Matches in SemOpenAlex for { <https://semopenalex.org/work/W2554816911> ?p ?o ?g. }
Showing items 1 to 59 of
59
with 100 items per page.
- W2554816911 abstract "For automatic screening of eye diseases, it is very important to segment regions corresponding to the different eye-parts from the fundal images. A challenging task, in this context, is to segment the network of blood vessels. The blood vessel network runs all along the fundal image, varying in density and fineness of structure. Besides, changes in illumination, color and pathology also add to the difficulties in blood vessel segmentation. In this paper, we propose segmentation of blood vessels from fundal images in the deep learning framework, without any pre-processing. A deep convolutional network, consisting of 8 convolutional layers and 3 pooling layers in between, is used to achieve the segmentation. In this work, a Convolutional Neural Network currently in use for semantic image segmentation is customized for blood vessel segmentation by replacing the output layer with a convolutional layer of kernel size 1 × 1 which generates the final segmented image. The output of CNN is a gray scale image and is binarized by thresholding. The proposed method is applied on 2 publicly available databases DRIVE and HRF (capturing diversity in image resolution), consisting of healthy and diseased fundal images boosted by mirror versions of the originals. The method results in an accuracy of 93.94% and yields 0.894 as area under the ROC curve on the test data comprising of randomly selected 23 images from HRF dataset. The promising results illustrate generalizability of the proposed approach." @default.
- W2554816911 created "2016-11-30" @default.
- W2554816911 creator A5014371833 @default.
- W2554816911 creator A5018193052 @default.
- W2554816911 creator A5062096014 @default.
- W2554816911 creator A5077672666 @default.
- W2554816911 date "2016-06-01" @default.
- W2554816911 modified "2023-10-06" @default.
- W2554816911 title "Customizing CNNs for blood vessel segmentation from fundus images" @default.
- W2554816911 cites W1579287100 @default.
- W2554816911 doi "https://doi.org/10.1109/spcom.2016.7746702" @default.
- W2554816911 hasPublicationYear "2016" @default.
- W2554816911 type Work @default.
- W2554816911 sameAs 2554816911 @default.
- W2554816911 citedByCount "11" @default.
- W2554816911 countsByYear W25548169112020 @default.
- W2554816911 countsByYear W25548169112021 @default.
- W2554816911 countsByYear W25548169112022 @default.
- W2554816911 countsByYear W25548169112023 @default.
- W2554816911 crossrefType "proceedings-article" @default.
- W2554816911 hasAuthorship W2554816911A5014371833 @default.
- W2554816911 hasAuthorship W2554816911A5018193052 @default.
- W2554816911 hasAuthorship W2554816911A5062096014 @default.
- W2554816911 hasAuthorship W2554816911A5077672666 @default.
- W2554816911 hasConcept C118487528 @default.
- W2554816911 hasConcept C124504099 @default.
- W2554816911 hasConcept C153180895 @default.
- W2554816911 hasConcept C154945302 @default.
- W2554816911 hasConcept C2776391266 @default.
- W2554816911 hasConcept C31972630 @default.
- W2554816911 hasConcept C41008148 @default.
- W2554816911 hasConcept C71924100 @default.
- W2554816911 hasConcept C89600930 @default.
- W2554816911 hasConceptScore W2554816911C118487528 @default.
- W2554816911 hasConceptScore W2554816911C124504099 @default.
- W2554816911 hasConceptScore W2554816911C153180895 @default.
- W2554816911 hasConceptScore W2554816911C154945302 @default.
- W2554816911 hasConceptScore W2554816911C2776391266 @default.
- W2554816911 hasConceptScore W2554816911C31972630 @default.
- W2554816911 hasConceptScore W2554816911C41008148 @default.
- W2554816911 hasConceptScore W2554816911C71924100 @default.
- W2554816911 hasConceptScore W2554816911C89600930 @default.
- W2554816911 hasLocation W25548169111 @default.
- W2554816911 hasOpenAccess W2554816911 @default.
- W2554816911 hasPrimaryLocation W25548169111 @default.
- W2554816911 hasRelatedWork W1669643531 @default.
- W2554816911 hasRelatedWork W1721780360 @default.
- W2554816911 hasRelatedWork W2110230079 @default.
- W2554816911 hasRelatedWork W2117664411 @default.
- W2554816911 hasRelatedWork W2117933325 @default.
- W2554816911 hasRelatedWork W2122581818 @default.
- W2554816911 hasRelatedWork W2159066190 @default.
- W2554816911 hasRelatedWork W2739874619 @default.
- W2554816911 hasRelatedWork W2965422042 @default.
- W2554816911 hasRelatedWork W1967061043 @default.
- W2554816911 isParatext "false" @default.
- W2554816911 isRetracted "false" @default.
- W2554816911 magId "2554816911" @default.
- W2554816911 workType "article" @default.