ライフサイエンスコーパス: fundus photograph

1 by validated deep learning grading of color fundus photographs).

2 the standardized ETDRS severity scale (using fundus photographs).

3 as assessed via grading of color stereo film fundus photographs.

4 generation was diagnosed and graded based on fundus photographs.

5 AMD was determined from graded, stereoscopic fundus photographs.

6 nged despite the lack of evidence other than fundus photographs.

7 lar changes during ophthalmoscopy or through fundus photographs.

8 lated macular degeneration was assessed from fundus photographs.

9 40 years or older with diabetes mellitus and fundus photographs.

10 s in this cohort, 38% were not detectable on fundus photographs.

11 ed 45-84 years with genotype information and fundus photographs.

12 aseline color non- simultaneous stereoscopic fundus photographs.

13 by systematic grading of stereoscopic color fundus photographs.

14 ear of follow-up, atrophy was measured using fundus photographs.

15 AREDS) grading scheme of corresponding color fundus photographs.

16 re independently obtained from corresponding fundus photographs.

17 used to stitch together overlapping retinal fundus photographs.

18 neration status was determined by grading of fundus photographs.

19 er temporal by grading of stereoscopic color fundus photographs.

20 224) was determined in 1993-1995 from graded fundus photographs.

21 was determined by grading stereoscopic color fundus photographs.

22 sessment of disc proliferations using stereo fundus photographs.

23 rmal, GON, or NGON, using 2183 digital color fundus photographs.

24 M) was used to predict RNFL thicknesses from fundus photographs.

25 erable diabetic retinopathy (rDR) from color fundus photographs.

26 Severity Scale (ETDRS-DRSS) on 7-field color fundus photographs.

27 ts validated the cohorts using OCT and color fundus photographs.

28 For grading, an end point committee assessed fundus photographs.

29 omatous optic nerve head features from color fundus photographs.

30 ng, which predicts reported sex from retinal fundus photographs.

31 ated) on the remaining (held-out) 15% of the fundus photographs.

32 AMD was diagnosed by grading of fundus photographs.

33 Incidence of advanced AMD based on retinal fundus photographs.

34 Incident AMD was graded on fundus photographs.

35 randomization with gradable DRSS on baseline fundus photographs.

36 DR screening examinations, including 7-field fundus photographs.

37 abetic retinopathy was graded using standard fundus photographs.

38 rk (GAN) capable of producing FA images from fundus photographs.

39 opathy and diabetic macular edema in retinal fundus photographs.

40 A total of 22 of 5193 fundus photographs (0.4%) in decile 10 had disc hemorrha

41 Semi-automated evaluation of fundus photographs (1 eye/participant) determined centra

42 Semi-automated grading of fundus photographs (1 eye/participant) determined centra

43 e three features of papilledema from digital fundus photographs: (1) sharpness of the optic disc bord

44 ic retinopathy (NPDR) to PDR based on graded fundus photographs, (2) panretinal photocoagulation (PRP

45 ons, DME and CSME prevalences from monocular fundus photographs (28.5% and 21.0%, respectively) appro

46 965 of 1052 patients (91.7%) had AI-gradable fundus photographs: 580 had gradable nonmydriatic imagin

47 re detected in 68.4% versus 0.0% using color fundus photographs, 73.3% versus 9.1% using FAF images,

48 fined based on grading of stereoscopic color fundus photographs according to the Wisconsin Age-Relate

49 To examine resolution, 40 fundus photographs acquired on high-resolution film were

50 for the case presented, first based on color fundus photographs alone, and then based on color fundus

51 Two posterior fundus photographs and 1 anterior segment photograph wer

52 Thirty-two sets (16 color fundus photographs and 16 color fundus photographs paire

53 position was assessed by 2 observers using 5 fundus photographs and 5 FoDi analyses each.

54 Eye examinations were conducted with annual fundus photographs and best-corrected visual acuity asse

55 edema was defined as absent or present from fundus photographs and confirmed by optical coherence to

56 s photographs alone, and then based on color fundus photographs and corresponding FA images.

