{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T11:57:29Z","timestamp":1758369449419,"version":"3.44.0"},"reference-count":19,"publisher":"Oxford University Press (OUP)","issue":"Supplement_2","funder":[{"DOI":"10.13039\/100016156","name":"U.S. Army Medical Research and Development Command","doi-asserted-by":"publisher","award":["BA190144","W81XWH-19-2-0052"],"award-info":[{"award-number":["BA190144","W81XWH-19-2-0052"]}],"id":[{"id":"10.13039\/100016156","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Introduction<\/jats:title>\n                  <jats:p>Posterior penetrating eye injury can lead to retinal tearing, detachment, and intraocular fibrosis that require timely intervention without compromising vision. Currently, ophthalmoscopy is the gold standard for visualizing the retina, even though one cannot consistently detect retinal abnormalities by relying on such a method alone. The objective of this work was to determine whether automated image processing systems based on machine learning (ML) could facilitate the identification of subtle changes in the retina following an injury.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Materials and Methods<\/jats:title>\n                  <jats:p>Ten Dutch Belted rabbits were subjected to a posterior penetrating eye injury in the right eye via a 23-gauge needle and monitored using fundus photography. The dataset consisted of 743 full-color fundus images that were randomly split into training and testing groups at a ratio of 7:3. Two types of ML models, a convolution neural network (CNN) and 4 varieties of support vector machine (SVM), were constructed using training group images and validated with testing group images. The 5 models were compared using measures such as Accuracy, Precision, and the area under the receiver operating characteristic curve (ROC AUC).<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>The SVM polynomial kernel performed the best across all metrics, with 92.37% accuracy and ROC AUC of 0.96. The CNN model exhibited a relatively high accuracy of 91.03% and an ROC AUC of 0.91. The SVM linear kernel presented comparable but slightly lower metrics, with 83.86% accuracy and ROC AUC of 0.89. The lowest performing models were the SVM sigmoid (64.57% accuracy, ROC AUC=0.72) and radial basis function kernels (73.09% accuracy, ROC AUC=0.82).<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusions<\/jats:title>\n                  <jats:p>Our study shows that trained ML algorithms can accurately identify retinal tears following trauma to the posterior segment of the eye. This is an important step toward developing computer-aided diagnostic tools that can be used to detect retinal injury and disease progression following posterior penetrating eye injury.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/milmed\/usaf236","type":"journal-article","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T22:22:58Z","timestamp":1758320578000},"page":"471-477","source":"Crossref","is-referenced-by-count":0,"title":["Computer-Assisted Detection of Retinal Injury Following Ocular Trauma Using Machine Learning Algorithms"],"prefix":"10.1093","volume":"190","author":[{"given":"Patrick Y","family":"Hsun","sequence":"first","affiliation":[{"name":"Metis Foundation , San Antonio, TX 78216,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christina L","family":"Rettinger","sequence":"additional","affiliation":[{"name":"Metis Foundation , San Antonio, TX 78216,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6964-2894","authenticated-orcid":false,"given":"Heuy-Ching","family":"Wang","sequence":"additional","affiliation":[{"name":"Combat Casualty Care and Operational Medicine, Naval Medical Research Unit\u2014San Antonio (NAMRU-SA) , Fort Sam Houston, TX 78234,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2025,9,16]]},"reference":[{"key":"2025092002193693400_usaf236-B1","doi-asserted-by":"publisher","first-page":"2172","DOI":"10.1056\/NEJMc1010683","article-title":"Closed-eye ocular injuries in the Iraq and Afghanistan wars","volume":"364","author":"Cockerham","year":"2011","journal-title":"N Engl J Med."},{"key":"2025092002193693400_usaf236-B2","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1097\/ICU.0b013e3283140e98","article-title":"Combat ocular trauma and systemic injury","volume":"19","author":"Weichel","year":"2008","journal-title":"Curr Opin Ophthalmol"},{"key":"2025092002193693400_usaf236-B3","doi-asserted-by":"publisher","first-page":"559","DOI":"10.1016\/s0002-9394(14)77369-6","article-title":"A comparison of different cellular inocula in an experimental model of massive periretinal proliferation","volume":"93","author":"Fastenberg","year":"1982","journal-title":"Am J Ophthalmol"},{"key":"2025092002193693400_usaf236-B4","doi-asserted-by":"publisher","first-page":"815937","DOI":"10.1155\/2012\/815937","article-title":"Mechanisms of inflammation in proliferative vitreoretinopathy: from bench to bedside","volume":"2012","author":"Moysidis","year":"2012","journal-title":"Mediators Inflamm"},{"key":"2025092002193693400_usaf236-B5","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1007\/978-1-62703-748-8_7","article-title":"Introduction