Machine learning classification for epilepsy lesions localization based on MRIs
Treatment of epilepsy patients usually involves antiepileptic drugs to control seizures. However, patients with drug-resistant, or refractory epilepsy go through various trials before becoming candidates for surgery to treat brain lesions that cause their seizures, and this process can take a long t...
- Autores:
-
González García, Néstor Felipe
- Tipo de recurso:
- Trabajo de grado de pregrado
- Fecha de publicación:
- 2024
- Institución:
- Universidad de los Andes
- Repositorio:
- Séneca: repositorio Uniandes
- Idioma:
- eng
- OAI Identifier:
- oai:repositorio.uniandes.edu.co:1992/73657
- Acceso en línea:
- https://hdl.handle.net/1992/73657
- Palabra clave:
- Machine learning
Epilepsy
Magnetic resonance images
Ingeniería
- Rights
- openAccess
- License
- Attribution-NonCommercial-NoDerivatives 4.0 International
| id |
UNIANDES2_c647d4df52a105148ff318f5e82c8191 |
|---|---|
| oai_identifier_str |
oai:repositorio.uniandes.edu.co:1992/73657 |
| network_acronym_str |
UNIANDES2 |
| network_name_str |
Séneca: repositorio Uniandes |
| repository_id_str |
|
| dc.title.eng.fl_str_mv |
Machine learning classification for epilepsy lesions localization based on MRIs |
| title |
Machine learning classification for epilepsy lesions localization based on MRIs |
| spellingShingle |
Machine learning classification for epilepsy lesions localization based on MRIs Machine learning Epilepsy Magnetic resonance images Ingeniería |
| title_short |
Machine learning classification for epilepsy lesions localization based on MRIs |
| title_full |
Machine learning classification for epilepsy lesions localization based on MRIs |
| title_fullStr |
Machine learning classification for epilepsy lesions localization based on MRIs |
| title_full_unstemmed |
Machine learning classification for epilepsy lesions localization based on MRIs |
| title_sort |
Machine learning classification for epilepsy lesions localization based on MRIs |
| dc.creator.fl_str_mv |
González García, Néstor Felipe |
| dc.contributor.advisor.none.fl_str_mv |
Garcés Pernett, Kelly Johany Duitama Castellanos, Jorge Alexander |
| dc.contributor.author.none.fl_str_mv |
González García, Néstor Felipe |
| dc.contributor.researchgroup.none.fl_str_mv |
Facultad de Ingeniería::TICSw: Tecnologías de Información y Construcción de Software |
| dc.subject.keyword.eng.fl_str_mv |
Machine learning Epilepsy Magnetic resonance images |
| topic |
Machine learning Epilepsy Magnetic resonance images Ingeniería |
| dc.subject.themes.spa.fl_str_mv |
Ingeniería |
| description |
Treatment of epilepsy patients usually involves antiepileptic drugs to control seizures. However, patients with drug-resistant, or refractory epilepsy go through various trials before becoming candidates for surgery to treat brain lesions that cause their seizures, and this process can take a long time. In this work, a machine learning approach was used to localize lesions in refractory patients by grouping lesions in two categories: hemisphere (left and right), and lobe (frontal lobe and other lobes). To train the model, a public magnetic resonance image (MRI) dataset was used and images went through a preprocessing pipeline that consisted of histogram oriented gradients, and principal component analysis. The models were tuned through cross validation techniques and then compared by their metrics to choose the best performing model for each type of image viewpoint (sagittal, coronal, and axial). |
