Discrimination of multiple sclerosis using scanning laser ophthalmoscopy images with autoencoder-based feature extraction
Optical coherence tomography (OCT) investigations have revealed that the thickness of inner retinal layers becomes decreased in multiple sclerosis (MS) patients, compared to healthy control (HC) individuals. To date, a number of studies have applied machine learning to OCT thickness measurements, ai...
Uloženo v:
| Vydáno v: | Multiple sclerosis and related disorders Ročník 88; s. 105743 |
|---|---|
| Hlavní autoři: | , , , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Netherlands
Elsevier B.V
01.08.2024
|
| Témata: | |
| ISSN: | 2211-0348, 2211-0356, 2211-0356 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Optical coherence tomography (OCT) investigations have revealed that the thickness of inner retinal layers becomes decreased in multiple sclerosis (MS) patients, compared to healthy control (HC) individuals. To date, a number of studies have applied machine learning to OCT thickness measurements, aiming to enable accurate and automated diagnosis of the disease. However, there have much less emphasis on other less common retinal imaging modalities, like infrared scanning laser ophthalmoscopy (IR-SLO), for classifying MS. IR-SLO uses laser light to capture high-resolution fundus images, often performed in conjunction with OCT to lock B-scans at a fixed position.
We incorporated two independent datasets of IR-SLO images from the Isfahan and Johns Hopkins centers, consisting of 164 MS and 150 HC images. A subject-wise data splitting approach was employed to ensure that there was no leakage between training and test datasets. Several state-of-the-art convolutional neural networks (CNNs), including VGG-16, VGG-19, ResNet-50, and InceptionV3, and a CNN with a custom architecture were employed. In the next step, we designed a convolutional autoencoder (CAE) to extract semantic features subsequently given as inputs to four conventional ML classifiers, including support vector machine (SVM), k-nearest neighbor (K-NN), random forest (RF), and multi-layer perceptron (MLP).
The custom CNN (85 % accuracy, 85 % sensitivity, 87 % specificity, 93 % area under the receiver operating characteristics [AUROC], and 94 % area under the precision-recall curve [AUPRC]) outperformed state-of-the-art models (84 % accuracy, 83 % sensitivity, 87 % specificity, 92 % AUROC, and 94 % AUPRC); however, utilizing a combination of the CAE and MLP yields even superior results (88 % accuracy, 86 % sensitivity, 91 % specificity, 94 % AUROC, and 95 % AUPRC).
We utilized IR-SLO images to differentiate between MS and HC eyes, with promising results achieved using a combination of CAE and MLP. Future multi-center studies involving more heterogenous data are necessary to assess the feasibility of integrating IR-SLO images into routine clinical practice. |
|---|---|
| AbstractList | Optical coherence tomography (OCT) investigations have revealed that the thickness of inner retinal layers becomes decreased in multiple sclerosis (MS) patients, compared to healthy control (HC) individuals. To date, a number of studies have applied machine learning to OCT thickness measurements, aiming to enable accurate and automated diagnosis of the disease. However, there have much less emphasis on other less common retinal imaging modalities, like infrared scanning laser ophthalmoscopy (IR-SLO), for classifying MS. IR-SLO uses laser light to capture high-resolution fundus images, often performed in conjunction with OCT to lock B-scans at a fixed position.
We incorporated two independent datasets of IR-SLO images from the Isfahan and Johns Hopkins centers, consisting of 164 MS and 150 HC images. A subject-wise data splitting approach was employed to ensure that there was no leakage between training and test datasets. Several state-of-the-art convolutional neural networks (CNNs), including VGG-16, VGG-19, ResNet-50, and InceptionV3, and a CNN with a custom architecture were employed. In the next step, we designed a convolutional autoencoder (CAE) to extract semantic features subsequently given as inputs to four conventional ML classifiers, including support vector machine (SVM), k-nearest neighbor (K-NN), random forest (RF), and multi-layer perceptron (MLP).
The custom CNN (85 % accuracy, 85 % sensitivity, 87 % specificity, 93 % area under the receiver operating characteristics [AUROC], and 94 % area under the precision-recall curve [AUPRC]) outperformed state-of-the-art models (84 % accuracy, 83 % sensitivity, 87 % specificity, 92 % AUROC, and 94 % AUPRC); however, utilizing a combination of the CAE and MLP yields even superior results (88 % accuracy, 86 % sensitivity, 91 % specificity, 94 % AUROC, and 95 % AUPRC).
We utilized IR-SLO images to differentiate between MS and HC eyes, with promising results achieved using a combination of CAE and MLP. Future multi-center studies involving more heterogenous data are necessary to assess the feasibility of integrating IR-SLO images into routine clinical practice. AbstractObjectiveOptical coherence tomography (OCT) investigations have revealed that the thickness of inner retinal layers becomes decreased in multiple sclerosis (MS) patients, compared to healthy control (HC) individuals. To date, a number of studies have applied machine learning to OCT thickness measurements, aiming to enable accurate and automated diagnosis of the disease. However, there have much less emphasis on other less common retinal imaging modalities, like infrared scanning laser ophthalmoscopy (IR-SLO), for classifying MS. IR-SLO uses laser light to capture high-resolution fundus images, often performed in conjunction with OCT to lock B-scans at a fixed position. MethodsWe incorporated two independent datasets of IR-SLO images from the Isfahan and Johns Hopkins centers, consisting of 164 MS and 150 HC images. A subject-wise data splitting approach was employed to ensure that there was no leakage between training and test datasets. Several state-of-the-art convolutional neural networks (CNNs), including VGG-16, VGG-19, ResNet-50, and InceptionV3, and