Machine Vision Approach for Diagnosing Tuberculosis (TB) Based on Computerized Tomography (CT) Scan Images

Abstract

Tuberculosis is curable, still the world’s second inflectional murderous disease, and ranked 13th (in 2020) by the World Health Organization on the list of leading death causes. One of the reasons for its fatality is the unavailability of modern technology and human experts for early detection. This study represents a precise and reliable machine vision-based approach for Tuberculosis detection in the lung through Symmetry CT scan images. TB spreads irregularly, which means it might not affect both lungs equally, and it might affect only some part of the lung. That’s why regions of interest (ROI’s) from TB infected and normal CT scan images of lungs were selected after pre-processing i.e., selection/cropping, grayscale image conversion, and filtration, Statistical texture features were extracted, and 30 optimized features using F (Fisher) + PA (probability of error + average correlation) + MI (mutual information) were selected for final optimization and only 6 most optimized features were selected. Several supervised learning classifiers were used to classify between normal and infected TB images. Artificial Neural Network (ANN: n class) based classifier Multi-Layer Perceptron (MLP) showed comparatively better and probably best accuracy of 99% with execution time of less than a second, followed by Random Forest 98.83%, J48 98.67%, Log it Boost 98%, AdaBoostM1 97.16% and Bayes Net 96.83%.

Fourier Synchrosqueezing Transform-ICA-EMD Framework Based EOG-Biometric Sustainable and Continuous Authentication via Voluntary Eye Blinking Activities

“…Hence, the other statistical performance metrics are described, including specificity (SPEC), sensitivity (SENS), precision (PREC), and F-score in this respect [ 48 ]. The F-score is the coherent coefficient of the precision and sensitivity [ 59 ]. The notations are below: …”

Exploring Machine Learning Classifiers for Breast Cancer Classification

“…Using symmetrical CT scan data, several ML classifiers differentiate between images of healthy and tuberculosis-infected lungs. The MLP classifier outperforms other classifiers with 98.83% accuracy and fast execution time [26].…”

“…The performance evaluation of the proposed classifiers was measured using the following metrics. These parameters were also used in the previous study [26].…”

YOLO and residual network for colorectal cancer cell detection and counting

“…The method involved the selection of ROI from TB-infected and normal lung images, followed by pre-processing and extracting statistical texture features. Supervised learning classifiers were employed, among which the MLP-based classifier, also known as the ANN, achieved 99 % accuracy in less than 1 s [ 38 ].…”