We propose a new technique for general purpose, semi-interactive and multi-object segmentation in N-dimensional images, applied to the extraction of cardiac structures in MultiSlice Computed Tomography (MSCT) imaging. The proposed approach makes use of a multi-agent scheme combined with a supervised classification methodology allowing the introduction of a priori information and presenting fast computing times. The multi-agent system is organised around a communicating agent which manages a population of situated agents which segment the image through cooperative and competitive interactions. The proposed technique has been tested on several patient data sets. Some typical results are finally presented and discussed.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2117716 | PMC |
| http://dx.doi.org/10.1109/IEMBS.2007.4353716 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Multi-scale multi-object semi-supervised consistency learning for ultrasound image segmentation.
Neural Netw
December 2024
Department of Mechanical Engineering, National University of Singapore, 9 Engineering Drive 1, Singapore 117575, Singapore. Electronic address:
Manual annotation of ultrasound images relies on expert knowledge and requires significant time and financial resources. Semi-supervised learning (SSL) exploits large amounts of unlabeled data to improve model performance under limited labeled data. However, it faces two challenges: fusion of contextual information at multiple scales and bias of spatial information between multiple objects.
View Article and Find Full Text PDFMulti-sensor fusion and segmentation for autonomous vehicle multi-object tracking using deep Q networks.
Sci Rep
December 2024
School of Electronics Engineering, Vellore Institute of Technology, Vellore, India.
Autonomous vehicles, often known as self-driving cars, have emerged as a disruptive technology with the promise of safer, more efficient, and convenient transportation. The existing works provide achievable results but lack effective solutions, as accumulation on roads can obscure lane markings and traffic signs, making it difficult for the self-driving car to navigate safely. Heavy rain, snow, fog, or dust storms can severely limit the car's sensors' ability to detect obstacles, pedestrians, and other vehicles, which pose potential safety risks.
View Article and Find Full Text PDFTapping line detection and rubber tapping pose estimation for natural rubber trees based on improved YOLOv8 and RGB-D information fusion.
Sci Rep
November 2024
School of Information and Communication Engineering, Hainan University, Haikou, 570228, China.
Tapping line detection and rubber tapping pose estimation are challenging tasks in rubber plantation environments for rubber tapping robots. This study proposed a method for tapping line detection and rubber tapping pose estimation based on improved YOLOv8 and RGB-D information fusion. Firstly, YOLOv8n was improved by introducing the CFB module into the backbone, adding an output layer into the neck, fusing the EMA attention mechanism into the neck, and modifying the loss function as NWD to realize multi-object detection and segmentation.
View Article and Find Full Text PDFRibFractureSys: A gem in the face of acute rib fracture diagnoses.
Comput Med Imaging Graph
October 2024
Department of Electrical and Computer Engineering, University of Saskatchewan, Saskatoon, Saskatchewan, S7N 5A9, Canada. Electronic address:
Article Synopsis
- Rib fracture patients have varying mortality rates and comorbidities based on the number and type of ribs fractured, highlighting the need for accurate prognosis and patient care prioritization.
- Tracking rib fractures in scans is challenging for radiologists due to the complexity and time involved, prompting the development of an automated three-stage assistance system.
- The proposed system uses advanced machine learning models to accurately segment and classify rib lesions, achieving high classification accuracy, though it still faces challenges in rib labeling accuracy for some patients.
Traffic conflict analysis in continuous confluence area of cross-river bridge driven by vehicle trajectory data.
Traffic Inj Prev
August 2024
School of Transportation and Civil Engineering, Fujian Agriculture and Forestry University, Fuzhou, China.
Objectives: To conduct an in-depth study on the spatial distribution of traffic conflicts in the continuous merging areas of cross-river bridges and ensure public transportation safety.
Methods: First, we utilized drone aerial photography to collect videos of vehicle movements. Using the YOLOv7 object detection algorithm and the Strong SORT multi-object tracking algorithm, we extracted high-precision vehicle trajectory time-series data.
Want 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!