57 s images alone versus interpreting the color fundus photographs and FA images was 47% (range, 35.3% t

58 egions were graded as to their appearance on fundus photographs and FAF images, and changes in FAF si

59 Incident GA most often appears on color fundus photographs and FAs as a small, singular, parafov

60 Baseline stereoscopic color fundus photographs and FAs of participants in the CATT s

61 Image analysis performed on serial fundus photographs and fluorescein angiograms did not de

62 monotherapy, including examination of RetCam fundus photographs and fluorescein angiograms.

63 Digital fundus photographs and fluorescein angiography (FA) usin

64 were trained and validated using 85% of the fundus photographs and further retested (validated) on t

65 Then, color fundus photographs and Humphrey Visual Field tests (HVF)

66 Based on the analysis of fundus photographs and HVF tests, 25% of these were misd

67 of zone in 28 (62%) of 45 cases using color fundus photographs and in 31 (69%) of 45 cases using FA

68 The color fundus photographs and infrared scanning laser ophthalmo

69 Ophthalmic examinations, including fundus photographs and mfERG testing, were performed at

70 onal study of DME grading based on monocular fundus photographs and OCT images obtained from patients

71 inal surface elevation estimated from stereo fundus photographs and OCT scans were positively correla

72 Twenty-nine pairs of stereoscopic fundus photographs and optic nerve head (ONH) centered s

73 iative for Macular Research, was assessed by fundus photographs and optical coherence tomographic ima

74 in retinal thickening measured by grading of fundus photographs and optical coherence tomography (OCT

75 We introduced a novel DL approach to assess fundus photographs and provide quantitative information

76 We retrospectively reviewed simultaneous fundus photographs and SD OCT and fundus autofluorescenc

77 The test sample consisted of 33 466 pairs of fundus photographs and SD OCT images collected during 71

78 on including color, red-free autofluorescent fundus photographs and spectral-domain optical coherence

79 fundus photographs compared with using color fundus photographs and the corresponding FA images.

80 utional neural network was trained to assess fundus photographs and to predict SD OCT global RNFL thi

81 Comparisons of fundus photographs and ultrasound measurements were perf

82 the level of DR detected by their screening fundus photographs and visit diagnosis.

83 Fundus photographs and visual fields were carefully exam

84 story, or other covariates or had ungradable fundus photographs and were excluded, leaving 9481 parti

85 on simulators or human volunteers, or use of fundus photographs) and recognition of normal and abnorm

86 ined by masked grading of stereoscopic color fundus photographs), and NEI-VFQ-25 subscale scores.

87 eloped to detect the presence of GA in color fundus photographs, and 2 additional models were develop

88 System for Myopic Maculopathy criteria from fundus photographs, and 3774 individuals were control pa

89 diabetic retinopathy was diagnosed on stereo fundus photographs, and glaucoma was diagnosed on the ba

90 The clinical examinations, fundus photographs, and OCT images of all patients with

91 full ophthalmic examinations, digital color fundus photographs, and OCT images were obtained.

92 Clinical records, fundus photographs, and OCT imaging for patients with CL

93 DR was measured every 6 months from standard fundus photographs, and refractive error was measured an

94 Best-corrected visual acuity, fundus photographs, and spectral-domain optical coherenc

95 atus was assessed by standardized grading of fundus photographs, and stored fasting blood specimens d

96 mfERG z-scores were mapped onto fundus photographs, and the relationship between baselin

97 graphic atrophy) were evaluated using annual fundus photographs assessed centrally.

98 4 participants were included with a gradable fundus photograph at baseline.

99 graphic atrophy area was measured from color fundus photographs at annual visits.

100 Geographic atrophy area was measured from fundus photographs at annual visits.

101 tages of AMD based on ocular examination and fundus photographs at baseline.

102 ascertained from grading stereoscopic color fundus photographs based on a standard protocol.

103 oved after specific teaching about assessing fundus photographs before testing (P = .02).

