Improving tuberculosis diagnostics using deep learning and mobile health technologies among resource-poor communities in Perú

Alcântara, Maria Regina; Cao, Yu; Liu, Chang; Liu, Benyuan; Brunette, Maria; Zhang, Ning; Sun, Tanfeng; Zhang, Peifeng; Chen, Qilei; Liu, Ying; Albarracín, César Morocho; Peinado, Jesús; Garavito, Epifanio Sánchez; Lecca, Leonid; Curioso, Walter H.

doi:10.1016/j.smhl.2017.04.003

Cited by 51 publications

(24 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It achieved 89.6% accuracy for binary classification of TB and 62.07% accuracy for multi-class classification of different TB manifestations. However, classes in dataset are uneven as Lymphadenopathy has 202 images whereas Infiltration comprises of 2252 images [28]. In [29], Melendez et al explored three techniques including SVM, multi-instance learning (MIL) and active learning (AL) for TB diagnosis.…”

Section: B Deep Learning Based Tb Diagnosismentioning

confidence: 99%

Uncertainty Assisted Robust Tuberculosis Identification With Bayesian Convolutional Neural Networks

et al. 2020

View full text Add to dashboard Cite

Tuberculosis (TB) is an infectious disease that can lead towards death if left untreated. TB detection involves extraction of complex TB manifestation features such as lung cavity, air space consolidation, endobronchial spread, and pleural effusions from chest x-rays (CXRs). Deep learning based approach named convolutional neural network (CNN) has the ability to learn complex features from CXR images. The main problem is that CNN does not consider uncertainty to classify CXRs using softmax layer. It lacks in presenting the true probability of CXRs by differentiating confusing cases during TB detection. This paper presents the solution for TB identification by using Bayesian-based convolutional neural network (B-CNN). It deals with the uncertain cases that have low discernibility among the TB and non-TB manifested CXRs. The proposed TB identification methodology based on B-CNN is evaluated on two TB benchmark datasets, i.e., Montgomery and Shenzhen. For training and testing of proposed scheme we have utilized Google Colab platform which provides NVidia Tesla K80 with 12 GB of VRAM, single core of 2.3 GHz Xeon Processor, 12 GB RAM and 320 GB of disk. B-CNN achieves 96.42% and 86.46% accuracy on both dataset, respectively as compared to the state-of-the-art machine learning and CNN approaches. Moreover, B-CNN validates its results by filtering the CXRs as confusion cases where the variance of B-CNN predicted outputs is more than a certain threshold. Results prove the supremacy of B-CNN for the identification of TB and non-TB sample CXRs as compared to counterparts in terms of accuracy, variance in the predicted probabilities and model uncertainty. INDEX TERMS Tuberculosis identification, computer-aided diagnostics, medical image analysis, Bayesian convolutional neural networks, model uncertainty.

show abstract

Section: B Deep Learning Based Tb Diagnosismentioning

confidence: 99%

Uncertainty Assisted Robust Tuberculosis Identification With Bayesian Convolutional Neural Networks

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Alcantara et al, [111] in their research implemented GoogLeNet model from the cafe, pre-trained on ImageNet for the classification of the CXRs. Their dataset consisted of 4701images, which were used for finetuning.…”

Section: G Convolutional Neural Networkmentioning

confidence: 99%

Artificial Intelligence in Diagnosing Tuberculosis: A Review

Meraj¹,

Yaakob²,

Azman³

et al. 2019

Int. J. Adv. Sci. Eng. Inf. Technol.

View full text Add to dashboard Cite

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.

show abstract

“…Smart healthcare applications on tuberculosis include identification of drug resistance-associated mutations [131], detection of tuberculosis [132][133][134][135], detection of multidrug resistance tuberculosis [136], prediction of treatment failure [137], identification between tuberculosis and human immunodeficiency virus (HIV) [138], predicting recent transmission of tuberculosis [139] and detection of smear-negative pulmonary tuberculosis [140]. These are summarized in Table 5.…”

Section: Alzheimer's Disease and Other Forms Of Dementiamentioning

confidence: 99%

“…There are 12 types of algorithms in seven applications in tuberculosis and the sample sizes of datasets are limited. The performance of two of the works [133,139] can be improved in the future. Other algorithms can be applied to obtain a favorable performance (>90%).…”

Section: Alzheimer's Disease and Other Forms Of Dementiamentioning

confidence: 99%

Disease Diagnosis in Smart Healthcare: Innovation, Technologies and Applications

et al. 2017

View full text Add to dashboard Cite

Abstract:To promote sustainable development, the smart city implies a global vision that merges artificial intelligence, big data, decision making, information and communication technology (ICT), and the internet-of-things (IoT). The ageing issue is an aspect that researchers, companies and government should devote efforts in developing smart healthcare innovative technology and applications. In this paper, the topic of disease diagnosis in smart healthcare is reviewed. Typical emerging optimization algorithms and machine learning algorithms are summarized. Evolutionary optimization, stochastic optimization and combinatorial optimization are covered. Owning to the fact that there are plenty of applications in healthcare, four applications in the field of diseases diagnosis (which also list in the top 10 causes of global death in 2015), namely cardiovascular diseases, diabetes mellitus, Alzheimer's disease and other forms of dementia, and tuberculosis, are considered. In addition, challenges in the deployment of disease diagnosis in healthcare have been discussed.

show abstract

Improving tuberculosis diagnostics using deep learning and mobile health technologies among resource-poor communities in Perú

Cited by 51 publications

References 37 publications

Uncertainty Assisted Robust Tuberculosis Identification With Bayesian Convolutional Neural Networks

Uncertainty Assisted Robust Tuberculosis Identification With Bayesian Convolutional Neural Networks

Artificial Intelligence in Diagnosing Tuberculosis: A Review

Disease Diagnosis in Smart Healthcare: Innovation, Technologies and Applications

Contact Info

Product

Resources

About