Logotipo del repositorio
Logotipo del repositorio
 

An innovative methodology for segmenting vessel like structures using artificial intelligence and image processing

Vista sencilla de ítem
datacite.rightshttp://purl.org/coar/access_right/c_abf2
dc.contributor.authorAyala Mantilla, Cristian Eduardo
dc.contributor.authorVillarreal, Reynaldo
dc.contributor.authorChamorro-Solano, Sindy
dc.contributor.authorCantillo, Steffen
dc.contributor.authorPestana-Nobles, Roberto
dc.contributor.authorArquez, Sair
dc.contributor.authorVega-Sampayo, Yolanda
dc.contributor.authorPacheco-Londoño, Leonardo
dc.contributor.authorPaez, Jheifer
dc.contributor.authorGalan-Freyle, Nataly
dc.contributor.authorAmar, Paola
dc.date.accessioned2025-05-19T16:45:37Z
dc.date.available2025-05-19T16:45:37Z
dc.date.issued2025
dc.description.abstractInnovation is currently driving enhanced performance and productivity across various fields through process automation. However, identifying intricate details in images can often pose challenges due to morphological variations or specific conditions. Here, artificial intelligence (AI) plays a crucial role by simplifying the segmentation of images.This is achieved by training algorithms to detect specific pixels, thereby recognizing details within images. In this study, an algorithm incorporating modules based on Efficient Sub-Pixel Convolutional Neural Network forimage super-resolution, U-Net based Neural baseline for image segmentation, and image binarization for masking was developed. The combination of these modules aimed to identify capillary structures at pixel level. The method was applied on different datasets containing images of eye fundus, citrus leaves, printed circuit boards to test how well it could segment the capillary structures. Notably, the trained model exhibited versatility in recognizing capillary structures across various image types.When tested with the Set 5 and Set 14 datasets, a PSNR of 37.92 and SSIM of 0.9219 was achieved, surpassing significantly other image superresolution methods.The enhancement module processes the image using three different varaiables in the same way, which imposes a complexity of O(n) and takes 308,734 ms to execute; the segmentation module evaluates each pixel against its neighbors to correctly segment regions of interes, generating an O(n2) quadratic complexity and taking 687,509 ms to execute; the masking module makes several runs through the whole image and in several occasions it calls processes of O(n log n) complexity at 581686 microseconds to execute, which makes it not only the most complex but also the most exhaustive part of the program. This versatility, rooted in its pixel-level operation, enables the algorithm to identify initially unnoticed details, enhancing its applicability across diverse image datasets. This innovation holds significant potential for precisely studying certain structures’ characteristics while enhancing and processing images with high fidelity through AI-driven machine learning algorithms.eng
dc.format.mimetypepdf
dc.identifier.citationVillarreal, R., Chamorro-Solano, S., Cantillo, S. et al. An innovative methodology for segmenting vessel like structures using artificial intelligence and image processing. Sci Rep 14, 30332 (2024). https://doi.org/10.1038/s41598-024-81680-9eng
dc.identifier.doihttps://doi.org/10.1038/s41598-024-81680-9
dc.identifier.issn2045-2322 (Electrónico)
dc.identifier.urihttps://hdl.handle.net/20.500.12442/16593
dc.identifier.urlhttps://www.nature.com/articles/s41598-024-81680-9#citeas
dc.language.isoeng
dc.publisherSpringer Naturespa
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 Internationaleng
dc.rights.accessrightsinfo:eu-repo/semantics/openAccess
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/
dc.sourceScientific Reportseng
dc.sourceSci Repeng
dc.sourceVol. 14 No. 30332, (2024)spa
dc.subject.keywordsArtificial intelligenceeng
dc.subject.keywordsImage segmentationeng
dc.subject.keywordsConvolutional neural networkeng
dc.subject.keywordsPixeleng
dc.titleAn innovative methodology for segmenting vessel like structures using artificial intelligence and image processingeng
dc.type.driverinfo:eu-repo/semantics/article
dc.type.spaArtículo científico
dcterms.referencesKollem, S. R. & Panlal, B. Enhancement of images using morphological transformations. Int. J. Comput. Sci. Inf. Technol.4, https:// doi.org/10.5121/ijcsit.2012.4103 (2012).eng
dcterms.referencesShi, W. et al. Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network (2016). arXiv:1609.05158.eng
dcterms.referencesShao, G. et al. Sub-pixel convolutional neural network for image super-resolution reconstruction. Electronics 12, 3572. https://doi.org/10.3390/electronics12173572 (2023).eng
dcterms.referencesConstante, P., Gordon, A., Chang, O., Pruna, E. & Escobar, I. Neural networks for optic nerve detection in digital optic fundus images. In 2016 IEEE International Conference on Automatica (ICA-ACCA), 1–5, https://doi.org/10.1109/ICA-ACCA.2016.7778415 (2016).eng
dcterms.referencesBukowy, J. D. et al. Region-based convolutional neural nets for localization of glomeruli in trichrome-stained whole kidney sections. J. Am. Soc. Nephrol. 29, 2081–2088 (2018).eng
