Dataset Information

Comparison of Subjective Assessment and Precise Quantitative Assessment of Lesion Distribution in Diabetic Retinopathy.

ABSTRACT: Predominantly peripheral disease in eyes with nonproliferative diabetic retinopathy (DR) is suggested as a potential strong risk factor for progression to proliferative disease. However, the reliability and optimal method for the assessment of lesion distribution are still uncertain.To compare agreement between subjective assessment and precise quantification of lesion burden in ultrawidefield (UWF) images of eyes with DR.This multisite cross-sectional study examines UWF pseudocolor images acquired from DR screening clinic patients from December 20, 2014, through August 1, 2014. Of 104 cases, 161 eyes with DR were included. Data analysis was conducted from June 1, 2016, through December 1, 2016 at the Doheny Image Reading Center.Distribution of DR lesions in eyes was assessed subjectively and quantitatively, and eyes were classified as having predominantly central lesions (PCLs) or predominantly peripheral lesions (PPLs). The frequency and surface area (SA) of each lesion type were quantified. Intergrader and subjective vs quantitative classification were compared for level of agreement. Several methods of determining PPL distribution were also compared.On subjective frequency-based evaluation by graders, 133 eyes were classified as having PCL, and 28 eyes as having PPL. On exact quantification of lesion SA, 121 eyes were classified as PCL, and 40 eyes as having PPL. On SA-based quantification, 134 eyes were classified as having PCL, and 27 eyes as having PPL. There was a significant difference between qualitative and quantitative classification of DR lesion distribution for both frequency-based (mean difference [SD]: PCL, 6 [2]; PPL, 13 [6]; P < .001) and SA-based (mean difference [SD]: PCL, 6 [1]; PPL, 20 [7]; P < .001) methods. Both intergrader reproducibility and subjective vs quantitative agreement were higher with frequency-based classification.Subjective assessment of PPL DR lesions on UWF images differed in some cases from precise quantitative assessments, particularly when considering the area of lesions. These findings highlight the benefit of objective quantitative approaches to DR assessment, which may facilitate the development of a more precise DR scoring system.

SUBMITTER: Sears CM

PROVIDER: S-EPMC5876824 | biostudies-other | 2018 Apr

REPOSITORIES: biostudies-other

ACCESS DATA

Publications

Comparison of Subjective Assessment and Precise Quantitative Assessment of Lesion Distribution in Diabetic Retinopathy.

Sears Connie Martin CM Nittala Muneeswar G MG Jayadev Chaitra C Verhoek Michael M Fleming Alan A van Hemert Jano J Tsui Irena I Sadda SriniVas R SR

JAMA ophthalmology 20180401 4

<h4>Importance</h4>Predominantly peripheral disease in eyes with nonproliferative diabetic retinopathy (DR) is suggested as a potential strong risk factor for progression to proliferative disease. However, the reliability and optimal method for the assessment of lesion distribution are still uncertain.<h4>Objective</h4>To compare agreement between subjective assessment and precise quantification of lesion burden in ultrawidefield (UWF) images of eyes with DR.<h4>Design, setting, and participants ...[more]

PMID: 29470566

Similar Datasets

Project description:Purpose:Evaluate efficiency, precision, and validity of RetCAT, which comprises ten diabetic retinopathy (DR) quality of life (QoL) computerized adaptive tests (CATs). Methods:In this cross-sectional clinical study, 183 English and/or Mandarin-speaking participants with DR (mean age ± standard deviation [SD] 56.4 ± 11.9 years; 38% proliferative DR [worse eye]) were recruited from retinal clinics in Singapore. Participants answered the RetCAT tests (Symptoms, Activity Limitation, Mobility, Emotional, Health Concerns, Social, Convenience, Economic, Driving, and Lighting), which were capped at seven items each, and other questionnaires, and underwent eye tests. Our primary evaluation focused on RetCAT efficiency (i.e. standard error of measurement [SEM] ± SD achieved and time needed to complete each CAT). Secondary evaluations included an assessment of RetCAT's test precision and validity. Results:Mean SEM across all RetCAT tests was 0.351, ranging from 0.272 ± 0.130 for Economic to 0.484 ± 0.130 for Emotional. Four tests (Mobility, Social, Convenience, and Driving) had a high level of measurement error. The median time to take each RetCAT test was 1.79 minutes, ranging from 1.12 (IQR [interquartile range] 1.63) for Driving to 3.28 (IQR 2.52) for Activity Limitation. Test precision was highest for participants at the most impaired end of the spectrum. Most RetCAT tests displayed expected correlations with other scales (convergent/divergent validity) and were sensitive to DR and/or vision impairment severity levels (criterion validity). Conclusions:RetCAT can provide efficient, precise, and valid measurement of DR-related QoL impact. Future application of RetCAT will employ a stopping rule based on SE rather than number of items to ensure that all tests can detect meaningful differences in person abilities. Responsiveness of RetCAT to treatment interventions must also be determined. Translational Relevance:RetCAT may be useful for measuring the patient-centered impact of DR severity and disease progression and evaluating the effectiveness of new therapies.

