{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T13:32:18Z","timestamp":1770816738765,"version":"3.50.1"},"reference-count":37,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T00:00:00Z","timestamp":1770163200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>This study examines the efficacy of phasor analysis in distinguishing between healthy and diseased retinas using multispectral imaging data together with machine learning approaches. Our results demonstrate that phasor analysis of multispectral images surpasses average reflectance values in classification performance, serving as an effective dimensionality reduction technique to extract essential features, with the first harmonic yielding optimal results when paired with Z-score normalization. To compare the effectiveness of multispectral images with that of a conventional color fundus camera, we extracted three spectral bands corresponding to the red, green, and blue regions and combined them to create RGB-like images, which were then subjected to the same analysis. Our study found that phasor analysis of multispectral images provided more accurate classification results than phasor analysis of RGB-like images. An examination of different regions of interest showed that using the entire retina yields the best classification performance, likely due to the advanced stage of the diseases, which had progressed to affect the entire fundus. Our findings suggest that phasor analysis of multispectral images and machine learning are a powerful tools for retinal disease classification.<\/jats:p>","DOI":"10.3390\/s26031021","type":"journal-article","created":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T14:55:11Z","timestamp":1770216911000},"page":"1021","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Comprehensive and Region-Specific Retinal Health Assessment Using Phasor Analysis of Multispectral Images and Machine Learning"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-6204-2600","authenticated-orcid":false,"given":"Armin","family":"Eskandarinasab","sequence":"first","affiliation":[{"name":"Center for Sensors, Instruments and Systems Development (CD6), Universitat Polit\u00e8cnica de Catalunya (UPC), Rambla Sant Nebridi 10, 08222 Terrassa, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6305-0609","authenticated-orcid":false,"given":"Laura","family":"Rey-Barroso","sequence":"additional","affiliation":[{"name":"Center for Sensors, Instruments and Systems Development (CD6), Universitat Polit\u00e8cnica de Catalunya (UPC), Rambla Sant Nebridi 10, 08222 Terrassa, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3749-6850","authenticated-orcid":false,"given":"Francisco J.","family":"Burgos-Fern\u00e1ndez","sequence":"additional","affiliation":[{"name":"Center for Sensors, Instruments and Systems Development (CD6), Universitat Polit\u00e8cnica de Catalunya (UPC), Rambla Sant Nebridi 10, 08222 Terrassa, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8166-1617","authenticated-orcid":false,"given":"Meritxell","family":"Vilaseca","sequence":"additional","affiliation":[{"name":"Center for Sensors, Instruments and Systems Development (CD6), Universitat Polit\u00e8cnica de Catalunya (UPC), Rambla Sant Nebridi 10, 08222 Terrassa, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,2,4]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"4828","DOI":"10.1038\/s41467-021-25138-w","article-title":"Automatic detection of 39 fundus diseases and conditions in retinal photographs using deep neural networks","volume":"12","author":"Cen","year":"2021","journal-title":"Nat. Commun."},{"key":"ref_2","first-page":"1079","article-title":"Development and evaluation of a deep learning model for the detection of multiple fundus diseases based on colour fundus photography","volume":"106","author":"Li","year":"2022","journal-title":"Br. J. Ophthalmol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"957","DOI":"10.31577\/cai_2021_5_957","article-title":"Detection of macula and recognition of aged-related macular degeneration in retinal fundus images","volume":"40","author":"Maqsood","year":"2021","journal-title":"Comput. Inform."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"2211","DOI":"10.1001\/jama.2017.18152","article-title":"Development and validation of a deep learning system for diabetic retinopathy and related eye diseases using retinal images from multiethnic populations with diabetes","volume":"318","author":"Ting","year":"2017","journal-title":"JAMA"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1167\/tvst.8.6.4","article-title":"Automatic detection of diabetic retinopathy in retinal fundus photographs based on deep learning algorithm","volume":"8","author":"Li","year":"2019","journal-title":"Transl. Vis. Sci. Technol."