Efficient and Accurate Tuberculosis Diagnosis: Attention Residual U-Net and Vision Transformer Based Detection Framework

TL;DR

This paper introduces a two-stage deep learning framework combining an attention residual U-Net for segmentation and a Vision Transformer for classification to improve tuberculosis bacilli detection in microscopic images, enhancing accuracy and automation.

Contribution

It presents a novel two-stage deep learning approach with an attention residual U-Net and a customized Vision Transformer for TB detection, outperforming existing methods.

Findings

Improved segmentation accuracy over existing models

Higher classification precision with TBViT

Enhanced automation in TB diagnosis workflow

Abstract

Tuberculosis (TB), an infectious disease caused by Mycobacterium tuberculosis, continues to be a major global health threat despite being preventable and curable. This burden is particularly high in low and middle income countries. Microscopy remains essential for diagnosing TB by enabling direct visualization of Mycobacterium tuberculosis in sputum smear samples, offering a cost effective approach for early detection and effective treatment. Given the labour-intensive nature of microscopy, automating the detection of bacilli in microscopic images is crucial to improve both the expediency and reliability of TB diagnosis. The current methodologies for detecting tuberculosis bacilli in bright field microscopic sputum smear images are hindered by limited automation capabilities, inconsistent segmentation quality, and constrained classification precision. This paper proposes a twostage deep learning methodology for tuberculosis bacilli detection, comprising bacilli segmentation followed by classification. In the initial phase, an advanced U-Net model employing attention blocks and residual connections is proposed to segment microscopic sputum smear images, enabling the extraction of Regions of Interest (ROIs). The extracted ROIs are then classified using a Vision Transformer, which we specifically customized as TBViT to enhance the precise detection of bacilli within the images. For the experiments, a newly developed dataset of microscopic sputum smear images derived from Ziehl-Neelsen-stained slides is used in conjunction with existing public datasets. The qualitative and quantitative evaluation of the experiments using various metrics demonstrates that the proposed model achieves significantly improved segmentation performance, higher classification accuracy, and a greater level of automation, surpassing existing methods.