a CNN with a custom architecture were employed. In the next step, we designed a convolutional autoencoder (CAE) to extract semantic features subsequently given as inputs to four conventional ML classifiers, including support vector machine (SVM), k-nearest neighbor (K-NN), random forest (RF), and multi-layer perceptron (MLP). ResultsThe custom CNN (85 % accuracy, 85 % sensitivity, 87 % specificity, 93 % area under the receiver operating characteristics [AUROC], and 94 % area under the precision-recall curve [AUPRC]) outperformed state-of-the-art models (84 % accuracy, 83 % sensitivity, 87 % specificity, 92 % AUROC, and 94 % AUPRC); however, utilizing a combination of the CAE and MLP yields even superior results (88 % accuracy, 86 % sensitivity, 91 % specificity, 94 % AUROC, and 95 % AUPRC). ConclusionsWe utilized IR-SLO images to differentiate between MS and HC eyes, with promising results achieved using a combination of CAE and MLP. Future multi-center studies involving more heterogenous data are necessary to assess the feasibility of integrating IR-SLO images into routine clinical practice. Optical coherence tomography (OCT) investigations have revealed that the thickness of inner retinal layers becomes decreased in multiple sclerosis (MS) patients, compared to healthy control (HC) individuals. To date, a number of studies have applied machine learning to OCT thickness measurements, aiming to enable accurate and automated diagnosis of the disease. However, there have much less emphasis on other less common retinal imaging modalities, like infrared scanning laser ophthalmoscopy (IR-SLO), for classifying MS. IR-SLO uses laser light to capture high-resolution fundus images, often performed in conjunction with OCT to lock B-scans at a fixed position.OBJECTIVEOptical coherence tomography (OCT) investigations have revealed that the thickness of inner retinal layers becomes decreased in multiple sclerosis (MS) patients, compared to healthy control (HC) individuals. To date, a number of studies have applied machine learning to OCT thickness measurements, aiming to enable accurate and automated diagnosis of the disease. However, there have much less emphasis on other less common retinal imaging modalities, like infrared scanning laser ophthalmoscopy (IR-SLO), for classifying MS. IR-SLO uses laser light to capture high-resolution fundus images, often performed in conjunction with OCT to lock B-scans at a fixed position.We incorporated two independent datasets of IR-SLO images from the Isfahan and Johns Hopkins centers, consisting of 164 MS and 150 HC images. A subject-wise data splitting approach was employed to ensure that there was no leakage between training and test datasets. Several state-of-the-art convolutional neural networks (CNNs), including VGG-16, VGG-19, ResNet-50, and InceptionV3, and a CNN with a custom architecture were employed. In the next step, we designed a convolutional autoencoder (CAE) to extract semantic features subsequently given as inputs to four conventional ML classifiers, including support vector machine (SVM), k-nearest neighbor (K-NN), random forest (RF), and multi-layer perceptron (MLP).METHODSWe incorporated two independent datasets of IR-SLO images from the Isfahan and Johns Hopkins centers, consisting of 164 MS and 150 HC images. A subject-wise data splitting approach was employed to ensure that there was no leakage between training and test datasets. Several state-of-the-art convolutional neural networks (CNNs), including VGG-16, VGG-19, ResNet-50, and InceptionV3, and a CNN with a custom architecture were employed. In the next step, we designed a convolutional autoencoder (CAE) to extract semantic features subsequently given as inputs to four conventional ML classifiers, including support vector machine (SVM), k-nearest neighbor (K-NN), random forest (RF), and multi-layer perceptron (MLP).The custom CNN (85 % accuracy, 85 % sensitivity, 87 % specificity, 93 % area under the receiver operating characteristics [AUROC], and 94 % area under the precision-recall curve [AUPRC]) outperformed state-of-the-art models (84 % accuracy, 83 % sensitivity, 87 % specificity, 92 % AUROC, and 94 % AUPRC); however, utilizing a combination of the CAE and MLP yields even superior results (88 % accuracy, 86 % sensitivity, 91 % specificity, 94 % AUROC, and 95 % AUPRC).RESULTSThe custom CNN (85 % accuracy, 85 % sensitivity, 87 % specificity, 93 % area under the receiver operating characteristics [AUROC], and 94 % area under the precision-recall curve [AUPRC]) outperformed state-of-the-art models (84 % accuracy, 83 % sensitivity, 87 % specificity, 92 % AUROC, and 94 % AUPRC); however, utilizing a combination of the CAE and MLP yields even superior results (88 % accuracy, 86 % sensitivity, 91 % specificity, 94 % AUROC, and 95 % AUPRC).We utilized IR-SLO images to differentiate between MS and HC eyes, with promising results achieved using a combination of CAE and MLP. Future multi-center studies involving more heterogenous data are necessary to assess the feasibility of integrating IR-SLO images into routine clinical practice.CONCLUSIONSWe utilized IR-SLO images to differentiate between MS and HC eyes, with promising results achieved using a combination of CAE and MLP. Future multi-center studies involving more heterogenous data are necessary to assess the feasibility of integrating IR-SLO images into routine clinical practice. |
| ArticleNumber | 105743 |
| Author | Kafieh, Raheleh Arian, Roya Soltanipour, Asieh Aghababaei, Ali Ashtari, Fereshteh Rabbani, Hossein |
