Dataset Information

ThicknessTool: automated ImageJ retinal layer thickness and profile in digital images.

ABSTRACT: To develop an automated retina layer thickness measurement tool for the ImageJ platform, to quantitate nuclear layers following the retina contour. We developed the ThicknessTool (TT), an automated thickness measurement plugin for the ImageJ platform. To calibrate TT, we created a calibration dataset of mock binary skeletonized mask images with increasing thickness masks and different rotations. Following, we created a training dataset and performed an agreement analysis of thickness measurements between TT and two masked manual observers. Finally, we tested the performance of TT measurements in a validation dataset of retinal detachment images. In the calibration dataset, there were no differences in layer thickness between measured and known thickness masks, with an overall coefficient of variation of 0.00%. Training dataset measurements of immunofluorescence retina nuclear layers disclosed no significant differences between TT and any observer's average outer nuclear layer (ONL) (p?=?0.998), inner nuclear layer (INL) (p?=?0.807), and ONL/INL ratio (p?=?0.944) measurements. Agreement analysis showed that bias between TT vs. observers' mean was lower than between any observers' mean against each other in the ONL (0.77?±?0.34 µm vs 3.25?±?0.33 µm) and INL (1.59?±?0.28 µm vs 2.82?±?0.36 µm). Validation dataset showed that TT can detect significant and true ONL thinning (p?=?0.006), more sensitive than manual measurement capabilities (p?=?0.069). ThicknessTool can measure retina nuclear layers thickness in a fast, accurate, and precise manner with multi-platform capabilities. In addition, the TT can be customized to user preferences and is freely available to download.

SUBMITTER: Maidana DE

PROVIDER: S-EPMC7595229 | biostudies-literature | 2020 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

ThicknessTool: automated ImageJ retinal layer thickness and profile in digital images.

Maidana Daniel E DE Notomi Shoji S Ueta Takashi T Zhou Tianna T Joseph Danica D Kosmidou Cassandra C Caminal-Mitjana Josep Maria JM Miller Joan W JW Vavvas Demetrios G DG

Scientific reports 20201028 1

To develop an automated retina layer thickness measurement tool for the ImageJ platform, to quantitate nuclear layers following the retina contour. We developed the ThicknessTool (TT), an automated thickness measurement plugin for the ImageJ platform. To calibrate TT, we created a calibration dataset of mock binary skeletonized mask images with increasing thickness masks and different rotations. Following, we created a training dataset and performed an agreement analysis of thickness measurement ...[more]

PMID: 33116161

Similar Datasets

Project description:Digital breast tomosynthesis (DBT) offers poor image quality along the depth direction. This paper presents a new method that improves the image quality of DBT considerably through the a priori information from automated ultrasound (AUS) images.DBT and AUS images of a complex breast-mimicking phantom are acquired by a DBT/AUS dual-modality system. The AUS images are taken in the same geometry as the DBT images and the gradient information of the in-slice AUS images is adopted into the new loss functional during the DBT reconstruction process. The additional data allow for new iterative equations through solving the optimization problem utilizing the gradient descent method. Both visual comparison and quantitative analysis are employed to evaluate the improvement on DBT images. Normalized line profiles of lesions are obtained to compare the edges of the DBT and AUS-corrected DBT images. Additionally, image quality metrics such as signal difference to noise ratio (SDNR) and artifact spread function (ASF) are calculated to quantify the effectiveness of the proposed method.In traditional DBT image reconstructions, serious artifacts can be found along the depth direction (Z direction), resulting in the blurring of lesion edges in the off-focus planes parallel to the detector. However, by applying the proposed method, the quality of the reconstructed DBT images is greatly improved. Visually, the AUS-corrected DBT images have much clearer borders in both in-focus and off-focus planes, fewer Z direction artifacts and reduced overlapping effect compared to the conventional DBT images. Quantitatively, the corrected DBT images have better ASF, indicating a great reduction in Z direction artifacts as well as better Z resolution. The sharper line profiles along the Y direction show enhancement on the edges. Besides, noise is also reduced, evidenced by the obviously improved SDNR values.The proposed method provides great improvement on the quality of DBT images. This improvement makes it easier to locate and to distinguish a lesion, which may help improve the accuracy of the diagnosis using DBT imaging.

Project description:PURPOSE:To investigate the role of sex on retinal nerve fiber layer (RNFL) thickness at 768 circumpapillary locations based on OCT findings. DESIGN:Population-based cross-sectional study. PARTICIPANTS:We investigated 5646 eyes of 5646 healthy participants from the Leipzig Research Centre for Civilization Diseases (LIFE)-Adult Study of a predominantly white population. METHODS:All participants underwent standardized systemic assessments and ocular imaging. Circumpapillary RNFL (cRNFL) thickness was measured at 768 points equidistant from the optic nerve head using spectral-domain OCT (Spectralis; Heidelberg Engineering, Heidelberg, Germany). To control ocular magnification effects, the true scanning radius was estimated by scanning focus. Student t test was used to evaluate sex differences in cRNFL thickness globally and at each of the 768 locations. Multivariable linear regression and analysis of variance were used to evaluate individual contributions of various factors to cRNFL thickness variance. MAIN OUTCOME MEASURES:Difference in cRNFL thickness between males and females. RESULTS:Our population consisted of 54.8% females. The global cRNFL thickness was 1 ?m thicker in females (P < 0.001). However, detailed analysis at each of the 768 locations revealed substantial location specificity of the sex effects, with RNFL thickness difference ranging from -9.98 to +8.00 ?m. Females showed significantly thicker RNFLs in the temporal, superotemporal, nasal, inferonasal, and inferotemporal regions (43.6% of 768 locations), whereas males showed significantly thicker RNFLs in the superior region (13.2%). The results were similar after adjusting for age, body height, and scanning radius. The superotemporal and inferotemporal RNFL peaks shifted temporally in females by 2.4° and 1.9°, respectively. On regions with significant sex effects, sex explained more RNFL thickness variance than age, whereas the major peak locations and interpeak angle explained most of the RNFL thickness variance unexplained by sex. CONCLUSIONS:Substantial sex effects on cRNFL thickness were found at 56.8% of all 768 circumpapillary locations, with specific patterns for different sectors. Over large regions, sex was at least as important in explaining the cRNFL thickness variance as was age, which is well established to have a substantial impact on cRNFL thickness. Including sex in the cRNFL thickness norm could therefore improve glaucoma diagnosis and monitoring.