104 agreement of retinal pathologies observed on fundus photographs between an ophthalmologist and two-mi

105 Fundus photographs, blood glucose (BG) concentration, Hb

106 , determined from the diagnosis of the color fundus photographs by 3 experienced readers in combinati

107 diagnosis, determined from the diagnosis of fundus photographs by 3 experienced readers in combinati

108 a-involving IRH was determined from baseline fundus photographs by human graders and confirmed with m

109 t of retinal degeneration observed in OCT or fundus photographs; by using the fellow eye as a control

110 ogists could be responsible for interpreting fundus photographs captured in a telemedicine program.

111 Stereoscopic color fundus photographs centered on the macula were taken on

112 ms have been developed for classifying color fundus photographs (CFP) of individual eyes by AREDS sev

113 o correlate hyperpigmentary changes on color fundus photographs (CFP) with abnormal morphology on SDO

114 lectance, fundus autofluorescence, and color fundus photographs (CFP).

115 Color fundus photographs (CFPs) from annual visits were graded

116 al Analysis: A comparative analysis of color fundus photographs (CFPs), OCT, and FAF was performed fo

117 All eyes were imaged with UWF color fundus photographs (CFPs), UWF FA, and SS-WF OCTA at bas

118 hose identified from review of digital color fundus photographs (CFPs).

119 ifference in zone diagnosis when using color fundus photographs compared with using color fundus phot

120 ng papilledema patients obtained from stereo fundus photographs compares favorably with that from OCT

121 eovascularization from ultra-widefield color fundus photographs could expand access to rapid retinal

122 By using 66 721 fundus photographs, deep learning models were trained an

123 Stereoscopic fundus photographs demonstrated a yellow-orange, localiz

124 mprehensive eye examination in which dilated fundus photographs (disc and macula centered) were obtai

125 e Early Treatment Diabetic Retinopathy Study fundus photograph field 1.

126 Retinal specialists evaluated color fundus photographs fluorescein and indocyanine green ang

127 Reading center staff evaluated digital color fundus photographs, fluorescein angiography (FA) images,

128 d baseline and follow-up morphology in color fundus photographs, fluorescein angiography (FA), and op

129 lity of procedure, ranibizumab, bevacizumab, fundus photographs, fluorescein angiography, and optical

130 art during a 20-year period and had gradable fundus photographs for AMD and genotype information on C

131 was initially tested using 12 baseline color fundus photographs for assessment of repeatability.

132 Students preferred fundus photographs for both learning and examining the o

133 the MLOPs and the ophthalmologist in grading fundus photographs for retinal hemorrhages and maculopat

134 Adults > or = 50 years of age whose fundus photographs for the eye to be tested psychophysic

135 We assessed images of previously obtained fundus photographs for the presence of macular pigmentat

136 for 36 months with ETDRS VA measurements and fundus photographs (FP) every 3 to 6 months.

137 ospectively collected, ultra-widefield color fundus photographs from 190 adults with sickle cell hemo

138 A total of 66 721 fundus photographs from 3272 eyes of 1636 subjects who p

139 Digital color stereoscopic fundus photographs from 4203 AREDS2 subjects collected a

140 Fundus photographs from 7 Early Treatment Diabetic Retin

141 Digital ocular fundus photographs from a random cohort of children with

142 and Relevance: In this evaluation of retinal fundus photographs from adults with diabetes, an algorit

143 Board, digitized images of field 2 (macular) fundus photographs from AREDS obtained over a 12-year lo

144 arm of artificial intelligence, using color fundus photographs from AREDS/AREDS2 was superior in som

145 Stereoscopic color fundus photographs from eyes with PCC were reviewed by 2

146 nalysis involved an approximate 1% sample of fundus photographs from patients screened using ARDA.

