SEGSRNet for Stereo-Endoscopic Image Super-Resolution and Surgical Instrument Segmentation

Simple item page
dc.contributor.authorHayat M.
dc.contributor.authorAramvith S.
dc.contributor.authorAchakulvisut T.
dc.contributor.correspondenceHayat M.
dc.contributor.otherMahidol University
dc.date.accessioned2025-01-22T18:09:16Z
dc.date.available2025-01-22T18:09:16Z
dc.date.issued2024-01-01
dc.description.abstractSEGSRNet addresses the challenge of precisely identifying surgical instruments in low-resolution stereo endoscopic images, a common issue in medical imaging and robotic surgery. Our innovative framework enhances image clarity and segmentation accuracy by applying state-of-the-art super-resolution techniques before segmentation. This ensures higher-quality inputs for more precise segmentation. SEGSRNet combines advanced feature extraction and attention mechanisms with spatial processing to sharpen image details, which is significant for accurate tool identification in medical images. Our proposed model, SEGSRNet, surpasses existing models in evaluation metrics including PSNR and SSIM for super-resolution tasks, as well as IoU and Dice Score for segmentation. SEGSRNet can provide image resolution and precise segmentation which can significantly enhance surgical accuracy and patient care outcomes.
dc.identifier.citationProceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS (2024)
dc.identifier.doi10.1109/EMBC53108.2024.10782794
dc.identifier.issn1557170X
dc.identifier.scopus2-s2.0-85214978829
dc.identifier.urihttps://repository.li.mahidol.ac.th/handle/20.500.14594/102710
dc.rights.holderSCOPUS
dc.subjectComputer Science
dc.subjectMedicine
dc.subjectEngineering
dc.titleSEGSRNet for Stereo-Endoscopic Image Super-Resolution and Surgical Instrument Segmentation
dc.typeConference Paper
mu.datasource.scopushttps://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85214978829&origin=inward
oaire.citation.titleProceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
oairecerif.author.affiliationChulalongkorn University
oairecerif.author.affiliationMahidol University
Files
Collections
Scopus 2024