1
|
Joye AS, Firlie MG, Wittberg DM, Aragie S, Nash SD, Tadesse Z, Dagnew A, Hailu D, Admassu F, Wondimteka B, Getachew H, Kabtu E, Beyecha S, Shibiru M, Getnet B, Birhanu T, Abdu S, Tekew S, Lietman TM, Keenan JD, Redd TK. Computer Vision Identification of Trachomatous Inflammation-Follicular Using Deep Learning. Cornea 2024:00003226-990000000-00692. [PMID: 39312712 DOI: 10.1097/ico.0000000000003701] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/14/2024] [Accepted: 07/25/2024] [Indexed: 09/25/2024]
Abstract
PURPOSE Trachoma surveys are used to estimate the prevalence of trachomatous inflammation-follicular (TF) to guide mass antibiotic distribution. These surveys currently rely on human graders, introducing a significant resource burden and potential for human error. This study describes the development and evaluation of machine learning models intended to reduce cost and improve reliability of these surveys. METHODS Fifty-six thousand seven hundred twenty-five everted eyelid photographs were obtained from 11,358 children of age 0 to 9 years in a single trachoma-endemic region of Ethiopia over a 3-year period. Expert graders reviewed all images from each examination to determine the estimated number of tarsal conjunctival follicles and the degree of trachomatous inflammation-intense. The median estimate of the 3 grader groups was used as the ground truth to train a MobileNetV3 large deep convolutional neural network to detect cases with TF. RESULTS The classification model predicted a TF prevalence of 32%, which was not significantly different from the human consensus estimate (30%; 95% confidence interval of difference, -2 to +4%). The model had an area under the receiver operating characteristic curve of 0.943, F1 score of 0.923, 88% accuracy, 83% sensitivity, and 91% specificity. The area under the receiver operating characteristic curve increased to 0.995 when interpreting nonborderline cases of TF. CONCLUSIONS Deep convolutional neural network models performed well at classifying TF and detecting the number of follicles evident in conjunctival photographs. Implementation of similar models may enable accurate, efficient, large-scale trachoma screening. Further validation in diverse populations with varying TF prevalence is needed before implementation at scale.
Collapse
Affiliation(s)
- Ashlin S Joye
- Casey Eye Institute, Oregon Health and Science University, Portland, OR
- Francis I Proctor Foundation, University of California San Francisco, San Francisco, CA
| | - Marissa G Firlie
- George Washington University, School of Medicine and Health Sciences, Washington, DC
| | - Dionna M Wittberg
- Francis I Proctor Foundation, University of California San Francisco, San Francisco, CA
| | | | | | | | - Adane Dagnew
- The Carter Center Ethiopia, Addis Ababa, Ethiopia
| | | | - Fisseha Admassu
- Department of Ophthalmology, University of Gondar, Gondar, Ethiopia
| | - Bilen Wondimteka
- Department of Ophthalmology, University of Gondar, Gondar, Ethiopia
| | - Habib Getachew
- Department of Ophthalmology, University of Gondar, Gondar, Ethiopia
| | - Endale Kabtu
- Department of Ophthalmology, University of Gondar, Gondar, Ethiopia
| | - Social Beyecha
- Department of Ophthalmology, University of Gondar, Gondar, Ethiopia
| | - Meskerem Shibiru
- Department of Ophthalmology, University of Gondar, Gondar, Ethiopia
| | - Banchalem Getnet
- Department of Ophthalmology, University of Gondar, Gondar, Ethiopia
| | - Tibebe Birhanu
- Department of Ophthalmology, University of Gondar, Gondar, Ethiopia
| | - Seid Abdu
- Department of Ophthalmology, University of Gondar, Gondar, Ethiopia
| | - Solomon Tekew
