Comparative Analysis of Kolmogorov-Inspired CNN and Traditional CNN Models for Pneumonia Detection: A Study on Chest CT Images

Muhammet Sinan  Basarslan; Nurgul  Bulut; Handan  Ankarali

doi:10.6000/1929-6029.2025.14.04

Authors

Muhammet Sinan Basarslan Department of Computer Engineering, Faculty of Engineering, Istanbul Medeniyet University, 34000, Istanbul, Turkey https://orcid.org/0000-0002-7996-9169
Nurgul Bulut Department of Biostatistics and Medical Informatics, Faculty of Medicine, Istanbul Medeniyet University, Istanbul, Turkey https://orcid.org/0000-0002-7247-6302
Handan Ankarali Department of Biostatistics and Medical Informatics, Faculty of Medicine, Istanbul Medeniyet University, Istanbul, Turkey https://orcid.org/0000-0002-3613-0523

DOI:

https://doi.org/10.6000/1929-6029.2025.14.04

Keywords:

Deep learning, Kolmogorov-Inspired Convolutional Neural Networks, Convolutional Neural Networks, Medical Imaging, Chest CT Images, Performance metrics

Abstract

Aim: In this study, our goal is to compare the effectiveness of Kolmogorov Inspired Convolutional Neural Networks (KAN) with traditional Convolutional Neural Networks (CNN) models in pneumonia detection and to contribute to the development of more efficient and accurate diagnostic tools in the field of medical imaging.

Methods: Both models are structured with the same layers and hyperparameters to ensure a fair comparison of their performance. For a robust evaluation, the relevant dataset was divided into 80% for training and 20% for testing.

Results and Conclusion: Performance metrics of KAN; 95.2% sensitivity, 97.6% specificity, 94.1% precision, 96.9% accuracy (Acc), 0.9466 F1 score (F1) and 0. 9251 Matthews Correlation Coefficient (MCC), while the CNN model was found 92.5%, 96.4%, 91.2%, 95.3%, 0.9188 and 0.8858 for the same criteria, indicating that KAN outperformed. This comparison emphasizes that KAN has the potential to be a more effective model for pneumonia detection in chest CT images.

References

Shamshiri S, Liu H, Sohn I. Adversarial robust image processing in medical digital twin. Information Fusion 2025; 115: 102728. DOI: https://doi.org/10.1016/j.inffus.2024.102728

Etli MU, Başarslan MS, Varol E, Sarıkaya H, Çakıcı YE, Öndüç GG, Bal F, Kayalar AE, Aykılıç Ö. Evaluating Deep Learning Techniques for Detecting Aneurysmal Subarachnoid Hemorrhage: A Comparative Analysis of Convolutional Neural Network and Transfer Learning Models. World Neurosurgery 2024. DOI: https://doi.org/10.1016/j.wneu.2024.04.168

Sarkar O, Islam MR, Syfullah MK, Islam MT, Ahamed MF, Ahsan M, Haider J. Multi-scale cnn: An explainable ai-integrated unique deep learning framework for lung-affected disease classification. Technologies 2023; 11(5): 134. DOI: https://doi.org/10.3390/technologies11050134

Özdemir Z, Keleş HY. COVID-19 detection in chest X-ray images with deep learning. In 2021 29th Signal Processing and Communications Applications Conference (SIU) 2021; pp. 1-4. IEEE. DOI: https://doi.org/10.1109/SIU53274.2021.9478028

Pan XL, Hua B, Tong K, Li X, Luo JL, Yang H, Ding JR. EL-CNN: An enhanced lightweight classification method for colorectal cancer histopathological images. Biomedical Signal Processing and Control 2025; 100: 106933. DOI: https://doi.org/10.1016/j.bspc.2024.106933

Xu Z, Ren H, Zhou W, Liu Z. ISANET: Non-small cell lung cancer classification and detection based on CNN and attention mechanism. Biomedical Signal Processing and Control 2022; 77: 103773. DOI: https://doi.org/10.1016/j.bspc.2022.103773

LeCun Y, Bengio Y, Hinton G. Deep learning. Nature, 2015; 521(7553): 436-444. DOI: https://doi.org/10.1038/nature14539

Sprecher, D. (1965). On the structure of continuous functions of several variables. Transactions of the American Mathematical Society, 115(2), 340-355. DOI: https://doi.org/10.1090/S0002-9947-1965-0210852-X

Hecht-Nielsen R. Theory of the backpropagation neural network. In Neural Networks for Perception 1992; pp. 65-93. DOI: https://doi.org/10.1016/B978-0-12-741252-8.50010-8

Kermany D; Zhang K, Goldbaum M. Labeled Optical Coherence Tomography (OCT) and Chest X-Ray Images for Classification. Mendeley Data 2018; V2.

Patel SB, Goh V, FitzGerald JF, Antoniades CA. 2D and 3D Deep Learning Models for MRI-based Parkinson's Disease Classification: A Comparative Analysis of Convolutional Kolmogorov-Arnold Networks, Convolutional Neural Networks, and Graph Convolutional Networks. arXiv preprint 2024; arXiv: 2407.17380.

Herbozo Contreras LF, Cui J, Yu L, Huang Z, Nikpour A, Kavehei O. KAN-EEG: Towards Replacing Backbone-MLP for an Effective Seizure Detection System. medRxiv 2024; 2024-06. DOI: https://doi.org/10.1101/2024.06.05.24308471

Bresson R, Nikolentzos G, Panagopoulos G, Chatzianastasis M, Pang J, Vazirgiannis M. Kagnns: Kolmogorov-arnold networks meet graph learning. arXiv preprint 2024; arXiv: 2406.18380.

Wang J, Cai P, Wang Z, Zhang H, Huang J. CEST-KAN: Kolmogorov-Arnold Networks for CEST MRI Data Analysis. arXiv preprint 2024; arXiv: 2406.16026.

Liu Z, Wang Y, Vaidya S, Ruehle F, Halverson J, Soljačić M, Hou TY, Tegmark M. KAN: Kolmogorov-arnold networks. arXiv preprint 2024; arXiv: 2404.19756.

Rohmah LN, Bustamam A. Improved classification of coronavirus disease (COVID-19) based on combination of texture features using CT scan and X-ray images. 2020 3rd International Conference on Information and Communications Technology (ICOIACT) 2020; 105-109. DOI: https://doi.org/10.1109/ICOIACT50329.2020.9332123

Wang S, Kang B, Ma J, Zeng X, Xiao M, Guo J, et al. A deep learning algorithm using CT images to screen for CoronaVirus Disease (COVID-19). European Radiology 2021; 31(8): 6096-6104. DOI: https://doi.org/10.1007/s00330-021-07715-1

Başarslan MS, Argun ID. Prediction of potential bank customers: application on data mining. In Artificial Intelligence and Applied Mathematics in Engineering Problems: Proceedings of the International Conference on Artificial Intelligence and Applied Mathematics in Engineering. Springer International Publishing 2020; pp. 96-106. DOI: https://doi.org/10.1007/978-3-030-36178-5_9

Turkoglu M. COVID-19 detection system using chest CT images and multiple kernels- extreme learning machine based on deep neural network. IRBM 2021; 42(4): 207-214. DOI: https://doi.org/10.1016/j.irbm.2021.01.004