Gradient vector flow (GVF), an elegant external force for parametric deformable models, can capture object boundaries from both sides. A new geometric deformable model is proposed that combines GVF and the geodesic active contour model. The level set method is used as the numerical method of this model. The model is applied for echocardiographic image segmentation.
Download full-text PDF |
Source |
|---|
Publication Analysis
Top Keywords
Similar Publications
Bacteria Flagella-Mimicking Polymer Multilayer Magnetic Microrobots.
Small Methods
January 2025
The First Affiliated Hospital of Harbin Medical University, Harbin Medical University, Harbin, 150001, China.
Mass production of biomedical microrobots demands expensive and complex preparation techniques and versatile biocompatible materials. Learning from natural bacteria flagella, the study demonstrates a magnetic polymer multilayer cylindrical microrobot that bestows the controllable propulsion upon an external rotating magnetic field with uniform intensity. The magnetic microrobots are constructed by template-assisted layer-by-layer technique and subsequent functionalization of magnetic particles onto the large opening of the microrobots.
View Article and Find Full Text PDFAdvancing Soft Robot Proprioception Through 6D Strain Sensors Embedding.
Soft Robot
January 2025
Department of Mechanical and Nuclear Engineering, Khalifa University of Science and Technology, Abu Dhabi, United Arab Emirates.
Soft robots and bioinspired systems have revolutionized robot design by incorporating flexibility and deformable materials inspired by nature's ingenious designs. Similar to many robotic applications, sensing and perception are paramount to enable soft robots to adeptly navigate the unpredictable real world, ensuring safe interactions with both humans and the environment. Despite recent progress, soft robot sensorization still faces significant challenges due to the virtual infinite degrees of freedom of the system and the need for efficient computational models capable of estimating valuable information from sensor data.
View Article and Find Full Text PDFAccuracy Evaluation of Dose Warping Using Deformable Image Registration in Carbon Ion Therapy.
Int J Part Ther
March 2025
Department of Heavy Particle Medical Science, Yamagata University Graduate School of Medical Science, Yamagata, Japan.
Purpose: The study's purpose was to use a simple geometry phantom to validate the deformable image registration (DIR) accuracy and dose warping accuracy in carbon ion radiotherapy (CIRT) and to provide an index for dosimetry in CIRT.
Materials And Methods: We used geometric and anatomical phantoms provided by AAPM TG-132. The DIRs of 3 different settings were performed between reference and translational images for each phantom.
Synthesized colonoscopy dataset from high-fidelity virtual colon with abnormal simulation.
Comput Biol Med
January 2025
State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, 150080, China. Electronic address:
With the advent of the deep learning-based colonoscopy system, the need for a vast amount of high-quality colonoscopy image datasets for training is crucial. However, the generalization ability of deep learning models is challenged by the limited availability of colonoscopy images due to regulatory restrictions and privacy concerns. In this paper, we propose a method for rendering high-fidelity 3D colon models and synthesizing diversified colonoscopy images with abnormalities such as polyps, bleeding, and ulcers, which can be used to train deep learning models.
View Article and Find Full Text PDFThermophysical properties of graphene reinforced with polymethyl methacrylate nanoparticles for technological applications: a molecular model.
J Mol Model
January 2025
Escuela Superior de Física y Matemáticas, IPN S/N, Edificio 9 de la Unidad Profesional "Adolfo López Mateos", Col. Lindavista, Alc. Gustavo A. Madero, 07738, Mexico City, Mexico.
Context: "Nanostructure of graphene-reinforced with polymethyl methacrylate" (PMMA-G), and vice versa, is investigated using its molecular structure, in the present work. The PMMA-G nanostructure was constructed by bonding PMMA with graphene nanosheet in a sense to get three different configurations. Each configuration consisted of polymeric structures with three degrees of polymerization (such as monomers, dimers, and trimers polymers, respectively).
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!