| Author_xml | – sequence: 1 givenname: Ali surname: Aghababaei fullname: Aghababaei, Ali organization: Medical Image and Signal Processing Research Center, Isfahan University of Medical Sciences, Isfahan, Iran – sequence: 2 givenname: Roya surname: Arian fullname: Arian, Roya organization: Medical Image and Signal Processing Research Center, Isfahan University of Medical Sciences, Isfahan, Iran – sequence: 3 givenname: Asieh surname: Soltanipour fullname: Soltanipour, Asieh organization: Medical Image and Signal Processing Research Center, Isfahan University of Medical Sciences, Isfahan, Iran – sequence: 4 givenname: Fereshteh surname: Ashtari fullname: Ashtari, Fereshteh organization: Isfahan Neurosciences Research Center, Isfahan University of Medical Sciences, Isfahan, Iran – sequence: 5 givenname: Hossein surname: Rabbani fullname: Rabbani, Hossein organization: Medical Image and Signal Processing Research Center, Isfahan University of Medical Sciences, Isfahan, Iran – sequence: 6 givenname: Raheleh orcidid: 0000-0003-0087-9476 surname: Kafieh fullname: Kafieh, Raheleh email: raheleh.kafieh@durham.ac.uk organization: Department of Engineering, Durham University, South Road, Durham, UK |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/38945032$$D View this record in MEDLINE/PubMed |
| BookMark | eNqFkl1rFDEUhoO02Fr7CwTJpTez5ms-FlEo9aOFghfqdcgkZ7pZM8mYZNT992a6bS8KsoGQk_C-53CekxfoyAcPCL2iZEUJbd5uV2NS0awYYaK81K3gz9ApY5RWhNfN0WMsuhN0ntKWlNXUVDT0OTrh3VrUhLNTtPtok452tF5lGzwOAx5nl-3kACftIIZkE56T9bflrrxfAqcSRBymTd4oN4akw7TDdlS3kPAfmzdYzTmA18FArPoiNngAlecIGP7mqPRS6iU6HpRLcH5_nqEfnz99v7yqbr5-ub68uKl0TWmu-NoMbc_auhODqQ1r-l7wslvW143QHR2MaHXPNOWs452CRd3wwRjT9W1H-Rl6s887xfBrhpTlWFoG55SHMCfJSSuKd921Rfr6Xjr3Ixg5FTAq7uQDriLge4EuXFKE4VFCiVzmIrfybi5ymYvcz6W41k9c2uY73IWFdQe87_deKIh-W4gyaVvQgrERdJYm2AP-D0_82llvtXI_YQdpG-boC31JZWKSyG_Lr1k-DROkNEwWfO_-n-Bg-X9tqtUe |
| CitedBy_id | crossref_primary_10_3390_bioengineering12080847 crossref_primary_10_3390_jcm14072166 crossref_primary_10_1016_j_cosrev_2025_100821 |
| Cites_doi | 10.1002/brb3.2302 10.1016/j.msard.2023.104725 10.1177/1352458517750009 10.3390/s19235323 10.1186/s12874-019-0681-4 10.1007/s42979-021-00592-x 10.3109/08820538.2013.810277 10.1093/brain/awaa427 10.1016/j.msard.2020.102625 10.1016/j.compbiomed.2020.104165 10.1038/nature14539 10.1007/s11263-019-01228-7 10.1016/j.neucom.2019.10.118 10.3390/s22010167 10.1371/journal.pone.0216410 10.1001/archopht.1982.01030030137016 10.1016/j.dib.2018.12.073 10.1080/01616412.2020.1726585 10.1136/bjophthalmol-2020-317659 10.1016/S1474-4422(17)30470-2 10.1007/s10439-022-02930-3 10.1017/9781108860604 10.21105/joss.00861 10.1016/S1474-4422(17)30278-8 10.1016/j.msard.2023.104846 10.1145/3292500.3330701 10.1177/1352458519845116 10.1136/bjophthalmol-2017-310477 10.1109/CVPR.2016.308 10.1016/j.compbiomed.2021.104416 10.1371/journal.pone.0289495 10.3390/photonics10030234 10.1177/13524585221112605 10.1212/WNL.0000000000200883 10.1111/aos.12156 10.1109/ACCESS.2020.3041291 10.1002/wics.101 10.1214/aoms/1177703732 |
| ContentType | Journal Article |
| Copyright | 2024 The Author(s) The Author(s) Copyright © 2024 The Author(s). Published by Elsevier B.V. All rights reserved. |
| Copyright_xml | – notice: 2024 The Author(s) – notice: The Author(s) – notice: Copyright © 2024 The Author(s). Published by Elsevier B.V. All rights reserved. |
| DBID | 6I. AAFTH AAYXX CITATION CGR CUY CVF ECM EIF NPM 7X8 |
| DOI | 10.1016/j.msard.2024.105743 |
| DatabaseName | ScienceDirect Open Access Titles Elsevier:ScienceDirect:Open Access CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic |
| DatabaseTitle | CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) MEDLINE - Academic |
| DatabaseTitleList | MEDLINE MEDLINE - Academic |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Medicine |
| EISSN | 2211-0356 |
| EndPage | 105743 |
| ExternalDocumentID | 38945032 10_1016_j_msard_2024_105743 S2211034824003201 1_s2_0_S2211034824003201 |
| Genre | Journal Article |
| GroupedDBID | --- --K --M .1- .FO .~1 0R~ 1P~ 1~. 1~5 4.4 457 4G. 53G 5VS 7-5 8P~ AAEDT AAEDW AAIKJ AAKOC AALRI AAOAW AAQFI AATTM AAXKI AAXLA AAXUO AAYWO ABBQC ABCQJ ABGSF ABJNI ABMAC ABMZM ABTEW ABUDA ABWVN ABXDB ACDAQ ACGFS ACIEU ACLOT ACRLP ACRPL ACVFH ADBBV ADCNI ADEZE ADMUD ADNMO ADUVX AEBSH AEHWI AEIPS AEKER AENEX AEUPX AEVXI AFJKZ AFPUW AFRHN AFTJW AFXIZ AGHFR AGUBO AGWIK AGYEJ AIEXJ AIGII AIIUN AIKHN AITUG AJRQY AJUYK AKBMS AKRWK AKYEP ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU ANZVX APXCP AXJTR BKOJK BLXMC BNPGV EBS EFJIC EFKBS EFLBG EJD FDB FEDTE FIRID FNPLU FYGXN GBLVA HVGLF HZ~ KOM M41 MO0 MOBAO O-L O9- OAUVE OP~ P-8 P-9 PC. Q38 ROL SDF SEL SPCBC SSH SSN SSU SSZ T5K Z5R ~G- ~HD AACTN AFKWA AJOXV AMFUW RIG 6I. AAFTH AAYXX CITATION AGCQF AGRNS CGR CUY CVF ECM EIF NPM 7X8 |
| ID | FETCH-LOGICAL-c511t-39df7b27584fd5d26bb43bb472b564c81fd47cb2c132838aef7b263fddd8b7813 |
| ISICitedReferencesCount | 3 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001284293200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 2211-0348 2211-0356 |
| IngestDate | Mon Sep 29 06:16:32 EDT 2025 Mon Jul 21 05:50:11 EDT 2025 Sat Nov 29 06:26:13 EST 2025 Tue Nov 18 21:49:06 EST 2025 Sat Aug 17 15:43:09 EDT 2024 Tue Feb 25 20:07:12 EST 2025 Tue Oct 14 19:33:39 EDT 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | false |
| IsScholarly | true |
| Keywords | Multiple Sclerosis Feature Extraction Optical Coherence Tomography Scanning Laser Ophthalmoscopy Machine Learning Deep Learning |
| Language | English |
| License | This is an open access article under the CC BY-NC license. Copyright © 2024 The Author(s). Published by Elsevier B.V. All rights reserved. |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c511t-39df7b27584fd5d26bb43bb472b564c81fd47cb2c132838aef7b263fddd8b7813 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| ORCID | 0000-0003-0087-9476 |
| OpenAccessLink | https://www.clinicalkey.es/playcontent/1-s2.0-S2211034824003201 |
| PMID | 38945032 |
| PQID | 3074132987 |
| PQPubID | 23479 |
| PageCount | 1 |
| ParticipantIDs | proquest_miscellaneous_3074132987 pubmed_primary_38945032 crossref_primary_10_1016_j_msard_2024_105743 crossref_citationtrail_10_1016_j_msard_2024_105743 elsevier_sciencedirect_doi_10_1016_j_msard_2024_105743 elsevier_clinicalkeyesjournals_1_s2_0_S2211034824003201 elsevier_clinicalkey_doi_10_1016_j_msard_2024_105743 |
| PublicationCentury | 2000 |
| PublicationDate | 2024-08-01 |
| PublicationDateYYYYMMDD | 2024-08-01 |
| PublicationDate_xml | – month: 08 year: 2024 text: 2024-08-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | Netherlands |
| PublicationPlace_xml | – name: Netherlands |
| PublicationTitle | Multiple sclerosis and related disorders |