Project description:Diabetic retinopathy (DR) is a late microvascular complication of Diabetes Mellitus (DM) that could lead to permanent blindness in patients, without early detection. Although adequate management of DM via regular eye examination can preserve vision in in 98% of the DR cases, DR screening and diagnoses based on clinical lesion features devised by expert clinicians; are costly, time-consuming and not sufficiently accurate. This raises the requirements for Artificial Intelligent (AI) systems which can accurately detect DR automatically and thus preventing DR before affecting vision. Hence, such systems can help clinician experts in certain cases and aid ophthalmologists in rapid diagnoses. To address such requirements, several approaches have been proposed in the literature that use Machine Learning (ML) and Deep Learning (DL) techniques to develop such systems. However, these approaches ignore the highly valuable clinical lesion features that could contribute significantly to the accurate detection of DR. Therefore, in this study we introduce a framework called DR-detector that employs the Extreme Gradient Boosting (XGBoost) ML model trained via the combination of the features extracted by the pretrained convolutional neural networks commonly known as transfer learning (TL) models and the clinical retinal lesion features for accurate detection of DR. The retinal lesion features are extracted via image segmentation technique using the UNET DL model and captures exudates (EXs), microaneurysms (MAs), and hemorrhages (HEMs) that are relevant lesions for DR detection. The feature combination approach implemented in DR-detector has been applied to two common TL models in the literature namely VGG-16 and ResNet-50. We trained the DR-detector model using a training dataset comprising of 1,840 color fundus images collected from e-ophtha, retinal lesions and APTOS 2019 Kaggle datasets of which 920 images are healthy. To validate the DR-detector model, we test the model on external dataset that consists of 81 healthy images collected from High-Resolution Fundus (HRF) dataset and MESSIDOR-2 datasets and 81 images with DR signs collected from Indian Diabetic Retinopathy Image Dataset (IDRID) dataset annotated for DR by expert. The experimental results show that the DR-detector model achieves a testing accuracy of 100% in detecting DR after training it with the combination of ResNet-50 and lesion features and 99.38% accuracy after training it with the combination of VGG-16 and lesion features. More importantly, the results also show a higher contribution of specific lesion features toward the performance of the DR-detector model. For instance, using only the hemorrhages feature to train the model, our model achieves an accuracy of 99.38 in detecting DR, which is higher than the accuracy when training the model with the combination of all lesion features (89%) and equal to the accuracy when training the model with the combination of all lesions and VGG-16 features together. This highlights the possibility of using only the clinical features, such as lesions that are clinically interpretable, to build the next generation of robust artificial intelligence (AI) systems with great clinical interpretability for DR detection. The code of the DR-detector framework is available on GitHub at https://github.com/Janga-Lab/DR-detector and can be readily employed for detecting DR from retinal image datasets.

Project description:ImportanceStudies have not yet determined whether the distribution of lesions in the retinal periphery alters the association between the severity of diabetic retinopathy (DR) and macular vessel density.ObjectiveTo evaluate the association of DR lesion distribution with optical coherence tomography angiography (OCTA) metrics and DR severity.Design, setting, and participantsThis cross-sectional observational study was conducted at a tertiary care center for diabetic eye disease among 225 patients with type 1 or 2 diabetes who had undergone imaging between February 15, 2016, and December 31, 2019.ExposuresOptical coherence tomography angiography 3 × 3-mm macular scans and ultra-widefield color imaging.Main outcomes and measuresOptical coherence tomography angiography vessel density in the superficial capillary plexus, intermediate capillary plexus, and deep capillary plexus and choriocapillaris flow density. The severity of DR and the predominantly peripheral lesions (PPL) were evaluated from ultra-widefield color imaging.ResultsThe study evaluated 352 eyes (225 patients; 125 men [55.6%]; mean [SD] age, 52.1 [15.1] years), of which 183 eyes (52.0%) had mild nonproliferative diabetic retinopathy (NPDR), 71 eyes (20.2%) had moderate NPDR, and 98 eyes (27.8%) had severe NPDR or proliferative diabetic retinopathy (PDR). In eyes with no PPL (209 [59.4%]), the mean (SD) vessel density in the superficial capillary plexus (mild NPDR, 38.1% [4.7%]; moderate NPDR, 36.4% [4.6%]; severe NPDR or PDR, 34.1% [4.1%]; P < .001) and the deep capillary plexus (mild NPDR, 45.8% [3.0%]; moderate NPDR, 45.8% [2.2%]; severe NPDR or PDR, 44.5% [1.9%]; P = .002), as well as the mean (SD) choriocapillaris flow density (mild NPDR, 69.7% [6.2%]; moderate NPDR, 67.6% [5.6%]; severe NPDR or PDR, 67.1% [5.6%]; P = .01), decreased with increasing DR severity. These associations remained statistically significant even after correcting for age, signal strength index, spherical equivalent, duration of diabetes, type of diabetes, and correlation between eyes of the same patient. In eyes with PPL (143 [40.6%]), mean (SD) vessel density in the superficial capillary plexus (mild NPDR, 34.1% [4.1%]; moderate NPDR, 35.2% [4.1%]; severe NPDR or PDR, 36.0% [4.3%]; P = .42) and the deep capillary plexus (mild NPDR, 44.5% [1.7%]; moderate NPDR, 45.4% [1.4%]; severe NPDR or PDR, 44.9% [1.5%]; P = .81), as well as the mean (SD) choriocapillaris flow density (mild NPDR, 67.1% [5.6%]; moderate NPDR, 69.3% [4.6%]; severe NPDR or PDR, 68.3% [5.6%]; P = .49), did not appear to change with increasing DR severity.Conclusions and relevanceThese results suggest that central retinal vessel density is associated with DR severity in eyes without, but not with, PPL. These findings suggest a potential need to stratify future optical coherence tomography angiography studies of eyes with DR by the presence or absence of PPL. If DR onset and worsening are associated with the location of retinal nonperfusion, assessment of global retinal nonperfusion using widefield angiography may improve the ability to evaluate DR severity and risk of DR worsening over time.

