ADC-Net: An Open-Source Deep Learning Network for Automated Dispersion Compensation in Optical Coherence Tomography
University of Illinois Chicago（伊利诺伊大学芝加哥分校）
Shaiban Ahmed, David Le, Taeyoon Son, Tobiloba Adejumo, Xincheng Yao, Department of Biomedical Engineering, University of Illinois at Chicago, Department of Oph… 展开作者
Shaiban Ahmed, David Le, Taeyoon Son, Tobiloba Adejumo, Xincheng Yao, Department of Biomedical Engineering, University of Illinois at Chicago, Department of Ophthalmology, Visual Science, University of Illinois at Chicago
Chromatic dispersion is a common problem to degrade the system resolution in optical coherence tomography (OCT). This study is to develop a deep learning network for automated dispersion compensation (ADC-Net) in OCT. The ADC-Net is based on a redesigned UNet architecture which employs an encoder-decoder pipeline. The input section encompasses partially compensated OCT B-scans with individual retinal layers optimized. Corresponding output is a fully compensated OCT B-scans with all retinal layers optimized. Two numeric parameters, i.e., peak signal to noise ratio (PSNR) and structural similarity index metric computed at multiple scales (MS-SSIM), were used for objective assessment of the ADC-Net performance. Comparative analysis of training models, including single, three, five, seven and nine input channels were implemented. The five-input channels implementation was observed as the optimal mode for ADC-Net training to achieve robust dispersion compensation in OCT
SAMCIRT: A Simultaneous Reconstruction and Affine Motion Compensation Technique for Four Dimensional Computed Tomography (4DCT)
University of Antwerp（安特卫普大学）；Phenikaa University（费因基亚大学）；Institut de Mathématiques de Jussieu – Paris Rive Gauche（巴黎右岸数学研究所）；Silverhead Innovation Strategies and Solutions SAS（Silverhead创新策略与解决方案SAS）
Physics-Driven Neural Compensation For Electrical Impedance Tomography
School of Biomedical engineering University of Science and Technology of China（生物医学工程学院 中国科学技术大学）；CAS Key Laboratory of Microscale Magnetic Resonance University of Science and Technology of China（微尺度磁共振CAS重点实验室 中国科学技术大学）
Deep Learning based 3D Volume Correlation for Additive Manufacturing Using High-Resolution Industrial X-ray Computed Tomography
Bundesanstalt Für Materialforschung Und -Prüfung (BAM, Federal Institute for Materials Research and Testing)（联邦材料研究和测试研究所）；Institute of Physics and Astronomy, University of Potsdam（物理与天文学学院）
Systematic dispersion compensation for spectral domain optical coherence tomography using time-frequency analysis and iterative optimization for iridocorneal angle imaging
DeshadowGAN: A Deep Learning Approach to Remove Shadows from Optical Coherence Tomography Images
National University of Singapore（新加坡国立大学）；Singapore Eye Research Institute（新加坡眼科研究所）；Singapore National Eye Centre（新加坡全国眼科中心）；Duke-NUS Graduate Medical School（杜克-新加坡国立大学研究生院）；Nanyang Technological University（南洋理工大学）；Medical University of Vienna（维也纳医科大学）
Development and task-based evaluation of a scatter-window projection and deep learning-based transmission-less attenuation compensation method for myocardial perfusion SPECT
Prediction of the motion of chest internal points using a recurrent neural network trained with real-time recurrent learning for latency compensation in lung cancer radiotherapy
The University of Tokyo（东京大学）；National Institute for Quantum and Radiological Science and Technology（国立量子与放射科学技术研究所）
在肺癌患者的放射治疗期间，需要最小化递送到肿瘤周围的健康组织的辐射，由于呼吸运动和线性加速器系统的延迟，这是困难的。在这项研究中，我们首先使用Lucas-Kanade金字塔光流算法进行变形图像配准的胸部计算机断层扫描图像的四个肺癌患者。然后，我们根据先前计算的变形场跟踪靠近肺肿瘤的三个内部点，并使用使用实时递归学习（RTRL）和梯度裁剪训练的递归神经网络（RNN）预测它们的位置。呼吸数据是相当规则的，以大约2.5Hz采样，并且包括脊柱方向上的人工漂移。追踪点的运动幅度范围为12.0 mm ~ 22.7 mm。最后，我们提出了一种简单的方法，用于恢复和预测三维肿瘤图像的跟踪点和初始肿瘤图像的基础上的线性对应模型和Nadaraya-Watson非线性回归。测试集上RNN预测对应的均方根误差，最大误差和抖动小于线性预测和最小均方（LMS）获得的相同性能指标。特别地，与RNN相关联的最大预测误差等于1.51mm，分别比与线性预测和LMS相关联的最大误差低16.1%和5.0%。RTRL的每个时间步长的平均预测时间等于119 ms，这小于400 ms标记位置采样时间。预测图像中的肿瘤位置在视觉上看起来是正确的，这通过原始图像和预测图像之间的高平均互相关（等于0.955）来确认。
