| ○種別 (必須): | □ | 学術論文 (審査論文)
| [継承] |
| ○言語 (必須): | □ | 英語
| [継承] |
| ○招待 (推奨): |
| ○審査 (推奨): | □ | Peer Review
| [継承] |
| ○カテゴリ (推奨): | □ | 研究
| [継承] |
| ○共著種別 (推奨): | □ | 国内共著 (徳島大学内研究者と国内(学外)研究者との共同研究 (国外研究者を含まない))
| [継承] |
| ○学究種別 (推奨): |
| ○組織 (推奨): |
| ○著者 (必須): | 1. | (英) Ozaki Sho (日) (読)
| ○役割 (任意): |
| ○貢献度 (任意): |
| ○学籍番号 (推奨): |
| [継承] |
| 2. | (英) Kaji Shizuo (日) (読)
| ○役割 (任意): |
| ○貢献度 (任意): |
| ○学籍番号 (推奨): |
| [継承] |
| 3. | (英) Nawa Kanabu (日) (読)
| ○役割 (任意): |
| ○貢献度 (任意): |
| ○学籍番号 (推奨): |
| [継承] |
| 4. | (英) Imae Toshikazu (日) (読)
| ○役割 (任意): |
| ○貢献度 (任意): |
| ○学籍番号 (推奨): |
| [継承] |
| 5. | (英) Aoki Atsushi (日) (読)
| ○役割 (任意): |
| ○貢献度 (任意): |
| ○学籍番号 (推奨): |
| [継承] |
| 6. | (英) Nakamoto Takahiro (日) (読)
| ○役割 (任意): |
| ○貢献度 (任意): |
| ○学籍番号 (推奨): |
| [継承] |
| 7. | (英) Ohta Takeshi (日) (読)
| ○役割 (任意): |
| ○貢献度 (任意): |
| ○学籍番号 (推奨): |
| [継承] |
| 8. | (英) Nozawa Yuki (日) (読)
| ○役割 (任意): |
| ○貢献度 (任意): |
| ○学籍番号 (推奨): |
| [継承] |
| 9. | (英) Yamashita Hideomi (日) (読)
| ○役割 (任意): |
| ○貢献度 (任意): |
| ○学籍番号 (推奨): |
| [継承] |
| 10. | 芳賀 昭弘 ([徳島大学.大学院医歯薬学研究部.保健学域.保健科学部門.放射線科学系.医用画像物理学])
| ○役割 (任意): |
| ○貢献度 (任意): |
| ○学籍番号 (推奨): |
| [継承] |
| 11. | (英) Nakagawa Keiichi (日) (読)
| ○役割 (任意): |
| ○貢献度 (任意): |
| ○学籍番号 (推奨): |
| [継承] |
| ○題名 (必須): | □ | (英) Training of deep cross-modality conversion models with a small dataset, and their application in megavoltage CT to kilovoltage CT conversion (日)
| [継承] |
| ○副題 (任意): |
| ○要約 (任意): | □ | (英) In recent years, deep learning-based image processing has emerged as a valuable tool for medical imaging owing to its high performance. However, the quality of deep learning-based methods heavily relies on the amount of training data; the high cost of acquiring a large data set is a limitation to their utilization in medical fields. Herein, based on deep learning, we developed a computed tomography (CT) modality conversion method requiring only a few unsupervised images. The proposed method is based on cycle-consistency generative adversarial network (CycleGAN) with several extensions tailored for CT images, which aims at preserving the structure in the processed images and reducing the amount of training data. This method was applied to realize the conversion of megavoltage computed tomography (MVCT) to kilovoltage computed tomography (kVCT) images. Training was conducted using several data sets acquired from patients with head and neck cancer. The size of the data sets ranged from 16 slices (two patients) to 2745 slices (137 patients) for MVCT and 2824 slices (98 patients) for kVCT. The required size of the training data was found to be as small as a few hundred slices. By statistical and visual evaluations, the quality improvement and structure preservation of the MVCT images converted by the proposed model were investigated. As a clinical benefit, it was observed by medical doctors that the converted images enhanced the precision of contouring. We developed an MVCT to kVCT conversion model based on deep learning, which can be trained using only a few hundred unpaired images. The stability of the model against changes in data size was demonstrated. This study promotes the reliable use of deep learning in clinical medicine by partially answering commonly asked questions, such as "Is our data sufficient?" and "How much data should we acquire?" (日)
| [継承] |
| ○キーワード (推奨): |
| ○発行所 (推奨): |
| ○誌名 (必須): | □ | Medical Physics (American Association of Physicists in Medicine/[American Institute of Physics])
(pISSN: 0094-2405, eISSN: 2473-4209)
| ○ISSN (任意): | □ | 2473-4209
ISSN: 0094-2405
(pISSN: 0094-2405, eISSN: 2473-4209) Title: Medical physicsTitle(ISO): Med PhysSupplier: American Association of Physicists in MedicinePublisher: Wiley (NLM Catalog)
(Wiley)
(Scopus)
(CrossRef)
(Scopus information is found. [need login]) | [継承] |
| [継承] |
| ○巻 (必須): | □ | 49
| [継承] |
| ○号 (必須): | □ | 5
| [継承] |
| ○頁 (必須): | □ |
| [継承] |
| ○都市 (任意): |
| ○年月日 (必須): | □ | 西暦 2022年 6月 初日 (令和 4年 6月 初日)
| [継承] |
| ○URL (任意): |
| ○DOI (任意): | □ | 10.1002/mp.15626 (→Scopusで検索)
| [継承] |
| ○PMID (任意): | □ | 35315529 (→Scopusで検索)
| [継承] |
| ○CRID (任意): |
| ○Scopus (任意): |
| ○researchmap (任意): |
| ○評価値 (任意): |
| ○被引用数 (任意): |
| ○指導教員 (推奨): |
| ○備考 (任意): | 1. | (英) Article.ELocationID: 10.1002/mp.15626 (日)
| [継承] |
| 2. | (英) Article.PublicationTypeList.PublicationType: Journal Article (日)
| [継承] |
| 3. | (英) KeywordList.Keyword: computed tomography (日)
| [継承] |
| 4. | (英) KeywordList.Keyword: cross-modality conversion (日)
| [継承] |
| 5. | (英) KeywordList.Keyword: deep learning (日)
| [継承] |
| 6. | (英) KeywordList.Keyword: training data reduction (日)
| [継承] |