About: Pathological lung segmentation based on random forest combined with deep model and multi-scale superpixels

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

About: Pathological lung segmentation based on random forest combined with deep model and multi-scale superpixels 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	Pathological lung segmentation based on random forest combined with deep model and multi-scale superpixels
Creator	Liu, Caixia Pang, Mingyong Xie, Wangli Zhao, Ruibin
Source	Medline; PMC
abstract	Accurate segmentation of lungs in pathological thoracic computed tomography (CT) scans plays an important role in pulmonary disease diagnosis. However, it is still a challenging task due to the variability of pathological lung appearances and shapes. In this paper, we proposed a novel segmentation algorithm based on random forest (RF), deep convolutional network, and multi-scale superpixels for segmenting pathological lungs from thoracic CT images accurately. A pathological thoracic CT image is first segmented based on multi-scale superpixels, and deep features, texture, and intensity features extracted from superpixels are taken as inputs of a group of RF classifiers. With the fusion of classification results of RFs by a fractional-order gray correlation approach, we capture an initial segmentation of pathological lungs. We finally utilize a divide-and-conquer strategy to deal with segmentation refinement combining contour correction of left lungs and region repairing of right lungs. Our algorithm is tested on a group of thoracic CT images affected with interstitial lung diseases. Experiments show that our algorithm can achieve a high segmentation accuracy with an average DSC of 96.45% and PPV of 95.07%. Compared with several existing lung segmentation methods, our algorithm exhibits a robust performance on pathological lung segmentation. Our algorithm can be employed reliably for lung field segmentation of pathologic thoracic CT images with a high accuracy, which is helpful to assist radiologists to detect the presence of pulmonary diseases and quantify its shape and size in regular clinical practices.
has issue date	2020-08-07(xsd:dateTime)
bibo:doi	10.1007/s11063-020-10330-8
bibo:pmid	32837245
has license	no-cc
sha1sum (hex)	c78c04b491986bb79c46cc9cf38f561d2a9cf7a9
schema:url	https://doi.org/10.1007/s11063-020-10330-8
resource representing a document's title	Pathological lung segmentation based on random forest combined with deep model and multi-scale superpixels
has PubMed Central identifier	PMC7413019
has PubMed identifier	32837245
schema:publication	Neural Process Lett
resource representing a document's body	covid:c78c04b491986bb79c46cc9cf38f561d2a9cf7a9#body_text
is schema:about of	named entity 'performance' named entity 'segmented' named entity 'repairing' named entity 'high' named entity 'texture' named entity 'lung' named entity 'regular' named entity 'shapes' named entity 'multi-scale' named entity 'Our' named entity 'intensity' named entity 'deep' covid:arg/c78c04b491986bb79c46cc9cf38f561d2a9cf7a9 named entity 'thoracic' named entity 'algorithm' named entity 'segmentation' named entity 'finally' named entity 'images' named entity 'extracted' named entity 'lungs' named entity 'classifiers' named entity 'thoracic' named entity 'group' named entity 'group' named entity 'pulmonary diseases' named entity 'pathological' named entity 'pathological' named entity 'convolutional' named entity 'segmentation' named entity 'segmentation' named entity 'random forest' named entity 'initial' named entity 'based' named entity 'divide-and-conquer' named entity 'radiologists' named entity 'random forest' named entity 'algorithm' named entity 'features extracted' named entity 'segmentation' named entity 'algorithm' named entity 'Gabor filter' named entity 'standard deviations' named entity 'algorithm' named entity 'Intel i7' named entity 'pooling layer' named entity 'correlation' named entity 'randomly select' named entity 'level set' named entity 'SUSAN' named entity 'Deep learning' named entity 'netease.com' named entity 'correlation' named entity 'data set' named entity 'corner detection' named entity 'representation learning' named entity 'feature extraction' named entity 'lungs' named entity 'medical images' named entity 'algorithm' named entity 'algorithm' named entity 'Interstitial lung disease' named entity 'DSC' named entity 'algorithm efficiency' named entity 'correlation' named entity 'matrices' named entity 'data series' named entity 'algorithm' named entity 'probability' named entity 'dimension reduction' named entity 'left lung' named entity 'lungs' named entity 'Dice similarity coefficient' named entity 'algorithm' named entity 'PCP' named entity 'TPR' named entity 'U-Net' named entity 'algorithm' named entity 'convolutional neural network'

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