| publishDate |
2024 |
| dc.date.accessioned.none.fl_str_mv |
2024-01-31T12:47:58Z |
| dc.date.available.none.fl_str_mv |
2024-01-31T12:47:58Z |
| dc.date.issued.none.fl_str_mv |
2024-01-24 |
| dc.type.none.fl_str_mv |
Trabajo de grado - Pregrado |
| dc.type.driver.none.fl_str_mv |
info:eu-repo/semantics/bachelorThesis |
| dc.type.version.none.fl_str_mv |
info:eu-repo/semantics/acceptedVersion |
| dc.type.coar.none.fl_str_mv |
http://purl.org/coar/resource_type/c_7a1f |
| dc.type.content.none.fl_str_mv |
Text |
| dc.type.redcol.none.fl_str_mv |
http://purl.org/redcol/resource_type/TP |
| format |
http://purl.org/coar/resource_type/c_7a1f |
| status_str |
acceptedVersion |
| dc.identifier.uri.none.fl_str_mv |
https://hdl.handle.net/1992/73657 |
| dc.identifier.instname.none.fl_str_mv |
instname:Universidad de los Andes |
| dc.identifier.reponame.none.fl_str_mv |
reponame:Repositorio Institucional Séneca |
| dc.identifier.repourl.none.fl_str_mv |
repourl:https://repositorio.uniandes.edu.co/ |
| url |
https://hdl.handle.net/1992/73657 |
| identifier_str_mv |
instname:Universidad de los Andes reponame:Repositorio Institucional Séneca repourl:https://repositorio.uniandes.edu.co/ |
| dc.language.iso.none.fl_str_mv |
eng |
| language |
eng |
| dc.relation.references.none.fl_str_mv |
Chauhan, V.K., Dahiya, K. & Sharma, A. (2019). Problem formulations and solvers in linear SVM: a review. Artif Intell Rev 52, 803–855. https://doi.org/10.1007/s10462-018-9614-6 Chen, T., & Guestrin, C. (2016). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining (pp. 785-794). El Azami M., Hammers A., Jung J., Costes N., Bouet R., et al. (2016). Detection of Lesions Underlying Intractable Epilepsy on T1-Weighted MRI as an Outlier Detection Problem. PLOS ONE 11(9): e0161498. https://doi.org/10.1371/journal.pone.0161498 Luckett, P., Maccotta, L., Lee, J., Park, K., Dosenbach, N., Ances, B., et al. (2022). Deep learning resting state functional magnetic resonance imaging lateralization of temporal lobe epilepsy. Epilepsia; 63: 1542–1552. https://doi.org/10.1111/epi.17233 Murphy, J. (2016). An overview of convolutional neural network architectures for deep learning. Microway Inc, 1-22. Schuch, F., Walger, L., Schmitz, M. et al. (2023). An open presurgery MRI dataset of people with epilepsy and focal cortical dysplasia type II. Sci Data 10, 475. https://doi.org/10.1038/s41597-023-02386-7 Shilaskar, S., Mahajan, T., Bhatlawande, S., Chaudhari, S., Mahajan, R. and Junnare, K. (2023). "Machine Learning based Brain Tumor Detection and Classification using HOG Feature Descriptor," 2023 International Conference on Sustainable Computing and Smart Systems (ICSCSS), pp. 67-75, doi: 