Tuberculosis (TB) is a serious infectious disease that remains a global health challenge. While chest X-rays (CXRs) are widely used for TB detection, manual interpretation can be subjective and time-consuming. Automated classification of CXRs into TB and non-TB cases can significantly support healthcare professionals in timely and accurate diagnosis. This paper introduces a hybrid deep learning approach for classifying CXR images. The solution is based on the CoAtNet framework, which combines the strengths of Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs). The model is pre-trained on the large-scale ImageNet dataset to ensure robust generalization across diverse images. The evaluation is conducted on the IN-CXR tuberculosis dataset from ICMR-NIRT, which contains a comprehensive collection of CXR images of both normal and abnormal categories. The hybrid model achieves a binary classification accuracy of 86.39% and an ROC-AUC score of 93.79%, outperforming tested baseline models that rely exclusively on either CNNs or ViTs when trained on this dataset. Furthermore, the integration of Local Interpretable Model-agnostic Explanations (LIME) enhances the interpretability of the model’s predictions. This combination of reliable performance and transparent, interpretable results strengthens the model’s role in AI-driven medical imaging research. Code will be made available upon request.

This research explores the detrimental effects of Rician and speckle noise in medical imaging, particularly within MRI and radiographic modalities. Such noise can significantly obscure critical details, potentially leading to misdiagnoses and inaccurate measurements. Rician noise candidly dangles on the signal strength. Removing this noise affects the origial information in image that makes this noise removal perplexing. On other hand speckle noise is visualised like granular clog in ultrasound imageries. It creates ambiguous details and edges in the images. To address this challenge, the study introduces a novel hybrid method implemented in Java. The method employs a frequency-based decomposition approach for speckle noise and separates images into magnitude and phase components for Rician noise. This allows for targeted filtering, utilizing customized versions of median and Gaussian filters, to effectively remove noise while preserving crucial image features. The proposed method was rigorously assessed using 200 contaminated brain and lung MRIs and radiographs, demonstrating superior performance compared to traditional filters based on crucial system of measurement like Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), and Mean Squared Error (MSE). This research presents a promising solution for enhancing the quality and reliability of medical images, potentially leading to improved diagnostic accuracy and patient outcomes.