FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4365452246> ?p ?o ?g. }

• W4365452246 abstract "Diabetic retinopathy (DR) is a major cause of vision impairment in diabetic patients worldwide. Due to its prevalence, early clinical diagnosis is essential to improve treatment management of DR patients. Despite recent demonstration of successful machine learning (ML) models for automated DR detection, there is a significant clinical need for robust models that can be trained with smaller cohorts of dataset and still perform with high diagnostic accuracy in independent clinical datasets (i.e., high model generalizability). Towards this need, we have developed a self-supervised contrastive learning (CL) based pipeline for classification of referable vs non-referable DR. Self-supervised CL based pretraining allows enhanced data representation, therefore, the development of robust and generalized deep learning (DL) models, even with small, labeled datasets. We have integrated a neural style transfer (NST) augmentation in the CL pipeline to produce models with better representations and initializations for the detection of DR in color fundus images. We compare our CL pretrained model performance with two state of the art baseline models pretrained with Imagenet weights. We further investigate the model performance with reduced labeled training data (down to 10 percent) to test the robustness of the model when trained with small, labeled datasets. The model is trained and validated on the EyePACS dataset and tested independently on clinical datasets from the University of Illinois, Chicago (UIC). Compared to baseline models, our CL pretrained FundusNet model had higher area under the receiver operating characteristics (ROC) curve (AUC) (CI) values (0.91 (0.898 to 0.930) vs 0.80 (0.783 to 0.820) and 0.83 (0.801 to 0.853) on UIC data). At 10 percent labeled training data, the FundusNet AUC was 0.81 (0.78 to 0.84) vs 0.58 (0.56 to 0.64) and 0.63 (0.60 to 0.66) in baseline models, when tested on the UIC dataset. CL based pretraining with NST significantly improves DL classification performance, helps the model generalize well (transferable from EyePACS to UIC data), and allows training with small, annotated datasets, therefore reducing ground truth annotation burden of the clinicians." @default.
• W4365452246 created "2023-04-15" @default.
• W4365452246 creator A5001530899 @default.
• W4365452246 creator A5004965117 @default.
• W4365452246 creator A5026587624 @default.
• W4365452246 creator A5033752926 @default.
• W4365452246 creator A5035477663 @default.
• W4365452246 creator A5048486021 @default.
• W4365452246 creator A5049608028 @default.
• W4365452246 creator A5071481167 @default.
• W4365452246 creator A5072253597 @default.
• W4365452246 date "2023-04-13" @default.
• W4365452246 modified "2023-09-26" @default.
• W4365452246 title "Contrastive learning-based pretraining improves representation and transferability of diabetic retinopathy classification models" @default.
• W4365452246 cites W2048082482 @default.
• W4365452246 cites W2317836139 @default.
• W4365452246 cites W2321533354 @default.
• W4365452246 cites W2557738935 @default.
• W4365452246 cites W2558381168 @default.
• W4365452246 cites W2598442119 @default.
• W4365452246 cites W2603777577 @default.
• W4365452246 cites W2604037227 @default.
• W4365452246 cites W2772246530 @default.
• W4365452246 cites W2806424800 @default.
• W4365452246 cites W2888424632 @default.
• W4365452246 cites W2893365278 @default.
• W4365452246 cites W2898192966 @default.
• W4365452246 cites W2942440727 @default.
• W4365452246 cites W2942586440 @default.
• W4365452246 cites W2946839276 @default.
• W4365452246 cites W2962858109 @default.
• W4365452246 cites W2965191493 @default.
• W4365452246 cites W2965325581 @default.
• W4365452246 cites W2976376778 @default.
• W4365452246 cites W2980444207 @default.
• W4365452246 cites W2981826026 @default.
• W4365452246 cites W3038835370 @default.
• W4365452246 cites W3039242854 @default.
• W4365452246 cites W3120430728 @default.
• W4365452246 cites W3128202743 @default.
• W4365452246 cites W3164440025 @default.
• W4365452246 cites W3203435379 @default.
• W4365452246 cites W3215326316 @default.
• W4365452246 cites W4281785677 @default.
• W4365452246 doi "https://doi.org/10.1038/s41598-023-33365-y" @default.
• W4365452246 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37055475" @default.
• W4365452246 hasPublicationYear "2023" @default.
• W4365452246 type Work @default.
• W4365452246 citedByCount "0" @default.
• W4365452246 crossrefType "journal-article" @default.
• W4365452246 hasAuthorship W4365452246A5001530899 @default.
• W4365452246 hasAuthorship W4365452246A5004965117 @default.
• W4365452246 hasAuthorship W4365452246A5026587624 @default.
• W4365452246 hasAuthorship W4365452246A5033752926 @default.
• W4365452246 hasAuthorship W4365452246A5035477663 @default.
• W4365452246 hasAuthorship W4365452246A5048486021 @default.
• W4365452246 hasAuthorship W4365452246A5049608028 @default.
• W4365452246 hasAuthorship W4365452246A5071481167 @default.
• W4365452246 hasAuthorship W4365452246A5072253597 @default.
• W4365452246 hasBestOaLocation W43654522461 @default.
• W4365452246 hasConcept C104317684 @default.
• W4365452246 hasConcept C105795698 @default.
• W4365452246 hasConcept C119857082 @default.
• W4365452246 hasConcept C134018914 @default.
• W4365452246 hasConcept C140331021 @default.
• W4365452246 hasConcept C153180895 @default.
• W4365452246 hasConcept C154945302 @default.
• W4365452246 hasConcept C185592680 @default.
• W4365452246 hasConcept C199360897 @default.
• W4365452246 hasConcept C27158222 @default.
• W4365452246 hasConcept C2776145971 @default.
• W4365452246 hasConcept C2779829184 @default.
• W4365452246 hasConcept C33923547 @default.
• W4365452246 hasConcept C41008148 @default.
• W4365452246 hasConcept C43521106 @default.
• W4365452246 hasConcept C55493867 @default.
• W4365452246 hasConcept C555293320 @default.
• W4365452246 hasConcept C58471807 @default.
• W4365452246 hasConcept C61272859 @default.
• W4365452246 hasConcept C63479239 @default.
• W4365452246 hasConcept C71924100 @default.
• W4365452246 hasConceptScore W4365452246C104317684 @default.
• W4365452246 hasConceptScore W4365452246C105795698 @default.
• W4365452246 hasConceptScore W4365452246C119857082 @default.
• W4365452246 hasConceptScore W4365452246C134018914 @default.
• W4365452246 hasConceptScore W4365452246C140331021 @default.
• W4365452246 hasConceptScore W4365452246C153180895 @default.
• W4365452246 hasConceptScore W4365452246C154945302 @default.
• W4365452246 hasConceptScore W4365452246C185592680 @default.
• W4365452246 hasConceptScore W4365452246C199360897 @default.
• W4365452246 hasConceptScore W4365452246C27158222 @default.
• W4365452246 hasConceptScore W4365452246C2776145971 @default.
• W4365452246 hasConceptScore W4365452246C2779829184 @default.
• W4365452246 hasConceptScore W4365452246C33923547 @default.
• W4365452246 hasConceptScore W4365452246C41008148 @default.
• W4365452246 hasConceptScore W4365452246C43521106 @default.
• W4365452246 hasConceptScore W4365452246C55493867 @default.
• W4365452246 hasConceptScore W4365452246C555293320 @default.
• W4365452246 hasConceptScore W4365452246C58471807 @default.
• W4365452246 hasConceptScore W4365452246C61272859 @default.

• next