{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T11:38:37Z","timestamp":1777289917180,"version":"3.51.4"},"reference-count":16,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2025,2,18]],"date-time":"2025-02-18T00:00:00Z","timestamp":1739836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"the Doctoral Scholarship of the Portuguese Ophthalmology Society","award":["UIDB\/00319\/2020"],"award-info":[{"award-number":["UIDB\/00319\/2020"]}]},{"name":"the project Advanced Computing Project 2024.AIVLAB. 00008.VISION","award":["UIDB\/00319\/2020"],"award-info":[{"award-number":["UIDB\/00319\/2020"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Applied Sciences"],"abstract":"<jats:p>Inherited retinal diseases (IRDs) are genetic disorders affecting photoreceptors and the retinal pigment epithelium, leading to progressive vision loss. Retinitis pigmentosa (RP), the most common IRD, manifests as night blindness, peripheral vision loss, and eventually central vision decline. RP is genetically diverse and can be categorized into non-syndromic and syndromic. Advanced imaging technologies such as fundus autofluorescence (FAF) and spectral-domain optical coherence tomography (SD-OCT) facilitate diagnosing and managing these conditions. The integration of artificial intelligence in analyzing retinal images has shown promise in identifying genes associated with RP. This study used a dataset from Portuguese public hospitals, comprising 2798 FAF images labeled for syndromic and non-syndromic RP across 66 genes. Three pre-trained models, Inception-v3, ResNet-50, and VGG-19, were used to classify these images, obtaining an accuracy of over 80% in the training data and 54%, 56%, and 54% in the test data for all models. Data preprocessing included class balancing and boosting to address variability in gene representation. Model performance was evaluated using some main metrics. The findings demonstrate the effectiveness of deep learning in automatically classifying retinal images for different RP-associated genes, marking a significant advancement in the diagnostic capabilities of artificial intelligence and advanced imaging techniques in IRD.<\/jats:p>","DOI":"10.3390\/app15042181","type":"journal-article","created":{"date-parts":[[2025,2,18]],"date-time":"2025-02-18T12:16:37Z","timestamp":1739880997000},"page":"2181","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Retinitis Pigmentosa Classification with Deep Learning and Integrated Gradients Analysis"],"prefix":"10.3390","volume":"15","author":[{"given":"H\u00e9lder","family":"Ferreira","sequence":"first","affiliation":[{"name":"School Sciences and Technologies, Universidade de Tr\u00e1s-os-Montes e Alto Douro, 5000-801 Vila Real, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3495-4649","authenticated-orcid":false,"given":"Ana","family":"Marta","sequence":"additional","affiliation":[{"name":"Department of Department of Ophthalmology, Unidade Local de Sa\u00fade de Santo Ant\u00f3nio, 4099-001 Porto, Portugal"},{"name":"Instituto de Ci\u00eancias Biom\u00e9dicas Abel Salazar (ICBAS), 4050-313 Porto, Portugal"}]},{"given":"Jorge","family":"Machado","sequence":"additional","affiliation":[{"name":"School Sciences and Technologies, Universidade de Tr\u00e1s-os-Montes e Alto Douro, 5000-801 Vila Real, Portugal"},{"name":"Department of Sciences and Technologies, Universidade Aberta, 1269-001 Lisboa, Portugal"}]},{"given":"In\u00eas","family":"Couto","sequence":"additional","affiliation":[{"name":"Department of Department of Ophthalmology, Unidade Local de Sa\u00fade de Santo Ant\u00f3nio, 4099-001 Porto, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1014-0483","authenticated-orcid":false,"given":"Jo\u00e3o Pedro","family":"Marques","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Hospital da Universidade de Coimbra, Unidade Local de Sa\u00fade de Coimbra, 3004-561 Coimbra, Portugal"},{"name":"Clinical and Academic Center of Coimbra (CACC), 3000-075 Coimbra, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8642-7010","authenticated-orcid":false,"given":"Jo\u00e3o Melo","family":"Beir\u00e3o","sequence":"additional","affiliation":[{"name":"Department of Department of Ophthalmology, Unidade Local de Sa\u00fade de Santo Ant\u00f3nio, 4099-001 Porto, Portugal"},{"name":"Instituto de Ci\u00eancias Biom\u00e9dicas Abel Salazar (ICBAS), 4050-313 Porto, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3458-7693","authenticated-orcid":false,"given":"Ant\u00f3nio","family":"Cunha","sequence":"additional","affiliation":[{"name":"School Sciences and Technologies, Universidade de Tr\u00e1s-os-Montes e Alto Douro, 5000-801 Vila Real, Portugal"},{"name":"ALGORITMI Research Centre, University of Minho, 4800-058 Guimar\u00e3es, Portugal"}]}],"member":"1968","published-online":{"date-parts":[[2025,2,18]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Hansen, S., McClements, M.E., Corydon, T.J., and MacLaren, R.E. (2023). Future perspectives of prime editing for the treatment of inherited retinal diseases. Cells, 12.","DOI":"10.3390\/cells12030440"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1016\/j.preteyeres.2018.03.005","article-title":"Non-syndromic retinitis pigmentosa","volume":"66","author":"Verbakel","year":"2018","journal-title":"Prog. Retin. Eye Res."