Deep-learning systems for diagnosing cleft palate on panoramic radiographs in patients with cleft alveolus,Oral Radiology

当前位置： X-MOL 学术 › Oral. Radiol. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

Deep-learning systems for diagnosing cleft palate on panoramic radiographs in patients with cleft alveolus
Oral Radiology ( IF 1.6 ) Pub Date : 2022-08-19 , DOI: 10.1007/s11282-022-00644-9
Chiaki Kuwada ₁ , Yoshiko Ariji ₂ , Yoshitaka Kise ₁ , Motoki Fukuda ₁ , Masako Nishiyama ₁ , Takuma Funakoshi ₁ , Rihoko Takeuchi ₃ , Airi Sana ₃ , Norinaga Kojima ₃ , Eiichiro Ariji ₁

Affiliation

Objectives

The aim of the present study was to create effective deep learning-based models for diagnosing the presence or absence of cleft palate (CP) in patients with unilateral or bilateral cleft alveolus (CA) on panoramic radiographs.

Methods

The panoramic images of 491 patients who had unilateral or bilateral cleft alveolus were used to create two models. Model A, which detects the upper incisor area on panoramic radiographs and classifies the areas into the presence or absence of CP, was created using both object detection and classification functions of DetectNet. Using the same data for developing Model A, Model B, which directly classifies the presence or absence of CP on panoramic radiographs, was created using classification function of VGG-16. The performances of both models were evaluated with the same test data and compared with those of two radiologists.

Results

The recall, precision, and F-measure were all 1.00 in Model A. The area under the receiver operating characteristic curve (AUC) values were 0.95, 0.93, 0.70, and 0.63 for Model A, Model B, and the radiologists, respectively. The AUCs of the models were significantly higher than those of the radiologists.

Conclusions

The deep learning-based models developed in the present study have potential for use in supporting observer interpretations of the presence of cleft palate on panoramic radiographs.

中文翻译：

深度学习系统用于诊断牙槽裂患者全景 X 光片上的腭裂

目标

本研究的目的是创建有效的基于深度学习的模型，用于诊断全景 X 光片上单侧或双侧牙槽裂 (CA) 患者是否存在腭裂 (CP)。

方法

使用 491 名患有单侧或双侧肺泡裂隙的患者的全景图像来创建两个模型。模型 A 检测全景 X 光片上的上切牙区域并将该区域分类为是否存在 CP，该模型是使用 DetectNet 的对象检测和分类功能创建的。使用用于开发模型 A 的相同数据，使用 VGG-16 的分类功能创建了模型 B，它直接对全景射线照片上是否存在 CP 进行分类。两种模型的性能均使用相同的测试数据进行评估，并与两位放射科医师的性能进行比较。