Cited 0 times in
Deep Learning-Based Image Conversion Improves the Reproducibility of Computed Tomography Radiomics Features: A Phantom Study
DC Field | Value | Language |
---|---|---|
dc.date.accessioned | 2023-06-02T00:47:19Z | - |
dc.date.available | 2023-06-02T00:47:19Z | - |
dc.date.issued | 2022-05 | - |
dc.identifier.issn | 0020-9996 | - |
dc.identifier.uri | https://ir.ymlib.yonsei.ac.kr/handle/22282913/194431 | - |
dc.description.abstract | Objectives: This study aimed to evaluate the usefulness of deep learning-based image conversion to improve the reproducibility of computed tomography (CT) radiomics features. Materials and methods: This study was conducted using an abdominal phantom with liver nodules. We developed an image conversion algorithm using a residual feature aggregation network to reproduce radiomics features with CT images under various CT protocols and reconstruction kernels. External validation was performed using images from different scanners, consisting of 8 different protocols. To evaluate the variability of radiomics features, regions of interest (ROIs) were drawn by targeting the liver parenchyma, vessels, paraspinal area, and liver nodules. We extracted 18 first-order, 68 second-order, and 688 wavelet radiomics features. Measurement variability was assessed using the concordance correlation coefficient (CCC), compared with the ground-truth image. Results: In the ROI-based analysis, there was an 83.3% improvement of CCC (80/96; 4 ROIs with 3 categories of radiomics features and 8 protocols) in synthetic images compared with the original images. Among them, the 56 CCC pairs showed a significant increase after image synthesis. In the radiomics feature-based analysis, 62.0% (3838 of 6192; 774 radiomics features with 8 protocols) features showed increased CCC after image synthesis, and a significant increase was noted in 26.9% (1663 of 6192) features. In particular, the first-order feature (79.9%, 115/144) showed better improvement in terms of the reproducibility of radiomics feature than the second-order (59.9%, 326/544) or wavelet feature (61.7%, 3397/5504). Conclusions: Our study demonstrated that a deep learning model for image conversion can improve the reproducibility of radiomics features across various CT protocols, reconstruction kernels, and CT scanners. | - |
dc.description.statementOfResponsibility | restriction | - |
dc.language | English | - |
dc.publisher | Lippincott Williams & Wilkins | - |
dc.relation.isPartOf | INVESTIGATIVE RADIOLOGY | - |
dc.rights | CC BY-NC-ND 2.0 KR | - |
dc.subject.MESH | Deep Learning* | - |
dc.subject.MESH | Image Processing, Computer-Assisted / methods | - |
dc.subject.MESH | Phantoms, Imaging | - |
dc.subject.MESH | Reproducibility of Results | - |
dc.subject.MESH | Tomography Scanners, X-Ray Computed | - |
dc.subject.MESH | Tomography, X-Ray Computed / methods | - |
dc.title | Deep Learning-Based Image Conversion Improves the Reproducibility of Computed Tomography Radiomics Features: A Phantom Study | - |
dc.type | Article | - |
dc.contributor.college | College of Medicine (의과대학) | - |
dc.contributor.department | Research Institute (부설연구소) | - |
dc.contributor.googleauthor | Seul Bi Lee | - |
dc.contributor.googleauthor | Yeon Jin Cho | - |
dc.contributor.googleauthor | Youngtaek Hong | - |
dc.contributor.googleauthor | Dawun Jeong | - |
dc.contributor.googleauthor | Jina Lee | - |
dc.contributor.googleauthor | Soo-Hyun Kim | - |
dc.contributor.googleauthor | Seunghyun Lee | - |
dc.contributor.googleauthor | Young Hun Choi | - |
dc.identifier.doi | 10.1097/RLI.0000000000000839 | - |
dc.relation.journalcode | J01188 | - |
dc.identifier.eissn | 1536-0210 | - |
dc.identifier.pmid | 34839305 | - |
dc.identifier.url | https://journals.lww.com/investigativeradiology/Fulltext/2022/05000/Deep_Learning_Based_Image_Conversion_Improves_the.4.aspx | - |
dc.citation.volume | 57 | - |
dc.citation.number | 5 | - |
dc.citation.startPage | 308 | - |
dc.citation.endPage | 317 | - |
dc.identifier.bibliographicCitation | INVESTIGATIVE RADIOLOGY, Vol.57(5) : 308-317, 2022-05 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.