Custom built ethnic-specific dataset from SAP tests for optic pathway disease diagnosis: baseline approach using graph convolutional networks
Automated interpretation and diagnostic classification of standard automated perimetry (SAP) plots has been researched using machine learning techniques, and multiple public datasets has been proposed. Therefore, our contribution is a more complete database than the already published ones, and we pr...
- Autores:
-
Gregory Tatis, Alvin David
Giraldo Trujillo, Luis Felipe
Marroquín, Guillermo
Jimenez Vargas, Jose Fernando
- Tipo de recurso:
- Trabajo de grado de pregrado
- Fecha de publicación:
- 2021
- Institución:
- Universidad de los Andes
- Repositorio:
- Séneca: repositorio Uniandes
- Idioma:
- eng
- OAI Identifier:
- oai:repositorio.uniandes.edu.co:1992/54464
- Acceso en línea:
- http://hdl.handle.net/1992/54464
- Palabra clave:
- Artificial intelligence
Perimetry
Visual field
Optic pathway disease diagnosis
Ingeniería
- Rights
- openAccess
- License
- https://repositorio.uniandes.edu.co/static/pdf/aceptacion_uso_es.pdf
| id |
UNIANDES2_8e4ee31fcb98ca7aa9dc4b1497870f74 |
|---|---|
| oai_identifier_str |
oai:repositorio.uniandes.edu.co:1992/54464 |
| network_acronym_str |
UNIANDES2 |
| network_name_str |
Séneca: repositorio Uniandes |
| repository_id_str |
|
| dc.title.none.fl_str_mv |
Custom built ethnic-specific dataset from SAP tests for optic pathway disease diagnosis: baseline approach using graph convolutional networks |
| title |
Custom built ethnic-specific dataset from SAP tests for optic pathway disease diagnosis: baseline approach using graph convolutional networks |
| spellingShingle |
Custom built ethnic-specific dataset from SAP tests for optic pathway disease diagnosis: baseline approach using graph convolutional networks Artificial intelligence Perimetry Visual field Optic pathway disease diagnosis Ingeniería |
| title_short |
Custom built ethnic-specific dataset from SAP tests for optic pathway disease diagnosis: baseline approach using graph convolutional networks |
| title_full |
Custom built ethnic-specific dataset from SAP tests for optic pathway disease diagnosis: baseline approach using graph convolutional networks |
| title_fullStr |
Custom built ethnic-specific dataset from SAP tests for optic pathway disease diagnosis: baseline approach using graph convolutional networks |
| title_full_unstemmed |
Custom built ethnic-specific dataset from SAP tests for optic pathway disease diagnosis: baseline approach using graph convolutional networks |
| title_sort |
Custom built ethnic-specific dataset from SAP tests for optic pathway disease diagnosis: baseline approach using graph convolutional networks |
| dc.creator.fl_str_mv |
Gregory Tatis, Alvin David Giraldo Trujillo, Luis Felipe Marroquín, Guillermo Jimenez Vargas, Jose Fernando |
| dc.contributor.advisor.none.fl_str_mv |
Giraldo Trujillo, Luis Felipe Jiménez Vargas, José Fernando |
| dc.contributor.author.none.fl_str_mv |
Gregory Tatis, Alvin David Giraldo Trujillo, Luis Felipe Marroquín, Guillermo Jimenez Vargas, Jose Fernando |
| dc.contributor.jury.none.fl_str_mv |
Zambrano Jacobo, Andrés Felipe |
| dc.subject.keyword.none.fl_str_mv |
Artificial intelligence Perimetry Visual field Optic pathway disease diagnosis |
| topic |
Artificial intelligence Perimetry Visual field Optic pathway disease diagnosis Ingeniería |
| dc.subject.themes.es_CO.fl_str_mv |
Ingeniería |
| description |
