Matches in SemOpenAlex for { <https://semopenalex.org/work/W3135598105> ?p ?o ?g. }
- W3135598105 endingPage "1039" @default.
- W3135598105 startingPage "1023" @default.
- W3135598105 abstract "Deep Learning (DL) and Artificial Intelligence (AI) have become widespread due to the advanced technologies and availability of digital data. Supervised learning algorithms have shown human-level performance or even better and are better feature extractor-quantifier than unsupervised learning algorithms. To get huge dataset with good quality control, there is a need of an annotation tool with a customizable feature set. This paper evaluates the viability of having an in house annotation tool which works on a smartphone and can be used in a healthcare setting.We developed a smartphone-based grading system to help researchers in grading multiple retinal fundi. The process consisted of designing the flow of user interface (UI) keeping in view feedback from experts. Quantitative and qualitative analysis of change in speed of a grader over time and feature usage statistics was done. The dataset size was approximately 16,000 images with adjudicated labels by a minimum of 2 doctors. Results for an AI model trained on the images graded using this tool and its validation over some public datasets were prepared.We created a DL model and analysed its performance for a binary referrable DR Classification task, whether a retinal image has Referrable DR or not. A total of 32 doctors used the tool for minimum of 20 images each. Data analytics suggested significant portability and flexibility of the tool. Grader variability for images was in favour of agreement on images annotated. Number of images used to assess agreement is 550. Mean of 75.9% was seen in agreement.Our aim was to make Annotation of Medical imaging easier and to minimize time taken for annotations without quality degradation. The user feedback and feature usage statistics confirm our hypotheses of incorporation of brightness and contrast variations, green channels and zooming add-ons in correlation to certain disease types. Simulation of multiple review cycles and establishing quality control can boost the accuracy of AI models even further. Although our study aims at developing an annotation tool for diagnosing and classifying diabetic retinopathy fundus images but same concept can be used for fundus images of other ocular diseases as well as other streams of medical science such as radiology where image-based diagnostic applications are utilised." @default.
- W3135598105 created "2021-03-15" @default.
- W3135598105 creator A5002045727 @default.
- W3135598105 creator A5003941685 @default.
- W3135598105 creator A5006520683 @default.
- W3135598105 creator A5011200955 @default.
- W3135598105 creator A5013818790 @default.
- W3135598105 creator A5014192765 @default.
- W3135598105 creator A5020123468 @default.
- W3135598105 creator A5023075135 @default.
- W3135598105 creator A5026276669 @default.
- W3135598105 creator A5031391644 @default.
- W3135598105 creator A5032377402 @default.
- W3135598105 creator A5043232192 @default.
- W3135598105 creator A5046556122 @default.
- W3135598105 creator A5053968971 @default.
- W3135598105 creator A5056175671 @default.
- W3135598105 creator A5058438445 @default.
- W3135598105 creator A5058556550 @default.
- W3135598105 creator A5069047922 @default.
- W3135598105 creator A5070243177 @default.
- W3135598105 creator A5071440651 @default.
- W3135598105 creator A5074997471 @default.
- W3135598105 creator A5075312418 @default.
- W3135598105 creator A5077781256 @default.
- W3135598105 creator A5082922067 @default.
- W3135598105 creator A5083859315 @default.
- W3135598105 creator A5087514641 @default.
- W3135598105 creator A5087863866 @default.
- W3135598105 creator A5091200076 @default.
- W3135598105 creator A5091704780 @default.
- W3135598105 date "2021-03-01" @default.
- W3135598105 modified "2023-10-02" @default.
- W3135598105 title "Evaluating the Viability of a Smartphone-Based Annotation Tool for Faster and Accurate Image Labelling for Artificial Intelligence in Diabetic Retinopathy" @default.
- W3135598105 cites W1567302321 @default.
- W3135598105 cites W1969496006 @default.
- W3135598105 cites W2015861736 @default.
- W3135598105 cites W2078242224 @default.
- W3135598105 cites W2103018059 @default.
- W3135598105 cites W2117539524 @default.
- W3135598105 cites W2529153069 @default.
- W3135598105 cites W2557738935 @default.
- W3135598105 cites W2762741128 @default.
- W3135598105 cites W2784652774 @default.
- W3135598105 cites W2886395189 @default.
- W3135598105 cites W2888424632 @default.
- W3135598105 cites W2995236054 @default.
- W3135598105 doi "https://doi.org/10.2147/opth.s289425" @default.
- W3135598105 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/7953891" @default.
- W3135598105 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33727785" @default.
- W3135598105 hasPublicationYear "2021" @default.
- W3135598105 type Work @default.
- W3135598105 sameAs 3135598105 @default.
- W3135598105 citedByCount "3" @default.
- W3135598105 countsByYear W31355981052021 @default.
- W3135598105 countsByYear W31355981052022 @default.
- W3135598105 crossrefType "journal-article" @default.
- W3135598105 hasAuthorship W3135598105A5002045727 @default.
- W3135598105 hasAuthorship W3135598105A5003941685 @default.
- W3135598105 hasAuthorship W3135598105A5006520683 @default.
- W3135598105 hasAuthorship W3135598105A5011200955 @default.
- W3135598105 hasAuthorship W3135598105A5013818790 @default.
- W3135598105 hasAuthorship W3135598105A5014192765 @default.
- W3135598105 hasAuthorship W3135598105A5020123468 @default.
- W3135598105 hasAuthorship W3135598105A5023075135 @default.
- W3135598105 hasAuthorship W3135598105A5026276669 @default.
- W3135598105 hasAuthorship W3135598105A5031391644 @default.
- W3135598105 hasAuthorship W3135598105A5032377402 @default.
- W3135598105 hasAuthorship W3135598105A5043232192 @default.
- W3135598105 hasAuthorship W3135598105A5046556122 @default.
- W3135598105 hasAuthorship W3135598105A5053968971 @default.
- W3135598105 hasAuthorship W3135598105A5056175671 @default.
- W3135598105 hasAuthorship W3135598105A5058438445 @default.
- W3135598105 hasAuthorship W3135598105A5058556550 @default.
- W3135598105 hasAuthorship W3135598105A5069047922 @default.
- W3135598105 hasAuthorship W3135598105A5070243177 @default.
- W3135598105 hasAuthorship W3135598105A5071440651 @default.
- W3135598105 hasAuthorship W3135598105A5074997471 @default.
- W3135598105 hasAuthorship W3135598105A5075312418 @default.
- W3135598105 hasAuthorship W3135598105A5077781256 @default.
- W3135598105 hasAuthorship W3135598105A5082922067 @default.
- W3135598105 hasAuthorship W3135598105A5083859315 @default.
- W3135598105 hasAuthorship W3135598105A5087514641 @default.
- W3135598105 hasAuthorship W3135598105A5087863866 @default.
- W3135598105 hasAuthorship W3135598105A5091200076 @default.
- W3135598105 hasAuthorship W3135598105A5091704780 @default.
- W3135598105 hasBestOaLocation W31355981051 @default.
- W3135598105 hasConcept C115961682 @default.
- W3135598105 hasConcept C119857082 @default.
- W3135598105 hasConcept C154945302 @default.
- W3135598105 hasConcept C199360897 @default.
- W3135598105 hasConcept C199579030 @default.
- W3135598105 hasConcept C2776321320 @default.
- W3135598105 hasConcept C41008148 @default.
- W3135598105 hasConcept C63000827 @default.
- W3135598105 hasConcept C9417928 @default.
- W3135598105 hasConcept C95623464 @default.
- W3135598105 hasConceptScore W3135598105C115961682 @default.