| PublicationTitleAlternate | Mult Scler Relat Disord |
| PublicationYear | 2024 |
| Publisher | Elsevier B.V |
| Publisher_xml | – name: Elsevier B.V |
| References | Ortiz, Mallen, Boquete, Sánchez-Morla, Cordón, Vilades (bib0012) 2023; 74 Simonyan K., Zisserman A. Very Deep Convolutional Networks for Large-Scale Image Recognition [Internet]. arXiv; 2015 [cited 2023 May 16]. Available from Arian, Mahmoudi, Riazi-Esfahani, Faghihi, Mirshahi, Ghassemi, Khodabande, Kafieh, Khalili Pour (bib50) 2023; 10 Hernandez, Ramon-Julvez, Vilades, Cordon, Mayordomo, Garcia-Martin, Raafat (bib0008) 2023; 18 Ciftci Kavaklioglu, Erdman, Goldenberg, Kavaklioglu, Alexander, Oppermann (bib0017) 2022; 28 Garcia-Martin, Ortiz, Boquete, Sánchez-Morla, Barea, Cavaliere (bib0021) 2021; 129 Akiba T., Sano S., Yanase T., Ohta T., Koyama M. Optuna: A Next-Generation Hyperparameter Optimization Framework [Internet]. arXiv; 2019 [cited 2023 Jul 25]. Available from LeCun, Bengio, Hinton (bib0042) 2015; 521 Abdi, Williams (bib0034) 2010; 2 Szegedy C., Vanhoucke V., Ioffe S., Shlens J., Wojna Z. Rethinking the Inception Architecture For Computer Vision [Internet]. arXiv; 2015 [cited 2023 May 10]. Available from . Mehlig B. Machine Learning with Neural Networks: An Introduction for Scientists and Engineers [Internet]. 1st ed. Cambridge University Press; 2021 [cited 2024 Jun 22]. Available from Cervantes, Garcia-Lamont, Rodríguez-Mazahua, Lopez (bib0041) 2020; 408 Fischer, Otto, Delori, Pace, Staurenghi (bib0024) 2019 Feucht, Maier, Lepennetier, Pettenkofer, Wetzlmair, Daltrozzo (bib0045) 2019; 25 Pathak, Krahenbuhl, Donahue, Darrell, Efros (bib0043) 2016 Quigley, Addicks, Green (bib0044) 1960; 100 Petzold, Balcer, Calabresi, Costello, Frohman, Frohman (bib0003) 2017; 16 Ashtari, Ataei, Kafieh, Khodabandeh, Barzegar, Raei (bib0026) 2021; 47 Khodabandeh, Rabbani, Bidabadi, Bonyani, Kafieh (bib0015) 2024 Ulusoy, Horasanlı, Işık-Ulusoy (bib0047) 2020; 42 López-Dorado, Ortiz, Satue, Rodrigo, Barea, Sánchez-Morla (bib0019) 2021; 22 Halder, Milner (bib0049) 2021; 144 Sidey-Gibbons, Sidey-Gibbons (bib0006) 2019; 19 Thompson, Banwell, Barkhof, Carroll, Coetzee, Comi (bib0001) 2018; 17 He K., Zhang X., Ren S., Sun J. Deep Residual Learning For Image Recognition [Internet]. arXiv; 2015 [cited 2023 May 10]. Available from Mehmood, Ali, Song, Din, Guo, Shah (bib0002) 2021; 11 Saeb, Lonini, Jayaraman, Mohr, Kording (bib0028) 2017; 6 Zhang, Wang, Wang, Delgado, Hernandez, Hu (bib0010) 2020; 8 Garcia-Martin, Pablo, Herrero, Ara, Martin, Larrosa (bib0009) 2013; 91 Liashchynskyi P., Liashchynskyi P. Grid Search, Random Search, Genetic Algorithm: A Big Comparison for NAS [Internet]. arXiv; 2019 [cited 2023 Jul 25]. Available from Huber (bib0037) 1964; 35 Bartler, Hinderer, Grad-LAM (bib0039) 2021 Wisely, Wang, Henao, Grewal, Thompson, Robbins (bib0025) 2022; 106 Deng, Dong, Socher, Li, Li, ImageNet (bib0032) 2009 Nabizadeh, Ramezannezhad, Kargar, Sharafi, Ghaderi (bib0022) 2022 Pérez del Palomar, Cegoñino, Montolío, Orduna, Vilades, Sebastián, Bhattacharya (bib0018) 2019; 14 Bank D., Koenigstein N., Giryes R. Autoencoders [Internet]. arXiv; 2021 [cited 2023 Jul 4]. Available from Aumann, Donner, Fischer, Müller (bib0023) 2019 Cavaliere, Vilades, Alonso-Rodríguez, Rodrigo, Pablo, Miguel (bib0020) 2019; 19 Garcia-Martin, Herrero, Bambo, Ara, Martin, Polo (bib0013) 2015; 30 Montolío, Martín-Gallego, Cegoñino, Orduna, Vilades, Garcia-Martin (bib0011) 2021; 133 Selvaraju, Cogswell, Das, Vedantam, Parikh, Batra (bib0038) 2020; 128 Kenney, Liu, Hasanaj, Joseph, Abu Al-Hassan, Balk (bib0014) 2022; 99 Sarker (bib0004) 2021; 2 Montolío, Cegoñino, Garcia-Martin, Pérez del Palomar (bib0007) 2022; 50 Spain, Liu, Zhang, Jia, Tan, Bourdette (bib0048) 2018; 102 Murphy, Kwakyi, Iftikhar, Zafar, Lambe, Pellegrini (bib0046) 2020; 26 McInnes, Healy, Saul (bib0040) 2018; 3 Khodabandeh, Rabbani, Ashtari, Zimmermann, Motamedi, Brandt (bib0016) 2023 He, Carass, Solomon, Saidha, Calabresi, Prince (bib0027) 2019; 22 Bartler (10.1016/j.msard.2024.105743_bib0039) 2021 Garcia-Martin (10.1016/j.msard.2024.105743_bib0021) 2021; 129 He (10.1016/j.msard.2024.105743_bib0027) 2019; 22 Khodabandeh (10.1016/j.msard.2024.105743_bib0015) 2024 Nabizadeh (10.1016/j.msard.2024.105743_bib0022) 2022 Abdi (10.1016/j.msard.2024.105743_bib0034) 2010; 2 Pathak (10.1016/j.msard.2024.105743_bib0043) 2016 López-Dorado (10.1016/j.msard.2024.105743_bib0019) 2021; 22 Saeb (10.1016/j.msard.2024.105743_bib0028) 2017; 6 Hernandez (10.1016/j.msard.2024.105743_bib0008) 2023; 18 McInnes (10.1016/j.msard.2024.105743_bib0040) 2018; 3 10.1016/j.msard.2024.105743_bib0005 Ashtari (10.1016/j.msard.2024.105743_bib0026) 2021; 47 Spain (10.1016/j.msard.2024.105743_bib0048) 2018; 102 Sidey-Gibbons (10.1016/j.msard.2024.105743_bib0006) 2019; 19 Feucht (10.1016/j.msard.2024.105743_bib0045) 2019; 25 Thompson (10.1016/j.msard.2024.105743_bib0001) 2018; 17 Ulusoy (10.1016/j.msard.2024.105743_bib0047) 2020; 42 Pérez del Palomar (10.1016/j.msard.2024.105743_bib0018) 2019; 14 Sarker (10.1016/j.msard.2024.105743_bib0004) 2021; 2 Huber (10.1016/j.msard.2024.105743_bib0037) 1964; 35 Cavaliere (10.1016/j.msard.2024.105743_bib0020) 2019; 19 Montolío (10.1016/j.msard.2024.105743_bib0007) 2022; 50 Kenney (10.1016/j.msard.2024.105743_bib0014) 2022; 99 Petzold (10.1016/j.msard.2024.105743_bib0003) 2017; 16 10.1016/j.msard.2024.105743_bib0030 10.1016/j.msard.2024.105743_bib0031 Garcia-Martin (10.1016/j.msard.2024.105743_bib0009) 2013; 91 10.1016/j.msard.2024.105743_bib0033 10.1016/j.msard.2024.105743_bib0035 10.1016/j.msard.2024.105743_bib0036 Quigley (10.1016/j.msard.2024.105743_bib0044) 1960; 100 Cervantes (10.1016/j.msard.2024.105743_bib0041) 2020; 408 Khodabandeh (10.1016/j.msard.2024.105743_bib0016) 2023 LeCun (10.1016/j.msard.2024.105743_bib0042) 2015; 521 Aumann (10.1016/j.msard.2024.105743_bib0023) 2019 Ciftci Kavaklioglu (10.1016/j.msard.2024.105743_bib0017) 2022; 28 Ortiz (10.1016/j.msard.2024.105743_bib0012) 2023; 74 Arian (10.1016/j.msard.2024.105743_bib50) 2023; 10 Montolío (10.1016/j.msard.2024.105743_bib0011) 2021; 133 Wisely (10.1016/j.msard.2024.105743_bib0025) 2022; 106 Selvaraju (10.1016/j.msard.2024.105743_bib0038) 2020; 128 10.1016/j.msard.2024.105743_bib0029 Fischer (10.1016/j.msard.2024.105743_bib0024) 2019 Deng (10.1016/j.msard.2024.105743_bib0032) 2009 Mehmood (10.1016/j.msard.2024.105743_bib0002) 2021; 11 Murphy (10.1016/j.msard.2024.105743_bib0046) 2020; 26 Zhang (10.1016/j.msard.2024.105743_bib0010) 2020; 8 Garcia-Martin (10.1016/j.msard.2024.105743_bib0013) 2015; 30 Halder (10.1016/j.msard.2024.105743_bib0049) 2021; 144 |
