使用3D U-Net通过深度学习从磁共振图像自动分割头颈部颅外静脉畸形
Deep Learning for the Automatic Segmentation of Extracranial Venous Malformations of the Head and Neck from MR Images Using 3D U-Net.
作者信息
Ryu Jeong Yeop, Hong Hyun Ki, Cho Hyun Geun, Lee Joon Seok, Yoo Byeong Cheol, Choi Min Hyeok, Chung Ho Yun
机构信息
Department of Plastic and Reconstructive Surgery, School of Medicine, Kyungpook National University, Daegu 41944, Korea.
DEEPNOID Co., Seoul 08376, Korea.
出版信息
J Clin Med. 2022 Sep 23;11(19):5593. doi: 10.3390/jcm11195593.
BACKGROUND
It is difficult to characterize extracranial venous malformations (VMs) of the head and neck region from magnetic resonance imaging (MRI) manually and one at a time. We attempted to perform the automatic segmentation of lesions from MRI of extracranial VMs using a convolutional neural network as a deep learning tool.
METHODS
T2-weighted MRI from 53 patients with extracranial VMs in the head and neck region was used for annotations. Preprocessing management was performed before training. Three-dimensional U-Net was used as a segmentation model. Dice similarity coefficients were evaluated along with other indicators.
RESULTS
Dice similarity coefficients in 3D U-Net were found to be 99.75% in the training set and 60.62% in the test set. The models showed overfitting, which can be resolved with a larger number of objects, i.e., MRI VM images.
CONCLUSIONS
Our pilot study showed sufficient potential for the automatic segmentation of extracranial VMs through deep learning using MR images from VM patients. The overfitting phenomenon observed will be resolved with a larger number of MRI VM images.
背景
通过手动且逐个地从磁共振成像（MRI）中表征头颈部区域的颅外静脉畸形（VMs）是困难的。我们尝试使用卷积神经网络作为深度学习工具，从颅外VMs的MRI中自动分割病变。
方法
使用来自53名头颈部区域颅外VMs患者的T2加权MRI进行标注。在训练前进行预处理管理。使用三维U-Net作为分割模型。评估Dice相似系数以及其他指标。
结果
发现三维U-Net中的Dice相似系数在训练集中为99.75%，在测试集中为60.62%。模型显示出过拟合，这可以通过更多数量的对象，即MRI VM图像来解决。
结论
我们的初步研究表明，使用来自VM患者的MR图像通过深度学习自动分割颅外VMs具有足够的潜力。观察到的过拟合现象将通过更多数量的MRI VM图像来解决。
Zotero 插件