DC Field | Value | Language |
---|---|---|
dc.contributor.author | Jun, Tae Joon | ko |
dc.contributor.author | Kweon, Jihoon | ko |
dc.contributor.author | Kim, Young-Hak | ko |
dc.contributor.author | Kim, Daeyoung | ko |
dc.date.accessioned | 2020-10-16T07:55:08Z | - |
dc.date.available | 2020-10-16T07:55:08Z | - |
dc.date.created | 2020-10-06 | - |
dc.date.created | 2020-10-06 | - |
dc.date.created | 2020-10-06 | - |
dc.date.issued | 2020-08 | - |
dc.identifier.citation | NEURAL NETWORKS, v.128, pp.216 - 233 | - |
dc.identifier.issn | 0893-6080 | - |
dc.identifier.uri | http://hdl.handle.net/10203/276661 | - |
dc.description.abstract | In this paper, we proposed nested encoder-decoder architecture named T-Net. T-Net consists of several small encoder-decoders for each block constituting convolutional network. T-Net overcomes the limitation that U-Net can only have a single set of the concatenate layer between encoder and decoder block. To be more precise, the U-Net symmetrically forms the concatenate layers, so the low-level feature of the encoder is connected to the latter part of the decoder, and the high-level feature is connected to the beginning of the decoder. T-Net arranges the pooling and up-sampling appropriately during the encoding process, and likewise during the decoding process so that feature maps of various sizes are obtained in a single block. As a result, all features from the low-level to the high-level extracted from the encoder are delivered from the beginning of the decoder to predict a more accurate mask. We evaluated T-Net for the problem of segmenting three main vessels in coronary angiography images. The experiment consisted of a comparison of U-Net and T-Nets under the same conditions, and an optimized T-Net for the main vessel segmentation. As a result, T-Net recorded a Dice Similarity Coefficient score (DSC) of 83.77%, 10.69% higher than that of U-Net, and the optimized T-Net recorded a DSC of 88.97% which was 15.89% higher than that of U-Net. In addition, we visualized the weight activation of the convolutional layer of T-Net and U-Net to show that T-Net actually predicts the mask from earlier decoders. Therefore, we expect that T-Net can be effectively applied to other similar medical image segmentation problems. | - |
dc.language | English | - |
dc.publisher | PERGAMON-ELSEVIER SCIENCE LTD | - |
dc.title | Special T-Net: Nested encoder-decoder architecture for the main vessel segmentation in coronary angiography | - |
dc.type | Article | - |
dc.identifier.wosid | 000567812200018 | - |
dc.identifier.scopusid | 2-s2.0-85084942995 | - |
dc.type.rims | ART | - |
dc.citation.volume | 128 | - |
dc.citation.beginningpage | 216 | - |
dc.citation.endingpage | 233 | - |
dc.citation.publicationname | NEURAL NETWORKS | - |
dc.identifier.doi | 10.1016/j.neunet.2020.05.002 | - |
dc.contributor.localauthor | Kim, Daeyoung | - |
dc.contributor.nonIdAuthor | Jun, Tae Joon | - |
dc.contributor.nonIdAuthor | Kweon, Jihoon | - |
dc.contributor.nonIdAuthor | Kim, Young-Hak | - |
dc.description.isOpenAccess | N | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | Convolutional neural network | - |
dc.subject.keywordAuthor | Main vessel segmentation | - |
dc.subject.keywordAuthor | Coronary angiography | - |
dc.subject.keywordAuthor | Encoder and decoder | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.