About: Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning

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

About: Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning 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	Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning
Creator	Lu, L Mollura, Daniel Xu, Z Yao, J Yao, Jianhua Gao, M Gao, Mingchen Nogues, Isabella Roth, Holger Shin, Hoo-Chang Summers, Ronald Xu, Ziyue Mollura, D Roth, H Shin, H.-C
topic	covid:65e1082f09dd9fc02fb06115b8ade1768c5e8fb0#this
Source	PMC
abstract	Remarkable progress has been made in image recognition, primarily due to the availability of large-scale annotated datasets and deep convolutional neural networks (CNNs). CNNs enable learning data-driven, highly representative, hierarchical image features from sufficient training data. However, obtaining datasets as comprehensively annotated as ImageNet in the medical imaging domain remains a challenge. There are currently three major techniques that successfully employ CNNs to medical image classification: training the CNN from scratch, using off-the-shelf pre-trained CNN features, and conducting unsupervised CNN pre-training with supervised fine-tuning. Another effective method is transfer learning, i.e., fine-tuning CNN models pre-trained from natural image dataset to medical image tasks. In this paper, we exploit three important, but previously understudied factors of employing deep convolutional neural networks to computer-aided detection problems. We first explore and evaluate different CNN architectures. The studied models contain 5 thousand to 160 million parameters, and vary in numbers of layers. We then evaluate the influence of dataset scale and spatial image context on performance. Finally, we examine when and why transfer learning from pre-trained ImageNet (via fine-tuning) can be useful. We study two specific computer-aided detection (CADe) problems, namely thoraco-abdominal lymph node (LN) detection and interstitial lung disease (ILD) classification. We achieve the state-of-the-art performance on the mediastinal LN detection, and report the first five-fold cross-validation classification results on predicting axial CT slices with ILD categories. Our extensive empirical evaluation, CNN model analysis and valuable insights can be extended to the design of high performance CAD systems for other medical imaging tasks.
has issue date	2016-02-11(xsd:dateTime)
bibo:doi	10.1109/tmi.2016.2528162
bibo:pmid	26886976
has license	cc-by
sha1sum (hex)	65e1082f09dd9fc02fb06115b8ade1768c5e8fb0
schema:url	https://doi.org/10.1109/tmi.2016.2528162
resource representing a document's title	Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning
has PubMed Central identifier	PMC4890616
has PubMed identifier	26886976
schema:publication	IEEE Trans Med Imaging
resource representing a document's body	covid:65e1082f09dd9fc02fb06115b8ade1768c5e8fb0#body_text
is http://vocab.deri.ie/void#inDataset of	proxy:http/ns.inria.fr/covid19/65e1082f09dd9fc02fb06115b8ade1768c5e8fb0
is schema:about of	named entity 'exploit' named entity 'layers' named entity 'numbers' named entity 'cross-validation' named entity 'transfer learning' named entity 'Architectures' named entity 'MEDIASTINAL' named entity 'STUDY' named entity 'IMAGE' named entity 'PROGRESS' named entity 'PAPER' named entity 'CONDUCTING' named entity 'SCRATCH' named entity 'SHELF' named entity 'ART' named entity 'EXTENSIVE' named entity 'PROBLEMS' named entity 'CLASSIFICATION' named entity 'SPECIFIC' named entity 'TECHNIQUES' named entity 'CNN' named entity 'OF-' named entity 'TRAINING' named entity 'SUFFICIENT' named entity 'mediastinal' named entity 'datasets' named entity 'conducting' named entity 'studied' named entity 'CADe' named entity 'CNNs' named entity 'image recognition' named entity 'There' named entity 'image' named entity 'medical imaging' named entity 'dataset' named entity 'ILD' named entity 'enable' named entity 'CNNs' named entity 'pre-trained' named entity 'CNN' named entity 'pre-trained' named entity 'ILD' named entity 'image classification' named entity 'CNNs' named entity 'image features' named entity 'cross-validation' named entity 'Transfer Learning' named entity 'GoogLeNet' named entity 'AlexNet' named entity 'convolution' named entity 'CNN' named entity 'CNN' named entity 'CNN' named entity 'feature extractors' named entity 'interstitial lung disease' named entity 'GoogLeNet' named entity 'Cifar-10' named entity 'GoogLeNet' named entity 'AlexNet' named entity 'CNN' named entity 'AlexNet' named entity 'CNNs' named entity 'CNN' named entity 'image features' named entity 'CNN'

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