147 ined using side-by-side comparisons of color fundus photographs from the initial and final visit as r

148 Best corrected visual acuity (BCVA), color fundus photograph, fundus autofluorescence (FAF), optica

149 ted visual acuity, fundus examination, color fundus photographs, fundus autofluorescence (FAF), fluor

150 each patient were evaluated, including color fundus photographs, fundus autofluorescence images, and

151 Demographic and clinical information, fundus photographs, fundus autofluorescence, and spectra

152 Color fundus photographs, fundus autofluorescence, and spectra

153 says of oxidized low-density lipoprotein and fundus photographs gradable for diabetic retinopathy and

154 Fundus photographs graded at baseline and years 1 and 2

155 tep AMD classification system based on color fundus photographs graded by experienced and masked eval

156 ge-related macular degeneration according to fundus photographs graded using a modified Wisconsin Age

157 Diabetic retinopathy was based on fundus photograph grading, using the Early Treatment Dia

158 e AMD, assessed by annual masked centralized fundus photograph grading.

159 -related macular degeneration from digitized fundus photographs has high sensitivity and specificity

160 vascular caliber measured from digital color fundus photographs have been independently associated wi

161 lgorithms to classify glaucomatous damage on fundus photographs have been limited by the requirement

162 nosed as not having DME or CSME on monocular fundus photographs have DME on OCT.

163 diagnosed as having DME or CSME on monocular fundus photographs have no DME based on OCT CST, while m

164 As a result, AI algorithms trained on fundus photographs have the potential for biased perform

165 ssed by masked grading of stereoscopic color fundus photographs in 1,709 persons who participated in

166 erity levels on reading center assessment of fundus photographs in eyes without PDR at baseline, (3)

167 ed 40 years or older with diabetes and valid fundus photographs in the 2005 to 2008 National Health a

168 ssessed the densitometric profile of DH from fundus photographs in the Ocular Hypertension Treatment

169 evaluation (slit lamp), Amsler chart, color fundus photographs, infrared reflectance, red-free image

170 tudents (70%) said they would prefer to have fundus photographs instead of using the ophthalmoscope d

171 e cross-sectional evaluation of deidentified fundus photographs matched to spectacle-corrected VA det

172 Fundus photographs, near infrared reflectance and enhanc

173 urrounding retina was documented with stereo fundus photographs obtained at multiple time points thro

174 same amount of details as conventional color fundus photographs obtained by an expert photographer.

175 ased grading algorithm can be used to screen fundus photographs obtained from diabetic patients and t

176 en all participants had mydriatic 45 degrees fundus photographs obtained from three fields of view wi

177 Demographics, eye exam findings, fundus photographs, OCT, and fluorescein angiography wer

178 Retrospective analysis of color fundus photographs, OCT, and OCTA of 20 eyes with CHRRPE

179 aphic data, visual acuity, refractive error, fundus photographs, OCT, visual fields, and full-field s

180 A nonmydriatic fundus photograph of one eye, taken in a mobile examinat

181 anually delineated atrophic lesions on color fundus photographs of 318 eyes with GA followed up over

182 We manually delineated GA on 1654 fundus photographs of 365 eyes.

183 Fundus photographs of 478 patients with IIH were reviewe

184 Fundus photographs of 500 eyes of 500 subjects were asse

185 Fundus photographs of all infants undergoing ROP screeni

186 Phenotypical features on fundus photographs of both eyes of patients were graded

187 Charts and fundus photographs of consecutive patients with active T

188 .001) for creating automontages from digital fundus photographs of eyes with CMV retinitis.

189 hotomontage software programs, using digital fundus photographs of eyes with cytomegalovirus (CMV) re

190 ased metrics and the clinical disc margin on fundus photographs of glaucoma subjects.

191 rded from the central 45 degrees, and stereo fundus photographs of the diabetic eyes were taken.

192 ts who were 40 years and older with gradable fundus photographs of the Fourth and the Fifth Korea Nat

193 d the 5- and 10-year follow-up examinations, fundus photographs of the macula and the optic disc were

194 SD-OCT scans and corresponding stereo fundus photographs of the optic nerve head were obtained

195 Fundus photographs of the remaining eyes showed that 18/

196 harts were reviewed for amblyopia treatment, fundus photographs, optical coherence tomography (OCT),

197 The SLG were not visible in color fundus photographs or in NIR images.

198 ce test for GON was specialist evaluation of fundus photographs or OCT, independent of the visual fie

199 Prevalence of DME based on monocular fundus photographs or OCT.

200 tive means (examination of the patient or of fundus photographs) or by quantitative techniques such a

201 ts (16 color fundus photographs and 16 color fundus photographs paired with the corresponding FA imag

202 direct ophthalmoscope) and 1 dilated digital fundus photograph per eye (graded by an ophthalmologist

203 ot receive specific training on interpreting fundus photographs prior to accuracy assessments.

