Ziehl–Neelsen sputum smear microscopy image database: a resource to facilitate automated bacilli detection for tuberculosis diagnosis

Abstract

Ziehl-Neelsen stained microscopy is a crucial bacteriological test for tuberculosis detection, but its sensitivity is poor. According to the World Health Organization (WHO) recommendation, 300 viewfields should be analyzed to augment sensitivity, but only a few viewfields are examined due to patient load. Therefore, tuberculosis diagnosis through automated capture of the focused image (autofocusing), stitching of viewfields to form mosaics (autostitching), and automatic bacilli segmentation (grading) can significantly improve the sensitivity. However, the lack of unified datasets impedes the development of robust algorithms in these three domains. Therefore, the Ziehl-Neelsen sputum smear microscopy image database (ZNSM iDB) has been developed, and is freely available. This database contains seven categories of diverse datasets acquired from three different bright-field microscopes. Datasets related to autofocusing, autostitching, and manually segmenting bacilli can be used for developing algorithms, whereas the other four datasets are provided to streamline the sensitivity and specificity. All three categories of datasets were validated using different automated algorithms. As images available in this database have distinctive presentations with high noise and artifacts, this referral resource can also be used for the validation of robust detection algorithms. The ZNSM-iDB also assists for the development of methods in automated microscopy.

Automated Tuberculosis Detection and Analysis Using CXR’s Images

“…Our proposed system would focus on tuberculosis and had shown reliability of use with accuracy of 92% which is greater than other algorithms designed [1]. Another automated system was designed named TBDx in which the sensitivity of 62% and specificity of 100% was obtained [4]. However for chest radiographs sensitivity is more important as compared to specificity as we are not counted AFB's in chest radiographs but detecting the abnormalities.…”

Towards Automated Tuberculosis detection using Deep Learning

“…This work has been possible by the release of annotated smear sputum slides made available by [7] and recent advances in Deep Learning [5,4] on images. To our knowledge, this is the first proof of concept that TB detection can be automated with Deep Learning.…”

“…Like any other Machine Learning solution, we need a dataset with annotations of TB bacteria in smear sputum images to train and test our method. We use dataset made available by [7] to build a prototype and evaluate our method. We describe the dataset and its usage in our work in detail in the dataset section 2.…”

“…Dataset 7 datasets of microscope view-fields made available for different TB diagnostic tasks by[7] referred to as dataset 1 through 7 respectively. The datasets were…”

Establishment of hybridized focus measure functions as a universal method for autofocusing

“…A total of 31 autofocusing stacks were extracted from ZN Sputum Smear Microscopy Image Database. 20 These stacks were prepared from 10 different ZN-stained sputum smear slides of tuberculosis patient using three different microscopes. Each stack contains 20 images captured at different focus points over the same view field [ Fig.…”