- Department of Ophthalmology, University of Gondar, Gondar, Ethiopia
| | - Thomas M Lietman
- Francis I Proctor Foundation, University of California San Francisco, San Francisco, CA
| | - Jeremy D Keenan
- Francis I Proctor Foundation, University of California San Francisco, San Francisco, CA
| | - Travis K Redd
- Casey Eye Institute, Oregon Health and Science University, Portland, OR
- Francis I Proctor Foundation, University of California San Francisco, San Francisco, CA
| |
Collapse
|
2
|
Bisanzio D, Butcher R, Turbé V, Matsumoto K, Dinesh C, Massae P, Dejene M, Jimenez C, Macleod C, Matayan E, Mpyet C, Pavluck A, Saboyá-Díaz MI, Tadesse F, Talero SL, Solomon AW, Ngondi J, Kabona G, Uisso C, Simon A, Mwingira U, Harding-Esch EM. Accuracy, acceptability and feasibility of photography for use in trachoma surveys: a mixed methods study in Tanzania. Int Health 2024; 16:416-427. [PMID: 38141035 PMCID: PMC11218887 DOI: 10.1093/inthealth/ihad111] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/02/2023] [Revised: 09/15/2023] [Accepted: 11/22/2023] [Indexed: 12/24/2023] Open
Abstract
BACKGROUND Photography could be used to train individuals to diagnose trachomatous inflammation-follicular (TF) as trachoma prevalence decreases and to ensure accurate field TF grading in trachoma prevalence surveys. We compared photograph and field TF grading and determined the acceptability and feasibility of eyelid photography to community members and trachoma survey trainers. METHODS A total of 100 children ages 1-9 y were examined for TF in two Maasai villages in Tanzania. Two images of the right everted superior tarsal conjunctiva of each child were taken with a smartphone and a digital single-lens reflex (DSLR) camera. Two graders independently graded all photos. Focus group discussions (FGDs) were conducted with community members and Tropical Data trainers. RESULTS Of 391 photos, one-fifth were discarded as ungradable. Compared with field grading, photo grading consistently underdiagnosed TF. Compared with field grading, DSLR photo grading resulted in a higher prevalence and sensitivity than smartphone photo grading. FGDs indicated that communities and trainers found photography acceptable and preferred smartphones to DSLR in terms of practicalities, but image quality was of paramount importance for trainers. CONCLUSIONS Photography is acceptable and feasible, but further work is needed to ensure high-quality images that enable accurate and consistent grading before being routinely implemented in trachoma surveys.
Collapse
Affiliation(s)
| | - Robert Butcher
- Clinical Research Department, London School of Hygiene & Tropical Medicine, London, UK
| | - Valérian Turbé
- Department of Medicine, University College London, London, UK
| | - Kenji Matsumoto
- Clinical Research Department, London School of Hygiene & Tropical Medicine, London, UK
| | - Chaitra Dinesh
- Clinical Research Department, London School of Hygiene & Tropical Medicine, London, UK
| | - Patrick Massae
- Department of Ophthalmology, Kilimanjaro Christian Medical Centre, Moshi, Tanzania
| | | | | | - Colin Macleod
- Clinical Research Department, London School of Hygiene & Tropical Medicine, London, UK
| | - Einoti Matayan
- Department of Ophthalmology, Kilimanjaro Christian Medical University College, Moshi, Tanzania
| | - Caleb Mpyet
- Department of Ophthalmology, University of Jos, Jos, Nigeria
- Sightsavers Nigeria Country Office, Kaduna, Nigeria
| | | | - Martha Idalí Saboyá-Díaz
- Communicable Diseases Prevention, Control, and Elimination Department, Pan American Health Organization, Washington, DC, USA
| | | | | | - Anthony W Solomon
