講演抄録/キーワード |
講演名 |
2021-12-17 15:30
[ショートペーパー]Prediction Model of Early Recurrence of Hepatocellular Carcinoma Based on Deep Learning with Attention Module ○Weibin Wang(Ritsumeikan Univ.)・Fang Wang・Qingqing Chen(Zhejiang Univ.)・Yutaro Iwamoto(Ritsumeikan Univ.)・Xianhua Han(Yamaguchi Univ.)・Yen-wei Chen(Ritsumeikan Univ.) PRMU2021-59 |
抄録 |
(和) |
(まだ登録されていません) |
(英) |
Early recurrence of hepatocyte carcinoma (HCC) will still lead to a decrease in the survival rate of patients who have accepted surgical treatment. Preoperative early recurrence prediction of patients with hepatocellular carcinoma can assist the doctor to formulate treatment plans and post-operative guidance of follow-up patients.In this paper, we propose a prediction model based on deep learning that contains intra phase attention and inter phase attention. Intra phase attention can focus on important information of different channels and spatial in the same phase, while inter phase attention can focus on important information between different phases. We also propose a fusion model to combine the image features with clinical data. Experimental results show that our fusion model has superior performance over the model using clinical data only or CT image only, achieving a prediction accuracy of 81.2% and the area under the curve (AUC) of 0.869 on our HCC database. |
キーワード |
(和) |
/ / / / / / / |
(英) |
Early recurrence / Deep learning / Multi-phase CT images / Intra phase attention / Inter phase attention / / / |
文献情報 |
信学技報, vol. 121, no. 304, PRMU2021-59, pp. 195-198, 2021年12月. |
資料番号 |
PRMU2021-59 |
発行日 |
2021-12-09 (PRMU) |
ISSN |
Online edition: ISSN 2432-6380 |
著作権に ついて |
技術研究報告に掲載された論文の著作権は電子情報通信学会に帰属します.(許諾番号:10GA0019/12GB0052/13GB0056/17GB0034/18GB0034) |
PDFダウンロード |
PRMU2021-59 |