DC Field | Value | Language |
---|---|---|
dc.contributor.author | Ashraf, Murtaza | ko |
dc.contributor.author | Robles, Willmer Rafell Quinones | ko |
dc.contributor.author | Kim, Mujin | ko |
dc.contributor.author | Ko, Young Sin | ko |
dc.contributor.author | Yi, Mun Yong | ko |
dc.date.accessioned | 2022-02-08T06:40:27Z | - |
dc.date.available | 2022-02-08T06:40:27Z | - |
dc.date.created | 2022-02-07 | - |
dc.date.created | 2022-02-07 | - |
dc.date.created | 2022-02-07 | - |
dc.date.issued | 2022-01 | - |
dc.identifier.citation | SCIENTIFIC REPORTS, v.12, no.1, pp.1 - 18 | - |
dc.identifier.issn | 2045-2322 | - |
dc.identifier.uri | http://hdl.handle.net/10203/292094 | - |
dc.description.abstract | This paper proposes a deep learning-based patch label denoising method (LossDiff) for improving the classification of whole-slide images of cancer using a convolutional neural network (CNN). Automated whole-slide image classification is often challenging, requiring a large amount of labeled data. Pathologists annotate the region of interest by marking malignant areas, which pose a high risk of introducing patch-based label noise by involving benign regions that are typically small in size within the malignant annotations, resulting in low classification accuracy with many Type-II errors. To overcome this critical problem, this paper presents a simple yet effective method for noisy patch classification. The proposed method, validated using stomach cancer images, provides a significant improvement compared to other existing methods in patch-based cancer classification, with accuracies of 98.81%, 97.30% and 89.47% for binary, ternary, and quaternary classes, respectively. Moreover, we conduct several experiments at different noise levels using a publicly available dataset to further demonstrate the robustness of the proposed method. Given the high cost of producing explicit annotations for whole-slide images and the unavoidable error-prone nature of the human annotation of medical images, the proposed method has practical implications for whole-slide image annotation and automated cancer diagnosis. | - |
dc.language | English | - |
dc.publisher | NATURE RESEARCH | - |
dc.title | A loss-based patch label denoising method for improving whole-slide image analysis using a convolutional neural network | - |
dc.type | Article | - |
dc.identifier.wosid | 000749232200010 | - |
dc.identifier.scopusid | 2-s2.0-85123601871 | - |
dc.type.rims | ART | - |
dc.citation.volume | 12 | - |
dc.citation.issue | 1 | - |
dc.citation.beginningpage | 1 | - |
dc.citation.endingpage | 18 | - |
dc.citation.publicationname | SCIENTIFIC REPORTS | - |
dc.identifier.doi | 10.1038/s41598-022-05001-8 | - |
dc.contributor.localauthor | Yi, Mun Yong | - |
dc.contributor.nonIdAuthor | Ko, Young Sin | - |
dc.description.isOpenAccess | N | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordPlus | GASTRIC-CANCERCLASS NOISEDEEPCLASSIFICATIONPATHOLOGYTRENDS | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.