Automated interpretation and diagnostic classification of standard automated perimetry (SAP) plots has been researched using machine learning techniques, and multiple public datasets has been proposed. Therefore, our contribution is a more complete database than the already published ones, and we propose an analysis of state of the art techniques over this dataset. This ethnic-specific database, contains 66 subjects from Colombia ranging from 17-79 years old, differentiating them in two major classes: visual field (VF) of optic pathway pathological patients, and healthy eyes. Moreover, we propose, in particular, a flexible representation using Graph Convolutional Networks that combines the three SAP plots, VF indices (MD, PSD, VFI) and patient¿s data (age, pupil diameter), into a simple graph to pursue improved classification performance compared to using any single SAP plot and a variety of CNN architectures. We achieved an accuracy of 1.0 in both validation and test sets. Performance was superior compared to using other Machine Learning (ML) methods tested. |
| publishDate |
2021 |
| dc.date.issued.none.fl_str_mv |
2021-12-14 |
| dc.date.accessioned.none.fl_str_mv |
2022-02-01T21:26:42Z |
| dc.date.available.none.fl_str_mv |
2022-02-01T21:26:42Z |
| dc.type.spa.fl_str_mv |
Trabajo de grado - Pregrado |
| dc.type.coarversion.fl_str_mv |
http://purl.org/coar/version/c_970fb48d4fbd8a85 |
| dc.type.driver.spa.fl_str_mv |
info:eu-repo/semantics/bachelorThesis |
| dc.type.coar.spa.fl_str_mv |
http://purl.org/coar/resource_type/c_7a1f |
| dc.type.content.spa.fl_str_mv |
Text |
| dc.type.redcol.spa.fl_str_mv |
http://purl.org/redcol/resource_type/TP |
| format |
http://purl.org/coar/resource_type/c_7a1f |
| dc.identifier.uri.none.fl_str_mv |
http://hdl.handle.net/1992/54464 |
| dc.identifier.instname.spa.fl_str_mv |
instname:Universidad de los Andes |
| dc.identifier.reponame.spa.fl_str_mv |
reponame:Repositorio Institucional Séneca |
| dc.identifier.repourl.spa.fl_str_mv |
repourl:https://repositorio.uniandes.edu.co/ |
| url |
http://hdl.handle.net/1992/54464 |
| identifier_str_mv |
instname:Universidad de los Andes reponame:Repositorio Institucional Séneca repourl:https://repositorio.uniandes.edu.co/ |
| dc.language.iso.es_CO.fl_str_mv |
eng |
| language |
eng |
| dc.relation.references.es_CO.fl_str_mv |
Kucur, S ¿.S., Holl ¿o, G. and Sznitman, R., 2018. A deep learning approach to automatic detection of early glaucoma from visual fields. PloS one, 13(11), p.e0206081. HEIJL, A., PATELLA, V. M., BENGTSSON, B. (2012). The Field analyzer primer: effective perimetry. Kahook, M. and Noecker, R., 2007. How Do You Interpret a 24-2 Humphrey Visual Field Printout? - Glaucoma Today. [online] Glaucoma Today. Available at: https://glaucomatoday.com/articles/2007-nov-dec/GT1107 10-php [Accessed 8 December 2021] Khoury, J.M., Donahue, S.P., Lavin, P.J. and Tsai, J.C., 1999. Comparison of 24-2 and 30-2 perimetry in glaucomatous and nonglaucomatous optic neuropathies. Journal of neuro-ophthalmology: the official journal of the North American Neuro-Ophthalmology Society, 19(2), pp.100-108. Artes, P.H., Iwase, A., Ohno, Y., Kitazawa, Y. and Chauhan, B.C., 2002. Properties of perimetric threshold estimates from Full Threshold, SITA Standard, and SITA Fast strategies. Investigative ophthalmology visual science, 43(8), pp.2654-2659. Bae, S.H. and Yi, K., 2021. Comparison of clinical usefulness of central 30¿2 and 24¿2 threshold tests using SITA strategy. International Ophthalmology, pp.1-6. Han, S., Baek, S.H. and Kim, U.S., 2017, September. Comparison of three visual field tests in children: frequency doubling test, 24-2 and 30-2 SITA