Automatic MRI segmentation of para-pharyngeal fat pads using interactive visual feature space analysis for classification

Autor: Tetyana Ivanovska, Teodora Chitiboi, Henry Völzke, Lars Linsen, Muhammad Laiq Ur Rahman Shahid, Vladimir Molchanov
Přispěvatelé: Publica
Rok vydání: 2017
Předmět:
Male
Upper airway segmentation
Obstructive sleep apnea (OSA)
02 engineering and technology
Pattern Recognition
Automated
Machine Learning
User-Computer Interface
0302 clinical medicine
0202 electrical engineering
electronic engineering
information engineering
Medicine
Segmentation
Aged
80 and over
Sleep Apnea
Obstructive
education.field_of_study
Anatomy
Middle Aged
Para-pharyngeal fat pads segmentation
Interactive visual analysis tool
Magnetic resonance imaging (MRI)
Magnetic Resonance Imaging
3. Good health
Adipose Tissue
Radiology Nuclear Medicine and imaging
Female
020201 artificial intelligence & image processing
Connected-component labeling
Algorithms
Research Article
Adult
Feature vector
Population
Context (language use)
Sensitivity and Specificity
Young Adult
03 medical and health sciences
Interactive visual analysis
Sørensen–Dice coefficient
Image Interpretation
Computer-Assisted
Humans
Radiology
Nuclear Medicine and imaging
education
Aged
business.industry
Reproducibility of Results
Pattern recognition
Image Enhancement
Pipeline (software)
030228 respiratory system
Pharynx
Artificial intelligence
business
Zdroj: BMC Medical Imaging
ISSN: 1471-2342
DOI: 10.1186/s12880-017-0179-7
Popis: Background: Obstructive sleep apnea (OSA) is a public health problem. Detailed analysis of the para-pharyngeal fat pads can help us to understand the pathogenesis of OSA and may mediate the intervention of this sleeping disorder. A reliable and automatic para-pharyngeal fat pads segmentation technique plays a vital role in investigating larger data bases to identify the anatomic risk factors for the OSA. Methods: Our research aims to develop a context-based automatic segmentation algorithm to delineate the fat pads from magnetic resonance images in a population-based study. Our segmentation pipeline involves texture analysis, connected component analysis, object-based image analysis, and supervised classification using an interactive visual analysis tool to segregate fat pads from other structures automatically. Results: We developed a fully automatic segmentation technique that does not need any user interaction to extract fat pads. Our algorithm is fast enough that we can apply it to population-based epidemiological studies that provide a large amount of data. We evaluated our approach qualitatively on thirty datasets and quantitatively against the ground truths of ten datasets resulting in an average of approximately 78% detected volume fraction and a 79% Dice coefficient, which is within the range of the inter-observer variation of manual segmentation results. Conclusion: The suggested method produces sufficiently accurate results and has potential to be applied for the study of large data to understand the pathogenesis of the OSA syndrome. peerReviewed
Databáze: OpenAIRE
Externí odkaz: