five

ibrahimhamamci/DENTEX

收藏
Hugging Face2024-04-04 更新2024-06-11 收录
下载链接:
https://hf-mirror.com/datasets/ibrahimhamamci/DENTEX
下载链接
链接失效反馈
官方服务:
资源简介:
--- title: "DENTEX Dataset" license: cc-by-nc-sa-4.0 --- <p align="center"> <img src="https://huggingface.co/datasets/ibrahimhamamci/DENTEX/resolve/main/figures/dentex.jpg?download=true" width="100%"> </p> Welcome to the official page of the DENTEX dataset, which has been released as part of the [Dental Enumeration and Diagnosis on Panoramic X-rays Challenge (DENTEX)](https://dentex.grand-challenge.org/), organized in conjunction with the International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI) in 2023. The primary objective of this challenge is to develop algorithms that can accurately detect abnormal teeth with dental enumeration and associated diagnosis. This not only aids in accurate treatment planning but also helps practitioners carry out procedures with a low margin of error. The challenge provides three types of hierarchically annotated data and additional unlabeled X-rays for optional pre-training. The annotation of the data is structured using the Fédération Dentaire Internationale (FDI) system. The first set of data is partially labeled because it only includes quadrant info. The second set of data is also partially labeled but contains additional enumeration information along with the quadrant. The third set is fully labeled because it includes all quadrant-enumeration-diagnosis information for each abnormal tooth, and all participant algorithms have been benchmarked on this third set, with an example output shown below. <p align="center"> <img src="https://huggingface.co/datasets/ibrahimhamamci/DENTEX/resolve/main/figures/output.png?download=true" width="100%"> </p> ## DENTEX Dataset The DENTEX dataset comprises panoramic dental X-rays obtained from three different institutions using standard clinical conditions but varying equipment and imaging protocols, resulting in diverse image quality reflecting heterogeneous clinical practice. The dataset includes X-rays from patients aged 12 and above, randomly selected from the hospital's database to ensure patient privacy and confidentiality. To enable effective use of the FDI system, the dataset is hierarchically organized into three types of data: - (a) 693 X-rays labeled for quadrant detection and quadrant classes only, - (b) 634 X-rays labeled for tooth detection with quadrant and tooth enumeration classes, - (c) 1005 X-rays fully labeled for abnormal tooth detection with quadrant, tooth enumeration, and diagnosis classes. The diagnosis class includes four specific categories: caries, deep caries, periapical lesions, and impacted teeth. An additional 1571 unlabeled X-rays are provided for pre-training. <p align="center"> <img src="https://huggingface.co/datasets/ibrahimhamamci/DENTEX/resolve/main/figures/data.png?download=true" width="100%"> </p> ## Annotation Protocol The DENTEX dataset provides three hierarchically annotated datasets to support various dental detection tasks: (1) quadrant-only for quadrant detection, (2) quadrant-enumeration for tooth detection, and (3) quadrant-enumeration-diagnosis for abnormal tooth detection. While offering a quadrant detection dataset might appear redundant, it's essential for effectively using the FDI Numbering System. This globally recognized system assigns numbers from 1 through 4 to each mouth quadrant: top right (1), top left (2), bottom left (3), and bottom right (4). Additionally, it numbers each of the eight teeth and each molar from 1 to 8, starting from the front middle tooth and increasing towards the back. For instance, the back tooth on the lower left side is designated as 48 in FDI notation, indicating quadrant 4, tooth 8. Thus, the quadrant segmentation dataset greatly simplifies the dental enumeration task, though evaluations are conducted only on the fully annotated third dataset. ## Data Split for Evaluation and Training The DENTEX 2023 dataset comprises three types of data: (a) partially annotated quadrant data, (b) partially annotated quadrant-enumeration data, and (c) fully annotated quadrant-enumeration-diagnosis data. The first two types of data are intended for training and development purposes, while the third type is used for training and evaluations. To comply with standard machine learning practices, the fully annotated third dataset, consisting of 1005 panoramic X-rays, is partitioned into training, validation, and testing subsets, comprising 705, 50, and 250 images, respectively. Ground truth labels are provided only for the training data, while the validation data is provided without associated ground truth. All the ground truth data is now available for researchers. Note: The datasets are fully identical to the data used for our baseline method, named HierarchicalDet. For more information, please visit the [MICCAI paper](https://conferences.miccai.org/2023/papers/205-Paper2550.html) and the [GitHub repository](https://github.com/ibrahimethemhamamci/DENTEX) of HierarchicalDet (Diffusion-Based Hierarchical Multi-Label Object Detection to Analyze Panoramic Dental X-rays). ## Citing Us If you use DENTEX, we would appreciate references to the following papers: ``` 1. @article{hamamci2023dentex, title={DENTEX: An Abnormal Tooth Detection with Dental Enumeration and Diagnosis Benchmark for Panoramic X-rays}, author={Hamamci, Ibrahim Ethem and Er, Sezgin and Simsar, Enis and Yuksel, Atif Emre and Gultekin, Sadullah and Ozdemir, Serife Damla and Yang, Kaiyuan and Li, Hongwei Bran and Pati, Sarthak and Stadlinger, Bernd and others}, journal={arXiv preprint arXiv:2305.19112}, year={2023} } 2. @inproceedings{hamamci2023diffusion, title={Diffusion-based hierarchical multi-label object detection to analyze panoramic dental x-rays}, author={Hamamci, Ibrahim Ethem and Er, Sezgin and Simsar, Enis and Sekuboyina, Anjany and Gundogar, Mustafa and Stadlinger, Bernd and Mehl, Albert and Menze, Bjoern}, booktitle={International Conference on Medical Image Computing and Computer-Assisted Intervention}, pages={389--399}, year={2023}, organization={Springer} } ``` ## License We are committed to fostering innovation and collaboration in the research community. To this end, all elements of the DENTEX dataset are released under a [Creative Commons Attribution (CC-BY-NC-SA) license](https://creativecommons.org/licenses/by-nc-sa/4.0/). This licensing framework ensures that our contributions can be freely used for non-commercial research purposes, while also encouraging contributions and modifications, provided that the original work is properly cited and any derivative works are shared under similar terms.

