About: Toward automated severe pharyngitis detection with smartphone camera using deep learning networks

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: Toward automated severe pharyngitis detection with smartphone camera using deep learning networks Goto Sponge NotDistinct Permalink

An Entity of Type : schema:ScholarlyArticle, within Data Space : wasabi.inria.fr associated with source document(s)

Attributes	Values
type	Academic Article research paper schema:ScholarlyArticle
isDefinedBy	Covid-on-the-Web dataset
has title	Toward automated severe pharyngitis detection with smartphone camera using deep learning networks
Creator	Choi, J Jang, Y Choi, Yul Jang, Il Oh, E Oh, Ein Ryu, I Ryu, Ik Yoo, T Yoo, Tae
Source	Elsevier; PMC
abstract	PURPOSE: Severe pharyngitis is frequently associated with inflammations caused by streptococcal pharyngitis, which can cause immune-mediated and post-infectious complications. The recent global pandemic of coronavirus disease (COVID-19) encourages the use of telemedicine for patients with respiratory symptoms. This study therefore purposes automated detection of severe pharyngitis using a deep learning framework with self-taken throat images. METHODS: A dataset composed of two classes of 131 throat images with pharyngitis and 208 normal throat images was collected. Before the training classifier, we constructed a cycle consistency generative adversarial network (CycleGAN) to augment the training dataset. The ResNet50, Inception-v3, and MobileNet-v2 architectures were trained with transfer learning and validated using a randomly selected test dataset. The performance of the models was evaluated based on the accuracy and area under the receiver operating characteristic curve (ROC-AUC). RESULTS: The CycleGAN-based synthetic images were reflected the pragmatic characteristic features of pharyngitis. Using the synthetic throat images, the deep learning model demonstrated a significant improvement in the accuracy of the pharyngitis diagnosis. ResNet50 with GAN-based augmentation showed the best ROC-AUC of 0.988 for pharyngitis detection in the test dataset. In the 4-fold cross-validation using the ResNet50, the highest detection accuracy and ROC-AUC achieved were 95.3% and 0.992, respectively. CONCLUSION: The deep learning model for smartphone-based pharyngitis screening allows for fast identification of severe pharyngitis with a potential of the timely diagnosis of pharyngitis. In the recent pandemic of COVID-19, this framework will help patients with upper respiratory symptoms to improve convenience in diagnosis and reduce transmission.
has issue date	2020-08-20(xsd:dateTime)
bibo:doi	10.1016/j.compbiomed.2020.103980
has license	no-cc
sha1sum (hex)	63b192467dc88fa4f7f05b83416f759ede4becb1
schema:url	https://doi.org/10.1016/j.compbiomed.2020.103980
resource representing a document's title	Toward automated severe pharyngitis detection with smartphone camera using deep learning networks
has PubMed Central identifier	PMC7440230
schema:publication	Comput Biol Med
resource representing a document's body	covid:63b192467dc88fa4f7f05b83416f759ede4becb1#body_text
is schema:about of	named entity 'severe' named entity 'Medicine' named entity 'camera' named entity 'COMPUTERS' named entity 'BIOLOGY' named entity 'deep learning' named entity 'networks' named entity 'Computers in Biology and Medicine' named entity 'training set' named entity 'smartphone' named entity 'transfer learning' named entity 'image resolution' named entity 'deep learning' named entity 'smartphone' named entity 'loss function' named entity 'telemedicine' named entity 'pre-trained' named entity 'pharyngitis' named entity 'image processing' named entity 'smartphones' named entity 'sore throat' named entity 'CNN' named entity 'pharyngitis' named entity 'linear transformation' named entity 'over-fitted' named entity 'training dataset' named entity 'JavaScript' named entity 'pharyngitis' named entity 'deep learning' named entity 'data augmentation' named entity 'Mallampati score' named entity 'pharyngitis' named entity 'generative adversarial network' named entity 'deep learning' named entity 'CNN' named entity 'pharyngitis' named entity 'cross-entropy' named entity 'ground truth' named entity 'tongue depressors' named entity 'CNN' named entity 'CNN' named entity 'deep learning' named entity 'CNN' named entity 'binary classifiers' named entity 'GAN' named entity 'deep learning' named entity 'pharyngitis' named entity 'GAN' named entity 'physical examination' named entity 'cloud-based' named entity 'smartphone' named entity 'smartphone' named entity 'decision boundaries' named entity 'deep learning' named entity 'deep learning' named entity 'deep learning' named entity 'pixel resolution' named entity 'validation dataset' named entity 'validation dataset' named entity 'smartphone' named entity 'colonoscope' named entity 'data augmentation' named entity 'deep learning' named entity 'deep learning' named entity 'pharyngitis' named entity 'anesthesiologist' named entity 'low resolution' named entity 'CNN' named entity 'Mallampati score' named entity 'otolaryngologist' named entity 'meta-data' named entity 'deep learning' named entity 'database' named entity 'GAN'

Faceted Search & Find service v1.13.91 as of Mar 24 2020

Alternative Linked Data Documents: Sponger | ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 07.20.3229 as of Jul 10 2020, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (94 GB total memory)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software