- Global Neglected Tropical Diseases Programme, World Health Organization, Geneva, Switzerland
| | | | - George Kabona
- Neglected Tropical Disease Control Program, Ministry of Health, Dodoma, Tanzania
| | - Cecilia Uisso
- Neglected Tropical Disease Control Program, Ministry of Health, Dodoma, Tanzania
| | - Alistidia Simon
- Neglected Tropical Disease Control Program, Ministry of Health, Dodoma, Tanzania
| | - Upendo Mwingira
- RTI International, Washington, DC, USA
- Neglected Tropical Disease Control Program, Ministry of Health, Dodoma, Tanzania
- National Institute for Medical Research, Dar-es-Salaam, Tanzania
| | - Emma M Harding-Esch
- Clinical Research Department, London School of Hygiene & Tropical Medicine, London, UK
| |
Collapse
|
3
|
Aguwa UT, Mkocha H, Munoz B, Wolle MA, Brady CJ, West SK. Comparing image quality and trachoma detection across three camera types from a survey in Kongwa, Tanzania. Int Health 2023; 15:ii19-ii24. [PMID: 38048378 PMCID: PMC10695420 DOI: 10.1093/inthealth/ihad054] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/20/2023] [Revised: 05/23/2023] [Accepted: 07/24/2023] [Indexed: 12/06/2023] Open
Abstract
BACKGROUND There is an increasing demand for photography for trachoma prevalence surveys. In previous studies, digital single lens reflex (DSLR) images were superior to smartphone images, but newer-model smartphones and/or lens attachments may be able to bridge this gap. This study compares the image quality and ability to detect trachomatous inflammation - follicular (TF) of three camera types: a DSLR Nikon camera, an iPhone SE and an iPhone 13 Pro with a cell scope. METHODS We surveyed 62 children ages 1-7 y from two Tanzanian communities. Upper tarsal conjunctiva images of both eyes were graded for TF by two standardized graders. The McNemar's test and a logistic regression model were used for analyses. RESULTS The DSLR camera malfunctioned during the study, thus the iPhone SE and iPhone 13 Pro with cell scope were both more likely to take high-quality, gradable photographs (88% and 86%, respectively) compared with the DSLR camera (69%) (p<0.001 and p=0.02, respectively). TF was detected in gradable images from the iPhone SE (8.8%) and iPhone 13 Pro with cell scope (9.0%) at the same rate (p=1.0) as images from the DSLR camera (9.7%). CONCLUSION Smartphones with high-quality image capture, like the iPhone SE/13 Pro, have the potential for use in trachoma surveys if the proportion of gradable images can be improved.
Collapse
Affiliation(s)
- Ugochi T Aguwa
- Johns Hopkins University School of Medicine, Baltimore, MD, USA
- Dana Center for Preventive Ophthalmology, Wilmer Eye Institute, Johns Hopkins University Hospital, 600 N. Wolfe St., Baltimore, MD 21287, USA
| | | | - Beatriz Munoz
- Dana Center for Preventive Ophthalmology, Wilmer Eye Institute, Johns Hopkins University Hospital, 600 N. Wolfe St., Baltimore, MD 21287, USA
| | - Meraf A Wolle
- Dana Center for Preventive Ophthalmology, Wilmer Eye Institute, Johns Hopkins University Hospital, 600 N. Wolfe St., Baltimore, MD 21287, USA
| | - Christopher J Brady
- Robert Larner College of Medicine, University of Vermont School of Medicine, 111 Colchester Ave, Burlington, VT 05401, USA
| | - Sheila K West
- Dana Center for Preventive Ophthalmology, Wilmer Eye Institute, Johns Hopkins University Hospital, 600 N. Wolfe St., Baltimore, MD 21287, USA
| |
Collapse
|
4
|