dcterms.referencesKrizhevsky, A., Sutskever, I. & Hinton, G. E. Imagenet classification with deep convolutional neural networks. In Proceedings of the 25th International Conference on Neural Information Processing Systems-Volume 1, NIPS’12, 1097–1105 (Curran Associates Inc., Red Hook, NY, USA, 2012).eng
dcterms.referencesMansar, Y. Vessel segmentation with python and keras (2019).eng
dcterms.referencesDrive: Digital retinal images for vessel extraction (n.d.).eng
dcterms.referencesJinkai, Y., Guozhong, W. & Liangqi, Z. Region of interest coding based on convolutional neural network. J. Phys. Conf. Ser. 1907, 012028. https://doi.org/10.1088/1742-6596/1907/1/012028 (2021).eng
dcterms.referencesAdamo, A. et al. Blood vessel detection algorithm for tissue engineering and quantitative histology. Ann. Biomed. Eng. 50, 387–400 (2022).eng
dcterms.referencesOoi, A. Z. H. et al. Interactive blood vessel segmentation from retinal fundus image based on canny edge detector. Sensors 21, 6380. https://doi.org/10.3390/s21196380 (2021).eng
dcterms.referencesDevane, V., Sahane, G., Khairmode, H. & Datkhile, G. Lane detection techniques using image processing. ITM Web of Conferences, vol. 40, 03011. https://doi.org/10.1051/itmconf/20214003011 (2021).eng
dcterms.referencesMcGarry, S. D. et al. Vessel metrics: A software tool for automated analysis of vascular structure in confocal imaging. Microvasc. Res. 151, 104610. https://doi.org/10.1016/j.mvr.2023.104610 (2024).eng
dcterms.referencesLong, X. Deep learning tutorial for kaggle ultrasound nerve segmentation competition, using keras. https://github.com/keras-team/keras-io/blob/master/examples/vision/super_resolution_sub_pixel.py (2020).eng
dcterms.referencesRonneberger, O., Fischer, P. & Brox, T. U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention (MICCAI), vol. 9351 of LNCS, 234–241 (Springer, 2015). (available on arXiv:1505.04597 [cs.CV]).eng
dcterms.referencesBevilacqua, M., Roumy, A., Guillemot, C. M. & Alberi-Morel, M.-L. Low-complexity single-image super-resolution based on nonnegative neighbor embedding. In British Machine Vision Conference (2012).eng
dcterms.referencesZeyde, R., Elad, M. & Protter, M. On single image scale-up using sparse-representations. In Curves and Surfaces (eds Boissonnat, J.-D. et al.) 711–730 (Springer, 2012).eng
dcterms.referencesHoover, A., Kouznetsova, V. & Goldbaum, M. Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response. IEEE Trans. Med. Imaging 19, 203–10. https://doi.org/10.1109/42.845178 (2000).eng
dcterms.referencesCitrus leaves dataset (n.d.).eng
dcterms.referencesHuang, W. & Wei, P. A PCB dataset for defects detection and classification (2019). arXiv:1901.08204.eng
dcterms.referencesSara, U., Akter, M. & Uddin, M. Image quality assessment through FSIM, SSIM, MSE and PSNR-a comparative study. J. Comput. Commun. 7, 8–18. https://doi.org/10.4236/jcc.2019.73002 (2019).eng
dcterms.referencesDeshpande, R. G., Ragha, L. L. & Sharma, S. K. Video quality assessment through PSNR estimation for different compression standards. Indones. J. Electr. Eng. Comput. Sci. 11, 918 (2018).eng
dcterms.referencesSøgaard, J. et al. Applicability of existing objective metrics of perceptual quality for adaptive video streaming. Electron. Imaging 28, 1–7. https://doi.org/10.2352/ISSN.2470-1173.2016.13.IQSP-206 (2016).eng
dcterms.referencesKumar, R. & Moyal, V. Visual image quality assessment technique using FSIM. Int. J. Comput. Appl. Technol. Res. 2, 250–254. https://doi.org/10.7753/IJCATR0203.1008 (2013).eng
dcterms.referencesYang, W., Liu, J., Yang, S. & Quo, Z. Image super-resolution via nonlocal similarity and group structured sparse representation. In 2015 Visual Communications and Image Processing (VCIP) (IEEE, 2015).eng
dcterms.referencesKim, K. I. & Kwon, Y. Single-image super-resolution using sparse regression and natural image prior. IEEE Trans. Pattern Anal. Mach. Intell. 32, 1127–1133 (2010).eng
dcterms.referencesGlasner, D., Bagon, S. & Irani, M. Super-resolution from a single image. In 2009 IEEE 12th International Conference on Computer Vision (IEEE, 2009).eng
dcterms.referencesDong, C., Loy, C. C., He, K. & Tang, X. Learning a deep convolutional network for image super-resolution. In Computer Vision–ECCV 2014, Lecture Notes in Computer Science, 184–199 (Springer International Publishing, Cham, 2014).eng
dcterms.referencesHuang, J.-B., Singh, A. & Ahuja, N. Single image super-resolution from transformed self-exemplars. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 5197–5206 (2015).eng
oaire.versioninfo:eu-repo/semantics/publishedVersion
sb.investigacionSistemas robóticos y control automático
sb.programaMaestría en Gestión y Emprendimiento Tecnológicospa
sb.sedeSede Barranquillaspa

Archivos

Bloque original
Mostrando 1 - 1 de 1
Miniatura
Nombre:
PDF.pdf
Tamaño:
1.23 MB
Formato:
Adobe Portable Document Format
Descargar
Bloque de licencias
Mostrando 1 - 1 de 1
No hay miniatura disponible
Nombre:
license.txt
Tamaño:
2.93 KB
Formato:
Item-specific license agreed upon to submission
Descripción:
Descargar

Colecciones

Maestrías
Artículos

Universidad Simón Bolívar: Todos los derechos reservados / Sistema de biblioteca