FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3033958560> ?p ?o ?g. }

• W3033958560 endingPage "3543" @default.
• W3033958560 startingPage "3543" @default.
• W3033958560 abstract "We report an end-to-end image compression framework for retina optical coherence tomography (OCT) images based on convolutional neural networks (CNNs), which achieved an image size compression ratio as high as 80. Our compression scheme consists of three parts: data preprocessing, compression CNNs, and reconstruction CNNs. The preprocessing module was designed to reduce OCT speckle noise and segment out the region of interest. Skip connections with quantization were developed and added between the compression CNNs and the reconstruction CNNs to reserve the fine-structure information. Two networks were trained together by taking the semantic segmented images from the preprocessing module as input. To train the two networks sensitive to both low and high frequency information, we leveraged an objective function with two components: an adversarial discriminator to judge the high frequency information and a differentiable multi-scale structural similarity (MS-SSIM) penalty to evaluate the low frequency information. The proposed framework was trained and evaluated on ophthalmic OCT images with pathological information. The evaluation showed reconstructed images can still achieve above 99% similarity in terms of MS-SSIM when the compression ratio reached 40. Furthermore, the reconstructed images after 80-fold compression with the proposed framework even presented comparable quality with those of a compression ratio 20 from state-of-the-art methods. The test results showed that the proposed framework outperformed other methods in terms of both MS-SSIM and visualization, which was more obvious at higher compression ratios. Compression and reconstruction were fast and took only about 0.015 seconds per image. The results suggested a promising potential of deep neural networks on customized medical image compression, particularly valuable for effective image storage and tele-transfer." @default.
• W3033958560 created "2020-06-12" @default.
• W3033958560 creator A5014330564 @default.
• W3033958560 creator A5058782332 @default.
• W3033958560 creator A5077533618 @default.
• W3033958560 date "2020-06-08" @default.
• W3033958560 modified "2023-10-18" @default.
• W3033958560 title "Deep OCT image compression with convolutional neural networks" @default.
• W3033958560 cites W1974438823 @default.
• W3033958560 cites W2013754472 @default.
• W3033958560 cites W2039243083 @default.
• W3033958560 cites W2040747879 @default.
• W3033958560 cites W2055834582 @default.
• W3033958560 cites W2056370875 @default.
• W3033958560 cites W2074598933 @default.
• W3033958560 cites W2115907784 @default.
• W3033958560 cites W2133665775 @default.
• W3033958560 cites W2140196014 @default.
• W3033958560 cites W2565237689 @default.
• W3033958560 cites W2606534623 @default.
• W3033958560 cites W2608854843 @default.
• W3033958560 cites W2766934651 @default.
• W3033958560 cites W2773475231 @default.
• W3033958560 cites W2913512232 @default.
• W3033958560 cites W2959574828 @default.
• W3033958560 cites W2963392702 @default.
• W3033958560 cites W3002421716 @default.
• W3033958560 cites W4250955649 @default.
• W3033958560 doi "https://doi.org/10.1364/boe.392882" @default.
• W3033958560 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/7510896" @default.
• W3033958560 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33014550" @default.
• W3033958560 hasPublicationYear "2020" @default.
• W3033958560 type Work @default.
• W3033958560 sameAs 3033958560 @default.
• W3033958560 citedByCount "11" @default.
• W3033958560 countsByYear W30339585602020 @default.
• W3033958560 countsByYear W30339585602021 @default.
• W3033958560 countsByYear W30339585602022 @default.
• W3033958560 countsByYear W30339585602023 @default.
• W3033958560 crossrefType "journal-article" @default.
• W3033958560 hasAuthorship W3033958560A5014330564 @default.
• W3033958560 hasAuthorship W3033958560A5058782332 @default.
• W3033958560 hasAuthorship W3033958560A5077533618 @default.
• W3033958560 hasBestOaLocation W30339585601 @default.
• W3033958560 hasConcept C102290492 @default.
• W3033958560 hasConcept C108583219 @default.
• W3033958560 hasConcept C115961682 @default.
• W3033958560 hasConcept C120665830 @default.
• W3033958560 hasConcept C121332964 @default.
• W3033958560 hasConcept C127413603 @default.
• W3033958560 hasConcept C13481523 @default.
• W3033958560 hasConcept C141379421 @default.
• W3033958560 hasConcept C153180895 @default.
• W3033958560 hasConcept C154945302 @default.
• W3033958560 hasConcept C171146098 @default.
• W3033958560 hasConcept C25797200 @default.
• W3033958560 hasConcept C2778818243 @default.
• W3033958560 hasConcept C31972630 @default.
• W3033958560 hasConcept C34736171 @default.
• W3033958560 hasConcept C41008148 @default.
• W3033958560 hasConcept C511840579 @default.
• W3033958560 hasConcept C55020928 @default.
• W3033958560 hasConcept C78548338 @default.
• W3033958560 hasConcept C81363708 @default.
• W3033958560 hasConcept C9417928 @default.
• W3033958560 hasConcept C94835093 @default.
• W3033958560 hasConceptScore W3033958560C102290492 @default.
• W3033958560 hasConceptScore W3033958560C108583219 @default.
• W3033958560 hasConceptScore W3033958560C115961682 @default.
• W3033958560 hasConceptScore W3033958560C120665830 @default.
• W3033958560 hasConceptScore W3033958560C121332964 @default.
• W3033958560 hasConceptScore W3033958560C127413603 @default.
• W3033958560 hasConceptScore W3033958560C13481523 @default.
• W3033958560 hasConceptScore W3033958560C141379421 @default.
• W3033958560 hasConceptScore W3033958560C153180895 @default.
• W3033958560 hasConceptScore W3033958560C154945302 @default.
• W3033958560 hasConceptScore W3033958560C171146098 @default.
• W3033958560 hasConceptScore W3033958560C25797200 @default.
• W3033958560 hasConceptScore W3033958560C2778818243 @default.
• W3033958560 hasConceptScore W3033958560C31972630 @default.
• W3033958560 hasConceptScore W3033958560C34736171 @default.
• W3033958560 hasConceptScore W3033958560C41008148 @default.
• W3033958560 hasConceptScore W3033958560C511840579 @default.
• W3033958560 hasConceptScore W3033958560C55020928 @default.
• W3033958560 hasConceptScore W3033958560C78548338 @default.
• W3033958560 hasConceptScore W3033958560C81363708 @default.
• W3033958560 hasConceptScore W3033958560C9417928 @default.
• W3033958560 hasConceptScore W3033958560C94835093 @default.
• W3033958560 hasFunder F4320332161 @default.
• W3033958560 hasIssue "7" @default.
• W3033958560 hasLocation W30339585601 @default.
• W3033958560 hasLocation W30339585602 @default.
• W3033958560 hasLocation W30339585603 @default.
• W3033958560 hasOpenAccess W3033958560 @default.
• W3033958560 hasPrimaryLocation W30339585601 @default.
• W3033958560 hasRelatedWork W1998019344 @default.
• W3033958560 hasRelatedWork W2134668030 @default.
• W3033958560 hasRelatedWork W2162295290 @default.

• next