Optical Coherence Tomography (OCT) shows the ability of real-time diagnosis for the external environment or internal small lumen. OCT has not been applied to larger internal lumen like the colon or stomach due to the difficulty of scanning. In this work, we use a robotized helical scanning probe to explore large lumen. Based on the segmentation of the stabilized OCT image, high accurate distance and quantitative contact feedback are obtained for the robotic scanning. The proposed method for distance/contact feedback shows robustness on both phantom and real deformable colon tissue. The robotic scanning is conducted on the soft phantom.
Side-viewing catheter-based medical imaging modalities are used to produce cross-sectional images underneath tissue surfaces. Mainstream side-viewing catheters are based on Optical Coherence Tomography (OCT) or Ultrasound, and they are often applied to the luminal environment. Automatic lumen segmentation provides geometry information for tasks like robotic control and lumen assessment for real-time diagnosis task with side-viewing catheters. In this work, we propose a novel lumen segmentation deep neural networks based on explicit coordinates encoding, which is named CE-net. CE-net is computationally efficient and produces and produces clean segmentation by explicitly encoding the boundaries coordinates in one shot. The experimental evaluation shows a processing time of approximately 8ms per frame while maintaining robustness. We propose a data generation method to improve CE-net generalization, which shows considerable performance by just training with a small dataset.
Endoscopic submucosal dissection (ESD) is a minimally invasive treatment for early stage colorectal cancer that can be performed in teleoperation with a robotized flexible interventional endoscope. However, the tissue elevation step which requires submucosal needle insertion still requires manual operation. In this work we present robotic needle placement using image-guidance that combines white-light camera images to control the alignment of the needle and the OCT catheter. OCT images are used to determine the position of the needle tip during its insertion. This procedure is experimentally tested in an optical phantom that simulates the tissue layers of the colon.
The rotational distortion of endoscopic Optical Coherence Tomography (OCT) is caused by friction of optical fiber and motor instabilities. On-line rotational distortion compensation is essential to provide real-time feedback. We proposed a new method that integrates a Convolutional Neural Network based warping parameters prediction algorithm to correct the azimuthal position of each image line. This method solves the problem of drift in iterative processing by an overall shifting parameter predicting nets with a processing time of 145ms/frame and variation reduction of 88.9% for the data obtained in ex-vivo and in-vivo experiments.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.