In this paper, we present a novel three dimensional interactive medical image segmentation method based on high level knowledge of training set. Since the interactive system should provide intermediate results to an user quickly, insufficient low level models are used for most of previous methods. To exploit the high level knowledge within a short time, we construct a structured patch model that consists of multiple corresponding patch sets. The structured patch model includes the spatial relationships between neighboring patch sets and the prior knowledge of the corresponding patch set on each local region. The spatial relationships accelerate the search of corresponding patch in test time, while the prior knowledge improves the segmentation accuracy. The proposed framework provides not only fast editing tool, but the incremental learning system through adding the segmentation result to the training set. Experiments demonstrate that the proposed method is useful for fast and accurate segmentation of target objects from the multiple medical images.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1007/978-3-642-38868-2_17 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Electrospun Chitosan/Polylactic Acid Nanofibers with Silver Nanoparticles: Structure, Antibacterial, and Cytotoxic Properties.
ACS Appl Bio Mater
January 2025
Department of Physical Chemistry, Institute of Chemistry, Faculty of Chemistry and Geosciences, Vilnius University, Naugarduko Str. 24, LT-03225 Vilnius, Lithuania.
Electrospinning, a technique for creating fabric materials from polymer solutions, is widely used in various fields, including biomedicine. The unique properties of electrospun fibrous membranes, such as large surface area, compositional versatility, and customizable porous structure, make them ideal for advanced biomedical applications like tissue engineering and wound healing. By considering the high biocompatibility and well-known regenerative potential of polylactic acid (PLA) and chitosan (CH), as well as the versatile antibacterial effect of silver nanoparticles (AgNPs), this study explores the antibacterial efficacy, adhesive properties, and cytotoxicity of electrospun chitosan membranes with a unique nanofibrous structure and varying concentrations of AgNPs.
View Article and Find Full Text PDFHigh efficiency high gain low side lobe level and slant polarization monopulse antenna using cavity backed slot coupled patch antenna.
Sci Rep
January 2025
Faculty of Electric and Computer, Malek Ashtar University of Technology, Tehran, Iran.
In this paper, a multilayer monopulse antenna at Ku-Band with high efficiency, high power handling capability, high gain, 45° linear polarization and low sidelobe is presented. A new slot antenna is proposed as a radiating element based on a cavity-backed slot-coupled patch antenna. Using an enclosed cavity structure reduces coupling between antenna elements, thus increasing the antenna efficiency.
View Article and Find Full Text PDFA wideband coaxial-to-waveguide transition devised with topology optimization.
Sci Rep
January 2025
Department of Electrical Engineering, University of New Mexico, Albuquerque, NM, 87606, USA.
Topology optimization is a powerful technique that utilizes the distribution of material properties along with surface topology as parameters to expand a specified performance. While primarily used as a foundational step in regenerative design for structural mechanics, the general TO framework is also applicable to many of the complex issues in electromagnetics such as frequency agile mode converters. This is considered a difficult parameter to optimize since RF components operate on resonance.
View Article and Find Full Text PDFVialess heterogeneous skin patch for multimodal monitoring and stimulation.
Nat Commun
January 2025
Department of Robotics and Mechatronics Engineering, Daegu Gyeongbuk Institute of Science and Technology (DGIST), Daegu, Republic of Korea.
System-level wearable electronics require to be flexible to ensure conformal contact with the skin, but they also need to integrate rigid and bulky functional components to achieve system-level functionality. As one of integration methods, folding integration offers simplified processing and enhanced functionality through rigid-soft region separation, but so far, it has mainly been applied to modality of electrical sensing and stimulation. This paper introduces a vialess heterogeneous skin patch with multi modalities that separates the soft region and strain-robust region through folded structure.
View Article and Find Full Text PDFDual-path neural network extracts tumor microenvironment information from whole slide images to predict molecular typing and prognosis of Glioma.
Comput Methods Programs Biomed
January 2025
School of Information Science and Technology, Fudan University, Shanghai, 200433, China; Key Laboratory of Medical Imaging, Computing and Computer Assisted Intervention, Shanghai, 200433, China. Electronic address:
Background And Objective: Utilizing AI to mine tumor microenvironment information in whole slide images (WSIs) for glioma molecular subtype and prognosis prediction is significant for treatment. Existing weakly-supervised learning frameworks based on multi-instance learning have potential in WSIs analysis, but the large number of patches from WSIs challenges the effective extraction of key local patch and neighboring patch microenvironment info. Therefore, this paper aims to develop an automatic neural network that effectively extracts tumor microenvironment information from WSIs to predict molecular typing and prognosis of glioma.
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!