Harding-Esch EM, Burgert-Brucker CR, Jimenez C, Bakhtiari A, Willis R, Dejene Bejiga M, Mpyet C, Ngondi J, Boyd S, Abdala M, Abdou A, Adamu Y, Alemayehu A, Alemayehu W, Al-Khatib T, Apadinuwe SC, Awaca N, Awoussi MS, Baayendag G, Badiane Mouctar D, Bailey RL, Batcho W, Bay Z, Bella A, Beido N, Bol YY, Bougouma C, Brady CJ, Bucumi V, Butcher R, Cakacaka R, Cama A, Camara M, Cassama E, Chaora SG, Chebbi AC, Chisambi AB, Chu B, Conteh A, Coulibaly SM, Courtright P, Dalmar A, Dat TM, Davids T, DJAKER MEA, de Fátima Costa Lopes M, Dézoumbé D, Dodson S, Downs P, Eckman S, Elshafie BE, Elmezoghi M, Elvis AA, Emerson P, Epée EEE, Faktaufon D, Fall M, Fassinou A, Fleming F, Flueckiger R, Gamael KK, Garae M, Garap J, Gass K, Gebru G, Gichangi MM, Giorgi E, Goépogui A, Gómez DVF, Gómez Forero DP, Gower EW, Harte A, Henry R, Honorio-Morales HA, Ilako DR, Issifou AAB, Jones E, Kabona G, Kabore M, Kadri B, Kalua K, Kanyi SK, Kebede S, Kebede F, Keenan JD, Kello AB, Khan AA, KHELIFI H, Kilangalanga J, KIM SH, Ko R, Lewallen S, Lietman T, Logora MSY, Lopez YA, MacArthur C, Macleod C, Makangila F, Mariko B, Martin DL, Masika M, Massae P, Massangaie M, Matendechero HS, Mathewos T, McCullagh S, Meite A, Mendes EP, Abdi HM, Miller H, Minnih A, Mishra SK, Molefi T, Mosher A, M’Po N, Mugume F, Mukwiza R, Mwale C, Mwatha S, Mwingira U, Nash SD, NASSA C, Negussu N, Nieba C, Noah Noah JC, Nwosu CO, Olobio N, Opon R, Pavluck A, Phiri I, Rainima-Qaniuci M, Renneker KK, Saboyá-Díaz MI, Sakho F, Sanha S, Sarah V, Sarr B, Szwarcwald CL, Shah Salam A, Sharma S, Seife F, Serrano Chavez GM, Sissoko M, Sitoe HM, Sokana O, Tadesse F, Taleo F, Talero SL, Tarfani Y, Tefera A, Tekeraoi R, Tesfazion A, Traina A, Traoré L, Trujillo-Trujillo J, Tukahebwa EM, Vashist P, Wanyama EB, WARUSAVITHANA SD, Watitu TK, West S, Win Y, Woods G, YAJIMA A, Yaya G, Zecarias A, Zewengiel S, Zoumanigui A, Hooper PJ, Millar T, Rotondo L, Solomon AW. Tropical Data: Approach and Methodology as Applied to Trachoma Prevalence Surveys. Ophthalmic Epidemiol 2023; 30:544-560. [PMID: 38085791 PMCID: PMC10751062 DOI: 10.1080/09286586.2023.2249546] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/09/2023] [Accepted: 08/11/2023] [Indexed: 12/18/2023]
Abstract
PURPOSE Population-based prevalence surveys are essential for decision-making on interventions to achieve trachoma elimination as a public health problem. This paper outlines the methodologies of Tropical Data, which supports work to undertake those surveys. METHODS Tropical Data is a consortium of partners that supports health ministries worldwide to conduct globally standardised prevalence surveys that conform to World Health Organization recommendations. Founding principles are health ministry ownership, partnership and collaboration, and quality assurance and quality control at every step of the survey process. Support covers survey planning, survey design, training, electronic data collection and fieldwork, and data management, analysis and dissemination. Methods are adapted to meet local context and needs. Customisations, operational research and integration of other diseases into routine trachoma surveys have also been supported. RESULTS Between 29th February 2016 and 24th April 2023, 3373 trachoma surveys across 50 countries have been supported, resulting in 10,818,502 people being examined for trachoma. CONCLUSION This health ministry-led, standardised approach, with support from the start to the end of the survey process, has helped all trachoma elimination stakeholders to know where interventions are needed, where interventions can be stopped, and when elimination as a public health problem has been achieved. Flexibility to meet specific country contexts, adaptation to changes in global guidance and adjustments in response to user feedback have facilitated innovation in evidence-based methodologies, and supported health ministries to strive for global disease control targets.