| References_xml | – volume: 19 start-page: 5323 year: 2019 ident: bib0020 article-title: Computer-aided diagnosis of multiple sclerosis using a support vector machine and optical coherence tomography features publication-title: Sensors – volume: 2 start-page: 160 year: 2021 ident: bib0004 article-title: Machine learning: algorithms, real-world applications and research directions publication-title: SN Comput. Sci. – volume: 28 start-page: 2253 year: 2022 end-page: 2262 ident: bib0017 article-title: Machine learning classification of multiple sclerosis in children using optical coherence tomography publication-title: Mult. Scler. J. – volume: 25 start-page: 224 year: 2019 end-page: 234 ident: bib0045 article-title: Optical coherence tomography angiography indicates associations of the retinal vascular network and disease activity in multiple sclerosis publication-title: Mult Scler – volume: 35 start-page: 73 year: 1964 end-page: 101 ident: bib0037 article-title: Robust estimation of a location parameter publication-title: Ann. Math. Stat. – reference: Simonyan K., Zisserman A. Very Deep Convolutional Networks for Large-Scale Image Recognition [Internet]. arXiv; 2015 [cited 2023 May 16]. Available from: – volume: 74 year: 2023 ident: bib0012 article-title: Diagnosis of multiple sclerosis using optical coherence tomography supported by artificial intelligence publication-title: Mult. Scler. Relat. Disord. – volume: 50 start-page: 507 year: 2022 end-page: 528 ident: bib0007 article-title: Comparison of machine learning methods using spectralis OCT for diagnosis and disability progression prognosis in multiple sclerosis publication-title: Ann. Biomed. Eng. – volume: 2 start-page: 433 year: 2010 end-page: 459 ident: bib0034 article-title: Principal component analysis publication-title: WIREs Comput. Stat. – volume: 30 start-page: 11 year: 2015 end-page: 19 ident: bib0013 article-title: Artificial neural network techniques to improve the ability of optical coherence tomography to detect optic neuritis publication-title: Semin. Ophthalmol. – volume: 99 start-page: e1100 year: 2022 end-page: e1112 ident: bib0014 article-title: The role of optical coherence tomography criteria and machine learning in multiple sclerosis and optic neuritis diagnosis publication-title: Neurology – year: 2024 ident: bib0015 article-title: Comprehensive Evaluation of Artificial Intelligence Models for Diagnosis of Multiple Sclerosis Using Information from Retinal Layers Multicenter OCT Images [Internet] – volume: 18 year: 2023 ident: bib0008 article-title: Explainable artificial intelligence toward usable and trustworthy computer-aided diagnosis of multiple sclerosis from optical coherence tomography publication-title: PLOS One – volume: 22 start-page: 601 year: 2019 end-page: 604 ident: bib0027 article-title: Retinal layer parcellation of optical coherence tomography images: data resource for multiple sclerosis and healthy controls publication-title: Data Brief – reference: Liashchynskyi P., Liashchynskyi P. Grid Search, Random Search, Genetic Algorithm: A Big Comparison for NAS [Internet]. arXiv; 2019 [cited 2023 Jul 25]. Available from: – reference: Szegedy C., Vanhoucke V., Ioffe S., Shlens J., Wojna Z. Rethinking the Inception Architecture For Computer Vision [Internet]. arXiv; 2015 [cited 2023 May 10]. Available from: – start-page: 35 year: 2019 end-page: 57 ident: bib0024 article-title: Scanning laser ophthalmoscopy (SLO) publication-title: In: High Resolution Imaging in Microscopy and Ophthalmology – volume: 91 start-page: e628 year: 2013 end-page: e634 ident: bib0009 article-title: Neural networks to identify multiple sclerosis with optical coherence tomography publication-title: Acta Ophthalmol. – start-page: 1407 year: 2021 end-page: 1411 ident: bib0039 publication-title: Proceedings of the 2020 28th European Signal Processing Conference (EUSIPCO) – year: 2023 ident: bib0016 article-title: Discrimination of multiple sclerosis using multicenter OCT images publication-title: Mult. Scler. Relat. Disord. – reference: Akiba T., Sano S., Yanase T., Ohta T., Koyama M. Optuna: A Next-Generation Hyperparameter Optimization Framework [Internet]. arXiv; 2019 [cited 2023 Jul 25]. Available from: – year: 2022 ident: bib0022 article-title: Diagnostic performance of artificial intelligence in multiple sclerosis: a systematic review and meta-analysis publication-title: Neurol. Sci. – start-page: 2536 year: 2016 end-page: 2544 ident: bib0043 article-title: Context encoders: feature learning by inpainting publication-title: Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) [Internet] – volume: 133 year: 2021 ident: bib0011 article-title: Machine learning in diagnosis and disability prediction of multiple sclerosis using optical coherence tomography publication-title: Comput. Biol. Med. – volume: 19 start-page: 64 year: 2019 ident: bib0006 article-title: Machine learning in medicine: a practical introduction publication-title: BMC Med. Res. Methodol. – reference: Mehlig B. Machine Learning with Neural Networks: An Introduction for Scientists and Engineers [Internet]. 