EUVIMEDDescoperă EUVIMED
Scoping ReviewOpen access · CC BY 4.0

Deep Learning for Automated Image Segmentation of the Middle Ear: A Scoping Review

Talisa Ross iD, Ravina Tanna, Watjana Lilaonitkul, Nishchay Mehta

Otolaryngology–Head and Neck Surgery · 2024-06 · 170 (6) · 1544-1554

DOI: 10.1002/ohn.758 ↗

At a glance

Scoping Review in Otolaryngology–Head and Neck Surgery, published online on 2024-04-26. Written by Talisa Ross and 3 co-authors. Institution: Department of Ear, Nose and Throat Surgery, Charing Cross Hospital, Imperial College Healthcare NHS Trust, London, UK. Major MEDLINE topics: Deep Learning, Ear, Middle, Tomography, X-Ray Computed. Cited 6 times so far (Crossref); 31 references. The full text is freely available (open access, CC BY 4.0).

RezumatSubjectsDate bibliograficeCiteRelated studies

Abstract (original language)

Objective

Convolutional neural networks (CNNs) have revolutionized medical image segmentation in recent years. This scoping review aimed to carry out a comprehensive review of the literature describing automated image segmentation of the middle ear using CNNs from computed tomography (CT) scans. Data Sources A comprehensive literature search, generated jointly with a medical librarian, was performed on Medline, Embase, Scopus, Web of Science, and Cochrane, using Medical Subject Heading terms and keywords. Databases were searched from inception to July 2023. Reference lists of included papers were also screened. Review Methods Ten studies were included for analysis, which contained a total of 866 scans which were used in model training/testing. Thirteen different architectures were described to perform automated segmentation. The best Dice similarity coefficient (DSC) for the entire ossicular chain was 0.87 using ResNet. The highest DSC for any structure was the incus using 3D‐V‐Net at 0.93. The most difficult structure to segment was the stapes, with the highest DSC of 0.84 using 3D‐V‐Net.

Conclusions

Numerous architectures have demonstrated good performance in segmenting the middle ear using CNNs. To overcome some of the difficulties in segmenting the stapes, we recommend the development of an architecture trained on cone beam CTs to provide improved spatial resolution to assist with delineating the smallest ossicle.

Implications for Practice

This has clinical applications for preoperative planning, diagnosis, and simulation.

Subjects

MeSH terms (MEDLINE)

Deep LearningEar, MiddleTomography, X-Ray ComputedHumansImage Processing, Computer-Assisted

Author keywords

artificial intelligenceconvolutional neural networksimage segmentation

Authors and institutions

  • Department of Ear, Nose and Throat Surgery, Charing Cross Hospital, Imperial College Healthcare NHS Trust, London, UK.
  • evidENT Team, Ear Institute, University College London, London, UK.
  • Department of Ear, Nose and Throat Surgery, Great Ormond Street Hospital, London, UK.
  • Department of Ear, Nose and Throat Surgery, Royal National Ear Nose and Throat Hospital, London, UK.

ORCID profiles: Talisa Ross

Cite

APA

Ross, T., Tanna, R., Lilaonitkul, W., & Mehta, N. (2024). Deep Learning for Automated Image Segmentation of the Middle Ear: A Scoping Review. Otolaryngology–Head and Neck Surgery, 170(6), 1544-1554. https://doi.org/10.1002/ohn.758

Vancouver

Ross T, Tanna R, Lilaonitkul W, Mehta N. Deep Learning for Automated Image Segmentation of the Middle Ear: A Scoping Review. Otolaryngology–Head and Neck Surgery. 2024;170(6):1544-1554. doi:10.1002/ohn.758

BibTeX
@article{Ross2024,
  author = {Ross, Talisa and Tanna, Ravina and Lilaonitkul, Watjana and Mehta, Nishchay},
  title = {Deep Learning for Automated Image Segmentation of the Middle Ear: A Scoping Review},
  journal = {Otolaryngology–Head and Neck Surgery},
  year = {2024},
  volume = {170},
  number = {6},
  pages = {1544--1554},
  doi = {10.1002/ohn.758}
}
Start for free →