perimetry. In Seminars in ophthalmology (Vol. 32, No. 5, pp. 647-650). Taylor Francis. Lee, S.D., Lee, J.H., Choi, Y.G., You, H.C., Kang, J.H. and Jun, C.H., 2019. Machine learning models based on the dimensionality reduction of standard automated perimetry data for glaucoma diagnosis. Artificial intelligence in medicine, 94, pp.110-116. Park, K., Kim, J. and Lee, J., 2019. Visual field prediction using recurrent neural network. Scientific reports, 9(1), pp.1-12. Bizios, D., Heijl, A. and Bengtsson, B., 2007. Trained artificial neural network for glaucoma diagnosis using visual field data: a comparison with conventional algorithms. Journal of glaucoma, 16(1), pp.20-28. Hatanaka, Y., Muramatsu, C., Sawada, A., Hara, T., Yamamoto, T. and Fujita, H., 2012, January. Glaucoma risk assessment based on clinical data and automated nerve fiber layer defects detection. In 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society (pp. 5963-5966). IEEE. Asaoka, R., Iwase, A., Hirasawa, K., Murata, H. and Araie, M., 2014. Identifying ¿preperimetric¿ glaucoma in standard automated perimetry visual fields. Investigative ophthalmology visual science, 55(12), pp.7814-7820. Goldbaum, M.H., Sample, P.A., Chan, K., Williams, J., Lee, T.W., Blumenthal, E., Girkin, C.A., Zangwill, L.M., Bowd, C., Sejnowski, T. and Weinreb, R.N., 2002. Comparing machine learning classifiers for diagnosing glaucoma from standard automated perimetry. Investigative ophthalmology visual science, 43(1), pp.162-169. Li, F., Wang, Z., Qu, G., Song, D., Yuan, Y., Xu, Y., Gao, K., Luo, G., Xiao, Z., Lam, D.S. and Zhong, H., 2018. Automatic differentiation of glaucoma visual field from non-glaucoma visual filed using deep convolutional neural network. BMC medical imaging, 18(1), pp.1-7. Wang, Z., Keane, P.A., Chiang, M., Cheung, C.Y., Wong, T.Y. and Ting, D.S.W., 2020. Artificial intelligence and deep learning in ophthalmology. Artificial Intelligence in Medicine, pp.1-34. Tan, X.L., Yap, S.C., Li, X. and Yip, L.W., 2017. Comparison of Ethnic-specific Databases in Heidelberg Retina Tomography-3 to Discriminate Between Early Glaucoma and Normal Chinese Eyes. The open ophthalmology journal, 11, p.40. Daniele Grattalora, others. Spektral. GitHub; 2019. Tong, Y., Huang, X., Qi, C.X. and Shen, Y., 2021. Altered Functional Connectivity of the Primary Visual Cortex in Patients With Iridocyclitis and Assessment of Its Predictive Value Using Machine Learning. Frontiers in immunology, 12, p.1650. Smith, T.B., Smith, N. and Weleber, R.G., 2017. Comparison of nonparametric methods for static visual field interpolation. Medical biological engineering computing, 55(1), pp.117-126. Zhang, X., Loewen, N., Tan, O., Greenfield, D.S., Schuman, J.S., Varma, R., Huang, D., Francis, B., Parrish II, R.K., Kishor, K.S. and Quinn, C.D., 2016. Predicting development of glaucomatous visual field conversion using baseline fourier-domain optical coherence tomography. American journal of ophthalmology, 163, pp.29-37. Li, J., Jin, P., Zhu, J., Zou, H., Xu, X., Tang, M., Zhou, M., Gan, Y., He, J., Ling, Y. and Su, Y., 2021. Multi-scale GCN-assisted two-stage network for joint segmentation of retinal layers and discs in peripapillary OCT images. Biomedical Optics Express, 12(4), pp.2204-2220. |
| dc.rights.uri.*.fl_str_mv |
https://repositorio.uniandes.edu.co/static/pdf/aceptacion_uso_es.pdf |
| dc.rights.accessrights.spa.fl_str_mv |
info:eu-repo/semantics/openAccess |
| dc.rights.coar.spa.fl_str_mv |
http://purl.org/coar/access_right/c_abf2 |
| rights_invalid_str_mv |
