Study on the TB and non-TB diagnosis using two-step deep learning-based binary classifier

Yoo, Seung Hoon; Geng, Hui; Chiu, Tin Lok; Yu, Siu Ki; Cho, D. C.; Heo, Jun; Choi, Min-Kook; Choi, I. H.; Cung, Cong Van; Nhung, N. V.; Min, Byung Jun

doi:10.1088/1748-0221/15/10/p10011

Cited by 6 publications

(8 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figures 2-3 illustrate the QUADAS-2 assessment results regarding the risk of bias and applicability concerns of included studies. There were 2 studies [13,71] that have a high risk of bias in terms of "patient selection." This is mainly due to incomplete information on data selection.…”

Section: Risk Of Bias Assessment Resultsmentioning

confidence: 99%

“…Various ML and DL methods have been applied in the included studies: 7/47 (15%) studies [13,14,37,40,43,63,67] focused on using ML approaches, while 34/47 (72%) studies [17][18][19][20][34][35][36]39,41,[44][45][46][47][48][49][50][51][52][53][54][55][56][58][59][60][61][62]65,66,[69][70][71][72]74] used DL approaches; 4/47 (9%) studies [38,64,68,73] used both ML and DL approaches, while 2/47 (4%) [42,57] focused on industrial-grade DL image analysis software and various deep AI models without further information on the types of AI techniques used.…”

Section: Study Resultsmentioning

confidence: 99%

“…Twenty-five of the included studies [ 14 , 17 - 19 , 34 , 36 - 38 , 47 - 49 , 52 , 53 , 56 , 59 , 62 - 66 , 68 , 70 , 72 - 74 ] reported comparison results with several other previous studies, while the remaining 22 did not. Twenty-six of 47 included studies [ 19 , 20 , 35 , 38 - 40 , 42 , 43 , 45 , 47 - 50 , 53 , 55 , 56 , 58 - 62 , 65 , 69 - 71 , 74 ] were funded or sponsored by companies, private or university research institutions, and governmental institutions, while for the remaining 21 studies no funding sources were identified. Most of the included studies focused on the development of a model or architecture as the proposed solution.…”

Section: Resultsmentioning

confidence: 99%

“…Twenty-five of the included studies [14,[17][18][19]34,[36][37][38][47][48][49]52,53,56,59,[62][63][64][65][66]68,70,[72][73][74] reported comparison results with several other previous studies, while the remaining 22 did not. Twenty-six of 47 included studies [19,20,35,[38][39][40]42,43,45,[47][48][49][50]53,55,56,[58][59][60][61][62]65,[69][70][71]74] were funded or sponsored by companies, private...…”

Section: General Characteristics Of the Included Studiesmentioning

confidence: 99%

See 3 more Smart Citations

Machine and Deep Learning for Tuberculosis Detection on Chest X-Rays: Systematic Literature Review

