A Framework for Automatic Morphological Feature Extraction and Analysis of Abdominal Organs in MRI Volumes.
J Med Syst
; 43(12): 334, 2019 Nov 12.
Article
em En
| MEDLINE
| ID: mdl-31720863
ABSTRACT
The accurate 3D reconstruction of organs from radiological scans is an essential tool in computer-aided diagnosis (CADx) and plays a critical role in clinical, biomedical and forensic science research. The structure and shape of the organ, combined with morphological measurements such as volume and curvature, can provide significant guidance towards establishing progression or severity of a condition, and thus support improved diagnosis and therapy planning. Furthermore, the classification and stratification of organ abnormalities aim to explore and investigate organ deformations following injury, trauma and illness. This paper presents a framework for automatic morphological feature extraction in computer-aided 3D organ reconstructions following organ segmentation in 3D radiological scans. Two different magnetic resonance imaging (MRI) datasets are evaluated. Using the MRI scans of 85 adult volunteers, the overall mean volume for the pancreas organ is 69.30 ± 32.50cm3, and the 3D global curvature is (35.23 ± 6.83) × 10-3. Another experiment evaluates the MRI scans of 30 volunteers, and achieves mean liver volume of 1547.48 ± 204.19cm3 and 3D global curvature (19.87 ± 3.62) × 10- 3. Both experiments highlight a negative correlation between 3D curvature and volume with a statistical difference (p < 0.0001). Such a tool can support the investigation into organ related conditions such as obesity, type 2 diabetes mellitus and liver disease.
Palavras-chave
Texto completo:
1
Coleções:
01-internacional
Base de dados:
MEDLINE
Assunto principal:
Pâncreas
/
Imageamento por Ressonância Magnética
/
Imageamento Tridimensional
/
Fígado
Tipo de estudo:
Guideline
Limite:
Adult
/
Female
/
Humans
/
Male
Idioma:
En
Revista:
J Med Syst
Ano de publicação:
2019
Tipo de documento:
Article
País de afiliação:
Reino Unido