1st ed. Cambridge University Press; 2021 [cited 2024 Jun 22]. Available from: – volume: 100 start-page: 135 year: 1960 end-page: 146 ident: bib0044 article-title: Optic nerve damage in human glaucoma. III. Quantitative correlation of nerve fiber loss and visual field defect in glaucoma, ischemic neuropathy, papilledema, and toxic neuropathy publication-title: Arch. Ophthalmol. – volume: 106 start-page: 388 year: 2022 end-page: 395 ident: bib0025 article-title: Convolutional neural network to identify symptomatic Alzheimer's disease using multimodal retinal imaging publication-title: Br. J. Ophthalmol. – volume: 10 start-page: 234 year: 2023 ident: bib50 article-title: Automatic choroid vascularity index calculation in optical coherence tomography images with low-contrast sclerochoroidal junction using deep learning publication-title: Photonics – start-page: 248 year: 2009 end-page: 255 ident: bib0032 article-title: A large-scale hierarchical image database publication-title: Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition – volume: 16 start-page: 797 year: 2017 end-page: 812 ident: bib0003 article-title: Retinal layer segmentation in multiple sclerosis: a systematic review and meta-analysis publication-title: Lancet Neurol. – volume: 42 start-page: 319 year: 2020 end-page: 326 ident: bib0047 article-title: Optical coherence tomography angiography findings of multiple sclerosis with or without optic neuritis publication-title: Neurol. Res. – volume: 22 start-page: 167 year: 2021 ident: bib0019 article-title: Early diagnosis of multiple sclerosis using swept-source optical coherence tomography and convolutional neural networks trained with data augmentation publication-title: Sensors – volume: 129 year: 2021 ident: bib0021 article-title: Early diagnosis of multiple sclerosis by OCT analysis using Cohen's d method and a neural network as classifier publication-title: Comput. Biol. Med. – start-page: 59 year: 2019 end-page: 85 ident: bib0023 article-title: Optical coherence tomography (OCT): principle and technical realization publication-title: High Resolution Imaging in Microscopy and Ophthalmology – volume: 144 start-page: 402 year: 2021 end-page: 410 ident: bib0049 article-title: Hypoxia in multiple sclerosis; is it the chicken or the egg? publication-title: Brain – volume: 128 start-page: 336 year: 2020 end-page: 359 ident: bib0038 article-title: Grad-CAM: visual explanations from deep networks via gradient-based localization publication-title: Int. J. Comput. Vis. – volume: 17 start-page: 162 year: 2018 end-page: 173 ident: bib0001 article-title: Diagnosis of multiple sclerosis: 2017 revisions of the McDonald criteria publication-title: Lancet Neurol. – reference: . – reference: He K., Zhang X., Ren S., Sun J. Deep Residual Learning For Image Recognition [Internet]. arXiv; 2015 [cited 2023 May 10]. Available from: – volume: 521 start-page: 436 year: 2015 end-page: 444 ident: bib0042 article-title: Deep learning publication-title: Nature – volume: 408 start-page: 189 year: 2020 end-page: 215 ident: bib0041 article-title: A comprehensive survey on support vector machine classification: applications, challenges and trends publication-title: Neurocomputing – volume: 11 year: 2021 ident: bib0002 article-title: Optical coherence tomography monitoring and diagnosing retinal changes in multiple sclerosis publication-title: Brain Behav. – volume: 26 start-page: 815 year: 2020 end-page: 828 ident: bib0046 article-title: Alterations in the retinal vasculature occur in multiple sclerosis and exhibit novel correlations with disability and visual function measures publication-title: Mult. Scler. J. – volume: 8 start-page: 221590 year: 2020 end-page: 221598 ident: bib0010 article-title: Wavelet features of the thickness map of retinal ganglion cell-inner plexiform layer best discriminate prior optic neuritis in patients with multiple sclerosis publication-title: IEEe Access – volume: 14 year: 2019 ident: bib0018 article-title: Swept source optical coherence tomography to early detect multiple sclerosis disease. The use of machine learning techniques publication-title: PLoS One – volume: 47 year: 2021 ident: bib0026 article-title: Optical coherence tomography in neuromyelitis optica spectrum disorder and multiple sclerosis: a population-based study publication-title: Mult. Scler. Relat. Disord. – volume: 102 start-page: 520 year: 2018 end-page: 524 ident: bib0048 article-title: Optical coherence tomography angiography enhances the detection of optic nerve damage in multiple sclerosis publication-title: Br. J. Ophthalmol. – volume: 6 year: 2017 ident: bib0028 publication-title: The Need to Approximate the Use-Case in Clinical Machine Learning – reference: Bank D., Koenigstein N., Giryes R. Autoencoders [Internet]. arXiv; 2021 [cited 2023 Jul 4]. Available from: – volume: 3 year: 2018 ident: bib0040 article-title: Großberger L. UMAP: Uniform Manifold Approximation and Projection publication-title: J. Open Source Softw. – volume: 11 issue: 10 year: 2021 ident: 10.1016/j.msard.2024.105743_bib0002 article-title: Optical coherence tomography monitoring and diagnosing retinal changes in multiple sclerosis publication-title: Brain Behav. doi: 10.1002/brb3.2302 – volume: 74 year: 2023 ident: 10.1016/j.msard.2024.105743_bib0012 article-title: Diagnosis of multiple sclerosis using optical coherence tomography supported by artificial intelligence publication-title: Mult. Scler. Relat. Disord. doi: 10.1016/j.msard.2023.104725 – start-page: 35 year: 2019 ident: 10.1016/j.msard.2024.105743_bib0024 article-title: Scanning laser ophthalmoscopy (SLO) – start-page: 248 year: 2009 ident: 10.1016/j.msard.2024.105743_bib0032 article-title: A large-scale hierarchical image database – volume: 25 start-page: 224 issue: 2 year: 2019 ident: 10.1016/j.msard.2024.105743_bib0045 article-title: Optical coherence tomography angiography indicates associations of the retinal vascular network and disease activity in multiple sclerosis publication-title: Mult Scler doi: 10.1177/1352458517750009 – volume: 19 start-page: 5323 issue: 23 year: 2019 ident: 10.1016/j.msard.2024.105743_bib0020 article-title: Computer-aided diagnosis of multiple sclerosis using a support vector machine and optical coherence tomography features publication-title: Sensors doi: 10.3390/s19235323 – volume: 19 start-page: 64 issue: 1 year: 2019 ident: 10.1016/j.msard.2024.105743_bib0006 article-title: Machine learning in medicine: a practical introduction publication-title: BMC Med. Res. Methodol. doi: 10.1186/s12874-019-0681-4 – volume: 2 start-page: 160 issue: 3 year: 2021 ident: 10.1016/j.msard.2024.105743_bib0004 