Improved sarcoidosis disease detection using deep learning and histogram of oriented gradients with quantum SVM
Ayalew, Aleka Melese; Degife, Worku Abebe; Asnake, Nigus Wereta; Nibret, Eyerusalem Alebachew; Bezabh, Yohannes Agegnehu; Abuhayi, Biniyam Mulugeta; Oussalah, Mourad (2025-02-19)
Springer
19.02.2025
Ayalew, A.M., Degife, W.A., Asnake, N.W. et al. Improved sarcoidosis disease detection using deep learning and histogram of oriented gradients with quantum SVM. Discov Appl Sci 7, 154 (2025). https://doi.org/10.1007/s42452-025-06504-5
https://creativecommons.org/licenses/by-nc-nd/4.0/
© The Author(s) 2025. This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
https://creativecommons.org/licenses/by-nc-nd/4.0/
© The Author(s) 2025. This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
https://creativecommons.org/licenses/by-nc-nd/4.0/
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:oulu-202504172752
https://urn.fi/URN:NBN:fi:oulu-202504172752
Tiivistelmä
Abstract
Sarcoidosis is a multisystem granulomatous disease with an unknown cause distinguished by the development of noncaseating granulomas in implicated organs. In patients with sarcoidosis, ventricular arrhythmias, and atrioventricular blocks can be deadly and result in sudden death. Clinically cardiac sarcoidosis affects five percent of sarcoidosis patients. Autopsy reports and imaging investigations, however, have revealed a higher frequency of cardiac involvement. Early detection of sarcoidosis through precise diagnosis, especially in cases with no evident symptoms, may reduce the patient’s mortality rate. This condition is primarily diagnosed via chest X-ray images. As a result, this research proposes a novel detection and classification approach for rapid diagnosis of sarcoidosis utilizing patient chest X-ray data. To diagnose sarcoidosis from chest X-ray images, we used state-of-the-art models like Inception and Residual Network-50, a handcrafted deep learning method, and a Quantum Support vector machine classifier. This study offers a convolutional neural network and histogram of oriented gradients method to aid medical experts in identifying sarcoidosis disease. The anisotropic diffusion filtering approach was used to improve image edge preservation, reduce noise, and augmentation to enhance the image. Gradient-weighted Class Activation Mapping was employed to illustrate the important activation areas that influenced the model’s decision. After evaluating the convolutional neural network model, it achieved 99.7% training accuracy and 98% test accuracy, while the histogram of oriented gradients achieved 100% training accuracy and 98% test accuracy.
Sarcoidosis is a multisystem granulomatous disease with an unknown cause distinguished by the development of noncaseating granulomas in implicated organs. In patients with sarcoidosis, ventricular arrhythmias, and atrioventricular blocks can be deadly and result in sudden death. Clinically cardiac sarcoidosis affects five percent of sarcoidosis patients. Autopsy reports and imaging investigations, however, have revealed a higher frequency of cardiac involvement. Early detection of sarcoidosis through precise diagnosis, especially in cases with no evident symptoms, may reduce the patient’s mortality rate. This condition is primarily diagnosed via chest X-ray images. As a result, this research proposes a novel detection and classification approach for rapid diagnosis of sarcoidosis utilizing patient chest X-ray data. To diagnose sarcoidosis from chest X-ray images, we used state-of-the-art models like Inception and Residual Network-50, a handcrafted deep learning method, and a Quantum Support vector machine classifier. This study offers a convolutional neural network and histogram of oriented gradients method to aid medical experts in identifying sarcoidosis disease. The anisotropic diffusion filtering approach was used to improve image edge preservation, reduce noise, and augmentation to enhance the image. Gradient-weighted Class Activation Mapping was employed to illustrate the important activation areas that influenced the model’s decision. After evaluating the convolutional neural network model, it achieved 99.7% training accuracy and 98% test accuracy, while the histogram of oriented gradients achieved 100% training accuracy and 98% test accuracy.
Kokoelmat
- Avoin saatavuus [37920]
Ellei muuten mainita, aineiston lisenssi on https://creativecommons.org/licenses/by-nc-nd/4.0/