FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4317383461> ?p ?o ?g. }

• W4317383461 abstract "Lung cancer, a major burden of disease causing most cancer related deaths worldwide, can be well treated with early diagnosis of malignant lung nodule using high resolution chest computed tomography. Low dose computed tomography, with lower radiation risk to patients than normal dose computed tomography, benefits the health of patients but degrades the image quality with interfering noise, which can compromise diagnostic performance. In this paper, a multi-function model is introduced that deals with both lung nodule classification and CT image noise deduction. The proposed model consists of a fully convolutional denoising auto-encoder and a 2.5D convolutional classifier and is referred as Convolutional Denoising Auto-Encoder and Classifier (CDAE-C). The training of the proposed model is conducted following a two-phase process in which CDAE is firstly trained to denoise and reconstruct low-dose CT images and then CDAE-C is trained on latent code from pretrained encoder and 3D spatial relationship of lung nodules to classify benign and malignant lung nodules. Fully convolutional structure of denoising auto-encoder ensures the model can accept and reconstruct a low-dose CT image independent of its size, which is practical and very beneficial to the 2.5D classifier as the classification work of benign and malignant lung nodules needs regions of interest cropped from whole low-dose CT images. Extracting lung nodule’s latent representation from the pretrained encoder and using 3D spatial relationship of cropped lung nodule slices, 3D embedded features of each lung nodule are constructed as input of the proposed 2.5D convolutional classifier. Experimental results indicate that CDAE’s denoising performance is of RMSEapprox0.0458 and PSNRapprox27.2004, and CDAE-C classification performance reaches recall rateapprox97.67%, AUC approx99.45% and FNRapprox2.17%. After ablation experiment, the proposed model is proved to have higher accuracy and convergence speed." @default.
• W4317383461 created "2023-01-19" @default.
• W4317383461 creator A5079395336 @default.
• W4317383461 date "2022-12-11" @default.
• W4317383461 modified "2023-09-28" @default.
• W4317383461 title "CDAE-C: A Fully Convolutional Denoising Auto-Encoder with 2.5D Convolutional Classifier" @default.
• W4317383461 cites W1974125392 @default.
• W4317383461 cites W2341106171 @default.
• W4317383461 cites W2344887191 @default.
• W4317383461 cites W2527841944 @default.
• W4317383461 cites W2584483805 @default.
• W4317383461 cites W2743008510 @default.
• W4317383461 cites W2743780012 @default.
• W4317383461 cites W2748739903 @default.
• W4317383461 cites W2790477006 @default.
• W4317383461 cites W2911282375 @default.
• W4317383461 cites W2947005892 @default.
• W4317383461 cites W3089876420 @default.
• W4317383461 cites W3130798577 @default.
• W4317383461 doi "https://doi.org/10.1109/tocs56154.2022.10015922" @default.
• W4317383461 hasPublicationYear "2022" @default.
• W4317383461 type Work @default.
• W4317383461 citedByCount "0" @default.
• W4317383461 crossrefType "proceedings-article" @default.
• W4317383461 hasAuthorship W4317383461A5079395336 @default.
• W4317383461 hasConcept C111919701 @default.
• W4317383461 hasConcept C118505674 @default.
• W4317383461 hasConcept C126838900 @default.
• W4317383461 hasConcept C142724271 @default.
• W4317383461 hasConcept C153180895 @default.
• W4317383461 hasConcept C154945302 @default.
• W4317383461 hasConcept C163294075 @default.
• W4317383461 hasConcept C2776256026 @default.
• W4317383461 hasConcept C31972630 @default.
• W4317383461 hasConcept C41008148 @default.
• W4317383461 hasConcept C71924100 @default.
• W4317383461 hasConcept C95623464 @default.
• W4317383461 hasConceptScore W4317383461C111919701 @default.
• W4317383461 hasConceptScore W4317383461C118505674 @default.
• W4317383461 hasConceptScore W4317383461C126838900 @default.
• W4317383461 hasConceptScore W4317383461C142724271 @default.
• W4317383461 hasConceptScore W4317383461C153180895 @default.
• W4317383461 hasConceptScore W4317383461C154945302 @default.
• W4317383461 hasConceptScore W4317383461C163294075 @default.
• W4317383461 hasConceptScore W4317383461C2776256026 @default.
• W4317383461 hasConceptScore W4317383461C31972630 @default.
• W4317383461 hasConceptScore W4317383461C41008148 @default.
• W4317383461 hasConceptScore W4317383461C71924100 @default.
• W4317383461 hasConceptScore W4317383461C95623464 @default.
• W4317383461 hasLocation W43173834611 @default.
• W4317383461 hasOpenAccess W4317383461 @default.
• W4317383461 hasPrimaryLocation W43173834611 @default.
• W4317383461 hasRelatedWork W2001652754 @default.
• W4317383461 hasRelatedWork W2379065761 @default.
• W4317383461 hasRelatedWork W2483420468 @default.
• W4317383461 hasRelatedWork W2549006548 @default.
• W4317383461 hasRelatedWork W2784352036 @default.
• W4317383461 hasRelatedWork W2807311372 @default.
• W4317383461 hasRelatedWork W2972035100 @default.
• W4317383461 hasRelatedWork W3043252291 @default.
• W4317383461 hasRelatedWork W4214932115 @default.
• W4317383461 hasRelatedWork W3158004940 @default.
• W4317383461 isParatext "false" @default.
• W4317383461 isRetracted "false" @default.
• W4317383461 workType "article" @default.