Collapse
Affiliation(s)
| | | | | | | | | | | | | | | | | | | | - Amza Abdou
- Programme National de Santé Oculaire, Niger
| | | | | | | | | | | | - Naomie Awaca
- Ministère de la Santé Publique, Democratic Republic of Congo
| | | | | | | | | | | | | | | | | | | | - Clarisse Bougouma
- Programme national de lutte contre les maladies tropicales négligées (PNMTN), Burkina Faso
| | | | - Victor Bucumi
- National Integrated Programme for the Control of Neglected Tropical Diseases and Blindness (PNIMTNC), Burundi
| | | | | | | | | | | | | | | | | | - Brian Chu
- International Trachoma Initiative, USA
| | | | | | - Paul Courtright
- Division of Ophthalmology, University of Cape Town, Cape Town, South Africa, South Africa
| | - Abdi Dalmar
- Ministry of Human Development and Public Services, Somalia
| | | | | | | | | | | | | | | | | | | | | | - Ange Aba Elvis
- Programme National de la Santé Oculaire et de la lutte contre l’Onchocercose, Côte d’Ivoire
| | | | | | | | | | | | | | | | | | | | - Jambi Garap
- Port Moresby General Hospital, Papua New Guinea
| | | | | | | | | | | | | | | | | | - Anna Harte
- London School of Hygiene & Tropical Medicine, UK
| | - Rob Henry
- U.S. Agency for International Development, USA
| | | | | | | | | | | | - Martin Kabore
- Programme national de lutte contre les maladies tropicales négligées (PNMTN), Burkina Faso
| | | | - Khumbo Kalua
- Blantyre Institute for Community Outreach, Malawi
| | | | | | | | | | | | | | | | | | | | - Robert Ko
- Port Moresby General Hospital, Papua New Guinea
| | - Susan Lewallen
- Division of Ophthalmology, University of Cape Town, Cape Town, South Africa, South Africa
| | | | | | - Yuri A Lopez
- SACAICET / MINISTERIO DEL PODER POPULAR PARA LA SALUD, Venezuela
| | | | | | | | | | | | | | | | | | | | | | | | - Aboulaye Meite
- Ministère de la Santé et de l’Hygiène Publique, Cote d’Ivoire
| | | | | | | | | | | | | | - Aryc Mosher
- U.S. Agency for International Development, USA
| | | | | | | | | | | | | | | | | | | | - Cece Nieba
- Ministère de la Santé et de l’Hygiene Publique, Guinea
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | - Oliver Sokana
- Solomon Islands Ministry of Health and Medical Services, Solomon Islands
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
Collapse
|
5
|
Naufal F, Brady CJ, Muñoz B, Mkocha H, West SK. Comparison of Five Camera Systems for Capturing and Grading Trachoma Images. Ophthalmic Epidemiol 2023:1-6. [PMID: 36775887 DOI: 10.1080/09286586.2023.2174559] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/08/2022] [Revised: 01/16/2023] [Accepted: 01/25/2023] [Indexed: 02/14/2023]
Abstract
PURPOSE As training of trachoma graders using live participants grows increasingly difficult and expensive, alternative ways are needed possibly through replacement of field grading with photography. However, minimum specifications for a camera system capable of capturing high quality images have not been defined. This study compared images captured using four smartphones with those from a Nikon SLR camera for image quality and assessment of trachomatous inflammation - follicular (TF). METHODS The smartphones - Samsung Galaxy S8 (S8), Techno Camon 17 pro (TC), Infinix Note 10 pro (IN), Huawei p30 pro (HP) - were chosen for their availability and likelihood of good performance based on specifications without external attachments. All smartphones were used in random order for each participant. RESULTS 129 children in Kongwa, Tanzania were enrolled (32.8% TF prevalence). The SLR camera had the least percent of ungradable images (3.1%), followed by the S8 (14%), HP (23.4%), IN (65.9%), and TC (71.2%). The S8 and the HP were significantly more likely to take ungradable images if they were used toward the end of the camera rotation. Agreement between the SLR and field grade was kappa = 0.73. Agreement between the field grade and gradable images from the S8 (0.68) and HP (0.8) was measured. CONCLUSIONS Published specifications did not predict the success of using different smartphones for everted eyelid photographs; proprietary post-processing software likely influenced gradeability. Smartphones, though we cannot recommend those tested in this study, may be viable for capturing images for trachoma provided the quality of images from the field are adequate.
