Photographic cranial shape analysis using deep learning
Photographic cranial shape analysis using deep learning
复制标题
使用深度学习进行摄影颅骨形状分析
DOI：
10.1117/12.2581990
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Linguraru, Marius G.
中科院分区：
文献类型：
--
作者：
Yektaie, Mohammad Ali;Ghasemi, Zahra;Hezaveh, Seyed Hossein;Aalamifar, Fereshteh;Seifabadi, Reza;Linguraru, Marius G.
目的确定使用深度学习算法识别和分类颅骨畸形类型的可行性，即，颅缝早闭和变形性斜头和短头畸形（DPB），使用婴儿头部的顶视图照片。方法我们使用了72个正常（13），DPB（34）和颅缝早闭（25）婴儿的三维头部体积。这些体积只包含关于头部形状的信息，缺乏纹理。从这些3D体积中，从不同的视角生成俯视2D渲染图。我们从每个3D体积中生成了37个2D文件，并应用了额外的数据增强以获得总共5，254个2D图像。然后，我们使用该数据集来研究用于图像分类的知名深度学习架构的性能，即，勒奈特将数据分为训练集和测试集（分别为85%和15%，测试集中每类至少有一个数据）。我们进行了交叉validation.ResultsThe的颅骨形状分析模型的整体准确率为87.5 ± 5.59%的模型评价。颅缝早闭病例的识别准确率为0.99±0.01，而DPB受试者的识别准确率为0.78 ± 0.1。该模型识别无颅骨畸形的正常人的准确率为0.96 ± 0.04。结论基于深度学习的方法可用于使用2D摄影数据准确检测和分类不同类型的头部畸形。这些算法将被打包为一个移动的健康解决方案，使决策支持工具在护理点可用。
PurposeTo determine the feasibility of using deep learning algorithms that can identify and classify types of cranial malformations, i.e., craniosynostosis and deformational plagiocephaly and brachycephaly (DPB), using top view photographs of the infant head.MethodWe used 72 3D head volumes of infants with normal (13), DPB (34), and craniosynostosis (25). These volumes contain only information about the head shape and lack texture. From these 3D volumes, top-view 2D renderings were generated from different viewing angles. We generated 37 2D files were generated from each 3D volume, and we applied additional data augmentation to obtain a total of 5,254 2D images. We then used this dataset to investigate the performance of a well-known deep learning architectures for image classification, i.e., LeNet. The data were divided into training and test sets (85% and 15%, respectively with minimum one data of each class in the test set). We performed model evaluation by cross-validation.ResultsThe overall accuracy of the cranial shape analysis model was 87.5 ± 5.59%. Cases with craniosynostosis were identified with 0.99±0.01 accuracy, while subjects with DPB were identified with 0.78 ± 0.1. The accuracy of the model to identify normal cases without cranial deformation was 0.96 ± 0.04.ConclusionsDeep learning-based methods can be used for the accurate detection, and classification of different types of conditions with head malformation using 2D photographic data. These algorithms will be packaged as a mobile health solution to make a decision support tool available at the point-of-care.
登录
查看更多内容
孤立性矢状骨融合的全颅穹重塑：第一部分：术后颅缝通畅
影响因子：
3.6
作者：
M. Seruya;Shubin Tan;A. Wray;A. Penington;A. Greensmith;A. Holmes;D. Chong
通讯作者：
D. Chong
在护理点对变形性斜头畸形和短头畸形进行定量评估
DOI：
10.1117/12.2581837
发表时间：
2021
期刊：
2021
影响因子：
--
作者：
Seifabadi, Reza;Aalamifar, Fereshteh;Hezaveh, Seyed Hossein;Kocabalkanli, Can;Linguraru, Marius G.
通讯作者：
Linguraru, Marius G.
影响因子：
120.7
作者：
Courchesne, E;Carper, R;Akshoomoff, N
通讯作者：
Akshoomoff, N
影响因子：
--
作者：
Moon IY;Lim SY;Oh KS
通讯作者：
Oh KS