FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313731434> ?p ?o ?g. }

• W4313731434 endingPage "102370" @default.
• W4313731434 startingPage "102370" @default.
• W4313731434 abstract "The Corona Virus Disease 2019 (COVID-19) has been declared a worldwide pandemic, and a key method for diagnosing COVID-19 is chest X-ray imaging. The application of convolutional neural network with medical imaging helps to diagnose the disease accurately, where the label quality plays an important role in the classification problem of COVID-19 chest X-rays. However, most of the existing classification methods ignore the problem that the labels are hardly completely true and effective, and noisy labels lead to a significant degradation in the performance of image classification frameworks. In addition, due to the wide distribution of lesions and the large number of local features of COVID-19 chest X-ray images, existing label recovery algorithms have to face the bottleneck problem of the difficult reuse of noisy samples. Therefore, this paper introduces a general classification framework for COVID-19 chest X-ray images with noisy labels and proposes a noisy label recovery algorithm based on subset label iterative propagation and replacement (SLIPR). Specifically, the proposed algorithm first obtains random subsets of the samples multiple times. Then, it integrates several techniques such as principal component analysis, low-rank representation, neighborhood graph regularization, and k-nearest neighbor for feature extraction and image classification. Finally, multi-level weight distribution and replacement are performed on the labels to cleanse the noise. In addition, for the label-recovered dataset, high confidence samples are further selected as the training set to improve the stability and accuracy of the classification framework without affecting its inherent performance. In this paper, three typical datasets are chosen to conduct extensive experiments and comparisons of existing algorithms under different metrics. Experimental results on three publicly available COVID-19 chest X-ray image datasets show that the proposed algorithm can effectively recover noisy labels and improve the accuracy of the image classification framework by 18.9% on the Tawsifur dataset, 19.92% on the Skytells dataset, and 16.72% on the CXRs dataset. Compared to the state-of-the-art algorithms, the gain of classification accuracy of SLIPR on the three datasets can reach 8.67%-19.38%, and the proposed algorithm also has certain scalability while ensuring data integrity." @default.
• W4313731434 created "2023-01-08" @default.
• W4313731434 creator A5002407264 @default.
• W4313731434 creator A5019418559 @default.
• W4313731434 creator A5088664989 @default.
• W4313731434 date "2023-04-01" @default.
• W4313731434 modified "2023-10-06" @default.
• W4313731434 title "COVID-19 chest X-ray image classification in the presence of noisy labels" @default.
• W4313731434 cites W1166921479 @default.
• W4313731434 cites W1514928307 @default.
• W4313731434 cites W1974656106 @default.
• W4313731434 cites W1988427463 @default.
• W4313731434 cites W1990165991 @default.
• W4313731434 cites W1994550352 @default.
• W4313731434 cites W2034841618 @default.
• W4313731434 cites W2043080228 @default.
• W4313731434 cites W2070534370 @default.
• W4313731434 cites W2163939328 @default.
• W4313731434 cites W2167460663 @default.
• W4313731434 cites W2262946425 @default.
• W4313731434 cites W2566079294 @default.
• W4313731434 cites W2801602507 @default.
• W4313731434 cites W2890022946 @default.
• W4313731434 cites W2892703179 @default.
• W4313731434 cites W2999421733 @default.
• W4313731434 cites W3002108456 @default.
• W4313731434 cites W3007497549 @default.
• W4313731434 cites W3013277995 @default.
• W4313731434 cites W3025394897 @default.
• W4313731434 cites W3046705914 @default.
• W4313731434 cites W3110297359 @default.
• W4313731434 cites W3120826129 @default.
• W4313731434 cites W3135057764 @default.
• W4313731434 cites W3135761882 @default.
• W4313731434 cites W3159230003 @default.
• W4313731434 cites W3175562011 @default.
• W4313731434 cites W3209622805 @default.
• W4313731434 cites W3212974566 @default.
• W4313731434 cites W4206676556 @default.
• W4313731434 cites W4206901246 @default.
• W4313731434 cites W4206930139 @default.
• W4313731434 cites W4210722522 @default.
• W4313731434 cites W4220828296 @default.
• W4313731434 cites W4224246723 @default.
• W4313731434 cites W4244259635 @default.
• W4313731434 cites W4280536070 @default.
• W4313731434 cites W4285098962 @default.
• W4313731434 cites W4285404792 @default.
• W4313731434 cites W4311908583 @default.
• W4313731434 doi "https://doi.org/10.1016/j.displa.2023.102370" @default.
• W4313731434 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36644695" @default.
• W4313731434 hasPublicationYear "2023" @default.
• W4313731434 type Work @default.
• W4313731434 citedByCount "2" @default.
• W4313731434 countsByYear W43137314342023 @default.
• W4313731434 crossrefType "journal-article" @default.
• W4313731434 hasAuthorship W4313731434A5002407264 @default.
• W4313731434 hasAuthorship W4313731434A5019418559 @default.
• W4313731434 hasAuthorship W4313731434A5088664989 @default.
• W4313731434 hasBestOaLocation W43137314341 @default.
• W4313731434 hasConcept C124101348 @default.
• W4313731434 hasConcept C153180895 @default.
• W4313731434 hasConcept C154945302 @default.
• W4313731434 hasConcept C41008148 @default.
• W4313731434 hasConcept C52622490 @default.
• W4313731434 hasConcept C81363708 @default.
• W4313731434 hasConceptScore W4313731434C124101348 @default.
• W4313731434 hasConceptScore W4313731434C153180895 @default.
• W4313731434 hasConceptScore W4313731434C154945302 @default.
• W4313731434 hasConceptScore W4313731434C41008148 @default.
• W4313731434 hasConceptScore W4313731434C52622490 @default.
• W4313731434 hasConceptScore W4313731434C81363708 @default.
• W4313731434 hasLocation W43137314341 @default.
• W4313731434 hasLocation W43137314342 @default.
• W4313731434 hasLocation W43137314343 @default.
• W4313731434 hasOpenAccess W4313731434 @default.
• W4313731434 hasPrimaryLocation W43137314341 @default.
• W4313731434 hasRelatedWork W1964120219 @default.
• W4313731434 hasRelatedWork W2144059113 @default.
• W4313731434 hasRelatedWork W2146076056 @default.
• W4313731434 hasRelatedWork W2406522397 @default.
• W4313731434 hasRelatedWork W2767651786 @default.
• W4313731434 hasRelatedWork W2811390910 @default.
• W4313731434 hasRelatedWork W2912288872 @default.
• W4313731434 hasRelatedWork W2913302899 @default.
• W4313731434 hasRelatedWork W3003836766 @default.
• W4313731434 hasRelatedWork W4312376745 @default.
• W4313731434 hasVolume "77" @default.
• W4313731434 isParatext "false" @default.
• W4313731434 isRetracted "false" @default.
• W4313731434 workType "article" @default.