to machine learning","volume":"1107","author":"Ba\u015ftanlar","year":"2014","journal-title":"Methods Mol Biol"},{"key":"2025092002193693400_usaf236-B6","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1167\/tvst.9.2.14","article-title":"Introduction to machine learning, neural networks, and deep learning","volume":"9","author":"Choi","year":"2020","journal-title":"Transl Vis Sci Technol"},{"key":"2025092002193693400_usaf236-B7","doi-asserted-by":"publisher","first-page":"1920","DOI":"10.1161\/CIRCULATIONAHA.115.001593","article-title":"Machine learning in medicine","volume":"132","author":"Deo","year":"2015","journal-title":"Circulation"},{"key":"2025092002193693400_usaf236-B8","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1186\/s12938-020-00767-2","article-title":"Machine learning applied to retinal image processing for glaucoma detection: review and perspective","volume":"19","author":"Barros","year":"2020","journal-title":"Biomed Eng Online"},{"key":"2025092002193693400_usaf236-B9","doi-asserted-by":"publisher","first-page":"4013","DOI":"10.1038\/s41598-024-54535-6","article-title":"Assessment of area and structural irregularity of retinal layers in diabetic retinopathy using machine learning and image processing techniques","volume":"14","author":"Riazi-Esfahani","year":"2024","journal-title":"Sci Rep"},{"key":"2025092002193693400_usaf236-B10","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1136\/bjophthalmol-2018-313173","article-title":"Artificial intelligence and deep learning in ophthalmology","volume":"103","author":"Ting","year":"2019","journal-title":"Br J Ophthalmol"},{"key":"2025092002193693400_usaf236-B11","doi-asserted-by":"publisher","first-page":"226","DOI":"10.1007\/s10916-018-1088-1","article-title":"Medical image analysis using convolutional neural networks: a review","volume":"42","author":"Anwar","year":"2018","journal-title":"J Med Syst"},{"key":"2025092002193693400_usaf236-B12","doi-asserted-by":"publisher","first-page":"407","DOI":"10.3233\/THC-202657","article-title":"Application of convolution neural network in medical image processing","volume":"29","author":"Liu","year":"2021","journal-title":"Technol Health Care"},{"key":"2025092002193693400_usaf236-B13","doi-asserted-by":"publisher","first-page":"781","DOI":"10.1007\/s13246-022-01143-1","article-title":"Retinal fundus image classification for diabetic retinopathy using SVM predictions","volume":"45","author":"Hardas","year":"2022","journal-title":"Phys Eng Sci Med"},{"key":"2025092002193693400_usaf236-B14","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1007\/s13246-013-0215-z","article-title":"A new automated assessment method for contrast-detail images by applying support vector machine and its robustness to nonlinear image processing","volume":"36","author":"Takei","year":"2013","journal-title":"Australas Phys Eng Sci Med"},{"key":"2025092002193693400_usaf236-B15","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1093\/bib\/5.4.328","article-title":"Biological applications of support vector machines","volume":"5","author":"Yang","year":"2004","journal-title":"Brief Bioinform"},{"key":"2025092002193693400_usaf236-B16","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1093\/milmed\/usz221","article-title":"Detection of retinal fibrosis in a rabbit model of penetrating eye injury","volume":"185","author":"Greene","year":"2020","journal-title":"Mil Med"},{"key":"2025092002193693400_usaf236-B17","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1007\/BF00142517","article-title":"The anatomical organization of the visual system of the rabbit","volume":"30","author":"Giolli","year":"1971","journal-title":"Doc Ophthalmol"},{"key":"2025092002193693400_usaf236-B18","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1016\/S0034-5288(18)31228-1","article-title":"Retinal vascular patterns in domestic animals","volume":"47","author":"De Schaepdrijver","year":"1989","journal-title":"Res Vet Sci."},{"key":"2025092002193693400_usaf236-B19","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1001\/archopht.1964.00970010109018","article-title":"The structure of human retinal vascular system","volume":"71","author":"Mutlu","year":"1964","journal-title":"Arch Ophthalmol"}],"container-title":["Military Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/milmed\/article-pdf\/190\/Supplement_2\/471\/64288218\/usaf236.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/milmed\/article-pdf\/190\/Supplement_2\/471\/64288218\/usaf236.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T06:20:12Z","timestamp":1758349212000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/milmed\/article\/190\/Supplement_2\/471\/8256322"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,1]]},"references-count":19,"journal-issue":{"issue":"Supplement_2","published-online":{"date-parts":[[2025,9,16]]},"published-print":{"date-parts":[[2025,9,1]]}},"URL":"https:\/\/doi.org\/10.1093\/milmed\/usaf236","relation":{},"ISSN":["0026-4075","1930-613X"],"issn-type":[{"type":"print","value":"0026-4075"},{"type":"electronic","value":"1930-613X"}],"subject":[],"published-other":{"date-parts":[[2025,9]]},"published":{"date-parts":[[2025,9,1]]}}}