Optimising computer aided detection to identify intra-thoracic tuberculosis on chest x-ray in South African children.
Diagnostic tools for paediatric tuberculosis remain limited, with heavy reliance on clinical algorithms which include chest x-ray. Computer aided detection (CAD) for tuberculosis on chest x-ray has shown promise in adults. We aimed to measure and optimise the performance of an adult CAD system, CAD4...
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2023-01-01
|
| Series: | PLOS Global Public Health |
| Online Access: | https://journals.plos.org/globalpublichealth/article/file?id=10.1371/journal.pgph.0001799&type=printable |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850159891830800384 |
|---|---|
| author | Megan Palmer James A Seddon Marieke M van der Zalm Anneke C Hesseling Pierre Goussard H Simon Schaaf Julie Morrison Bram van Ginneken Jaime Melendez Elisabetta Walters Keelin Murphy |
| author_facet | Megan Palmer James A Seddon Marieke M van der Zalm Anneke C Hesseling Pierre Goussard H Simon Schaaf Julie Morrison Bram van Ginneken Jaime Melendez Elisabetta Walters Keelin Murphy |
| author_sort | Megan Palmer |
| collection | DOAJ |
| description | Diagnostic tools for paediatric tuberculosis remain limited, with heavy reliance on clinical algorithms which include chest x-ray. Computer aided detection (CAD) for tuberculosis on chest x-ray has shown promise in adults. We aimed to measure and optimise the performance of an adult CAD system, CAD4TB, to identify tuberculosis on chest x-rays from children with presumptive tuberculosis. Chest x-rays from 620 children <13 years enrolled in a prospective observational diagnostic study in South Africa, were evaluated. All chest x-rays were read by a panel of expert readers who attributed each with a radiological reference of either 'tuberculosis' or 'not tuberculosis'. Of the 525 chest x-rays included in this analysis, 80 (40 with a reference of 'tuberculosis' and 40 with 'not tuberculosis') were allocated to an independent test set. The remainder made up the training set. The performance of CAD4TB to identify 'tuberculosis' versus 'not tuberculosis' on chest x-ray against the radiological reference read was calculated. The CAD4TB software was then fine-tuned using the paediatric training set. We compared the performance of the fine-tuned model to the original model. Our findings were that the area under the receiver operating characteristic curve (AUC) of the original CAD4TB model, prior to fine-tuning, was 0.58. After fine-tuning there was an improvement in the AUC to 0.72 (p = 0.0016). In this first-ever description of the use of CAD to identify tuberculosis on chest x-ray in children, we demonstrate a significant improvement in the performance of CAD4TB after fine-tuning with a set of well-characterised paediatric chest x-rays. CAD has the potential to be a useful additional diagnostic tool for paediatric tuberculosis. We recommend replicating the methods we describe using a larger chest x-ray dataset from a more diverse population and evaluating the potential role of CAD to replace a human-read chest x-ray within treatment-decision algorithms for paediatric tuberculosis. |
| format | Article |
| id | doaj-art-de885dfa724744d1b938afacb724e63c |
| institution | OA Journals |
| issn | 2767-3375 |
| language | English |
| publishDate | 2023-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLOS Global Public Health |
| spelling | doaj-art-de885dfa724744d1b938afacb724e63c2025-08-20T02:23:19ZengPublic Library of Science (PLoS)PLOS Global Public Health2767-33752023-01-0135e000179910.1371/journal.pgph.0001799Optimising computer aided detection to identify intra-thoracic tuberculosis on chest x-ray in South African children.Megan PalmerJames A SeddonMarieke M van der ZalmAnneke C HesselingPierre GoussardH Simon SchaafJulie MorrisonBram van GinnekenJaime MelendezElisabetta WaltersKeelin MurphyDiagnostic tools for paediatric tuberculosis remain limited, with heavy reliance on clinical algorithms which include chest x-ray. Computer aided detection (CAD) for tuberculosis on chest x-ray has shown promise in adults. We aimed to measure and optimise the performance of an adult CAD system, CAD4TB, to identify tuberculosis on chest x-rays from children with presumptive tuberculosis. Chest