@article{XING2025, 
author = {Guangxin XING and Jingjing FAN and Yelong ZHENG and Meirong ZHAO},
title = {Multi-scale input mirror network for tuberculosis detection in CXR image},
year = {2025},
journal = {Journal of Measurement Science and Instrumentation},
volume = {16},
number = {1},
pages = {1-10},
keywords = {computer-aided diagnosis (CAD), medical image classification, deep learning, feature symmetry, mirror loss},
url = {https://www.sciopen.com/article/10.62756/jmsi.1674-8042.2025001},
doi = {10.62756/jmsi.1674-8042.2025001},
abstract = {Computer-aided diagnosis (CAD) can detect tuberculosis (TB) cases, providing radiologists with more accurate and efficient diagnostic solutions. Various noise information in TB chest X-ray (CXR) images is a major challenge in this classification task. This study aims to propose a model with high performance in TB CXR image detection named multi-scale input mirror network(MIM-Net) based on CXR image symmetry, which consists of a multi-scale input feature extraction network and mirror loss. The multi-scale image input can enhance feature extraction, while the mirror loss can improve the network performance through self-supervision. We used a publicly available TB CXR image classification dataset to evaluate our proposed method via 5-fold cross-validation, with accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and area under curve (AUC) of 99.67%, 100%, 99.60%, 99.80%, 100%, and 0.9999, respectively. Compared to other models, MIM-Net performed best in all metrics. Therefore, the proposed MIM-Net can effectively help the network learn more features and can be used to detect TB in CXR images, thus assisting doctors in diagnosing.}
}