Deep learning-based pancreas volume assessment in individuals with type 1 diabetes.
Deep learning-based pancreas volume assessment in individuals with type 1 diabetes.
复制标题
基于深度学习的 1 型糖尿病患者胰腺体积评估。
DOI：
10.1186/s12880-021-00729-7
复制
发表时间：
2022-01-05
影响因子：
2.7
通讯作者：
Virostko J
中科院分区：
文献类型：
--
作者：
Roger R;Hilmes MA;Williams JM;Moore DJ;Powers AC;Craddock RC;Virostko J
糖尿病患者和自身抗体阳性的 1 型糖尿病 (T1D) 高风险个体的胰腺体积会减小。正在进行调查胰腺体积的研究，以评估大型临床数据库和研究中的胰腺体积，但手动胰腺注释既耗时又主观，阻碍了扩展到大型研究和数据库。这项研究开发了深度学习来自动测量糖尿病患者的胰腺体积。使用来自 T1D 个体、对照或其组合的 160 幅腹部磁共振成像 (MRI) 扫描的手动胰腺注释来训练卷积神经网络。然后使用每个队列训练的模型在 25 名 T1D 患者的扫描中进行测试。胰腺的深度学习和手动分割显示出高度重叠（Dice 系数 = 0.81）和胰腺体积测量的良好相关性（R2 = 0.94）。当训练数据包括患有和不患有 T1D 的个体时，相关性最高。 T1D 患者的胰腺可以自动分割以测量胰腺体积。该算法可以应用于大型成像数据集来量化人类胰腺体积的光谱。
Pancreas volume is reduced in individuals with diabetes and in autoantibody positive individuals at high risk for developing type 1 diabetes (T1D). Studies investigating pancreas volume are underway to assess pancreas volume in large clinical databases and studies, but manual pancreas annotation is time-consuming and subjective, preventing extension to large studies and databases. This study develops deep learning for automated pancreas volume measurement in individuals with diabetes. A convolutional neural network was trained using manual pancreas annotation on 160 abdominal magnetic resonance imaging (MRI) scans from individuals with T1D, controls, or a combination thereof. Models trained using each cohort were then tested on scans of 25 individuals with T1D. Deep learning and manual segmentations of the pancreas displayed high overlap (Dice coefficient = 0.81) and excellent correlation of pancreas volume measurements (R2 = 0.94). Correlation was highest when training data included individuals both with and without T1D. The pancreas of individuals with T1D can be automatically segmented to measure pancreas volume. This algorithm can be applied to large imaging datasets to quantify the spectrum of human pancreas volume.
登录
查看更多内容
影响因子：
16.2
作者：
Campbell-Thompson, Martha L.;Filipp, Stephanie L.;Haller, Michael J.
通讯作者：
Haller, Michael J.
影响因子：
3.7
作者：
Virostko J;Craddock RC;Williams JM;Triolo TM;Hilmes MA;Kang H;Du L;Wright JJ;Kinney M;Maki JH;Medved M;Waibel M;Kay TWH;Thomas HE;Greeley SAW;Steck AK;Moore DJ;Powers AC
通讯作者：
Powers AC
影响因子：
10.9
作者：
Zhang, Yue;Wu, Jiong;Tang, Xiaoying
通讯作者：
Tang, Xiaoying
影响因子：
3.5
作者：
Chupin, Marie;Gerardin, Emilie;Cuingnet, Remi;Boutet, Claire;Lemieux, Louis;Lehericy, Stephane;Benali, Habib;Garnero, Line;Colliot, Olivier
通讯作者：
Colliot, Olivier
影响因子：
16.2
作者：
Virostko, John;Williams, Jon;Moore, Daniel J.
通讯作者：
Moore, Daniel J.