About: MultiCheXNet: A Multi-Task Learning Deep Network For Pneumonia-like Diseases Diagnosis From X-ray Scans

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

About: MultiCheXNet: A Multi-Task Learning Deep Network For Pneumonia-like Diseases Diagnosis From X-ray Scans 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	MultiCheXNet: A Multi-Task Learning Deep Network For Pneumonia-like Diseases Diagnosis From X-ray Scans
Creator	El-Hakeem, Abd El-Wahab, Abd Farag, Abdullah Nada, Mahmoud Raafat, Ahmed Rashwan, Reem Sallab, Ahmad Sayed, Omar Yasser, Mohamed
Source	ArXiv
abstract	We present MultiCheXNet, an end-to-end Multi-task learning model, that is able to take advantage of different X-rays data sets of Pneumonia-like diseases in one neural architecture, performing three tasks at the same time; diagnosis, segmentation and localization. The common encoder in our architecture can capture useful common features present in the different tasks. The common encoder has another advantage of efficient computations, which speeds up the inference time compared to separate models. The specialized decoders heads can then capture the task-specific features. We employ teacher forcing to address the issue of negative samples that hurt the segmentation and localization performance. Finally,we employ transfer learning to fine tune the classifier on unseen pneumonia-like diseases. The MTL architecture can be trained on joint or dis-joint labeled data sets. The training of the architecture follows a carefully designed protocol, that pre trains different sub-models on specialized datasets, before being integrated in the joint MTL model. Our experimental setup involves variety of data sets, where the baseline performance of the 3 tasks is compared to the MTL architecture performance. Moreover, we evaluate the transfer learning mode to COVID-19 data set,both from individual classifier model, and from MTL architecture classification head.
has issue date	2020-08-05(xsd:dateTime)
has license	arxiv
sha1sum (hex)	e29c7c4d6ea9e1a10025582121de6f36019e49c4
resource representing a document's title	MultiCheXNet: A Multi-Task Learning Deep Network For Pneumonia-like Diseases Diagnosis From X-ray Scans
resource representing a document's body	covid:e29c7c4d6ea9e1a10025582121de6f36019e49c4#body_text
is schema:about of	named entity 'EXPERIMENTAL' named entity 'FINE' named entity 'DIFFERENT' named entity 'MTL' named entity 'SPECIALIZED' named entity 'WHERE' named entity 'HURT' named entity 'FOLLOWS' named entity 'Multi-Task Learning' named entity 'X-rays' named entity 'MTL' named entity 'COVID-19' named entity 'binary classification' named entity 'Multi-Task Learning' named entity 'medical imaging' named entity 'Transfer learning' named entity 'multi-label' named entity 'MTL' named entity 'Multi-task learning' named entity 'COVID-19' named entity 'MTL' named entity 'COVID-19' named entity 'Chest X-ray' named entity 'radiologists' named entity 'Computer Vision' named entity 'MTL' named entity 'SARS' named entity 'pre-trained' named entity 'inference' named entity 'Convolutional networks' named entity 'ground truth' named entity 'MTL' named entity 'CheX' named entity 'inference' named entity 'MTL' named entity 'multi-label' named entity 'cross entropy' named entity 'ground truth' named entity 'feature map' named entity 'ARDS' named entity 'MTL' named entity 'Pneumonia' named entity 'data sets' named entity 'feature map' named entity 'Kaggle' named entity 'ground truth' named entity 'data set' named entity 'good performance' named entity 'training dataset' named entity 'COVID-19' named entity 'data sets' named entity 'COVID-19' named entity 'subnetwork' named entity 'pre-trained' named entity 'MTL' named entity 'algorithm' named entity 'pre-trained' named entity 'MTL' named entity 'CT scans' named entity 'Multi-task learning' named entity 'MTL' named entity 'Pneumonia' named entity 'binary classifier' named entity 'ReLU' named entity 'MTL' named entity 'pre-trained' named entity 'MTL' named entity 'algorithm' named entity 'bounding box' named entity 'data set' named entity 'X-ray' named entity 'F1 score' named entity 'algorithm' named entity 'MTL' named entity 'Pneumonia' named entity 'ground truth' named entity 'MTL' named entity 'X-ray scans' named entity 'Pneumonia'

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 © 2009-2025 OpenLink Software