2019年
Segmentation of Bone Metastasis in CT Images Based on Modified HED
2019 19TH INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION AND SYSTEMS (ICCAS 2019)
- ,
- ,
- ,
- ,
- ,
- ,
- 開始ページ
- 812
- 終了ページ
- 815
- 記述言語
- 英語
- 掲載種別
- 出版者・発行元
- IEEE
Segmentation of the bone metastasis area in medical images can reduce the workload for diagnosis and treatment. However, there are various shapes and sizes of bone metastasis also affected by noise. As a result, it is difficult to segment using classical segmentation methods. In this paper, we propose a convolutional neural network model-based segmentation method. The proposed method easily predicts the contour and location of the lesion area using side connection and modified network. In this study, we modified again the modified HED network to match the characteristics of bone metastasis. The experimental results using the proposed method for segmenting bone metastasis in the lesion area has 79.8[%] of TP rate and 69.2[%] of IOU rate.
- リンク情報
- ID情報
-
- ISSN : 2093-7121
- Web of Science ID : WOS:000555707100116