https://repositorio.uniandes.edu.co/static/pdf/aceptacion_uso_es.pdf http://purl.org/coar/access_right/c_abf2 |
| eu_rights_str_mv |
openAccess |
| dc.format.extent.es_CO.fl_str_mv |
12 páginas |
| dc.publisher.es_CO.fl_str_mv |
Universidad de los Andes |
| dc.publisher.program.es_CO.fl_str_mv |
Ingeniería Electrónica |
| dc.publisher.faculty.es_CO.fl_str_mv |
Facultad de Ingeniería |
| dc.publisher.department.es_CO.fl_str_mv |
Departamento de Ingeniería Eléctrica y Electrónica |
| institution |
Universidad de los Andes |
| bitstream.url.fl_str_mv |
https://repositorio.uniandes.edu.co/bitstreams/9c100648-cd53-4f57-a30b-d615e3c3e89b/download https://repositorio.uniandes.edu.co/bitstreams/0e2bea34-22e5-44f2-ac31-c11a656ad974/download https://repositorio.uniandes.edu.co/bitstreams/5d974fba-b535-4faf-aa51-3da8da00b846/download https://repositorio.uniandes.edu.co/bitstreams/01629277-bcc3-4f8f-bfb6-233644e7ef92/download |
| bitstream.checksum.fl_str_mv |
17d4853f1869415e98c0c44026f8c36c 5aa5c691a1ffe97abd12c2966efcb8d6 333ccb4699fe6fc0a7f68b8c19723e1a 04683e7447a510c12734e56dbd3d7d4e |
| bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 |
| repository.name.fl_str_mv |
Repositorio institucional Séneca |
| repository.mail.fl_str_mv |
adminrepositorio@uniandes.edu.co |
| _version_ |
1818111957839904768 |
| spelling |
Al consultar y hacer uso de este recurso, está aceptando las condiciones de uso establecidas por los autores.https://repositorio.uniandes.edu.co/static/pdf/aceptacion_uso_es.pdfinfo:eu-repo/semantics/openAccesshttp://purl.org/coar/access_right/c_abf2Giraldo Trujillo, Luis Felipevirtual::13547-1Jiménez Vargas, José Fernandovirtual::13548-1Gregory Tatis, Alvin David24af9efe-6a97-4704-b59e-24bf8cd64c38600Giraldo Trujillo, Luis Felipe6ec7994b-6a25-4e45-94e3-5d7337a159c9600Marroquín, Guillermo511c615b-9923-4b39-94c9-531cdf8d5506600Jimenez Vargas, Jose Fernando48142086-d7d4-42bb-8ac5-8c36dec6d4cd600Zambrano Jacobo, Andrés Felipe2022-02-01T21:26:42Z2022-02-01T21:26:42Z2021-12-14http://hdl.handle.net/1992/54464instname:Universidad de los Andesreponame:Repositorio Institucional Sénecarepourl:https://repositorio.uniandes.edu.co/Automated interpretation and diagnostic classification of standard automated perimetry (SAP) plots has been researched using machine learning techniques, and multiple public datasets has been proposed. Therefore, our contribution is a more complete database than the already published ones, and we propose an analysis of state of the art techniques over this dataset. This ethnic-specific database, contains 66 subjects from Colombia ranging from 17-79 years old, differentiating them in two major classes: visual field (VF) of optic pathway pathological patients, and healthy eyes. Moreover, we propose, in particular, a flexible representation using Graph Convolutional Networks that combines the three SAP plots, VF indices (MD, PSD, VFI) and patient¿s data (age, pupil diameter), into a simple graph to pursue improved classification performance compared to using any single SAP plot and a variety of CNN architectures. We achieved an accuracy of 1.0 in both validation and test sets. Performance was superior compared to using other Machine Learning (ML) methods tested.Ingeniero ElectrónicoPregrado12 páginasengUniversidad de los AndesIngeniería ElectrónicaFacultad de IngenieríaDepartamento de Ingeniería Eléctrica y ElectrónicaCustom built ethnic-specific dataset from SAP tests for optic pathway disease diagnosis: baseline approach using graph convolutional networksTrabajo de grado - Pregradoinfo:eu-repo/semantics/bachelorThesishttp://purl.org/coar/resource_type/c_7a1fhttp://purl.org/coar/version/c_970fb48d4fbd8a85Texthttp://purl.org/redcol/resource_type/TPArtificial intelligencePerimetryVisual fieldOptic pathway disease diagnosisIngenieríaKucur, S ¿.S., Holl ¿o, G. and Sznitman, R., 2018. A deep learning approach to automatic detection of early glaucoma from visual fields. PloS one, 13(11), p.e0206081.HEIJL, A., PATELLA, V. M., BENGTSSON, B. (2012). The Field analyzer primer: effective perimetry.Kahook, M. and Noecker, R., 2007. How Do You Interpret a 24-2 Humphrey Visual Field Printout? - Glaucoma Today. [online] Glaucoma Today. Available at: https://glaucomatoday.com/articles/2007-nov-dec/GT1107 10-php [Accessed 8 December 2021]Khoury, J.M., Donahue, S.P., Lavin, P.J. and Tsai, J.C., 1999. Comparison of 24-2 and 30-2 perimetry in glaucomatous and nonglaucomatous optic neuropathies. Journal of neuro-ophthalmology: the official journal of the North American Neuro-Ophthalmology Society, 19(2), pp.100-108.Artes, P.H., Iwase, A., Ohno, Y., Kitazawa, Y. and Chauhan, B.C., 2002. Properties of perimetric threshold estimates from Full Threshold, SITA Standard, and SITA Fast strategies. Investigative ophthalmology visual science, 43(8), pp.2654-2659.Bae, S.H. and Yi, K., 2021. Comparison of clinical usefulness of central 30¿2 and 24¿2 threshold tests using SITA strategy. International Ophthalmology, pp.1-6.Han, S., Baek, S.H. and Kim, U.S., 2017, September. Comparison of three visual field tests in children: frequency doubling test, 24-2 and 30-2 SITA perimetry. In Seminars in ophthalmology (Vol. 32, No. 5, pp. 647-650). Taylor Francis.Lee, S.D., Lee, J.H., Choi, Y.G., You, H.C., Kang, J.H. and Jun, C.H., 2019. Machine learning models based on the dimensionality reduction of standard automated perimetry data for glaucoma diagnosis. Artificial intelligence in medicine, 94, pp.110-116.Park, K., Kim, J. and Lee, J., 2019. Visual field prediction using recurrent neural network. Scientific reports, 9(1), pp.1-12.Bizios, D., Heijl, A. and Bengtsson, B., 2007. Trained artificial neural network for glaucoma diagnosis using visual field data: a comparison with conventional algorithms. Journal of glaucoma, 16(1), pp.20-28.Hatanaka, Y., Muramatsu, C., Sawada, A., Hara, T., Yamamoto, T. and Fujita, H., 2012, January. Glaucoma risk assessment based on clinical data and automated nerve fiber layer defects detection. In 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society (pp. 5963-5966). IEEE.Asaoka, R., Iwase, A., Hirasawa, K., Murata, H. and Araie, M., 2014. Identifying ¿preperimetric¿ glaucoma in standard automated perimetry visual fields. Investigative ophthalmology visual science, 55(12), pp.7814-7820.Goldbaum, M.H., Sample, P.A., Chan, K., Williams, J., Lee, T.W., Blumenthal, E., Girkin, C.A., Zangwill, L.M., Bowd, C., Sejnowski, T. and Weinreb, R.N., 2002. Comparing machine learning classifiers for diagnosing glaucoma from standard automated perimetry. Investigative ophthalmology visual science, 43(1), pp.162-169.Li, F., Wang, Z., Qu, G., Song, D., Yuan, Y., Xu, Y., Gao, K., Luo, G., Xiao, Z., Lam, D.S. and Zhong, H., 2018. Automatic differentiation of glaucoma visual field from non-glaucoma visual filed using deep convolutional neural network. BMC medical imaging, 18(1), pp.1-7.Wang, Z., Keane, P.A., Chiang, M., Cheung, C.Y., Wong, T.Y. and Ting, D.S.W., 2020. Artificial intelligence and deep learning in ophthalmology. Artificial Intelligence in Medicine, pp.1-34.Tan, X.L., Yap, S.C., Li, X. and Yip, L.W., 2017. Comparison of