10.1109/ICSCSS57650.2023.10169700 Tabatabaei, S., Rezaee, K. and Zhu, M. (2023). ‘Attention transformer mechanism and fusion-based deep learning architecture for MRI Brain Tumor Classification System’, Biomedical Signal Processing and Control, 86, p. 105119. doi:10.1016/j.bspc.2023.105119. World Health Organization. (n.d.). Epilepsy. https://www.who.int/es/news-room/fact-sheets/detail/epilepsy Wu, X., Kumar, V., Ross Quinlan, J. et al. (2008). Top 10 algorithms in data mining. Knowl Inf Syst 14, 1–37. https://doi.org/10.1007/s10115-007-0114-2 |
| dc.rights.en.fl_str_mv |
Attribution-NonCommercial-NoDerivatives 4.0 International |
| dc.rights.uri.none.fl_str_mv |
http://creativecommons.org/licenses/by-nc-nd/4.0/ |
| dc.rights.accessrights.none.fl_str_mv |
info:eu-repo/semantics/openAccess |
| dc.rights.coar.none.fl_str_mv |
http://purl.org/coar/access_right/c_abf2 |
| rights_invalid_str_mv |
Attribution-NonCommercial-NoDerivatives 4.0 International http://creativecommons.org/licenses/by-nc-nd/4.0/ http://purl.org/coar/access_right/c_abf2 |
| eu_rights_str_mv |
openAccess |
| dc.format.extent.none.fl_str_mv |
22 páginas |
| dc.format.mimetype.none.fl_str_mv |
application/pdf |
| dc.publisher.none.fl_str_mv |
Universidad de los Andes |
| dc.publisher.program.none.fl_str_mv |
Ingeniería de Sistemas y Computación |
| dc.publisher.faculty.none.fl_str_mv |
Facultad de Ingeniería |
| dc.publisher.department.none.fl_str_mv |
Departamento de Ingeniería Sistemas y Computación |
| publisher.none.fl_str_mv |
Universidad de los Andes |
| institution |
Universidad de los Andes |
| bitstream.url.fl_str_mv |
https://repositorio.uniandes.edu.co/bitstreams/1a7165d5-e8af-40fa-8d9a-1aa4dc9eef2b/download https://repositorio.uniandes.edu.co/bitstreams/01886164-b5c9-400b-98b7-5a3a96014bc7/download https://repositorio.uniandes.edu.co/bitstreams/ac7a2954-9da3-4fdb-8938-703f14f75577/download https://repositorio.uniandes.edu.co/bitstreams/400d80f9-717e-4bb7-8b60-6da3f67b626a/download https://repositorio.uniandes.edu.co/bitstreams/4ac4f705-8f19-4460-b105-d30fd782a5dc/download https://repositorio.uniandes.edu.co/bitstreams/d0b0126a-af9f-4b78-ac2b-9b8a3b59b774/download https://repositorio.uniandes.edu.co/bitstreams/b3b94b8a-1623-4e07-8d34-8c7c4a0e5c34/download https://repositorio.uniandes.edu.co/bitstreams/bd40bf08-6892-4d2d-ad31-8c93e134aadf/download |
| bitstream.checksum.fl_str_mv |
c4acb876afc719a522f37e64abaace30 c9757d7f6f9ef7e4449191f3519cd582 4460e5956bc1d1639be9ae6146a50347 ae9e573a68e7f92501b6913cc846c39f 2dd32494168cb60222b579c46d1a62c9 66a327c004d91f9e6c786faf8b074150 d32ea5cc088fbf6f511146e546d72cd8 968ac647169c91d96034bb8451b8e269 |
| bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 MD5 MD5 MD5 MD5 |
| repository.name.fl_str_mv |
Repositorio institucional Séneca |
| repository.mail.fl_str_mv |
adminrepositorio@uniandes.edu.co |
| _version_ |
1812133981990158336 |
| spelling |
