Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhu, Shenji, Hu, Miaoxin, Pan, Tianya, Hong, Yue, Li, Bin, Zhou, Zhiguang, Xu, Ting
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2405.08573
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916245976121344
author Zhu, Shenji
Hu, Miaoxin
Pan, Tianya
Hong, Yue
Li, Bin
Zhou, Zhiguang
Xu, Ting
author_facet Zhu, Shenji
Hu, Miaoxin
Pan, Tianya
Hong, Yue
Li, Bin
Zhou, Zhiguang
Xu, Ting
contents Tooth segmentation is a key step for computer aided diagnosis of dental diseases. Numerous machine learning models have been employed for tooth segmentation on dental panoramic radiograph. However, it is a difficult task to achieve accurate tooth segmentation due to complex tooth shapes, diverse tooth categories and incomplete sample set for machine learning. In this paper, we propose ViSTooth, a visualization framework for tooth segmentation on dental panoramic radiograph. First, we employ Mask R-CNN to conduct preliminary tooth segmentation, and a set of domain metrics are proposed to estimate the accuracy of the segmented teeth, including tooth shape, tooth position and tooth angle. Then, we represent the teeth with high-dimensional vectors and visualize their distribution in a low-dimensional space, in which experts can easily observe those teeth with specific metrics. Further, we expand the sample set with the expert-specified teeth and train the tooth segmentation model iteratively. Finally, we conduct case study and expert study to demonstrate the effectiveness and usability of our ViSTooth, in aiding experts to implement accurate tooth segmentation guided by expert knowledge.
format Preprint
id arxiv_https___arxiv_org_abs_2405_08573
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ViSTooth: A Visualization Framework for Tooth Segmentation on Panoramic Radiograph
Zhu, Shenji
Hu, Miaoxin
Pan, Tianya
Hong, Yue
Li, Bin
Zhou, Zhiguang
Xu, Ting
Human-Computer Interaction
Tooth segmentation is a key step for computer aided diagnosis of dental diseases. Numerous machine learning models have been employed for tooth segmentation on dental panoramic radiograph. However, it is a difficult task to achieve accurate tooth segmentation due to complex tooth shapes, diverse tooth categories and incomplete sample set for machine learning. In this paper, we propose ViSTooth, a visualization framework for tooth segmentation on dental panoramic radiograph. First, we employ Mask R-CNN to conduct preliminary tooth segmentation, and a set of domain metrics are proposed to estimate the accuracy of the segmented teeth, including tooth shape, tooth position and tooth angle. Then, we represent the teeth with high-dimensional vectors and visualize their distribution in a low-dimensional space, in which experts can easily observe those teeth with specific metrics. Further, we expand the sample set with the expert-specified teeth and train the tooth segmentation model iteratively. Finally, we conduct case study and expert study to demonstrate the effectiveness and usability of our ViSTooth, in aiding experts to implement accurate tooth segmentation guided by expert knowledge.
title ViSTooth: A Visualization Framework for Tooth Segmentation on Panoramic Radiograph
topic Human-Computer Interaction
url https://arxiv.org/abs/2405.08573