研究目的
To develop a robust tissue matching based motion correction approach from a sequence of 2D intracoronary OCT images.
研究成果
The study proposes a framework for motion correction of the OCT images, contributing to evaluate the functionality of coronary arteries by analyzing the volume variation and considering the motion of the vessel. The application of deep features in solving the problem of motion correction of intracoronary OCT images is the main contribution of this work.
研究不足
The proposed non-rigid motion correction approach may lead to a deformation of the artery that should be considered in future works.
1：Experimental Design and Method Selection:
The study employs a motion correction technique based on the correlation between deep features obtained from Convolutional Neural Network (CNN) for each frame of a sequence. The optimal transformation of each frame is obtained by maximizing the similarity between the tissues of reference and moving frames.
2：Sample Selection and Data Sources:
The experiments are performed on 26 retrospective cases comprising of pullbacks of intracoronary cross-sectional images obtained from different pediatric patients with Kawasaki Disease (KD) using ILUMIEN OCT system.
3：List of Experimental Equipment and Materials:
ILUMIEN OCT system (St. Jude Medical Inc., St. Paul, Minnesota, USA) with axial and lateral resolutions of 12-15 μm and 20-40 μm respectively.
4：Experimental Procedures and Operational Workflow:
The motion correction is formulated as a non-rigid registration problem when the first frame is considered as the reference frame. The deep feature vector for the reference frame is extracted using the fine-tuned CNN.
5：Data Analysis Methods:
The results are validated by comparing the centerlines of the 3D models before and after motion correction and by estimating the joint entropy of two consecutive frames before and after motion correction.
独家科研数据包，助您复现前沿成果，加速创新突破
获取完整内容
