DuETNet: Dual Encoder based Transfer Network for thoracic disease classification
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, Min Seok | - |
dc.contributor.author | Han, Sung Won | - |
dc.date.accessioned | 2022-11-19T01:40:19Z | - |
dc.date.available | 2022-11-19T01:40:19Z | - |
dc.date.created | 2022-11-17 | - |
dc.date.issued | 2022-09 | - |
dc.identifier.issn | 0167-8655 | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/145827 | - |
dc.description.abstract | In thoracic disease classification, the original chest X-ray images are high resolution images. Nevertheless, in existing convolution neural network (CNN) models, the original images are resized to 224 x 224 before use. Diseases in local areas may not be sufficiently represented because the chest X-ray images have been resized, which compresses information excessively. Therefore, a higher resolution is required to focus on the local representations. Although the large input resolution reduces memory efficiency, previous studies have investigated using CNNs with the large input for classification performance improvement. Moreover, optimization for imbalanced classes is required because chest X-ray images have highly imbalanced pathology labels. Hence, this study proposes the Dual Encoder based Transfer Network (DuETNet) to counter the inefficiency caused by large input resolution and improve classification performance by adjusting the input size based on the RandomResizedCrop method. This image transformation method crops a random area of a given image and resizes it to a given size. Thus, a resolution calibration guideline is a practical way to achieve memory efficiency and performance gains under restricted resources by adjusting the scale factor a on the training and test images. To treat high class imbalance, we propose entropy based label smoothing method. The method enhances generalization performance for the imbalanced minor classes by penalizing the major classes. The dual encoder comprises channel and spatial encoders, which apply channel-and spatial-wise attention to enhance the relatively significant features from the adjusted images. To evaluate the performance of DuETNet, we used the ChestX-ray14 and MIMIC-CXR-JPG datasets, and DuETNet achieved a new state-of-the-art method. (C) 2022 Elsevier B.V. All rights reserved. | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | ELSEVIER | - |
dc.title | DuETNet: Dual Encoder based Transfer Network for thoracic disease classification | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Han, Sung Won | - |
dc.identifier.doi | 10.1016/j.patrec.2022.08.007 | - |
dc.identifier.scopusid | 2-s2.0-85136478713 | - |
dc.identifier.wosid | 000858844200001 | - |
dc.identifier.bibliographicCitation | PATTERN RECOGNITION LETTERS, v.161, pp.143 - 153 | - |
dc.relation.isPartOf | PATTERN RECOGNITION LETTERS | - |
dc.citation.title | PATTERN RECOGNITION LETTERS | - |
dc.citation.volume | 161 | - |
dc.citation.startPage | 143 | - |
dc.citation.endPage | 153 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Artificial Intelligence | - |
dc.subject.keywordAuthor | Thoracic disease classification | - |
dc.subject.keywordAuthor | Imbalanced multi -class classification | - |
dc.subject.keywordAuthor | Convolutional neural networks | - |
dc.subject.keywordAuthor | Resolution calibration | - |
dc.subject.keywordAuthor | Entropy based label smoothing | - |
dc.subject.keywordAuthor | Attention mechanism | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
145 Anam-ro, Seongbuk-gu, Seoul, 02841, Korea+82-2-3290-2963
COPYRIGHT © 2021 Korea University. All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.