论文阅读:Individual tooth segmentation from CT images scanned with contacts of maxillary and mandible te

【论文信息】

Individual tooth segmentation from CT images scanned with contacts of maxillary and mandible teeth
computer methods and programs in biomedicine 2017
深圳中科院,上海交大

【背景】

以前的文章几乎都是针对的上颌骨/下颌骨CT牙齿分割,也就是说是在open mouth的状态下分割。本文要来对要和状态的牙齿CT分割。
previous work分为两大类,3D Segmentation 以及 2D slice-by-slice Segmentation.
3D:
【2】用区域生长;【3,4】用3DLS提取牙齿表面;【5,6】graph cut交互分割。【7】对单牙根的牙齿迭代建模(要读一下

2D:
基本上是用了相邻slice间contour相似的特性,用LS分割,一般需要手动初始化起始slice。【8,9】用B样条snake以及遗传算法来提取轮廓,没能解决牙齿中的拓扑变化,而【10-13】的LS可以;【10】LS with Shape和Intensity,效果好。【11】用相同的模型来分割牙根。【12】修改了这个模型来分割前牙。【13】也是分割牙根。(看下11和13

但当上下牙接触时,aforementioned 方法由于在部分slice中上下牙轮廓接触,不好检测边界,而分割失败。
【14,15】从上下颌牙齿接触的CT中把上下颌分开,但他们没有把牙齿从颌骨上分割下来

As an AI language model, I can suggest some possible steps for automatic tooth instance segmentation and identification from cone beam CT images: 1. Pre-processing: The first step is to pre-process the CBCT images to remove noise, artifacts, and other image distortions. This can be achieved through various image processing techniques, such as filtering, thresholding, and morphological operations. 2. Tooth segmentation: The next step is to segment the individual teeth from the CBCT images. This can be done using various segmentation algorithms, such as region-growing, active contours, and watershed-based techniques. The segmentation can be further refined by incorporating shape and texture information. 3. Tooth instance identification: Once the individual teeth are segmented, the next step is to identify the specific tooth instance (e.g., mandibular left central incisor). This can be done using various methods, such as template matching, feature extraction, and machine learning-based approaches. 4. Post-processing: Finally, the segmented teeth and identified instances can be post-processed to remove any remaining artifacts or noise. This can be achieved through various techniques, such as smoothing, filtering, and morphological operations. Overall, automatic tooth instance segmentation and identification from CBCT images is a challenging task that requires the integration of various image processing, computer vision, and machine learning techniques. However, with recent advancements in AI and deep learning, there is great potential for developing accurate and reliable automated systems for dental image analysis.
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值