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"667","DOI":"10.1038\/s41433-024-03135-9","article-title":"Hyperspectral retinal imaging biomarkers of ocular and systemic diseases","volume":"39","author":"Saeed","year":"2025","journal-title":"Eye"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Lee, N., Wielaard, J., Fawzi, A., Sajda, P., Laine, A., Martin, G., Humayun, M., and Smith, R. (2010). In vivo snapshot hyperspectral image analysis of age-related macular degeneration. Proceedings of the 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology, IEEE.","DOI":"10.1109\/IEMBS.2010.5626463"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"134","DOI":"10.3928\/23258160-20160126-06","article-title":"Imaging of melanin disruption in age-related macular degeneration using multispectral imaging","volume":"47","author":"Dugel","year":"2016","journal-title":"Ophthalmic Surg. Lasers Imaging Retin."},{"key":"ref_9","unstructured":"Banupriya, V., and Anusuya, S. (2023). Improving classification of retinal fundus image using flow dynamics optimized deep learning methods. arXiv."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1701","DOI":"10.1097\/IAE.0000000000002225","article-title":"Evaluation of multispectral imaging in diagnosing diabetic retinopathy","volume":"39","author":"Li","year":"2019","journal-title":"Retina"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"2851","DOI":"10.1167\/iovs.10-6217","article-title":"Validation of human whole blood oximetry, using a hyperspectral fundus camera with a model eye","volume":"52","author":"Mordant","year":"2011","journal-title":"Investig. Ophthalmol. Vis. Sci."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1097\/IIO.0000000000000139","article-title":"Hyperspectral image mapping spectrometry for retinal oximetry measurements in four diseased eyes","volume":"56","author":"Dwight","year":"2016","journal-title":"Int. Ophthalmol. Clin."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"330","DOI":"10.1016\/j.exer.2016.04.001","article-title":"Preliminary investigation of multispectral retinal tissue oximetry mapping using a hyperspectral retinal camera","volume":"146","author":"Desjardins","year":"2016","journal-title":"Exp. Eye Res."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"4227","DOI":"10.1038\/s41467-019-12242-1","article-title":"Non-invasive in vivo hyperspectral imaging of the retina for potential biomarker use in Alzheimer\u2019s disease","volume":"10","author":"Hadoux","year":"2019","journal-title":"Nat. Commun."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1186\/s40478-024-01868-y","article-title":"Hyperspectral retinal imaging in Alzheimer\u2019s disease and age-related macular degeneration: A review","volume":"12","author":"Du","year":"2024","journal-title":"Acta Neuropathol. Commun."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1186\/s13195-025-01887-4","article-title":"Hyperspectral retinal imaging to detect Alzheimer\u2019s disease in a memory clinic setting","volume":"17","author":"Dallora","year":"2025","journal-title":"Alzheimer\u2019s Res. Ther."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"306","DOI":"10.1021\/cn500242z","article-title":"Hyperspectral imaging signatures detect amyloidopathy in Alzheimer\u2019s mouse retina well before onset of cognitive decline","volume":"6","author":"More","year":"2015","journal-title":"ACS Chem. Neurosci."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Lin, W.S., Chen, C.L., Liang, S.W., and Wang, H.C. (2025). Dementia Detection via Retinal Hyperspectral Imaging and Deep Learning: Clinical Dataset Analysis and Comparative Evaluation of Multiple Architectures. Bioengineering, 12.","DOI":"10.3390\/bioengineering12121362"},{"key":"ref_19","first-page":"096007","article-title":"Fast visible and extended near-infrared multispectral fundus camera","volume":"24","author":"Alterini","year":"2019","journal-title":"J. Biomed. Opt."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"2482","DOI":"10.1364\/BOE.563950","article-title":"Development of a multispectral imaging apparatus for cost-effective fundus disease detection","volume":"16","author":"Shi","year":"2025","journal-title":"Biomed. Opt. Express"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"L14","DOI":"10.1529\/biophysj.107.120154","article-title":"The phasor approach to fluorescence lifetime imaging analysis","volume":"94","author":"Digman","year":"2008","journal-title":"Biophys. J."