Garcés Pernett, Kelly JohanyDuitama Castellanos, Jorge AlexanderGonzález García, Néstor FelipeFacultad de Ingeniería::TICSw: Tecnologías de Información y Construcción de Software2024-01-31T12:47:58Z2024-01-31T12:47:58Z2024-01-24https://hdl.handle.net/1992/73657instname:Universidad de los Andesreponame:Repositorio Institucional Sénecarepourl:https://repositorio.uniandes.edu.co/Treatment of epilepsy patients usually involves antiepileptic drugs to control seizures. However, patients with drug-resistant, or refractory epilepsy go through various trials before becoming candidates for surgery to treat brain lesions that cause their seizures, and this process can take a long time. In this work, a machine learning approach was used to localize lesions in refractory patients by grouping lesions in two categories: hemisphere (left and right), and lobe (frontal lobe and other lobes). To train the model, a public magnetic resonance image (MRI) dataset was used and images went through a preprocessing pipeline that consisted of histogram oriented gradients, and principal component analysis. The models were tuned through cross validation techniques and then compared by their metrics to choose the best performing model for each type of image viewpoint (sagittal, coronal, and axial).Ingeniero de Sistemas y ComputaciónPregrado22 páginasapplication/pdfengUniversidad de los AndesIngeniería de Sistemas y ComputaciónFacultad de IngenieríaDepartamento de Ingeniería Sistemas y ComputaciónAttribution-NonCommercial-NoDerivatives 4.0 Internationalhttp://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccesshttp://purl.org/coar/access_right/c_abf2Machine learning classification for epilepsy lesions localization based on MRIsTrabajo de grado - Pregradoinfo:eu-repo/semantics/bachelorThesisinfo:eu-repo/semantics/acceptedVersionhttp://purl.org/coar/resource_type/c_7a1fTexthttp://purl.org/redcol/resource_type/TPMachine learningEpilepsyMagnetic resonance imagesIngenieríaChauhan, V.K., Dahiya, K. & Sharma, A. (2019). Problem formulations and solvers in linear SVM: a review. Artif Intell Rev 52, 803–855. https://doi.org/10.1007/s10462-018-9614-6Chen, T., & Guestrin, C. (2016). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining (pp. 785-794).El Azami M., Hammers A., Jung J., Costes N., Bouet R., et al. (2016). Detection of Lesions Underlying Intractable Epilepsy on T1-Weighted MRI as an Outlier Detection Problem. PLOS ONE 11(9): e0161498. https://doi.org/10.1371/journal.pone.0161498 Luckett, P., Maccotta, L., Lee, J., Park, K., Dosenbach, N., Ances, B., et al. (2022). Deep learning resting state functional magnetic resonance imaging lateralization of temporal lobe epilepsy. Epilepsia; 63: 1542–1552. https://doi.org/10.1111/epi.17233Murphy, J. (2016). An overview of convolutional neural network architectures for deep learning. Microway Inc, 1-22.Schuch, F., Walger, L., Schmitz, M. et al. (2023). An open presurgery MRI dataset of people with epilepsy and focal cortical dysplasia type II. Sci Data 10, 475. https://doi.org/10.1038/s41597-023-02386-7 Shilaskar, S., Mahajan, T., Bhatlawande, S., Chaudhari, S., Mahajan, R. and Junnare, K. (2023). "Machine Learning based Brain Tumor Detection and Classification using HOG Feature Descriptor," 2023 International Conference on Sustainable