MétaCan
Menu
Back to cohort

Retinal Vessel Segmentation Techniques

2022· article· en· W4220853026 on OpenAlexaff
Santhosh Krishna B V, Sanjeev Sharma, K.R Indrajith, Eric Joe, Amith Sabu, Mali Satish Dilip

Bibliographic record

Venue2022 Second International Conference on Artificial Intelligence and Smart Energy (ICAIS) · 2022
Typearticle
Languageen
FieldMedicine
TopicRetinal Imaging and Analysis
Canadian institutionsHorizon College and Seminary
Fundersnot available
KeywordsRetinalComputer scienceFundus (uterus)CategorizationArtificial intelligenceContrast (vision)SegmentationComputer visionRetinaImage segmentationFeature extractionMedicineOphthalmologyBiologyNeuroscience

Abstract

fetched live from OpenAlex

In recent times, there has been progress in developing new automated software aided approaches for extraction and categorization of retinal blood vessels, with clinical applications being the most common. The purpose of this review is to give a comprehensive overview of the procedures for segmenting and classifying retinal veins. The basics of retinal fundus imaging and pattern of retinal pictures are covered first. Then there's a discussion of pre-processing operations and improved ways for recognizing retinal vessels. In addition, there is a conversation of the authentication step and evaluation of the results of retinal vascular extraction. The proposed methods for categorizing veins and arteries in fundus images are evaluated in depth in this work. The low contrast of the fundus image, as well as the lack of homogeneity of the lighting in background, present some obstacles dis the classification of vessels in retinal fundus imaging. The image's inhomogeneity is created by the imaging technique, whereas the image's low contrast is caused by differences dis the environment and the difference of the individual blood arteries. This indicates that the difference between thicker and thinner vessels is greater. Another issue is the color differences in the retina of various persons, which are based on biological characteristics. The majority of strategies for categorization of retinal blood vessels depend on dimensional and optical criteria that distinguish veins from arteries. Different key contributions are discussed in this article that compares various methods to solve all of the constraints and challenges in retinal vessel extraction and categorization procedures.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.001
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.005
Threshold uncertainty score0.018

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.001
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0040.003
Science and technology studies0.0010.001
Scholarly communication0.0020.001
Open science0.0010.001
Research integrity0.0020.001
Insufficient payload (model declined to judge)0.0050.004

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.057
GPT teacher head0.324
Teacher spread0.268 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations5
Published2022
Admission routes1
Has abstractyes

Explore more

Same venue2022 Second International Conference on Artificial Intelligence and Smart Energy (ICAIS)Same topicRetinal Imaging and AnalysisFrench-language works237,207