Ethnic-specific Databases in Heidelberg Retina Tomography-3 to Discriminate Between Early Glaucoma and Normal Chinese Eyes. The open ophthalmology journal, 11, p.40.Daniele Grattalora, others. Spektral. GitHub; 2019.Tong, Y., Huang, X., Qi, C.X. and Shen, Y., 2021. Altered Functional Connectivity of the Primary Visual Cortex in Patients With Iridocyclitis and Assessment of Its Predictive Value Using Machine Learning. Frontiers in immunology, 12, p.1650.Smith, T.B., Smith, N. and Weleber, R.G., 2017. Comparison of nonparametric methods for static visual field interpolation. Medical biological engineering computing, 55(1), pp.117-126.Zhang, X., Loewen, N., Tan, O., Greenfield, D.S., Schuman, J.S., Varma, R., Huang, D., Francis, B., Parrish II, R.K., Kishor, K.S. and Quinn, C.D., 2016. Predicting development of glaucomatous visual field conversion using baseline fourier-domain optical coherence tomography. American journal of ophthalmology, 163, pp.29-37.Li, J., Jin, P., Zhu, J., Zou, H., Xu, X., Tang, M., Zhou, M., Gan, Y., He, J., Ling, Y. and Su, Y., 2021. Multi-scale GCN-assisted two-stage network for joint segmentation of retinal layers and discs in peripapillary OCT images. Biomedical Optics Express, 12(4), pp.2204-2220.20162218Publicationhttps://scholar.google.es/citations?user=4TGvo8AAAAJvirtual::13547-1https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0000802506virtual::13547-1https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0000252247virtual::13548-1eb386eec-3ec8-40c2-829d-ae8cbf0e384evirtual::13547-1eb2e8f22-acc4-4b9f-8883-6f65219e5b67virtual::13548-1eb386eec-3ec8-40c2-829d-ae8cbf0e384evirtual::13547-1eb2e8f22-acc4-4b9f-8883-6f65219e5b67virtual::13548-1ORIGINALCustom Built Ethnic-Specific Dataset from SAP Tests for Optic Pathway Disease Diagnosis_Baseline approach using Graph Convolutional Networks.pdfCustom Built Ethnic-Specific Dataset from SAP Tests for Optic Pathway Disease Diagnosis_Baseline approach using Graph Convolutional Networks.pdfMain articleapplication/pdf1657897https://repositorio.uniandes.edu.co/bitstreams/9c100648-cd53-4f57-a30b-d615e3c3e89b/download17d4853f1869415e98c0c44026f8c36cMD54LICENSElicense.txtlicense.txttext/plain; charset=utf-81810https://repositorio.uniandes.edu.co/bitstreams/0e2bea34-22e5-44f2-ac31-c11a656ad974/download5aa5c691a1ffe97abd12c2966efcb8d6MD53THUMBNAILCustom Built Ethnic-Specific Dataset from SAP Tests for Optic Pathway Disease Diagnosis_Baseline approach using Graph Convolutional Networks.pdf.jpgCustom Built Ethnic-Specific Dataset from SAP Tests for Optic Pathway Disease Diagnosis_Baseline approach using Graph Convolutional Networks.pdf.jpgIM Thumbnailimage/jpeg17696https://repositorio.uniandes.edu.co/bitstreams/5d974fba-b535-4faf-aa51-3da8da00b846/download333ccb4699fe6fc0a7f68b8c19723e1aMD58TEXTCustom Built Ethnic-Specific Dataset from SAP Tests for Optic Pathway Disease Diagnosis_Baseline approach using Graph Convolutional Networks.pdf.txtCustom Built Ethnic-Specific Dataset from SAP Tests for Optic Pathway Disease Diagnosis_Baseline approach using Graph Convolutional Networks.pdf.txtExtracted texttext/plain23927https://repositorio.uniandes.edu.co/bitstreams/01629277-bcc3-4f8f-bfb6-233644e7ef92/download04683e7447a510c12734e56dbd3d7d4eMD571992/54464oai:repositorio.uniandes.edu.co:1992/544642024-03-13 14:57:54.348https://repositorio.uniandes.edu.co/static/pdf/aceptacion_uso_es.pdfopen.accesshttps://repositorio.uniandes.edu.coRepositorio institucional Sénecaadminrepositorio@uniandes.edu.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 |