A5054631792- Surgical Simulation and Training
- Advanced Vision and Imaging
- Anatomy and Medical Technology
- Robotics and Sensor-Based Localization
- Soft Robotics and Applications
- Image Processing Techniques and Applications
- Image Enhancement Techniques
- Image and Video Quality Assessment
- Advanced X-ray and CT Imaging
- Optical measurement and interference techniques
- Advanced Image Processing Techniques
- Advanced Image Fusion Techniques
- Advanced Fluorescence Microscopy Techniques
- Cell Image Analysis Techniques
- Advanced Neural Network Applications
- Dental Radiography and Imaging
Tianjin University
2021-2024
Due to the large number and complex structure of bronchial branches, frequent orientation insertions during bronchoscopy are likely cause surgeon fatigue errors. Therefore, we designed a robotic-assisted automatic intervention system (RAIS) based on image guidance, which aims realize insertion bronchoscope, for improving intelligence efficiency bronchoscopy. To proposed highly robust accurate lumen center detection method, combines deep learning-based object histogram back-projection. With...
Abstract Background Accurately estimating the 6D pose of snake‐like wrist‐type surgical instruments is challenging due to their complex kinematics and flexible design. Methods We propose ERegPose, a comprehensive strategy for precise estimation. The consists two components: ERegPoseNet, an original deep neural network model designed explicit regression instrument's pose, annotated in‐house dataset simulated operations. To capture rotational features, we employ Single Shot multibox Detector...
While time-lapse imaging is desirable for recording dynamic development processes, such as cell division and migration, the image quality suffers from fluorescent blending phototoxicity. Theoretically, confocal microscopy can collect images with high resolution if livability not priority. In this work, we leverage of by formulating transformation timelapse to single-point an adversarial learning task, which bypasses lack pairwise training. Compared other non-blind denoising algorithms, our...