Collapse
Affiliation(s)
- Fahd Naufal
- Dana Center for Preventive Ophthalmology, Wilmer Eye Institute, Johns Hopkins University, Baltimore, Maryland, USA
| | | | - Beatriz Muñoz
- Dana Center for Preventive Ophthalmology, Wilmer Eye Institute, Johns Hopkins University, Baltimore, Maryland, USA
| | | | - Sheila K West
- Dana Center for Preventive Ophthalmology, Wilmer Eye Institute, Johns Hopkins University, Baltimore, Maryland, USA
| |
Collapse
|
6
|
Whitson CC, Nute AW, Hailemariam B, Deathe AR, Astale T, Ayele Z, Gessese D, Sata E, Zerihun M, Melak B, Haile M, Zeru T, Getnet B, Wondimteka B, Kabtu E, Getachew H, Shibiru M, Bayecha S, Aragie S, Wittberg DM, Tadesse Z, Callahan EK, Keenan JD, Admassu F, Nash SD. Photographic grading for trachoma diagnosis within trachoma impact surveys in Amhara region, Ethiopia. Trans R Soc Trop Med Hyg 2023; 117:111-117. [PMID: 36162054 PMCID: PMC9890315 DOI: 10.1093/trstmh/trac090] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/28/2022] [Revised: 05/03/2022] [Accepted: 09/06/2022] [Indexed: 02/04/2023] Open
Abstract
BACKGROUND As countries reach the trachoma elimination threshold and cases of trachomatous inflammation follicular (TF) become rare, it becomes difficult to train survey graders to recognize clinical signs. We assess the use of photography as a grading tool, the efficiency of an in-country grading center and the comparability of field and photographic grading. METHODS During January-February 2017 surveys in Amhara, Ethiopia, field graders assessed TF, trachomatous inflammation intense (TI) and trachomatous scarring (TS). Photographs were taken from each conjunctiva and later graded at the Gondar Grading Center (GGC) at the University of Gondar in Amhara. Two trained ophthalmology residents graded each set of photographs and a third grader provided an adjudicating grade when needed. RESULTS A total of 4953 photographs of 2477 conjunctivae from 1241 participants in 10 communities were graded over 5 d at the GGC. Six examined participants were not photographed. Agreement between field and photographic grades were for TF: percent agreement (PA) 96.7%, κ=0.70 (95% confidence interval [CI] 0.64 to 0.77; for TI: PA 94.7%, κ=0.32 (95% CI 0.20 to 0.43); and for TS: PA 83.5%, κ=0.22 (95% CI 0.15 to 0.29). CONCLUSIONS Conjunctival photography may be a solution for programs near the elimination threshold where there are few available community cases for training field graders.
