Matches in SemOpenAlex for { <https://semopenalex.org/work/W2892904216> ?p ?o ?g. }
- W2892904216 abstract "Purpose: To develop a deep learning approach to de-noise optical coherence tomography (OCT) of the optic nerve head (ONH). Methods: Volume scans consisting of 97 horizontal were acquired through the center of the ONH using a commercial OCT device (Spectralis) for both eyes of 20 subjects. For each eye, single-frame (without signal averaging), and multi-frame (75x signal averaging) volume scans were obtained. A custom deep learning network was then designed and trained with 2,328 clean B-scans (multi-frame B-scans), and their corresponding noisy B-scans (clean + gaussian noise) to de-noise the single-frame B-scans. The performance of the de-noising algorithm was assessed qualitatively, and quantitatively on 1,552 using the signal to noise ratio (SNR), contrast to noise ratio (CNR), and mean structural similarity index metrics (MSSIM). Results: The proposed algorithm successfully denoised unseen single-frame OCT B-scans. The denoised were qualitatively similar to their corresponding multi-frame B-scans, with enhanced visibility of the ONH tissues. The mean SNR increased from $4.02 pm 0.68$ dB (single-frame) to $8.14 pm 1.03$ dB (denoised). For all the ONH tissues, the mean CNR increased from $3.50 pm 0.56$ (single-frame) to $7.63 pm 1.81$ (denoised). The MSSIM increased from $0.13 pm 0.02$ (single frame) to $0.65 pm 0.03$ (denoised) when compared with the corresponding multi-frame B-scans. Conclusions: Our deep learning algorithm can denoise a single-frame OCT B-scan of the ONH in under 20 ms, thus offering a framework to obtain superior quality OCT with reduced scanning times and minimal patient discomfort." @default.
- W2892904216 created "2018-10-05" @default.
- W2892904216 creator A5003710170 @default.
- W2892904216 creator A5010107902 @default.
- W2892904216 creator A5015017045 @default.
- W2892904216 creator A5022464374 @default.
- W2892904216 creator A5028702225 @default.
- W2892904216 creator A5052850959 @default.
- W2892904216 creator A5054878311 @default.
- W2892904216 creator A5075419354 @default.
- W2892904216 creator A5077948782 @default.
- W2892904216 creator A5084165526 @default.
- W2892904216 date "2018-09-27" @default.
- W2892904216 modified "2023-10-01" @default.
- W2892904216 title "A Deep Learning Approach to Denoise Optical Coherence Tomography Images of the Optic Nerve Head" @default.
- W2892904216 cites W1522301498 @default.
- W2892904216 cites W1901129140 @default.
- W2892904216 cites W1963681859 @default.
- W2892904216 cites W1969370809 @default.
- W2892904216 cites W1969824248 @default.
- W2892904216 cites W1987304071 @default.
- W2892904216 cites W1989313966 @default.
- W2892904216 cites W1993982894 @default.
- W2892904216 cites W1996144177 @default.
- W2892904216 cites W1996176493 @default.
- W2892904216 cites W2001966277 @default.
- W2892904216 cites W2004537679 @default.
- W2892904216 cites W2011645092 @default.
- W2892904216 cites W2034581610 @default.
- W2892904216 cites W2043567700 @default.
- W2892904216 cites W2047015107 @default.
- W2892904216 cites W2051247865 @default.
- W2892904216 cites W2057535513 @default.
- W2892904216 cites W2061240737 @default.
- W2892904216 cites W2061608967 @default.
- W2892904216 cites W2066254554 @default.
- W2892904216 cites W2070673984 @default.
- W2892904216 cites W2080843549 @default.
- W2892904216 cites W2086358109 @default.
- W2892904216 cites W2092191888 @default.
- W2892904216 cites W2092569091 @default.
- W2892904216 cites W2092608990 @default.
- W2892904216 cites W2103457061 @default.
- W2892904216 cites W2110325483 @default.
- W2892904216 cites W2112437734 @default.
- W2892904216 cites W2121357494 @default.
- W2892904216 cites W2123284830 @default.
- W2892904216 cites W2123784391 @default.
- W2892904216 cites W2127998931 @default.
- W2892904216 cites W2133665775 @default.
- W2892904216 cites W2134582192 @default.
- W2892904216 cites W2139609138 @default.
- W2892904216 cites W2155062230 @default.
- W2892904216 cites W2156163116 @default.
- W2892904216 cites W2167103060 @default.
- W2892904216 cites W2170059143 @default.
- W2892904216 cites W2194775991 @default.
- W2892904216 cites W2252058454 @default.
- W2892904216 cites W2291483074 @default.
- W2892904216 cites W2314451966 @default.
- W2892904216 cites W2398507096 @default.
- W2892904216 cites W2510850936 @default.
- W2892904216 cites W2512757087 @default.
- W2892904216 cites W2547055928 @default.
- W2892904216 cites W2560622558 @default.
- W2892904216 cites W2589074029 @default.
- W2892904216 cites W2591274972 @default.
- W2892904216 cites W2621028221 @default.
- W2892904216 cites W2741247953 @default.
- W2892904216 cites W2741826584 @default.
- W2892904216 cites W2766624546 @default.
- W2892904216 cites W2787375075 @default.
- W2892904216 cites W2893483035 @default.
- W2892904216 cites W2949117887 @default.
- W2892904216 cites W2951702837 @default.
- W2892904216 cites W2952426750 @default.
- W2892904216 cites W2953139530 @default.
- W2892904216 cites W2963251008 @default.
- W2892904216 cites W2964015468 @default.
- W2892904216 cites W3015841582 @default.
- W2892904216 cites W302579078 @default.
- W2892904216 cites W2132846665 @default.
- W2892904216 cites W2962948707 @default.
- W2892904216 hasPublicationYear "2018" @default.
- W2892904216 type Work @default.
- W2892904216 sameAs 2892904216 @default.
- W2892904216 citedByCount "0" @default.
- W2892904216 crossrefType "posted-content" @default.
- W2892904216 hasAuthorship W2892904216A5003710170 @default.
- W2892904216 hasAuthorship W2892904216A5010107902 @default.
- W2892904216 hasAuthorship W2892904216A5015017045 @default.
- W2892904216 hasAuthorship W2892904216A5022464374 @default.
- W2892904216 hasAuthorship W2892904216A5028702225 @default.
- W2892904216 hasAuthorship W2892904216A5052850959 @default.
- W2892904216 hasAuthorship W2892904216A5054878311 @default.
- W2892904216 hasAuthorship W2892904216A5075419354 @default.
- W2892904216 hasAuthorship W2892904216A5077948782 @default.
- W2892904216 hasAuthorship W2892904216A5084165526 @default.
- W2892904216 hasConcept C115961682 @default.
- W2892904216 hasConcept C120665830 @default.