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"047001","DOI":"10.1088\/2050-6120\/3\/4\/047001","article-title":"Model-free methods to study membrane environmental probes: A comparison of the spectral phasor and generalized polarization approaches","volume":"3","author":"Malacrida","year":"2015","journal-title":"Methods Appl. Fluoresc."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"e2315043121","DOI":"10.1073\/pnas.2315043121","article-title":"METAPHOR: Metabolic evaluation through phasor-based hyperspectral imaging and organelle recognition for mouse blastocysts and oocytes","volume":"121","author":"Parra","year":"2024","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1186\/s13195-022-00983-z","article-title":"Comparative analysis of machine learning algorithms for multi-syndrome classification of neurodegenerative syndromes","volume":"14","author":"Lampe","year":"2022","journal-title":"Alzheimer\u2019s Res. Ther."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"3504","DOI":"10.1364\/BOE.457412","article-title":"Reflectance evaluation of eye fundus structures with a visible and near-infrared multispectral camera","volume":"13","author":"Alterini","year":"2022","journal-title":"Biomed. Opt. Express"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1038\/nmeth.4134","article-title":"Hyperspectral phasor analysis enables multiplexed 5D in vivo imaging","volume":"14","author":"Cutrale","year":"2017","journal-title":"Nat. Methods"},{"key":"ref_27","unstructured":"Goldberger, J., Hinton, G.E., Roweis, S., and Salakhutdinov, R.R. (2004, January 13\u201318). Neighbourhood components analysis. Proceedings of the Annual Conference on Neural Information Processing Systems, Vancouver, BC, Canada."},{"key":"ref_28","unstructured":"Rennie, J.D., Shih, L., Teevan, J., and Karger, D.R. (2003). Tackling the poor assumptions of naive bayes text classifiers. Proceedings of the 20th International Conference on Machine Learning (ICML-03), AAAI Press."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"27:1","DOI":"10.1145\/1961189.1961199","article-title":"LIBSVM: A library for support vector machines","volume":"2","author":"Chang","year":"2011","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1207","DOI":"10.1162\/089976600300015565","article-title":"New support vector algorithms","volume":"12","author":"Smola","year":"2000","journal-title":"Neural Comput."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1016\/j.ipm.2009.03.002","article-title":"A systematic analysis of performance measures for classification tasks","volume":"45","author":"Sokolova","year":"2009","journal-title":"Inf. Process. Manag."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"471","DOI":"10.1093\/biomet\/24.3-4.471","article-title":"Certain generalizations in the analysis of variance","volume":"24","author":"Wilks","year":"1932","journal-title":"Biometrika"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"12729","DOI":"10.1364\/OE.20.012729","article-title":"Spectral phasor analysis allows rapid and reliable unmixing of fluorescence microscopy spectral images","volume":"20","author":"Fereidouni","year":"2012","journal-title":"Opt. Express"},{"key":"ref_34","first-page":"101956","article-title":"Applying first & second harmonic spectral phasor analysis on a single-wavelength calcium fluorophore","volume":"41","author":"Lingotti","year":"2025","journal-title":"Biochem. Biophys. Rep."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Rey-Barroso, L., Vilaseca, M., Royo, S., D\u00edaz-Dout\u00f3n, F., Lihacova, I., Bondarenko, A., and Burgos-Fern\u00e1ndez, F.J. (2025). Training state-of-the-art deep learning algorithms with visible and extended near-infrared multispectral images of skin lesions for the improvement of skin cancer diagnosis. Diagnostics, 15.","DOI":"10.3390\/diagnostics15030355"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"3195","DOI":"10.1364\/BOE.386338","article-title":"Hyperspectral and multispectral imaging in digital and computational pathology: A systematic review","volume":"11","author":"Ortega","year":"2020","journal-title":"Biomed. Opt. Express"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"914","DOI":"10.1364\/BOE.10.000914","article-title":"Drusen diagnosis comparison between hyper-spectral and color retinal images","volume":"10","author":"Wang","year":"2019","journal-title":"Biomed. Opt. Express"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/3\/1021\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T05:33:40Z","timestamp":1770788020000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/3\/1021"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,4]]},"references-count":37,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["s26031021"],"URL":"https:\/\/doi.org\/10.3390\/s26031021","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,4]]}}}