--- title: "DENTEX数据集" license: cc-by-nc-sa-4.0 --- <p align="center"> <img src="https://huggingface.co/datasets/ibrahimhamamci/DENTEX/resolve/main/figures/dentex.jpg?download=true" width="100%"> </p> 欢迎来到DENTEX数据集的官方页面,本数据集作为2023年与国际医学图像计算与计算机辅助干预会议(MICCAI)联合举办的**全景牙科X射线牙齿计数与诊断挑战赛(Dental Enumeration and Diagnosis on Panoramic X-rays Challenge, DENTEX)**的配套资源正式发布。本次挑战赛的核心目标是开发可精准检测异常牙齿、完成牙齿计数并给出对应诊断的算法,该技术不仅有助于制定精准的治疗方案,还能帮助临床从业者降低操作误差。 本次挑战赛提供三类层级标注数据集,以及额外的未标注X射线影像供选手进行可选预训练。数据集的标注采用国际牙科联盟(Fédération Dentaire Internationale, FDI)标准。第一类数据为部分标注数据集,仅包含牙象限信息;第二类数据同样为部分标注,但额外包含牙象限与牙齿计数信息;第三类为全标注数据集,涵盖每颗异常牙齿的象限、计数与诊断信息,所有参赛算法均在第三套数据集上完成基准测试,示例输出如下。 <p align="center"> <img src="https://huggingface.co/datasets/ibrahimhamamci/DENTEX/resolve/main/figures/output.png?download=true" width="100%"> </p> ## DENTEX数据集 DENTEX数据集包含来自三家不同机构的全景牙科X射线影像,采集时均采用标准临床流程,但设备与成像协议存在差异,因此图像质量呈现多样性,反映了真实临床实践的异质性。数据集选取12岁及以上患者的X射线影像,从医院数据库中随机抽取,以充分保障患者隐私与信息保密性。 为适配FDI标注系统,数据集按层级划分为三类: - (a) 693张仅标注牙象限检测与象限类别的X射线影像; - (b) 634张标注了牙齿检测、牙象限与牙齿计数类别的X射线影像; - (c) 1005张针对异常牙齿检测完成全标注的X射线影像,包含牙象限、牙齿计数与诊断类别。 诊断类别包含四类具体场景:龋病、深龋、根尖周病变与阻生齿。此外还提供1571张未标注X射线影像用于预训练。 <p align="center"> <img src="https://huggingface.co/datasets/ibrahimhamamci/DENTEX/resolve/main/figures/data.png?download=true" width="100%"> </p> ## 标注规范 DENTEX数据集提供三类层级标注数据集,以支持不同的牙科检测任务:(1) 仅牙象限数据集用于牙象限检测;(2) 牙象限-计数数据集用于牙齿检测;(3) 牙象限-计数-诊断数据集用于异常牙齿检测。尽管仅提供牙象限检测数据集看似冗余,但对于有效使用FDI编号系统至关重要。这套全球通用的编号系统为口腔四个象限分配1至4的编号:右上(1)、左上(2)、左下(3)、右下(4)。同时,从中切牙开始向后方依次为1至8,标注每颗恒牙。例如,左下后方的磨牙在FDI标注体系中记为48,代表象限4、牙齿8。因此,牙象限分割数据集可极大简化牙齿计数任务,不过模型评估仅在全标注的第三套数据集上进行。 ## 训练与评估数据拆分 DENTEX 2023数据集包含三类数据:(a) 部分标注的牙象限数据、(b) 部分标注的牙象限-计数数据、(c) 全标注的牙象限-计数-诊断数据。前两类数据仅用于模型训练与开发,第三类数据则用于模型训练与评估。 遵循标准机器学习实践,包含1005张全景X射线的全标注第三套数据集被划分为训练、验证与测试子集,分别包含705、50与250张影像。仅训练数据提供真值标签,验证数据不附带真值标签。目前所有真值标签数据均已对研究人员开放。 > 注:本数据集与我们的基线方法HierarchicalDet所使用的数据完全一致。如需了解更多信息,请访问HierarchicalDet的[MICCAI论文](https://conferences.miccai.org/2023/papers/205-Paper2550.html)与[GitHub仓库](https://github.com/ibrahimethemhamamci/DENTEX)(基于扩散的层级多标签目标检测算法用于全景牙科X射线分析)。 ## 引用声明 若您使用DENTEX数据集,请引用以下论文: 1. @article{hamamci2023dentex, title={DENTEX: 面向全景牙科X射线的异常牙齿检测、牙齿计数与诊断基准数据集}, author={Hamamci, Ibrahim Ethem and Er, Sezgin and Simsar, Enis and Yuksel, Atif Emre and Gultekin, Sadullah and Ozdemir, Serife Damla and Yang, Kaiyuan and Li, Hongwei Bran and Pati, Sarthak and Stadlinger, Bernd 等}, journal={arXiv预印本arXiv:2305.19112}, year={2023} } 2. @inproceedings{hamamci2023diffusion, title={基于扩散的层级多标签目标检测算法用于全景牙科X射线分析}, author={Hamamci, Ibrahim Ethem and Er, Sezgin and Simsar, Enis and Sekuboyina, Anjany and Gundogar, Mustafa and Stadlinger, Bernd and Mehl, Albert and Menze, Bjoern}, booktitle={国际医学图像计算与计算机辅助干预会议}, pages={389--399}, year={2023}, organization={Springer} } ## 许可协议 我们致力于推动研究社区的创新与合作。为此,DENTEX数据集的所有内容均采用[知识共享署名-非商业性使用-相同方式共享(Creative Commons Attribution-NonCommercial-ShareAlike, CC-BY-NC-SA)许可协议](https://creativecommons.org/licenses/by-nc-sa/4.0/)发布。该许可框架确保我们的成果可免费用于非商业研究目的,同时鼓励对原工作进行引用与修改,且衍生作品需采用相同许可协议共享。
提供机构:
ibrahimhamamci
原始信息汇总

