s44401-026-00087-y.
[9] E. Yuliawan and Shofwatul ‘Uyun, “Chest X-ray Image Classification for COVID-19 diagnoses,” J. Inf. Syst. Eng. Bus. Intell., vol. 8, no. 2, pp. 109–118, Oct. 2022, doi: 10.20473/jisebi.8.2.109-118.
[10] A. Sinra and H. Angriani, “Automated Classification of COVID-19 Chest X-ray Images Using Ensemble Machine Learning Methods,” Indones. J. Data Sci., vol. 5, no. 1, pp. 45–53, Mar. 2024, doi: 10.56705/ijodas.v5i1.127.
[11] Y. Pamungkas, M. R. N. Ramadani, and E. N. Njoto, “Effectiveness of CNN Architectures and SMOTE to Overcome Imbalanced X-Ray Data in Childhood Pneumonia Detection | Journal of Robotics and Control (JRC),” May 2024, Accessed: Oct. 25, 2025. [Online]. Available: https://journal.umy.ac.id/index.php/jrc/article/view/21494
[12] C.-T. Yen and C.-Y. Tsao, “Lightweight convolutional neural network for chest X-ray images classification,” Sci. Rep., vol. 14, no. 1, p. 29759, Nov. 2024, doi: 10.1038/s41598-024-80826-z.
[13] M. A. Anwar, Y. A. Gerhana, and U. Syaripudin, “Implementasi Model CNN ResNet50V2 untuk Klasifikasi Pneumonia pada Citra X-Ray,” SMATIKA J. STIKI Inform. J., vol. 15, no. 01, pp. 126–135, Jun. 2025, doi: 10.32664/smatika.v15i01.1538.
[14] T. Huang, R. Yang, L. Shen, A. Feng, L. Li, N. He, S. Li, L. Huang, and J. Lyu, "Deep transfer learning to quantify pleural effusion severity in chest X-rays," BMC Med. Imaging, vol. 22, art. no. 100, May 2022, doi: 10.1186/s12880-022-00827-0.
[15] L. Liong-Rung et al., “Using Artificial Intelligence to Establish Chest X-Ray Image Recognition Model to Assist Crucial Diagnosis in Elder Patients With Dyspnea,” Front. Med., vol. 9, p. 893208, Jun. 2022, doi: 10.3389/fmed.2022.893208.
[16] “Pulmonary Edema and Pleural Effusion Detection Using EfficientNet-V1-B4 Architecture and AdamW Optimizer from Chest X-Rays Images,” Comput. Mater. Contin., vol. 80, no. 1, pp. 1055–1073, Jul. 2024, doi: 10.32604/cmc.2024.051420.
[17] D. Bokhan, A. S. Mastiukova, A. S. Boev, D. N. Trubnikov, and A. K. Fedorov, “Multiclass classification using quantum convolutional neural networks with hybrid quantum-classical learning,” Front. Phys., vol. 10, p. 1069985, Nov. 2022, doi: 10.3389/fphy.2022.1069985.
[18] R. Giuntini, F. Holik, D. K. Park, H. Freytes, C. Blank, and G. Sergioli, “Quantum-inspired algorithm for direct multi-class classification,” Appl. Soft Comput., vol. 134, p. 109956, Feb. 2023, doi: 10.1016/j.asoc.2022.109956.
[19] J. Yang et al., “MedMNIST v2 - A large-scale lightweight benchmark for 2D and 3D biomedical image classification,” Sci. Data, vol. 10, no. 1, p. 41, Jan. 2023, doi: 10.1038/s41597-022-01721-8.
[20] M. Yousif, B. Al-Khateeb, and B. Garcia-Zapirain, "A New Quantum Circuits of Quantum Convolutional Neural Network for X-Ray Images Classification," IEEE Access, vol. 12, pp. 61973–61990, May 2024, doi: 10.1109/ACCESS.2024.3396411.
[21] “Pulmonary Edema Classified - By NIH.” Accessed: Oct. 25, 2025. [Online]. Available: https://www.kaggle.com/datasets/samiulbari/pulmonary-edema-classified-by-nih
[22] J. Guan, "Fundamental Overview of Medical Scientific Data Sharing," in Governance and Management of Medical Scientific Data Sharing and Application, Singapore: Springer, 2026, pp. 1–35, doi: 10.1007/978-981-95-2806-6_1.
[23] A. S, S. Kashyap, D. Patel H N, and P. Kumar Y R, “Hybrid deep learning and machine learning framework for automated pneumonia detection in chest X-ray images,” MethodsX, vol. 15, p. 103729, Dec. 2025, doi: 10.1016/j.mex.2025.103729.
[24] S. Dwijayanti et al., "Facial recognition and body temperature measurements based on thermal images using a deep-learning algorithm," IAES Int. J. Artif. Intell. (IJ-AI), vol. 12, no. 4, pp. 1654–1665, Dec. 2023, doi: 10.11591/ijai.v12.i4.pp1654-1665.
[25] K. Y. Cheng, M. Lange-Hegermann, J.-B. Hövener, and B. Schreiweis, “Instance-level medical image classification for text-based retrieval in a medical data integration center,” Comput. Struct. Biotechnol. J., vol. 24, pp. 434–450, Jun. 2024, doi: 10.1016/j.csbj.2024.06.006.
[26] J. Lee, H. Chung, M. Suh, J.-H. Lee, and K. S. Choi, “Deep learning for deep learning performance: How much data is needed for segmentation in biomedical imaging?,” PLOS ONE, vol. 20, no. 12, p. e0339064, Des 2025, doi: 10.1371/journal.pone.0339064.
[27] J. Hofmeister et al., "Validating the accuracy of deep learning for the diagnosis of pneumonia on chest x-ray against a robust multimodal reference diagnosis: a post hoc analysis of two prospective studies," Eur. Radiol. Exp., vol. 8, no. 1, art. no. 20, Feb. 2024, doi: 10.1186/s41747-023-00416-y.
[28] I. D. Mienye, T. G. Swart, G. Obaido, M. Jordan, and P. Ilono, “Deep Convolutional Neural Networks in Medical Image Analysis: A Review,” Information, vol. 16, no. 3, p. 195, Mar. 2025, doi: 10.3390/info16030195.
[29] Y. Liu, K. Kaneko, K. Baba, J. Koyama, K. Kimura, and N. Takeda, “Analysis of Parameterized Quantum Circuits: On the Connection Between Expressibility and Types of Quantum Gates,” IEEE Trans. Quantum Eng., vol. 6, pp. 1–12, 2025, doi: 10.1109/TQE.2025.3571484.
[30] H. Hirai, “Practical application of quantum neural network to materials informatics,” Sci. Rep., vol. 14, no. 1, p. 8583, Apr. 2024, doi: 10.1038/s41598-024-59276-0.
[31] A. Cicero, M. A. Maleki, M. W. Azhar, A. F. Kockum, and P. Trancoso, “Simulation of Quantum Computers: Review and Acceleration Opportunities,” ACM Trans. Quantum Comput., vol. 7, no. 1, p. 3:1-3:35, Nov. 2025, doi: 10.1145/3762672.
[32] M. C. Caro, H.-Y. Huang, M. Cerezo, K. Sharma, A. Sornborger, L. Cincio, and P. J. Coles, "Generalization in quantum machine learning from few training data," Nat. Commun., vol. 13, no. 1, art. no. 4919, Aug. 2022, doi: 10.1038/s41467-022-32550-3.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Adri Sopiana, Tony Sumaryada, Sitti Yani
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
-a.jpg)
-b.jpg)