article-title: Machine learning: algorithms, real-world applications and research directions publication-title: SN Comput. Sci. doi: 10.1007/s42979-021-00592-x – volume: 30 start-page: 11 issue: 1 year: 2015 ident: 10.1016/j.msard.2024.105743_bib0013 article-title: Artificial neural network techniques to improve the ability of optical coherence tomography to detect optic neuritis publication-title: Semin. Ophthalmol. doi: 10.3109/08820538.2013.810277 – ident: 10.1016/j.msard.2024.105743_bib0035 – ident: 10.1016/j.msard.2024.105743_bib0029 – start-page: 1407 year: 2021 ident: 10.1016/j.msard.2024.105743_bib0039 – year: 2024 ident: 10.1016/j.msard.2024.105743_bib0015 – volume: 144 start-page: 402 issue: 2 year: 2021 ident: 10.1016/j.msard.2024.105743_bib0049 article-title: Hypoxia in multiple sclerosis; is it the chicken or the egg? publication-title: Brain doi: 10.1093/brain/awaa427 – volume: 47 year: 2021 ident: 10.1016/j.msard.2024.105743_bib0026 article-title: Optical coherence tomography in neuromyelitis optica spectrum disorder and multiple sclerosis: a population-based study publication-title: Mult. Scler. Relat. Disord. doi: 10.1016/j.msard.2020.102625 – volume: 129 year: 2021 ident: 10.1016/j.msard.2024.105743_bib0021 article-title: Early diagnosis of multiple sclerosis by OCT analysis using Cohen's d method and a neural network as classifier publication-title: Comput. Biol. Med. doi: 10.1016/j.compbiomed.2020.104165 – volume: 521 start-page: 436 issue: 7553 year: 2015 ident: 10.1016/j.msard.2024.105743_bib0042 article-title: Deep learning publication-title: Nature doi: 10.1038/nature14539 – volume: 128 start-page: 336 issue: 2 year: 2020 ident: 10.1016/j.msard.2024.105743_bib0038 article-title: Grad-CAM: visual explanations from deep networks via gradient-based localization publication-title: Int. J. Comput. Vis. doi: 10.1007/s11263-019-01228-7 – volume: 408 start-page: 189 year: 2020 ident: 10.1016/j.msard.2024.105743_bib0041 article-title: A comprehensive survey on support vector machine classification: applications, challenges and trends publication-title: Neurocomputing doi: 10.1016/j.neucom.2019.10.118 – volume: 22 start-page: 167 issue: 1 year: 2021 ident: 10.1016/j.msard.2024.105743_bib0019 article-title: Early diagnosis of multiple sclerosis using swept-source optical coherence tomography and convolutional neural networks trained with data augmentation publication-title: Sensors doi: 10.3390/s22010167 – volume: 14 issue: 5 year: 2019 ident: 10.1016/j.msard.2024.105743_bib0018 article-title: Swept source optical coherence tomography to early detect multiple sclerosis disease. The use of machine learning techniques publication-title: PLoS One doi: 10.1371/journal.pone.0216410 – volume: 100 start-page: 135 issue: 1 year: 1960 ident: 10.1016/j.msard.2024.105743_bib0044 article-title: Optic nerve damage in human glaucoma. III. Quantitative correlation of nerve fiber loss and visual field defect in glaucoma, ischemic neuropathy, papilledema, and toxic neuropathy publication-title: Arch. Ophthalmol. doi: 10.1001/archopht.1982.01030030137016 – volume: 22 start-page: 601 year: 2019 ident: 10.1016/j.msard.2024.105743_bib0027 article-title: Retinal layer parcellation of optical coherence tomography images: data resource for multiple sclerosis and healthy controls publication-title: Data Brief doi: 10.1016/j.dib.2018.12.073 – volume: 42 start-page: 319 issue: 4 year: 2020 ident: 10.1016/j.msard.2024.105743_bib0047 article-title: Optical coherence tomography angiography findings of multiple sclerosis with or without optic neuritis publication-title: Neurol. Res. doi: 10.1080/01616412.2020.1726585 – ident: 10.1016/j.msard.2024.105743_bib0036 – volume: 106 start-page: 388 issue: 3 year: 2022 ident: 10.1016/j.msard.2024.105743_bib0025 article-title: Convolutional neural network to identify symptomatic Alzheimer's disease using multimodal retinal imaging publication-title: Br. J. Ophthalmol. doi: 10.1136/bjophthalmol-2020-317659 – start-page: 2536 year: 2016 ident: 10.1016/j.msard.2024.105743_bib0043 article-title: Context encoders: feature learning by inpainting – volume: 17 start-page: 162 issue: 2 year: 2018 ident: 10.1016/j.msard.2024.105743_bib0001 article-title: Diagnosis of multiple sclerosis: 2017 revisions of the McDonald criteria publication-title: Lancet Neurol. doi: 10.1016/S1474-4422(17)30470-2 – volume: 50 start-page: 507 issue: 5 year: 2022 ident: 10.1016/j.msard.2024.105743_bib0007 article-title: Comparison of machine learning methods using spectralis OCT for diagnosis and disability progression prognosis in multiple sclerosis publication-title: Ann. Biomed. Eng. doi: 10.1007/s10439-022-02930-3 – ident: 10.1016/j.msard.2024.105743_bib0005 doi: 10.1017/9781108860604 – volume: 3 issue: 29 year: 2018 ident: 10.1016/j.msard.2024.105743_bib0040 article-title: Großberger L. UMAP: Uniform Manifold Approximation and Projection publication-title: J. Open Source Softw. doi: 10.21105/joss.00861 – volume: 16 start-page: 797 issue: 10 year: 2017 ident: 10.1016/j.msard.2024.105743_bib0003 article-title: Retinal layer segmentation in multiple sclerosis: a systematic review and meta-analysis publication-title: Lancet Neurol. doi: 10.1016/S1474-4422(17)30278-8 – year: 2023 ident: 10.1016/j.msard.2024.105743_bib0016 article-title: Discrimination of multiple sclerosis using multicenter OCT images publication-title: Mult. Scler. Relat. Disord. doi: 10.1016/j.msard.2023.104846 – ident: 10.1016/j.msard.2024.105743_bib0033 doi: 10.1145/3292500.3330701 – start-page: 59 year: 2019 ident: 10.1016/j.msard.2024.105743_bib0023 article-title: Optical coherence tomography (OCT): principle and technical realization – year: 2022 ident: 10.1016/j.msard.2024.105743_bib0022 article-title: Diagnostic performance of artificial intelligence in multiple sclerosis: a systematic review and meta-analysis publication-title: Neurol. Sci. – volume: 26 start-page: 815 issue: 7 year: 2020 ident: 10.1016/j.msard.2024.105743_bib0046 article-title: Alterations in the retinal vasculature occur in multiple sclerosis and exhibit novel correlations with disability and visual