Comparative Study of Encoder-decoder-based Convolutional Neural Networks in Cartilage Delineation from Knee Magnetic Resonance Images

Osteoarthritis (OA) is a common degenerative joint inflammation that may lead to disability. Although OA is not lethal, this disease will remarkably affect patient's mobility and their daily lives. Detecting OA at an early stage allows for early intervention and may slow down disease progressio...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Current medical imaging reviews Jg. 17; H. 8; S. 981
Hauptverfasser: Yong, Ching Wai, Lai, Khin Wee, Murphy, Belinda Pingguan, Hum, Yan Chai
Format: Journal Article
Sprache:Englisch
Veröffentlicht: United Arab Emirates 2021
Schlagworte:
Cartilage
Humans
Knee Joint - diagnostic imaging
Magnetic Resonance Imaging
Neural Networks, Computer
Osteoarthritis, Knee - diagnostic imaging
encoder-decoder neural network
magnetic resonance imaging
convolutional neural network
osteoarthritis
Comparative study
knee cartilage segmentation
ISSN:1573-4056, 1573-4056
Online-Zugang:Weitere Angaben
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Osteoarthritis (OA) is a common degenerative joint inflammation that may lead to disability. Although OA is not lethal, this disease will remarkably affect patient's mobility and their daily lives. Detecting OA at an early stage allows for early intervention and may slow down disease progression. Magnetic resonance imaging is a useful technique to visualize soft tissues within the knee joint. Cartilage delineation in magnetic resonance (MR) images helps in understanding the disease progressions. Convolutional neural networks (CNNs) have shown promising results in computer vision tasks, and various encoder-decoder-based segmentation neural networks are introduced in the last few years. However, the performances of such networks are unknown in the context of cartilage delineation. This study trained and compared 10 encoder-decoder-based CNNs in performing cartilage delineation from knee MR images. The knee MR images are obtained from the Osteoarthritis Initiative (OAI). The benchmarking process is to compare various CNNs based on physical specifications and segmentation performances. LadderNet has the least trainable parameters with the model size of 5 MB. UNetVanilla crowned the best performances by having 0.8369, 0.9108, and 0.9097 on JSC, DSC, and MCC. UNetVanilla can be served as a benchmark for cartilage delineation in knee MR images, while LadderNet served as an alternative if there are hardware limitations during production.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1573-4056
1573-4056
DOI:10.2174/1573405616666201214122409