x-rays from 620 children <13 years enrolled in a prospective observational diagnostic study in South Africa, were evaluated. All chest x-rays were read by a panel of expert readers who attributed each with a radiological reference of either 'tuberculosis' or 'not tuberculosis'. Of the 525 chest x-rays included in this analysis, 80 (40 with a reference of 'tuberculosis' and 40 with 'not tuberculosis') were allocated to an independent test set. The remainder made up the training set. The performance of CAD4TB to identify 'tuberculosis' versus 'not tuberculosis' on chest x-ray against the radiological reference read was calculated. The CAD4TB software was then fine-tuned using the paediatric training set. We compared the performance of the fine-tuned model to the original model. Our findings were that the area under the receiver operating characteristic curve (AUC) of the original CAD4TB model, prior to fine-tuning, was 0.58. After fine-tuning there was an improvement in the AUC to 0.72 (p = 0.0016). In this first-ever description of the use of CAD to identify tuberculosis on chest x-ray in children, we demonstrate a significant improvement in the performance of CAD4TB after fine-tuning with a set of well-characterised paediatric chest x-rays. CAD has the potential to be a useful additional diagnostic tool for paediatric tuberculosis. We recommend replicating the methods we describe using a larger chest x-ray dataset from a more diverse population and evaluating the potential role of CAD to replace a human-read chest x-ray within treatment-decision algorithms for paediatric tuberculosis.https://journals.plos.org/globalpublichealth/article/file?id=10.1371/journal.pgph.0001799&type=printable |
| spellingShingle | Megan Palmer James A Seddon Marieke M van der Zalm Anneke C Hesseling Pierre Goussard H Simon Schaaf Julie Morrison Bram van Ginneken Jaime Melendez Elisabetta Walters Keelin Murphy Optimising computer aided detection to identify intra-thoracic tuberculosis on chest x-ray in South African children. PLOS Global Public Health |
| title | Optimising computer aided detection to identify intra-thoracic tuberculosis on chest x-ray in South African children. |
| title_full | Optimising computer aided detection to identify intra-thoracic tuberculosis on chest x-ray in South African children. |
| title_fullStr | Optimising computer aided detection to identify intra-thoracic tuberculosis on chest x-ray in South African children. |
| title_full_unstemmed | Optimising computer aided detection to identify intra-thoracic tuberculosis on chest x-ray in South African children. |
| title_short | Optimising computer aided detection to identify intra-thoracic tuberculosis on chest x-ray in South African children. |
| title_sort | optimising computer aided detection to identify intra thoracic tuberculosis on chest x ray in south african children |
| url | https://journals.plos.org/globalpublichealth/article/file?id=10.1371/journal.pgph.0001799&type=printable |
| work_keys_str_mv | AT meganpalmer optimisingcomputeraideddetectiontoidentifyintrathoracictuberculosisonchestxrayinsouthafricanchildren AT jamesaseddon optimisingcomputeraideddetectiontoidentifyintrathoracictuberculosisonchestxrayinsouthafricanchildren AT mariekemvanderzalm optimisingcomputeraideddetectiontoidentifyintrathoracictuberculosisonchestxrayinsouthafricanchildren AT annekechesseling optimisingcomputeraideddetectiontoidentifyintrathoracictuberculosisonchestxrayinsouthafricanchildren AT pierregoussard optimisingcomputeraideddetectiontoidentifyintrathoracictuberculosisonchestxrayinsouthafricanchildren AT hsimonschaaf optimisingcomputeraideddetectiontoidentifyintrathoracictuberculosisonchestxrayinsouthafricanchildren AT juliemorrison optimisingcomputeraideddetectiontoidentifyintrathoracictuberculosisonchestxrayinsouthafricanchildren AT bramvanginneken optimisingcomputeraideddetectiontoidentifyintrathoracictuberculosisonchestxrayinsouthafricanchildren AT jaimemelendez optimisingcomputeraideddetectiontoidentifyintrathoracictuberculosisonchestxrayinsouthafricanchildren AT elisabettawalters optimisingcomputeraideddetectiontoidentifyintrathoracictuberculosisonchestxrayinsouthafricanchildren AT keelinmurphy optimisingcomputeraideddetectiontoidentifyintrathoracictuberculosisonchestxrayinsouthafricanchildren |