Deep learning for the fully automated segmentation of the inner ear on MRI

Segmentation of anatomical structures is valuable in a variety of tasks, including 3D visualization, surgical planning, and quantitative image analysis. Manual segmentation is time-consuming and deals with intra and inter-observer variability. To develop a deep-learning approach for the fully automa...

Full description

Saved in:
Bibliographic Details
Published in:Scientific reports 2021-02, Vol.11 (1), p.2885-2885, Article 2885
Main Authors: Vaidyanathan, Akshayaa, van der Lubbe, Marly F. J. A., Leijenaar, Ralph T. H., van Hoof, Marc, Zerka, Fadila, Miraglio, Benjamin, Primakov, Sergey, Postma, Alida A., Bruintjes, Tjasse D., Bilderbeek, Monique A. L., Sebastiaan, Hammer, Dammeijer, Patrick F. M., van Rompaey, Vincent, Woodruff, Henry C., Vos, Wim, Walsh, Seán, van de Berg, Raymond, Lambin, Philippe
Format: Article
Language:English
Subjects:
631/114/1564
639/705
639/705/117
Automation
Deep learning
Humanities and Social Sciences
Image processing
Inner ear
Magnetic resonance imaging
multidisciplinary
Science
Science (multidisciplinary)
Segmentation
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Segmentation of anatomical structures is valuable in a variety of tasks, including 3D visualization, surgical planning, and quantitative image analysis. Manual segmentation is time-consuming and deals with intra and inter-observer variability. To develop a deep-learning approach for the fully automated segmentation of the inner ear in MRI, a 3D U-net was trained on 944 MRI scans with manually segmented inner ears as reference standard. The model was validated on an independent, multicentric dataset consisting of 177 MRI scans from three different centers. The model was also evaluated on a clinical validation set containing eight MRI scans with severe changes in the morphology of the labyrinth. The 3D U-net model showed precise Dice Similarity Coefficient scores (mean DSC-0.8790) with a high True Positive Rate (91.5%) and low False Discovery Rate and False Negative Rates (14.8% and 8.49% respectively) across images from three different centers. The model proved to perform well with a DSC of 0.8768 on the clinical validation dataset. The proposed auto-segmentation model is equivalent to human readers and is a reliable, consistent, and efficient method for inner ear segmentation, which can be used in a variety of clinical applications such as surgical planning and quantitative image analysis.
ISSN:2045-2322
2045-2322
DOI:10.1038/s41598-021-82289-y