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1001\/jamaophthalmol.2022.6254","article-title":"Changes in retinal sensitivity associated with cotoretigene toliparvovec in X-linked retinitis pigmentosa with RPGR gene variations","volume":"141","author":"Liu","year":"2023","journal-title":"JAMA Ophthalmol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1883","DOI":"10.1007\/s00417-023-06360-2","article-title":"Genetic profile of syndromic retinitis pigmentosa in Portugal","volume":"262","author":"Cortinhal","year":"2024","journal-title":"Graefes. Arch. Clin. Exp. Ophthalmol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1016\/0002-9394(88)90242-5","article-title":"Clinical findings and common symptoms in retinitis pigmentosa","volume":"105","author":"Heckenlively","year":"1988","journal-title":"Am. J. Ophthalmol."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"238","DOI":"10.2174\/138920211795860107","article-title":"Retinitis pigmentosa: Genes and disease mechanisms","volume":"12","author":"Ferrari","year":"2011","journal-title":"Curr. Genom."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1111\/cge.12203","article-title":"Genes and mutations causing retinitis pigmentosa","volume":"84","author":"Daiger","year":"2013","journal-title":"Clin. Genet."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1018","DOI":"10.1007\/s00417-005-1186-x","article-title":"Abnormal fundus autofluorescence in relation to retinal function in patients with retinitis pigmentosa","volume":"243","author":"Hawlina","year":"2005","journal-title":"Graefe\u2019s Arch. Clin. Exp. Ophthalmol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1827","DOI":"10.1016\/j.ophtha.2013.01.050","article-title":"Wide-field fundus autofluorescence imaging of retinitis pigmentosa","volume":"120","author":"Oishi","year":"2013","journal-title":"Ophthalmology"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1016\/j.neucom.2018.04.065","article-title":"Learning-based approach to segment pigment signs in fundus images for retinitis pigmentosa analysis","volume":"308","author":"Brancati","year":"2018","journal-title":"Neurocomputing"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Pontikos, N., Woof, W., Krawitz, P., Arno, G., Hess, K., Varela, M.D., Liefers, B., Guimaraes, T., Shah, M., and Madhusudhan, S. (2022). Eye2Gene: Prediction of causal inherited retinal disease gene from multimodal imaging using AI. Investig. Ophthalmol. Vis. Sci., 63.","DOI":"10.21203\/rs.3.rs-2110140\/v1"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"345","DOI":"10.2337\/diacare.23.3.345","article-title":"A telemedical approach to the screening of diabetic retinopathy: Digital fundus photography","volume":"23","author":"Liesenfeld","year":"2000","journal-title":"Diabetes Care"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"660","DOI":"10.1097\/IAE.0000000000000937","article-title":"Ultra-widefield fundus imaging: A review of clinical applications and future trends","volume":"36","author":"Nagiel","year":"2016","journal-title":"Retina"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Kapishnikov, A., Venugopalan, S., Avci, B., Wedin, B., Terry, M., and Bolukbasi, T. (2021, January 20\u201325). Guided integrated gradients: An adaptive path method for removing noise. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.00501"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Mujahid, M., Rustam, F., \u00c1lvarez, R., Luis Vidal Maz\u00f3n, J., D\u00edez, I.D.L.T., and Ashraf, I. (2022). Pneumonia classification from X-ray images with inception-V3 and convolutional neural network. Diagnostics, 12.","DOI":"10.3390\/diagnostics12051280"},{"key":"ref_16","unstructured":"Raschka, S. (2018). Model evaluation, model selection, and algorithm selection in machine learning. arXiv."}],"container-title":["Applied Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2076-3417\/15\/4\/2181\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T16:37:09Z","timestamp":1760027829000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2076-3417\/15\/4\/2181"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,18]]},"references-count":16,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,2]]}},"alternative-id":["app15042181"],"URL":"https:\/\/doi.org\/10.3390\/app15042181","relation":{},"ISSN":["2076-3417"],"issn-type":[{"value":"2076-3417","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,18]]}}}