DENTEX 数据集概述

数据集简介

DENTEX 数据集是由国际医学图像计算与计算机辅助干预会议(MICCAI)2023年举办的“牙科全景X光片上的牙列计数与诊断挑战赛(DENTEX)”发布的数据集。该数据集旨在开发能够准确检测异常牙齿并进行牙列计数和相关诊断的算法,以辅助精确治疗计划和减少操作误差。

数据集组成

DENTEX 数据集包含来自三个不同机构的标准临床条件下获得的全景牙科X光片,涵盖12岁及以上患者的X光片,确保患者隐私和保密性。数据集分为三种类型的数据:

  • (a) 693张仅标注象限信息的X光片
  • (b) 634张标注象限和牙齿编号信息的X光片
  • (c) 1005张完全标注象限、牙齿编号和诊断信息的X光片

此外,还提供了1571张未标注的X光片用于预训练。

标注协议

数据集采用国际牙科联盟(FDI)系统进行分层标注,包括:

  • (1) 仅标注象限信息
  • (2) 标注象限和牙齿编号信息
  • (3) 完全标注象限、牙齿编号和诊断信息

诊断类别包括龋齿、深龋、根尖周病变和阻生牙四种。

数据划分

完全标注的第三类数据(1005张X光片)被划分为训练集(705张)、验证集(50张)和测试集(250张)。训练集提供真实标签,验证集和测试集不提供。

引用

如使用该数据集,请引用以下论文:

  1. @article{hamamci2023dentex, title={DENTEX: An Abnormal Tooth Detection with Dental Enumeration and Diagnosis Benchmark for Panoramic X-rays}, author={Hamamci, Ibrahim Ethem and Er, Sezgin and Simsar, Enis and Yuksel, Atif Emre and Gultekin, Sadullah and Ozdemir, Serife Damla and Yang, Kaiyuan and Li, Hongwei Bran and Pati, Sarthak and Stadlinger, Bernd and others}, journal={arXiv preprint arXiv:2305.19112}, year={2023} }