Collapse
Affiliation(s)
| | - Andrew W Nute
- Trachoma Control Program, The Carter Center, Atlanta, GA, USA
| | | | - Andrew R Deathe
- Trachoma Control Program, The Carter Center, Atlanta, GA, USA
| | - Tigist Astale
- Trachoma Control Program, The Carter Center, Addis Ababa, Ethiopia
| | - Zebene Ayele
- Trachoma Control Program, The Carter Center, Addis Ababa, Ethiopia
| | - Demelash Gessese
- Trachoma Control Program, The Carter Center, Addis Ababa, Ethiopia
| | - Eshetu Sata
- Trachoma Control Program, The Carter Center, Addis Ababa, Ethiopia
| | - Mulat Zerihun
- Trachoma Control Program, The Carter Center, Addis Ababa, Ethiopia
| | - Berhanu Melak
- Trachoma Control Program, The Carter Center, Addis Ababa, Ethiopia
| | - Mahteme Haile
- Research and Technology Transfer Directorate, Amhara Public Health Institute, Bahir Dar, Ethiopia
| | - Taye Zeru
- Research and Technology Transfer Directorate, Amhara Public Health Institute, Bahir Dar, Ethiopia
| | - Banchalem Getnet
- Department of Ophthalmology, University of Gondar, Gondar, Ethiopia
| | - Bilen Wondimteka
- Department of Ophthalmology, University of Gondar, Gondar, Ethiopia
| | - Endale Kabtu
- Department of Ophthalmology, University of Gondar, Gondar, Ethiopia
| | - Habib Getachew
- Department of Ophthalmology, University of Gondar, Gondar, Ethiopia
| | - Meskerem Shibiru
- Department of Ophthalmology, University of Gondar, Gondar, Ethiopia
| | - Social Bayecha
- Department of Ophthalmology, University of Gondar, Gondar, Ethiopia
| | - Solomon Aragie
- Trachoma Control Program, The Carter Center, Addis Ababa, Ethiopia
| | - Dionna M Wittberg
- Francis I. Proctor Foundation, University of California, San Francisco, San Francisco, CA, USA
| | - Zerihun Tadesse
- Trachoma Control Program, The Carter Center, Addis Ababa, Ethiopia
| | | | - Jeremy D Keenan
- Francis I. Proctor Foundation, University of California, San Francisco, San Francisco, CA, USA
| | - Fisseha Admassu
- Department of Ophthalmology, University of Gondar, Gondar, Ethiopia
| | - Scott D Nash
- Trachoma Control Program, The Carter Center, Atlanta, GA, USA
| |
Collapse
|
7
|
Detection of trachoma using machine learning approaches. PLoS Negl Trop Dis 2022; 16:e0010943. [DOI: 10.1371/journal.pntd.0010943] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/30/2022] [Revised: 12/19/2022] [Accepted: 11/12/2022] [Indexed: 12/12/2022] Open
Abstract
Background
Though significant progress in disease elimination has been made over the past decades, trachoma is the leading infectious cause of blindness globally. Further efforts in trachoma elimination are paradoxically being limited by the relative rarity of the disease, which makes clinical training for monitoring surveys difficult. In this work, we evaluate the plausibility of an Artificial Intelligence model to augment or replace human image graders in the evaluation/diagnosis of trachomatous inflammation—follicular (TF).
Methods
We utilized a dataset consisting of 2300 images with a 5% positivity rate for TF. We developed classifiers by implementing two state-of-the-art Convolutional Neural Network architectures, ResNet101 and VGG16, and applying a suite of data augmentation/oversampling techniques to the positive images. We then augmented our data set with additional images from independent research groups and evaluated performance.
Results
Models performed well in minimizing the number of false negatives, given the constraint of the low numbers of images in which TF was present. The best performing models achieved a sensitivity of 95% and positive predictive value of 50–70% while reducing the number images requiring skilled grading by 66–75%. Basic oversampling and data augmentation techniques were most successful at improving model performance, while techniques that are grounded in clinical experience, such as highlighting follicles, were less successful.
