Classification of teeth in cone-beam CT using deep convolutional neural network

详细信息    查看全文

• 作者：Yuma Miki^a ; Chisako Muramatsu^a ; ^{chisa@fjt.info.gifu-u.ac.jp} ; Tatsuro Hayashi^b ; Xiangrong Zhou^a ; Takeshi Hara^a ; Akitoshi Katsumata^c ; Hiroshi Fujita^a
• 关键词：Deep convolutional neural networks ; Tooth classification ; Dental cone-beam CT ; Forensic identification ; Dental chart
• 刊名：Computers in Biology and Medicine
• 出版年：2017
• 出版时间：1 January 2017
• 年：2017
• 卷：80
• 期：Complete
• 页码：24-29
• 全文大小：790 K
• 卷排序：80

文摘

A new application of deep convolutional neural network to dental images was explored. Good classification performance was obtained even with a small number of data. Data augmentation, especially the intensity transformation was effective in improving the classification performance. Performance was not strongly dependent on resizing methods except for the crop method. DCNN was effective in tooth classification without the need for precise tooth segmentation