  2. @inproceedings{hamamci2023diffusion, title={Diffusion-based hierarchical multi-label object detection to analyze panoramic dental x-rays}, author={Hamamci, Ibrahim Ethem and Er, Sezgin and Simsar, Enis and Sekuboyina, Anjany and Gundogar, Mustafa and Stadlinger, Bernd and Mehl, Albert and Menze, Bjoern}, booktitle={International Conference on Medical Image Computing and Computer-Assisted Intervention}, pages={389--399}, year={2023}, organization={Springer} }

许可

DENTEX 数据集采用Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)许可协议,允许非商业性研究用途的自由使用、共享和修改,前提是正确引用原始作品,且任何衍生作品也需遵守类似条款。

搜集汇总
数据集介绍
main_image_url
构建方式
DENTEX数据集的构建基于国际牙科联盟(FDI)系统,旨在支持牙科全景X光片的异常牙齿检测、枚举和诊断。该数据集包括来自三个不同医疗机构的1005张全景X光片,这些图像在标准临床条件下使用不同的设备和成像协议获取,确保了图像质量的多样性。数据集被分为三类:仅包含象限信息的693张X光片、包含象限和牙齿枚举信息的634张X光片,以及包含象限、牙齿枚举和诊断信息的1005张X光片。此外,还提供了1571张未标记的X光片用于预训练。
特点
DENTEX数据集的主要特点在于其层次化的注释结构,这种结构不仅支持象限检测,还涵盖了牙齿枚举和异常牙齿的诊断。数据集中的诊断类别包括龋齿、深龋、根尖周病变和阻生牙四种。此外,数据集的多样性体现在来自不同机构和不同成像协议的X光片,这使得数据集在反映临床实践的异质性方面具有显著优势。
使用方法
DENTEX数据集适用于开发和评估能够准确检测和诊断异常牙齿的算法。数据集被划分为训练、验证和测试子集,分别包含705、50和250张X光片。训练数据提供了真实标签,而验证数据则未提供。研究者可以使用该数据集进行模型训练和性能评估,同时也可以利用未标记的数据进行预训练。为了确保研究的透明性和可重复性,数据集的构建和使用方法均遵循标准机器学习实践。
背景与挑战
背景概述
DENTEX数据集是由Ibrahim Ethem Hamamci等人于2023年创建,作为国际医学图像计算与计算机辅助干预会议(MICCAI)的一部分,旨在解决全景X光片中的牙齿异常检测、枚举和诊断问题。该数据集的核心研究问题是通过算法准确识别异常牙齿,并进行相应的诊断,以辅助精确的治疗计划和减少临床操作的误差。DENTEX数据集的发布不仅推动了口腔医学领域的技术进步,还为相关研究提供了宝贵的资源,展示了其在医学图像分析中的重要性。
当前挑战
DENTEX数据集在构建过程中面临多重挑战。首先,数据集包含了来自不同机构的全景X光片,这些图像在设备和成像协议上存在差异,导致图像质量的多样性,这增加了模型训练的复杂性。其次,数据集的标注采用了国际牙科联盟(FDI)系统,需要对牙齿进行分层标注,包括象限、枚举和诊断信息,这种复杂的标注结构对算法的准确性和鲁棒性提出了高要求。此外,数据集的评估和训练数据分割需要严格遵循机器学习标准,确保模型的泛化能力和可靠性。这些挑战共同构成了DENTEX数据集在实际应用中的重要研究方向。
常用场景
经典使用场景
在牙科医学领域,DENTEX数据集的经典使用场景主要集中在全景X光片的异常牙齿检测与诊断。该数据集通过提供不同层次的标注信息,支持从简单的象限检测到复杂的牙齿异常诊断等多种任务。研究者可以利用这些标注数据训练算法,以实现对牙齿异常的自动检测与分类,从而辅助牙科医生进行精确的治疗规划。
解决学术问题
DENTEX数据集解决了牙科医学中常见的学术研究问题,即如何通过计算机辅助技术提高全景X光片的诊断准确性。该数据集通过提供多层次的标注数据,使得研究者能够开发和验证更为复杂的牙齿检测与诊断算法,从而推动了牙科影像分析技术的发展。其意义在于,通过自动化手段减少人为诊断的误差,提高诊断效率,为临床实践提供了有力的技术支持。
衍生相关工作
DENTEX数据集的发布催生了一系列相关的经典工作,特别是在牙科影像分析和计算机辅助诊断领域。例如,基于该数据集的研究者开发了名为HierarchicalDet的基线方法,该方法利用扩散模型进行层次化的多标签物体检测,显著提升了全景X光片的分析精度。此外,该数据集还促进了多种深度学习模型的应用研究,推动了牙科医学与人工智能技术的深度融合。
以上内容由遇见数据集搜集并总结生成
5,000+
优质数据集
54 个
任务类型
进入经典数据集
二维码
社区交流群

面向社区/商业的数据集话题

二维码
科研交流群

面向高校/科研机构的开源数据集话题

数据驱动未来

携手共赢发展

商业合作