Hansun¹,

Argha²,

Liaw³

et al. 2023

J Med Internet Res

View full text Add to dashboard Cite

Background Tuberculosis (TB) was the leading infectious cause of mortality globally prior to COVID-19 and chest radiography has an important role in the detection, and subsequent diagnosis, of patients with this disease. The conventional experts reading has substantial within- and between-observer variability, indicating poor reliability of human readers. Substantial efforts have been made in utilizing various artificial intelligence–based algorithms to address the limitations of human reading of chest radiographs for diagnosing TB. Objective This systematic literature review (SLR) aims to assess the performance of machine learning (ML) and deep learning (DL) in the detection of TB using chest radiography (chest x-ray [CXR]). Methods In conducting and reporting the SLR, we followed the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. A total of 309 records were identified from Scopus, PubMed, and IEEE (Institute of Electrical and Electronics Engineers) databases. We independently screened, reviewed, and assessed all available records and included 47 studies that met the inclusion criteria in this SLR. We also performed the risk of bias assessment using Quality Assessment of Diagnostic Accuracy Studies version 2 (QUADAS-2) and meta-analysis of 10 included studies that provided confusion matrix results. Results Various CXR data sets have been used in the included studies, with 2 of the most popular ones being Montgomery County (n=29) and Shenzhen (n=36) data sets. DL (n=34) was more commonly used than ML (n=7) in the included studies. Most studies used human radiologist’s report as the reference standard. Support vector machine (n=5), k-nearest neighbors (n=3), and random forest (n=2) were the most popular ML approaches. Meanwhile, convolutional neural networks were the most commonly used DL techniques, with the 4 most popular applications being ResNet-50 (n=11), VGG-16 (n=8), VGG-19 (n=7), and AlexNet (n=6). Four performance metrics were popularly used, namely, accuracy (n=35), area under the curve (AUC; n=34), sensitivity (n=27), and specificity (n=23). In terms of the performance results, ML showed higher accuracy (mean ~93.71%) and sensitivity (mean ~92.55%), while on average DL models achieved better AUC (mean ~92.12%) and specificity (mean ~91.54%). Based on data from 10 studies that provided confusion matrix results, we estimated the pooled sensitivity and specificity of ML and DL methods to be 0.9857 (95% CI 0.9477-1.00) and 0.9805 (95% CI 0.9255-1.00), respectively. From the risk of bias assessment, 17 studies were regarded as having unclear risks for the reference standard aspect and 6 studies were regarded as having unclear risks for the flow and timing aspect. Only 2 included studies had built applications based on the proposed solutions. Conclusions Findings from this SLR confirm the high potential of both ML and DL for TB detection using CXR. Future studies need to pay a close attention on 2 aspects of risk of bias, namely, the reference standard and the flow and timing aspects. Trial Registration PROSPERO CRD42021277155; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=277155

show abstract

Section: Risk Of Bias Assessment Resultsmentioning

confidence: 99%

Section: Study Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: General Characteristics Of the Included Studiesmentioning

confidence: 99%

See 2 more Smart Citations

Machine and Deep Learning for Tuberculosis Detection on Chest X-Rays: Systematic Literature Review

Hansun¹,

Argha²,

Liaw³

et al. 2023

J Med Internet Res

View full text Add to dashboard Cite

show abstract

“…ML uses an algorithm that does not depend on human decisions to analyze dominant variables [30]. While DL models the brain architecture that can learn more precise data representations as the data used increases [31]. Many studies have found algorithms that strive to improve the accuracy of TB detection results even with all their limitations.…”

mentioning

confidence: 99%

Database System for Storing Tuberculosis Sputum Sample Images as an AI Training Dataset

et al. 2022

View full text Add to dashboard Cite

The high prevalence of Tuberculosis (TB) in Indonesia puts Indonesia in the second-highest national TB prevalence in the world after India. This high prevalence can cause a failure to deliver medical treatments to TB patients, which is exacerbated by the disproportionate distribution of doctors in Indonesia. To address this issue, an AI system is necessary to help doctors in screening a large number of patients in a short time. However, to develop a robust AI for this purpose, we need a large dataset. This study aims to develop a database system for storing TB sputum sample images, which can be used as the dataset to train an AI for TB detection. The developed system can help doctors and health workers to manage the images during their daily job. After a period of time, the stored images can be utilized as the dataset to train AI.

show abstract

A decade’s overview of artificial intelligence in diagnosing: a scoping review

Balakrishnan,

Rustamov,

Ramanathan

et al. 2024

Int. J. Mach. Learn. & Cyber.

View full text Add to dashboard Cite

Study on the TB and non-TB diagnosis using two-step deep learning-based binary classifier

Cited by 6 publications

References 26 publications

Machine and Deep Learning for Tuberculosis Detection on Chest X-Rays: Systematic Literature Review

Machine and Deep Learning for Tuberculosis Detection on Chest X-Rays: Systematic Literature Review

Database System for Storing Tuberculosis Sputum Sample Images as an AI Training Dataset

A decade’s overview of artificial intelligence in diagnosing: a scoping review

Contact Info

Product

Resources

About