TY - GEN
T1 - Tuberculosis Detection Comparison by Using Preprocessed and Non-preprocessed Chest X-Ray Images
AU - Jiménez-Fernández, Rubén Saúl
AU - Ramírez-Ángel, Axel Yahir
AU - Orjuela-Cañón, Alvaro David
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.
PY - 2025
Y1 - 2025
N2 - Tuberculosis (TB) remains a significant global health challenge, with a high rate of infection and mortality. Chest X-ray (CXR) imaging is a common diagnostic tool for TB, but its effectiveness depends heavily on the expertise of the radiologist. This study explores the impact of image preprocessing on the performance of deep learning models in TB detection from CXR images, evaluating whether the computational cost of preprocessing is justified compared to using non-preprocessed images. A combination of all these preprocessing techniques was applied on the dataset, including Contrast Limited Adaptive Histogram Equalization (CLAHE), wavelet transform, gamma correction, and histogram equalization, as provided by the dataset itself. The results indicate that preprocessing enhanced the accuracy of the ResNet50 model significantly, achieving 99% accuracy compared to 94% on raw images. However, for MobileNet and the custom model, the improvement was marginal, suggesting that these models can perform adequately without extensive preprocessing. This finding highlights the potential for implementing deep learning models in low-resource settings where computational capabilities are limited. The study underscores the importance of selecting appropriate preprocessing techniques and neural network architectures to optimize TB detection accuracy in diverse clinical environments.
AB - Tuberculosis (TB) remains a significant global health challenge, with a high rate of infection and mortality. Chest X-ray (CXR) imaging is a common diagnostic tool for TB, but its effectiveness depends heavily on the expertise of the radiologist. This study explores the impact of image preprocessing on the performance of deep learning models in TB detection from CXR images, evaluating whether the computational cost of preprocessing is justified compared to using non-preprocessed images. A combination of all these preprocessing techniques was applied on the dataset, including Contrast Limited Adaptive Histogram Equalization (CLAHE), wavelet transform, gamma correction, and histogram equalization, as provided by the dataset itself. The results indicate that preprocessing enhanced the accuracy of the ResNet50 model significantly, achieving 99% accuracy compared to 94% on raw images. However, for MobileNet and the custom model, the improvement was marginal, suggesting that these models can perform adequately without extensive preprocessing. This finding highlights the potential for implementing deep learning models in low-resource settings where computational capabilities are limited. The study underscores the importance of selecting appropriate preprocessing techniques and neural network architectures to optimize TB detection accuracy in diverse clinical environments.
UR - http://www.scopus.com/inward/record.url?scp=85215930112&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85215930112&partnerID=8YFLogxK
U2 - 10.1007/978-3-031-82123-3_5
DO - 10.1007/978-3-031-82123-3_5
M3 - Conference contribution
AN - SCOPUS:85215930112
SN - 9783031821226
T3 - IFMBE Proceedings
SP - 53
EP - 64
BT - 47th Mexican Conference on Biomedical Engineering - Proceedings of CNIB 2024 - Signal Processing And Bioinformatics Congreso Nacional de Ingeniería Biomédica CNIB Hermosillo
A2 - Flores Cuautle, José de Jesús Agustín
A2 - Benítez-Mata, Balam
A2 - Reyes-Lagos, José Javier
A2 - Hernandez Acosta, Humiko Yahaira
A2 - Ames Lastra, Gerardo
A2 - Zuñiga-Aguilar, Esmeralda
A2 - Del Hierro-Gutierrez, Edgar
A2 - Salido-Ruiz, Ricardo Antonio
PB - Springer Science and Business Media Deutschland GmbH
T2 - 47th Mexican Conference on Biomedical Engineering, CNIB 2024
Y2 - 7 November 2024 through 9 November 2024
ER -