Project description:ImportanceModerate to substantial agreement between Early Treatment Diabetic Retinopathy Study (ETDRS) 7-field imaging and ultrawide-field (UWF) imaging has been suggested in single-center studies. Comparing images obtained by multiple centers could increase confidence that UWF images can be used reliably in place of ETDRS imaging in future clinical trials.ObjectiveTo compare diabetic retinopathy (DR) severity from modified ETDRS 7-field imaging and UWF imaging.Design, setting, and participantsThis preplanned, cross-sectional analysis included modified ETDRS 7-field images obtained using the Diabetic Retinopathy Clinical Research Network acquisition protocol and UWF images obtained captured with the Optos 200Tx system (Optos, PLC) from adult participants (≥18 years old) with type 1 or type 2 diabetes. Both image types were evaluated by trained graders masked to clinical data. Data collection occurred from February 2015 to December 2015, and data analysis from June 2016 to December 2017.Main outcomes and measuresAgreement between UWF images, UWF images masked to include only the ETDRS 7-field area, and ETDRS 7-field images were calculated using κ statistics.ResultsA total of 764 eyes from 385 participants were included; participants had a median (IQR) age of 62.2 (53.6-69.2) years, 194 (50.4%) were women, and 256 (66.5%) were white. Of 742 eyes with both ETDRS 7-field images and UWF masked images graded, 359 (48.4% [95% CI, 44.4%-52.4%]) eyes had exact agreement, and 653 eyes (88.0% [95% CI, 85.2%-90.3%]) agreed within 1 step (weighted κ, 0.51 [95% CI, 0.44-0.58]). After open adjudication by an independent senior grader of all images with more than a 2-step discrepancy, perfect agreement was found in 435 eyes (59.0% [95% CI, 55.1%-62.8%]) and agreement within 1 step in 714 eyes (96.9% [95% CI, 95.1%-98.0%]; κ, 0.77 [95% CI, 0.73-0.82]). Ability of the imaging modalities to detect retinopathy severity in an individual eye was considered similar in 59 eyes (50.9% [95% CI, 41.3%-60.4%]), better for ETDRS 7-field imaging in 22 eyes (19.0% [95% CI, 12.5%-27.7%]), and better for UWF-masked images in 31 eyes (26.7% [95% CI 18.8%-36.5%]). Comparing UWF masked and unmasked images, 94 of 751 eyes (12.5%) had DR graded as at least 1 step more severe on UWF unmasked images vs UWF masked images. Predominantly peripheral DR lesions were present in 308 of 751 eyes (41.0%); this suggested increased DR severity by 2 or more steps in 34 eyes (11.0%).Conclusions and relevanceImaging by the ETDRS 7-field and UWF imaging systems have moderate to substantial agreement when determining the severity of DR within the 7 standard fields. Disparities in an individual eye are equivalently distributed between imaging modalities and can be better or worse on 1 or the other. Longitudinal follow-up will evaluate the primary outcome of this study to determine if peripheral retinal findings are associated with future retinopathy outcomes.

Dataset Information

Comparison of Subjective Assessment and Precise Quantitative Assessment of Lesion Distribution in Diabetic Retinopathy.

Publications

Comparison of Subjective Assessment and Precise Quantitative Assessment of Lesion Distribution in Diabetic Retinopathy.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets