Artificial Intelligence in Diagnosing Tuberculosis: A Review

Abstract

Tuberculosis (TB) is among top ten causes of deaths worldwide. It is the single most cause of deaths by an infectious disease and is ranked 2nd only after the HIV/AIDS. In third world countries, the diagnosis of TB is done through conventional methods. To diagnostic results are obtain from conventional methods such as blood, culture, sputum and biopsies. They are tedious as well as take long time like 1-2 weeks or maybe evenmore. Therefore, to lower the detection time and raise the accuracy of diagnosis several researches have been carried out. In the past fifty years, due to the advanced and sophisticated technologies, in medical as well as computer science fields, have paved a way to utilize the essence of both the areas. In Artificial Intelligence (AI) various Machine Learning (ML) algorithms have furthered the interests in Computer-aided Detection (CADe) and Diagnosis (CADx) methods. These methodologies assist in medical field for diagnosing the diseases through clinical signs and symptoms as well as radiological images of the patient. They have been implemented for the diagnosis of TB. Advances in AI algorithms, has unveiled great promises in identifying the presence and absence of TB. As of late, many attempts have been made to formulate the strategies to increase the classification accuracy of TB diagnosis using the AI and machine learning approach. This review paper, aims to describes the diverse AI approaches employed in the diagnosis of TB.

Inteligencia artificial e innovación para optimizar el proceso de diagnóstico de la tuberculosis

“…El campo de la inteligencia artificial ha progresado hacia una nueva era de aprendizaje profundo. En particular, las redes neuronales convolucionales (convolutional neural networks) son una clase de aprendizaje profundo que utiliza una red neuronal artificial para analizar imágenes visuales (18) . Las redes neuronales convolucionales se han convertido en la técnica preferida para analizar imágenes médicas.…”

Ensemble deep learning for tuberculosis detection

“…In this paper, we employed three CNN architectures, InceptionV3, VGG16 and a custom-built architecture. CNN was selected due to its ability to extract and learn meaningful features on its own [8]. Further readings on InceptionV3 and VGG16 can be found in [22] and [23] respectively.…”

“…For century, challenges for radiologists to avoid confused and misdiagnose tuberculosis to other lung related diseases because they mimic each other [7]. A semi-automated system to effectively classify pulmonary nodules with low false positive rate is deemed necessary to assist radiologist to screen the chest radiograph images [8].…”

Tuberculosis detection using deep learning and contrastenhanced canny edge detected X-Ray images

“…The lower level features help generates the higher-level features. The ability of deep learning to identify high-level features is shown to produce better classification results [7]. Numerous works using deep learning for TB detection on chest x-rays can be found in [8][9][10][11][12][13][14][15][16][17][18][19].…”