Discussion
The developed models perform well and significantly reduce the burden on graders by minimizing the number of false negative identifications. Further improvements in model skill will benefit from data sets with more TF as well as a range in image quality and image capture techniques used. While these models approach/meet the community-accepted standard for skilled field graders (i.e., Cohen’s Kappa >0.7), they are insufficient to be deployed independently/clinically at this time; rather, they can be utilized to significantly reduce the burden on skilled image graders.
Collapse
|
8
|
Brady CJ, Cockrell RC, Aldrich LR, Wolle MA, West SK. A Virtual Reading Center Model Using Crowdsourcing to Grade Photographs for Trachoma: Validation Study (Preprint). J Med Internet Res 2022; 25:e41233. [PMID: 37023420 PMCID: PMC10132003 DOI: 10.2196/41233] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/26/2022] [Revised: 01/30/2023] [Accepted: 02/19/2023] [Indexed: 02/21/2023] Open
Abstract
BACKGROUND As trachoma is eliminated, skilled field graders become less adept at correctly identifying active disease (trachomatous inflammation-follicular [TF]). Deciding if trachoma has been eliminated from a district or if treatment strategies need to be continued or reinstated is of critical public health importance. Telemedicine solutions require both connectivity, which can be poor in the resource-limited regions of the world in which trachoma occurs, and accurate grading of the images. OBJECTIVE Our purpose was to develop and validate a cloud-based "virtual reading center" (VRC) model using crowdsourcing for image interpretation. METHODS The Amazon Mechanical Turk (AMT) platform was used to recruit lay graders to interpret 2299 gradable images from a prior field trial of a smartphone-based camera system. Each image received 7 grades for US $0.05 per grade in this VRC. The resultant data set was divided into training and test sets to internally validate the VRC. In the training set, crowdsourcing scores were summed, and the optimal raw score cutoff was chosen to optimize kappa agreement and the resulting prevalence of TF. The best method was then applied to the test set, and the sensitivity, specificity, kappa, and TF prevalence were calculated. RESULTS In this trial, over 16,000 grades were rendered in just over 60 minutes for US $1098 including AMT fees. After choosing an AMT raw score cut point to optimize kappa near the World Health Organization (WHO)-endorsed level of 0.7 (with a simulated 40% prevalence TF), crowdsourcing was 95% sensitive and 87% specific for TF in the training set with a kappa of 0.797. All 196 crowdsourced-positive images received a skilled overread to mimic a tiered reading center and specificity improved to 99%, while sensitivity remained above 78%. Kappa for the entire sample improved from 0.162 to 0.685 with overreads, and the skilled grader burden was reduced by over 80%. This tiered VRC model was then applied to the test set and produced a sensitivity of 99% and a specificity of 76% with a kappa of 0.775 in the entire set. The prevalence estimated by the VRC was 2.70% (95% CI 1.84%-3.80%) compared to the ground truth prevalence of 2.87% (95% CI 1.98%-4.01%). CONCLUSIONS A VRC model using crowdsourcing as a first pass with skilled grading of positive images was able to identify TF rapidly and accurately in a low prevalence setting. The findings from this study support further validation of a VRC and crowdsourcing for image grading and estimation of trachoma prevalence from field-acquired images, although further prospective field testing is required to determine if diagnostic characteristics are acceptable in real-world surveys with a low prevalence of the disease.
Collapse
Affiliation(s)
- Christopher J Brady
- Division of Ophthalmology, Department of Surgery, Larner College of Medicine at The University of Vermont, Burlington, VT, United States
| | - R Chase Cockrell
- Division of Surgical Research, Department of Surgery, Larner College of Medicine at The University of Vermont, Burlington, VT, United States
| | - Lindsay R Aldrich
- Larner College of Medicine at The University of Vermont, Burlington, VT, United States
| | - Meraf A Wolle
- Dana Center for Preventive Ophthalmology, Wilmer Eye Institute, Baltimore, MD, United States
| | - Sheila K West
- Dana Center for Preventive Ophthalmology, Wilmer Eye Institute, Baltimore, MD, United States
| |
Collapse
|