Computing and Smart Systems (ICSCSS), pp. 67-75, doi: 10.1109/ICSCSS57650.2023.10169700Tabatabaei, S., Rezaee, K. and Zhu, M. (2023). ‘Attention transformer mechanism and fusion-based deep learning architecture for MRI Brain Tumor Classification System’, Biomedical Signal Processing and Control, 86, p. 105119. doi:10.1016/j.bspc.2023.105119. World Health Organization. (n.d.). Epilepsy. https://www.who.int/es/news-room/fact-sheets/detail/epilepsyWu, X., Kumar, V., Ross Quinlan, J. et al. (2008). Top 10 algorithms in data mining. Knowl Inf Syst 14, 1–37. https://doi.org/10.1007/s10115-007-0114-2201912670PublicationORIGINALMachine Learning Classification for Epilepsy.pdfMachine Learning Classification for Epilepsy.pdfapplication/pdf2297958https://repositorio.uniandes.edu.co/bitstreams/1a7165d5-e8af-40fa-8d9a-1aa4dc9eef2b/downloadc4acb876afc719a522f37e64abaace30MD52AutorizacionTesisNestorGonzalez_firmaJDKG.pdfAutorizacionTesisNestorGonzalez_firmaJDKG.pdfHIDEapplication/pdf314727https://repositorio.uniandes.edu.co/bitstreams/01886164-b5c9-400b-98b7-5a3a96014bc7/downloadc9757d7f6f9ef7e4449191f3519cd582MD55CC-LICENSElicense_rdflicense_rdfapplication/rdf+xml; charset=utf-8805https://repositorio.uniandes.edu.co/bitstreams/ac7a2954-9da3-4fdb-8938-703f14f75577/download4460e5956bc1d1639be9ae6146a50347MD53LICENSElicense.txtlicense.txttext/plain; charset=utf-82535https://repositorio.uniandes.edu.co/bitstreams/400d80f9-717e-4bb7-8b60-6da3f67b626a/downloadae9e573a68e7f92501b6913cc846c39fMD54TEXTMachine Learning Classification for Epilepsy.pdf.txtMachine Learning Classification for Epilepsy.pdf.txtExtracted texttext/plain36146https://repositorio.uniandes.edu.co/bitstreams/4ac4f705-8f19-4460-b105-d30fd782a5dc/download2dd32494168cb60222b579c46d1a62c9MD56AutorizacionTesisNestorGonzalez_firmaJDKG.pdf.txtAutorizacionTesisNestorGonzalez_firmaJDKG.pdf.txtExtracted texttext/plain1643https://repositorio.uniandes.edu.co/bitstreams/d0b0126a-af9f-4b78-ac2b-9b8a3b59b774/download66a327c004d91f9e6c786faf8b074150MD58THUMBNAILMachine Learning Classification for Epilepsy.pdf.jpgMachine Learning Classification for Epilepsy.pdf.jpgGenerated Thumbnailimage/jpeg14603https://repositorio.uniandes.edu.co/bitstreams/b3b94b8a-1623-4e07-8d34-8c7c4a0e5c34/downloadd32ea5cc088fbf6f511146e546d72cd8MD57AutorizacionTesisNestorGonzalez_firmaJDKG.pdf.jpgAutorizacionTesisNestorGonzalez_firmaJDKG.pdf.jpgGenerated Thumbnailimage/jpeg11470https://repositorio.uniandes.edu.co/bitstreams/bd40bf08-6892-4d2d-ad31-8c93e134aadf/download968ac647169c91d96034bb8451b8e269MD591992/73657oai:repositorio.uniandes.edu.co:1992/736572024-02-16 15:14:06.33http://creativecommons.org/licenses/by-nc-nd/4.0/Attribution-NonCommercial-NoDerivatives 4.0 Internationalopen.accesshttps://repositorio.uniandes.edu.coRepositorio institucional