DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, H. | - |
dc.contributor.author | Yoon, H. | - |
dc.contributor.author | Thakur, N. | - |
dc.contributor.author | Hwang, G. | - |
dc.contributor.author | Lee, E.J. | - |
dc.contributor.author | Kim, C. | - |
dc.contributor.author | Chong, Y. | - |
dc.date.accessioned | 2022-01-05T04:20:20Z | - |
dc.date.available | 2022-01-05T04:20:20Z | - |
dc.date.created | 2021-12-12 | - |
dc.date.issued | 2021-11 | - |
dc.identifier.issn | 2045-2322 | - |
dc.identifier.uri | https://oasis.postech.ac.kr/handle/2014.oak/109064 | - |
dc.description.abstract | Automatic pattern recognition using deep learning techniques has become increasingly important. Unfortunately, due to limited system memory, general preprocessing methods for high-resolution images in the spatial domain can lose important data information such as high-frequency information and the region of interest. To overcome these limitations, we propose an image segmentation approach in the compressed domain based on principal component analysis (PCA) and discrete wavelet transform (DWT). After inference for each tile using neural networks, a whole prediction image was reconstructed by wavelet weighted ensemble (WWE) based on inverse discrete wavelet transform (IDWT). The training and validation were performed using 351 colorectal biopsy specimens, which were pathologically confirmed by two pathologists. For 39 test datasets, the average Dice score, the pixel accuracy, and the Jaccard score were 0.804 �� 0.125, 0.957 �� 0.025, and 0.690 �� 0.174, respectively. We can train the networks for the high-resolution image with the large region of interest compared to the result in the low-resolution and the small region of interest in the spatial domain. The average Dice score, pixel accuracy, and Jaccard score are significantly increased by 2.7%, 0.9%, and 2.7%, respectively. We believe that our approach has great potential for accurate diagnosis. ? 2021, The Author(s). | - |
dc.language | English | - |
dc.publisher | Nature Research | - |
dc.relation.isPartOf | Scientific Reports | - |
dc.title | Deep learning-based histopathological segmentation for whole slide images of colorectal cancer in a compressed domain | - |
dc.type | Article | - |
dc.identifier.doi | 10.1038/s41598-021-01905-z | - |
dc.type.rims | ART | - |
dc.identifier.bibliographicCitation | Scientific Reports, v.11, no.1 | - |
dc.identifier.wosid | 000720520100021 | - |
dc.citation.number | 1 | - |
dc.citation.title | Scientific Reports | - |
dc.citation.volume | 11 | - |
dc.contributor.affiliatedAuthor | Kim, C. | - |
dc.identifier.scopusid | 2-s2.0-85119269718 | - |
dc.description.journalClass | 1 | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | Y | - |
dc.type.docType | Article | - |
dc.relation.journalWebOfScienceCategory | Multidisciplinary Sciences | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
library@postech.ac.kr Tel: 054-279-2548
Copyrights © by 2017 Pohang University of Science ad Technology All right reserved.