function measures publication-title: Mult. Scler. J. doi: 10.1177/1352458519845116 – volume: 102 start-page: 520 issue: 4 year: 2018 ident: 10.1016/j.msard.2024.105743_bib0048 article-title: Optical coherence tomography angiography enhances the detection of optic nerve damage in multiple sclerosis publication-title: Br. J. Ophthalmol. doi: 10.1136/bjophthalmol-2017-310477 – ident: 10.1016/j.msard.2024.105743_bib0031 doi: 10.1109/CVPR.2016.308 – volume: 6 year: 2017 ident: 10.1016/j.msard.2024.105743_bib0028 – volume: 133 year: 2021 ident: 10.1016/j.msard.2024.105743_bib0011 article-title: Machine learning in diagnosis and disability prediction of multiple sclerosis using optical coherence tomography publication-title: Comput. Biol. Med. doi: 10.1016/j.compbiomed.2021.104416 – volume: 18 issue: 8 year: 2023 ident: 10.1016/j.msard.2024.105743_bib0008 article-title: Explainable artificial intelligence toward usable and trustworthy computer-aided diagnosis of multiple sclerosis from optical coherence tomography publication-title: PLOS One doi: 10.1371/journal.pone.0289495 – volume: 10 start-page: 234 year: 2023 ident: 10.1016/j.msard.2024.105743_bib50 article-title: Automatic choroid vascularity index calculation in optical coherence tomography images with low-contrast sclerochoroidal junction using deep learning publication-title: Photonics doi: 10.3390/photonics10030234 – volume: 28 start-page: 2253 issue: 14 year: 2022 ident: 10.1016/j.msard.2024.105743_bib0017 article-title: Machine learning classification of multiple sclerosis in children using optical coherence tomography publication-title: Mult. Scler. J. doi: 10.1177/13524585221112605 – ident: 10.1016/j.msard.2024.105743_bib0030 – volume: 99 start-page: e1100 issue: 11 year: 2022 ident: 10.1016/j.msard.2024.105743_bib0014 article-title: The role of optical coherence tomography criteria and machine learning in multiple sclerosis and optic neuritis diagnosis publication-title: Neurology doi: 10.1212/WNL.0000000000200883 – volume: 91 start-page: e628 issue: 8 year: 2013 ident: 10.1016/j.msard.2024.105743_bib0009 article-title: Neural networks to identify multiple sclerosis with optical coherence tomography publication-title: Acta Ophthalmol. doi: 10.1111/aos.12156 – volume: 8 start-page: 221590 year: 2020 ident: 10.1016/j.msard.2024.105743_bib0010 article-title: Wavelet features of the thickness map of retinal ganglion cell-inner plexiform layer best discriminate prior optic neuritis in patients with multiple sclerosis publication-title: IEEe Access doi: 10.1109/ACCESS.2020.3041291 – volume: 2 start-page: 433 issue: 4 year: 2010 ident: 10.1016/j.msard.2024.105743_bib0034 article-title: Principal component analysis publication-title: WIREs Comput. Stat. doi: 10.1002/wics.101 – volume: 35 start-page: 73 issue: 1 year: 1964 ident: 10.1016/j.msard.2024.105743_bib0037 article-title: Robust estimation of a location parameter publication-title: Ann. Math. Stat. doi: 10.1214/aoms/1177703732 |
| SSID | ssj0000651461 |
| Score | 2.3288336 |
| Snippet | Optical coherence tomography (OCT) investigations have revealed that the thickness of inner retinal layers becomes decreased in multiple sclerosis (MS)... AbstractObjectiveOptical coherence tomography (OCT) investigations have revealed that the thickness of inner retinal layers becomes decreased in multiple... |
| SourceID | proquest pubmed crossref elsevier |
| SourceType | Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 105743 |
| SubjectTerms | Adult Deep Learning Feature Extraction Female Humans Machine Learning Male Middle Aged Multiple Sclerosis Multiple Sclerosis - diagnostic imaging Neural Networks, Computer Neurology Ophthalmoscopy - methods Optical Coherence Tomography Scanning Laser Ophthalmoscopy Sensitivity and Specificity Tomography, Optical Coherence - methods |
| Title | Discrimination of multiple sclerosis using scanning laser ophthalmoscopy images with autoencoder-based feature extraction |
| URI | https://www.clinicalkey.com/#!/content/1-s2.0-S2211034824003201 https://www.clinicalkey.es/playcontent/1-s2.0-S2211034824003201 https://dx.doi.org/10.1016/j.msard.2024.105743 https://www.ncbi.nlm.nih.gov/pubmed/38945032 https://www.proquest.com/docview/3074132987 |
| Volume | 88 |
| WOSCitedRecordID | wos001284293200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 2211-0356 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000651461 issn: 2211-0348 databaseCode: AIEXJ dateStart: 20210701 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1bb9MwFLa6DiFeEHfKZTISbyEVsZPaeaxgEyBtQtqQ-mYlsUMztUmVtNP6r_iJHMeOSykr7AFVjdrUdlKfL-d8cc4FobdUgRVkPPPzkEo_ZFHixzQP_WAUyUTFaZ4kptgEOzvjk0n8tdf70cXCXM1YWfLr63jxX0UN-0DYOnT2FuJ2g8IO-AxChy2IHbb_JPiPhdYE2sOlI4POabCBpmAVi8ZbtUsETWYqFnlAoVXtVYvpcprM5pUOVVl7xTzRCSBM9NtqWemUl1LVvjZ80stVmxLUA-Vem-CIX3nu6e4hW0d27XoHnaXN-ekI_fj7NEnhpQoTdVNsgFjYJ1XV2lmQ82oGnLZYwHS0zZtCuVXtcTNdJiZ8_kTVCr7Z3-zSBgmdY53VgITo9VtqUnF26tpUAbT6VlcpNmmedkyBWZW4HM4buNSGevjhpvV24u3fDKJzU-w84C5FO4jQgwgzyAE6JCyKeR8djj8fT764dT2gdLpUuq5p2J19l-yqdSvcOZ2bCNFNNzwt8bl4gO7bOxY8Nkh7iHqqfITunlqfjMdovQ04XOW4Axx20sct4HAHONwCDm8DDhvAYQ04vAM4bAGHN4B7gr6dHF98-OTbgh5-Brx-6dNY5iyFeeNhLiNJRmkaUngzkkajMONBLkOWpSQLKLBenijdekRzKSVPGQ_oU9Qvq1I9R5glQU4kyRRTPOQRS1KwVSkNZBSnKQ_JAJFuVkVms93roiszsUeoA_TOdVqYZC_7m4eduEQXxwyWVwAC93djf-qmGqtEGhGIhoj34lwjSANI-3lTYOoDNHI9LUE2xPfvh3zToUmA-dDPBJNSVatGUH1LQUnM2QA9MzBzfx20eBjBgV_cblpeonubi_kV6i_rlXqN7mRXy6Kpj9ABm_Aje9X8BE0c-ls |
| linkProvider | Elsevier |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Discrimination+of+multiple+sclerosis+using+scanning+laser+ophthalmoscopy+images+with+autoencoder-based+feature+extraction&rft.jtitle=Multiple+sclerosis+and+related+disorders&rft.au=Aghababaei%2C+Ali&rft.au=Arian%2C+Roya&rft.au=Soltanipour%2C+Asieh&rft.au=Ashtari%2C+Fereshteh&rft.date=2024-08-01&rft.issn=2211-0348&rft.volume=88&rft.spage=105743&rft_id=info:doi/10.1016%2Fj.msard.2024.105743&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_msard_2024_105743 |
| thumbnail_m | http://cvtisr.summon.serialssolutions.com/2.0.0/image/custom?url=https%3A%2F%2Fcdn.clinicalkey.com%2Fck-thumbnails%2F22110348%2Fcov200h.gif |