204 BS scores were highly correlated for OCT and fundus photographs (r = 0.96 and 0.82, respectively).

205 r DR severity and DME in a masked fashion by Fundus Photograph Reading Center (Madison, WI) graders.

206 in the CATT study were assessed at a central fundus photograph reading center by masked readers.

207 0.92 and -0.83, respectively; P < 0.001) and fundus photograph scores (r = -0.80 and -0.83, respectiv

208 Grading of fundus photographs showed a statistically significant de

209 Fundus photographs showed circular red dots in 3 eyes, a

210 Fundus photographs showed large, uncorrelated difference

211 Fundus photographs showed large, uncorrelated difference

212 in the absence of a clinical examination or fundus photographs, subject self-report could be a relia

213 plitude and implicit time were compared with fundus photographs taken at the time of testing.

214 ust 1, 2019, and March 31, 2020, with ocular fundus photographs taken concurrently.

215 scale and applied this scale to nonmydriatic fundus photographs taken during routine ED patient encou

216 y were assessed from grading of stereoscopic fundus photographs taken in 2001-2004.

217 presence of a notch or disc hemorrhage) from fundus photographs taken with a nonmydriatic portable ca

218 , including FDT perimetry screening, and had fundus photographs taken.

219 ticipants underwent eye examinations and had fundus photographs taken.

220 racy of answers was better when interpreting fundus photographs than when performing ophthalmoscopy o

221 he capabilities of angiography imaging, a 2D fundus photograph that requires an intravenous injection

222 ts, slit-lamp examinations, and stereoscopic fundus photographs that were centrally graded for develo

223 ophthalmic histories (n = 25), and clinical fundus photographs that were graded using the Wisconsin

224 We captured mosaic fundus photographs through a dilated pupil using a digit

225 hthalmologist and had independent grading of fundus photographs to confirm their disease status.

226 deep learning model was trained to use color fundus photographs to predict GA presence from a populat

227 gnificant macular edema (CSME), on monocular fundus photographs used definitions from the Multi-Ethni

228 imension) were measured from digital retinal fundus photographs using a computer-assisted program fol

229 l shape of the ONH was estimated from stereo fundus photographs using an automated multi-scale stereo

230 ed as having either DME or CSME on monocular fundus photographs using MESA and NHANES definitions, re

231 %) were diagnosed as having DME on monocular fundus photographs using MESA and NHANES definitions, re

232 Features of AMD were graded on fundus photographs using the 3CC AMD severity scale.

233 o expert grading of papilledema from digital fundus photographs using the Frisen grading scale.

234 ined by masked grading of stereoscopic color fundus photographs using the modified Early Treatment Di

235 AMD features were graded on fundus photographs using the Rotterdam classification.

236 AMD was diagnosed based on fundus photographs using the Rotterdam Classification.

237 ere determined by grading stereoscopic color fundus photographs using the Wisconsin Age-Related Macul

238 was determined by grading stereoscopic color fundus photographs using the Wisconsin Age-related Macul

239 ined by masked grading of stereoscopic color fundus photographs using the Wisconsin Age-Related Macul

240 An OCT fundus image, akin to a fundus photograph was generated by axial summation of th

241 Based on stereoscopic fundus photographs, we evaluated diabetic macular edema

242 Axial lengths (ALs) and 45 degrees fundus photographs were acquired from 64 eyes (34 health

243 Additional SAP and fundus photographs were acquired throughout follow-up.

244 nts, and phenotypic characteristics on color fundus photographs were analyzed comparing patients with