Project description:ImportanceRetinal layer thickness is hypothesized to be related to cognitive function in patients with mild cognitive impairment (MCI) and Alzheimer disease (AD). However, longitudinal cohort studies of the healthy older population are scarce.ObjectiveTo investigate the association between retinal layer thickness and cognitive impairment and future cognitive decline in a community-based population cohort.Design, setting, and participantsA total of 430 randomly sampled community-dwelling Korean individuals 60 years or older participated in the baseline assessment (mean [SD], 76.3 [6.6] years) 215 of whom completed a mean (SD) of 5.4 (0.6) years (range, 4.1-6.2 years) of follow-up. Using spectral-domain optical coherence tomography, the study team assessed the thickness of 6 retinal layers in the macular region, the peripapillary retinal nerve fiber layers (RNFLs), and the subfoveal choroid at baseline.ExposuresAge, sex, education, diabetes, hypertension, and apolipoprotein E4 gene status.Main outcomes and measuresRetinal layer thickness and cognitive function test scores were analyzed.ResultsThis study included 430 participants (female, 208 [48.6%]). Baseline macular RNFL thickness was associated with baseline Consortium to Establish a Registry for Alzheimer's Disease (CERAD) score (coefficient [β] = 0.077; 95% CI, 0.054-0.100; P = .04 for total macular area) and Mini-Mental State Examination (MMSE) score (coefficient [β] = 0.082; 95% CI, 0.063-0.101; P = .03 for total macular area). A thinner baseline total macular RNFL thickness (lowest quartile, <231 μm) was associated with a larger decline in the CERAD and MMSE scores during the follow-up period (P = .003 and P = .01, respectively). Furthermore, participants with baseline total macular RNFL thickness below the lowest quartile cutoff value presented a greater decline in cognitive scores and a higher prevalence of cognitive impairment and Alzheimer disease than those with RNFL thickness above the lowest quartile cutoff value.Conclusions and relevanceIn this study, macular RNFL thickness could be used as a prognostic biomarker of long-term cognitive decline in adults 60 years or older. However, to confirm these results, further large-scale population-based studies should be performed.

Project description:PurposeTo develop and evaluate a deep learning system for differentiating between eyes with and without glaucomatous visual field damage (GVFD) and predicting the severity of GFVD from spectral domain OCT (SD OCT) optic nerve head images.DesignEvaluation of a diagnostic technology.ParticipantsA total of 9765 visual field (VF) SD OCT pairs collected from 1194 participants with and without GVFD (1909 eyes).MethodsDeep learning models were trained to use SD OCT retinal nerve fiber layer (RNFL) thickness maps, RNFL en face images, and confocal scanning laser ophthalmoscopy (CSLO) images to identify eyes with GVFD and predict quantitative VF mean deviation (MD), pattern standard deviation (PSD), and mean VF sectoral pattern deviation (PD) from SD OCT data.Main outcome measuresDeep learning models were compared with mean RNFL thickness for identifying GVFD using area under the curve (AUC), sensitivity, and specificity. For predicting MD, PSD, and mean sectoral PD, models were evaluated using R2 and mean absolute error (MAE).ResultsIn the independent test dataset, the deep learning models based on RNFL en face images achieved an AUC of 0.88 for identifying eyes with GVFD and 0.82 for detecting mild GVFD significantly (P < 0.001) better than using mean RNFL thickness measurements (AUC = 0.82 and 0.73, respectively). Deep learning models outperformed standard RNFL thickness measurements in predicting all quantitative VF metrics. In predicting MD, deep learning models based on RNFL en face images achieved an R2 of 0.70 and MAE of 2.5 decibels (dB) compared with 0.45 and 3.7 dB for RNFL thickness measurements. In predicting mean VF sectoral PD, deep learning models achieved high accuracy in the inferior nasal (R2 = 0.60) and superior nasal (R2 = 0.67) sectors, moderate accuracy in inferior (R2 = 0.26) and superior (R2 = 0.35) sectors, and lower accuracy in the central (R2 = 0.15) and temporal (R2 = 0.12) sectors.ConclusionsDeep learning models had high accuracy in identifying eyes with GFVD and predicting the severity of functional loss from SD OCT images. Accurately predicting the severity of GFVD from SD OCT imaging can help clinicians more effectively individualize the frequency of VF testing to the individual patient.

Dataset Information

ThicknessTool: automated ImageJ retinal layer thickness and profile in digital images.

Publications

ThicknessTool: automated ImageJ retinal layer thickness and profile in digital images.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets