2022
DOI: 10.1177/00034894221095899
|View full text |Cite
|
Sign up to set email alerts
|

Convolutional Neural Networks in ENT Radiology: Systematic Review of the Literature

Abstract: Introduction: Convolutional neural networks (CNNs) represent a state-of-the-art methodological technique in AI and deep learning, and were specifically created for image classification and computer vision tasks. CNNs have been applied in radiology in a number of different disciplines, mostly outside otolaryngology, potentially due to a lack of familiarity with this technology within the otolaryngology community. CNNs have the potential to revolutionize clinical practice by reducing the time required to perform… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
9
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
7

Relationship

0
7

Authors

Journals

citations
Cited by 9 publications
(9 citation statements)
references
References 56 publications
0
9
0
Order By: Relevance
“…Artificial intelligence is demonstrating increased uptake among the otolaryngology community. 4 This review has demonstrated multiple CNN architectures that have been successful in automated image segmentation for the structures of the middle ear. It reflects the advances on previous work in automated image segmentation using atlas-based models by Powell et al 23 and Ding et al 24 Atlas-based segmentation incorporates anatomical labels with a surrounding region on interest as the gold standard atlas to apply to unseen new images.…”
Section: Discussionmentioning
confidence: 99%
See 1 more Smart Citation
“…Artificial intelligence is demonstrating increased uptake among the otolaryngology community. 4 This review has demonstrated multiple CNN architectures that have been successful in automated image segmentation for the structures of the middle ear. It reflects the advances on previous work in automated image segmentation using atlas-based models by Powell et al 23 and Ding et al 24 Atlas-based segmentation incorporates anatomical labels with a surrounding region on interest as the gold standard atlas to apply to unseen new images.…”
Section: Discussionmentioning
confidence: 99%
“…The matrices are formed by individual pixel values correlating to digital images. 4 CNNs are composed of multiple layers, including 1 or more convolutional layers, a pooling layer, and 1 or more fully connected layers. 5 A convolution is where each pixel is given a numerical value through a mathematical operation.…”
mentioning
confidence: 99%
“…Structure identification on temporal bone imaging is an area of paucity in the AI literature 21 and hence may be a good test of the ability of CNNs in identifying fine anatomical structures within a confined space. The aim of this study is to determine the accuracy of using a deep-learning CNN algorithm to identify critical structures in temporal bone CT imaging through object detection with bounding boxes.…”
Section: Introductionmentioning
confidence: 99%
“…Radiology presents unique opportunities and challenges for the implementation of DL AI. Currently, different uses are defined by the detection of disease, classification, and segmentation [ 7 , 8 ]. Concisely, detection consists of identifying abnormal features on imaging and is widely employed in thoracic imaging to assist in identifying pulmonary nodules [ 6 , 7 ].…”
Section: Introductionmentioning
confidence: 99%