245 Color fundus photographs were assessed by the 9-step Age-Relat

246 Baseline and annual stereoscopic fundus photographs were assessed centrally by masked gra

247 Baseline and annual color fundus photographs were assessed for GA area and proximi

248 Gradable fundus photographs were available for 1809 participants

249 Color fundus photographs were collected at annual study visits

250 Fundus photographs were collected at annual study visits

251 Color fundus photographs were collected at annual study visits

252 Color fundus photographs were collected at annual study visits

253 Fundus photographs were collected from one quarter of th

254 Baseline and annual stereoscopic color fundus photographs were evaluated for (1) GA presence an

255 Of 4,381 participants, fundus photographs were gradable for 3,304 persons (75.4

256 Fundus photographs were gradable for 665 (90.4%) of thes

257 Baseline and annual stereoscopic fundus photographs were graded centrally to detect DPED,

258 Fundus photographs were graded for ARM using a modificat

259 Fundus photographs were graded for drusen and retinal pi

260 Annual fundus photographs were graded for GA presence/morpholog

261 Digital color fundus photographs were graded for predominant phenotype

262 Fundus photographs were graded for the presence or absen

263 Color fundus photographs were graded manually and OCT scans un

264 Baseline color fundus photographs were graded using an innovative gradi

265 Fundus photographs were graded using the Wisconsin AMD g

266 .5%) based on MESA definitions for monocular fundus photographs were greater than the DME prevalence

267 mfERG and fundus photographs were measured in both eyes of 68 adol

268 To evaluate the progression to late AMD, fundus photographs were obtained at baseline and annual

269 al data and standardized red-reflex lens and fundus photographs were obtained at baseline and annuall

270 Color retinal fundus photographs were obtained at each examination.

271 To evaluate the retinal vasculature, digital fundus photographs were obtained at the same ages, and t

272 Fundus photographs were obtained followed by neuro-ophth

273 mfERGs and fundus photographs were obtained from 28 eyes of 28 diab

274 Nonmydriatic fundus photographs were obtained of each eye and graded

275 Fundus photographs were obtained serially for 26 eyes of

276 Fundus photographs were performed at each examination an

277 Deidentified ultra-widefield color fundus photographs were retrospectively collected.

278 nthoma elasticum and at least 1 set of color fundus photographs were reviewed (41 eyes of 21 patients

279 Fundus photographs were reviewed and the locations of 18

280 Fundus photographs were reviewed to assess the presence

281 Fundus photographs were reviewed to compare SD OCT ascer

282 Color fundus photographs were reviewed to correlate with the s

283 Bilateral, 7-field fundus photographs were scored by masked readers for dia

284 Color fundus photographs were taken and graded in a masked man

285 Eye examinations and fundus photographs were taken at baseline and year 4.

286 isual acuity, spectral-domain OCT, and color fundus photographs were taken at baseline.

287 Fundus photographs were taken at the 26-year follow-up,

288 Fundus photographs were taken of all participating famil

289 Two fundus photographs were taken of each eye with a digital

290 ehensive ocular evaluation was conducted and fundus photographs were taken to measure the size of the

291 ere recorded from 103 retinal locations, and fundus photographs were taken within 1 month of each rec

292 Fundus photographs were used to compare the number of ar

293 Color fundus photographs were used to grade for the presence o

294 or identifying early GA.(23) Color-optimized fundus photographs were viewed concurrently with the FAs

295 perpigmentation, selected using stereo color fundus photographs, were quantified in three types of po

296 interpreted 40 sets (20 sets with individual fundus photographs with >/=3 fields and 20 computer-gene

297 erimetry (PHP) testing, stereoscopic digital fundus photographs with FA, and OCT imaging.

298 Comparison of fundus photographs with fluorescein angiograms showed th

299 a deep learning model to predict ci-DME from fundus photographs, with an ROC-AUC of 0.89 (95% CI: 0.8

300 Eighty-four eyes of 42 patients had baseline fundus photographs, with baseline OCT in 31 eyes of 16 p