1. NCCU Academic Hub
  2. 學術產出
  3. College of Liberal Arts
  4. Periodical Articles
  5. Item

學術產出-Periodical Articles

Article View/Open

Publication Export

Google ScholarTM

政大圖書館

Citation Infomation

題名 Detecting microsatellite instability in colorectal cancer using Transformer-based colonoscopy image classification and retrieval
作者 羅崇銘
Lo, Chung-Ming;Jiang, Jeng-Kai;Lin, Chun-Chi
貢獻者 圖檔所
日期 2024-01
上傳時間 10-Apr-2024 16:26:53 (UTC+8)
摘要 Colorectal cancer (CRC) is a major global health concern, with microsatellite instability-high (MSI-H) being a defining characteristic of hereditary nonpolyposis colorectal cancer syndrome and affecting 15% of sporadic CRCs. Tumors with MSI-H have unique features and better prognosis compared to MSI-L and microsatellite stable (MSS) tumors. This study proposed establishing a MSI prediction model using more available and low-cost colonoscopy images instead of histopathology. The experiment utilized a database of 427 MSI-H and 1590 MSS colonoscopy images and vision Transformer (ViT) with different feature training approaches to establish the MSI prediction model. The accuracy of combining pre-trained ViT features was 84% with an area under the receiver operating characteristic curve of 0.86, which was better than that of DenseNet201 (80%, 0.80) in the experiment with support vector machine. The content-based image retrieval (CBIR) approach showed that ViT features can obtain a mean average precision of 0.81 compared to 0.79 of DenseNet201. ViT reduced the issues that occur in convolutional neural networks, including limited receptive field and gradient disappearance, and may be better at interpreting diagnostic information around tumors and surrounding tissues. By using CBIR, the presentation of similar images with the same MSI status would provide more convincing deep learning suggestions for clinical use.
關聯 PLOS One, Vol.19, No.1, e0292277
資料類型 article
DOI https://doi.org/10.1371/journal.pone.0292277
dc.contributor 圖檔所
dc.creator (作者) 羅崇銘
dc.creator (作者) Lo, Chung-Ming;Jiang, Jeng-Kai;Lin, Chun-Chi
dc.date (日期) 2024-01
dc.date.accessioned 10-Apr-2024 16:26:53 (UTC+8)-
dc.date.available 10-Apr-2024 16:26:53 (UTC+8)-
dc.date.issued (上傳時間) 10-Apr-2024 16:26:53 (UTC+8)-
dc.identifier.uri (URI) https://nccur.lib.nccu.edu.tw/handle/140.119/150695-
dc.description.abstract (摘要) Colorectal cancer (CRC) is a major global health concern, with microsatellite instability-high (MSI-H) being a defining characteristic of hereditary nonpolyposis colorectal cancer syndrome and affecting 15% of sporadic CRCs. Tumors with MSI-H have unique features and better prognosis compared to MSI-L and microsatellite stable (MSS) tumors. This study proposed establishing a MSI prediction model using more available and low-cost colonoscopy images instead of histopathology. The experiment utilized a database of 427 MSI-H and 1590 MSS colonoscopy images and vision Transformer (ViT) with different feature training approaches to establish the MSI prediction model. The accuracy of combining pre-trained ViT features was 84% with an area under the receiver operating characteristic curve of 0.86, which was better than that of DenseNet201 (80%, 0.80) in the experiment with support vector machine. The content-based image retrieval (CBIR) approach showed that ViT features can obtain a mean average precision of 0.81 compared to 0.79 of DenseNet201. ViT reduced the issues that occur in convolutional neural networks, including limited receptive field and gradient disappearance, and may be better at interpreting diagnostic information around tumors and surrounding tissues. By using CBIR, the presentation of similar images with the same MSI status would provide more convincing deep learning suggestions for clinical use.
dc.format.extent 108 bytes-
dc.format.mimetype text/html-
dc.relation (關聯) PLOS One, Vol.19, No.1, e0292277
dc.title (題名) Detecting microsatellite instability in colorectal cancer using Transformer-based colonoscopy image classification and retrieval
dc.type (資料類型) article
dc.identifier.doi (DOI) 10.1371/journal.pone.0292277
dc.doi.uri (DOI) https://doi.org/10.1371/journal.pone.0292277