Sénecaadminrepositorio@uniandes.edu.coPGgzPjxzdHJvbmc+RGVzY2FyZ28gZGUgUmVzcG9uc2FiaWxpZGFkIC0gTGljZW5jaWEgZGUgQXV0b3JpemFjacOzbjwvc3Ryb25nPjwvaDM+CjxwPjxzdHJvbmc+UG9yIGZhdm9yIGxlZXIgYXRlbnRhbWVudGUgZXN0ZSBkb2N1bWVudG8gcXVlIHBlcm1pdGUgYWwgUmVwb3NpdG9yaW8gSW5zdGl0dWNpb25hbCBTw6luZWNhIHJlcHJvZHVjaXIgeSBkaXN0cmlidWlyIGxvcyByZWN1cnNvcyBkZSBpbmZvcm1hY2nDs24gZGVwb3NpdGFkb3MgbWVkaWFudGUgbGEgYXV0b3JpemFjacOzbiBkZSBsb3Mgc2lndWllbnRlcyB0w6lybWlub3M6PC9zdHJvbmc+PC9wPgo8cD5Db25jZWRhIGxhIGxpY2VuY2lhIGRlIGRlcMOzc2l0byBlc3TDoW5kYXIgc2VsZWNjaW9uYW5kbyBsYSBvcGNpw7NuIDxzdHJvbmc+J0FjZXB0YXIgbG9zIHTDqXJtaW5vcyBhbnRlcmlvcm1lbnRlIGRlc2NyaXRvcyc8L3N0cm9uZz4geSBjb250aW51YXIgZWwgcHJvY2VzbyBkZSBlbnbDrW8gbWVkaWFudGUgZWwgYm90w7NuIDxzdHJvbmc+J1NpZ3VpZW50ZScuPC9zdHJvbmc+PC9wPgo8aHI+CjxwPllvLCBlbiBtaSBjYWxpZGFkIGRlIGF1dG9yIGRlbCB0cmFiYWpvIGRlIHRlc2lzLCBtb25vZ3JhZsOtYSBvIHRyYWJham8gZGUgZ3JhZG8sIGhhZ28gZW50cmVnYSBkZWwgZWplbXBsYXIgcmVzcGVjdGl2byB5IGRlIHN1cyBhbmV4b3MgZGUgc2VyIGVsIGNhc28sIGVuIGZvcm1hdG8gZGlnaXRhbCB5L28gZWxlY3Ryw7NuaWNvIHkgYXV0b3Jpem8gYSBsYSBVbml2ZXJzaWRhZCBkZSBsb3MgQW5kZXMgcGFyYSBxdWUgcmVhbGljZSBsYSBwdWJsaWNhY2nDs24gZW4gZWwgU2lzdGVtYSBkZSBCaWJsaW90ZWNhcyBvIGVuIGN1YWxxdWllciBvdHJvIHNpc3RlbWEgbyBiYXNlIGRlIGRhdG9zIHByb3BpbyBvIGFqZW5vIGEgbGEgVW5pdmVyc2lkYWQgeSBwYXJhIHF1ZSBlbiBsb3MgdMOpcm1pbm9zIGVzdGFibGVjaWRvcyBlbiBsYSBMZXkgMjMgZGUgMTk4MiwgTGV5IDQ0IGRlIDE5OTMsIERlY2lzacOzbiBBbmRpbmEgMzUxIGRlIDE5OTMsIERlY3JldG8gNDYwIGRlIDE5OTUgeSBkZW3DoXMgbm9ybWFzIGdlbmVyYWxlcyBzb2JyZSBsYSBtYXRlcmlhLCB1dGlsaWNlIGVuIHRvZGFzIHN1cyBmb3JtYXMsIGxvcyBkZXJlY2hvcyBwYXRyaW1vbmlhbGVzIGRlIHJlcHJvZHVjY2nDs24sIGNvbXVuaWNhY2nDs24gcMO6YmxpY2EsIHRyYW5zZm9ybWFjacOzbiB5IGRpc3RyaWJ1Y2nDs24gKGFscXVpbGVyLCBwcsOpc3RhbW8gcMO6YmxpY28gZSBpbXBvcnRhY2nDs24pIHF1ZSBtZSBjb3JyZXNwb25kZW4gY29tbyBjcmVhZG9yIGRlIGxhIG9icmEgb2JqZXRvIGRlbCBwcmVzZW50ZSBkb2N1bWVudG8uPC9wPgo8cD5MYSBwcmVzZW50ZSBhdXRvcml6YWNpw7NuIHNlIGVtaXRlIGVuIGNhbGlkYWQgZGUgYXV0b3IgZGUgbGEgb2JyYSBvYmpldG8gZGVsIHByZXNlbnRlIGRvY3VtZW50byB5IG5vIGNvcnJlc3BvbmRlIGEgY2VzacOzbiBkZSBkZXJlY2hvcywgc2lubyBhIGxhIGF1dG9yaXphY2nDs24gZGUgdXNvIGFjYWTDqW1pY28gZGUgY29uZm9ybWlkYWQgY29uIGxvIGFudGVyaW9ybWVudGUgc2XDsWFsYWRvLiBMYSBwcmVzZW50ZSBhdXRvcml6YWNpw7NuIHNlIGhhY2UgZXh0ZW5zaXZhIG5vIHNvbG8gYSBsYXMgZmFjdWx0YWRlcyB5IGRlcmVjaG9zIGRlIHVzbyBzb2JyZSBsYSBvYnJhIGVuIGZvcm1hdG8gbyBzb3BvcnRlIG1hdGVyaWFsLCBzaW5vIHRhbWJpw6luIHBhcmEgZm9ybWF0byBlbGVjdHLDs25pY28sIHkgZW4gZ2VuZXJhbCBwYXJhIGN1YWxxdWllciBmb3JtYXRvIGNvbm9jaWRvIG8gcG9yIGNvbm9jZXIuPC9wPgo8cD5FbCBhdXRvciwgbWFuaWZpZXN0YSBxdWUgbGEgb2JyYSBvYmpldG8gZGUgbGEgcHJlc2VudGUgYXV0b3JpemFjacOzbiBlcyBvcmlnaW5hbCB5IGxhIHJlYWxpesOzIHNpbiB2aW9sYXIgbyB1c3VycGFyIGRlcmVjaG9zIGRlIGF1dG9yIGRlIHRlcmNlcm9zLCBwb3IgbG8gdGFudG8sIGxhIG9icmEgZXMgZGUgc3UgZXhjbHVzaXZhIGF1dG9yw61hIHkgdGllbmUgbGEgdGl0dWxhcmlkYWQgc29icmUgbGEgbWlzbWEuPC9wPgo8cD5FbiBjYXNvIGRlIHByZXNlbnRhcnNlIGN1YWxxdWllciByZWNsYW1hY2nDs24gbyBhY2Npw7NuIHBvciBwYXJ0ZSBkZSB1biB0ZXJjZXJvIGVuIGN1YW50byBhIGxvcyBkZXJlY2hvcyBkZSBhdXRvciBzb2JyZSBsYSBvYnJhIGVuIGN1ZXN0acOzbiwgZWwgYXV0b3IgYXN1bWlyw6EgdG9kYSBsYSByZXNwb25zYWJpbGlkYWQsIHkgc2FsZHLDoSBkZSBkZWZlbnNhIGRlIGxvcyBkZXJlY2hvcyBhcXXDrSBhdXRvcml6YWRvcywgcGFyYSB0b2RvcyBsb3MgZWZlY3RvcyBsYSBVbml2ZXJzaWRhZCBhY3TDumEgY29tbyB1biB0ZXJjZXJvIGRlIGJ1ZW5hIGZlLjwvcD4KPHA+U2kgdGllbmUgYWxndW5hIGR1ZGEgc29icmUgbGEgbGljZW5jaWEsIHBvciBmYXZvciwgY29udGFjdGUgY29uIGVsIDxhIGhyZWY9Im1haWx0bzpiaWJsaW90ZWNhQHVuaWFuZGVzLmVkdS5jbyIgdGFyZ2V0PSJfYmxhbmsiPkFkbWluaXN0cmFkb3IgZGVsIFNpc3RlbWEuPC9hPjwvcD4K |