Table 1.

Summary of automated TB detection schemes employed to examine X-ray images.

Reference	Developed procedure
Rajaraman and Antani [18]	A customized DL system is proposed to examine the Shenzhen CXR pictures, and the proposed system provided an accuracy of 83.7%. However, this work confirms that implementing a customized DL approach is complex and time-consuming
Hwa et al. [19]	Examination of TB from X-ray using ensemble DL system and canny-edge detection is implemented and achieved better values of accuracy (89.77%), sensitivity (90.91%), and specificity (88.64%). However, the implementation of canny-edge detection along with the ensemble DL scheme needs a larger image preprocessing task, and it will increase the detection time
Wong et al. [20]	The development of a customized DL technique called TB-Net is proposed, and this work helped to achieve better performance measures, such as accuracy (99.86%), sensitivity (100%), and specificity (99.71%). This research also proposes a customary model, which is relatively more complex than the pretrained models
Hooda et al. [21]	Seven convolutional layers and three fully connected layer-based customized DL method are proposed for TB detection and achieved a classification accuracy of 94.73%
Rohilla et al. [22]	This work employed the conventional AlexNet and VGG16 methods to examine the X-ray images and attained an accuracy of >81%
Nguyen et al. [23]	X-ray diagnosis performance of pretrained DL schemes is presented, and the employed technique helped to provide better TB recognition
Afzali et al. [24]	The contour-based silhouette descriptor technique is employed to detect TB, and the selected features provided an accuracy of 92.86%
Stirenko et al. [25]	The CNN-based disease diagnosis with lossless and lossy data expansion is employed, and the proposed method offers a better TB diagnosis with X-ray pictures
Rahman et al. [14]	Implementation of combined CNN segmentation and categorization is presented to identify TB from X-ray images. This work implemented the classification task with and without segmentation and achieved a TB detection accuracy of 96.47% and 98.6%, respectively. This work also presented a detailed evaluation methodology for TB detection using various pretrained DL methods