Automatic identification of tuberculosis mycobacterium

Abstract

Introduction: According to the Global TB control report of 2013, "Tuberculosis (TB) remains a major global health problem. In 2012, an estimated 8.6 million people developed TB and 1.3 million died from the disease. Two main sputum smear microscopy techniques are used for TB diagnosis: Fluorescence microscopy and conventional microscopy. Fluorescence microscopy is a more expensive diagnostic method because of the high costs of the microscopy unit and its maintenance. Therefore, conventional microscopy is more appropriate for use in developing countries. Methods: This paper presents a new method for detecting tuberculosis bacillus in conventional sputum smear microscopy. The method consists of two main steps, bacillus segmentation and post-processing. In the fi rst step, the scalar selection technique was used to select input variables for the segmentation classifi ers from four color spaces. Thirty features were used, including the subtractions of the color components of different color spaces. In the post-processing step, three fi lters were used to separate bacilli from artifact: a size fi lter, a geometric fi lter and a Rule-based fi lter that uses the components of the RGB color space. Results: In bacillus identifi cation, an overall sensitivity of 96.80% and an error rate of 3.38% were obtained. An image database with 120-sputum-smear microscopy slices of 12 patients with objects marked as bacillus, agglomerated bacillus and artifact was generated and is now available online. Conclusions: The best results were obtained with a support vector machine in bacillus segmentation associated with the application of the three post-processing fi lters.

Applications of artificial neural networks in microorganism image analysis: a comprehensive review from conventional multilayer perceptron to popular convolutional neural network and potential visual transformer

“…Nevertheless, it is time-consuming. Therefore, in Costa Filho et al (2015), a novel method based on image processing techniques is proposed to assist the diagnosis. It contains three steps: image acquisition, segmentation, and post-processing.…”

A New Artificial Intelligence-Based Method for Identifying Mycobacterium Tuberculosis in Ziehl–Neelsen Stain on Tissue

“…Several other studies proposing methods of automated detection of AFB on ZN stains evaluated smears. Other than delCarpio et al, and Law et al (who evaluated scans of slides containing the whole section present on the slide whole slide images (WSIs)) [ 4 , 5 ], all the other studies evaluated images captured with cameras (small parts of slides) [ 6 , 7 , 8 , 9 , 10 , 11 , 12 , 13 , 14 ]. The specificity and sensibility varied from study to study as shown in Table 1 .…”

Automatic Bacillus Detection in Light Field Microscopy Images Using Convolutional Neural Networks and Mosaic Imaging Approach

“…In recent years, in the literature, methods have been published to automate the diagnosis of TB. These process a sputum smear microscopy image using a variety of computational techniques: digital image processing [2] and [3]), traditional machine learning algorithms [4] and [5], and shallow neural networks and deep neural networks (such as the convolutional neural networks) [6], [7] and [8].…”