Matches in SemOpenAlex for { <https://semopenalex.org/work/W3039539109> ?p ?o ?g. }
Showing items 1 to 54 of
54
with 100 items per page.
- W3039539109 abstract "Lung cancer is the leading cause of cancer-related death worldwide. Due to the difficulty of artificial extraction of medical image features and the development of artificial intelligence in the field of medical image, various deep learning methods for lung nodules classification have been proposed to help doctors diagnose and detect lung cancer in the early stage. The traditional 2D CNN cannot make use of the 3D spatial characteristics of CT data, while the 3D CNN has many parameters, which leads to low model efficiency. Residual Network (ResNet) is a residual structure using skip connection that makes deep classification network easier to train. Therefore, motivated by the work of 3D CNN and ResNet, in this paper, a VGG based 3D residual connection network, called VGG+ResCon, is proposed to mine the vertical information of tumor CT images and accelerate the training efficiency of the model. Besides, after enhancing the dataset, focal loss is used to replace the traditional cross-entropy as the loss function, which solves the problem of uneven distribution of positive and negative samples of medical data (more negative samples than positive samples). And it also makes the model more focused on difficult-to-classify samples. This methodology was evaluated on the LUng Nodule Analysis 2016 (LUNA16) dataset, with the best precision of 93.62%, recall of 92.48%, specificity of 96.83% and f1-score of 93.04%. Experimental results demonstrate the effectiveness of the proposed method in classifying malignant and benign pulmonary nodules." @default.
- W3039539109 created "2020-07-10" @default.
- W3039539109 creator A5026477717 @default.
- W3039539109 creator A5039104345 @default.
- W3039539109 creator A5075888012 @default.
- W3039539109 date "2020-05-29" @default.
- W3039539109 modified "2023-09-24" @default.
- W3039539109 title "Using 3D Convolutional Networks with Shortcut Connections for Improved Lung Nodules Classification" @default.
- W3039539109 cites W1983364832 @default.
- W3039539109 cites W2134939446 @default.
- W3039539109 cites W2303706856 @default.
- W3039539109 cites W2322371438 @default.
- W3039539109 cites W2394599079 @default.
- W3039539109 cites W2526259914 @default.
- W3039539109 cites W2556470218 @default.
- W3039539109 cites W2566620708 @default.
- W3039539109 cites W2755631890 @default.
- W3039539109 cites W2766803371 @default.
- W3039539109 cites W2963150920 @default.
- W3039539109 cites W2967098998 @default.
- W3039539109 cites W2994793120 @default.
- W3039539109 cites W948663339 @default.
- W3039539109 doi "https://doi.org/10.1145/3404512.3404525" @default.
- W3039539109 hasPublicationYear "2020" @default.
- W3039539109 type Work @default.
- W3039539109 sameAs 3039539109 @default.
- W3039539109 citedByCount "0" @default.
- W3039539109 crossrefType "proceedings-article" @default.
- W3039539109 hasAuthorship W3039539109A5026477717 @default.
- W3039539109 hasAuthorship W3039539109A5039104345 @default.
- W3039539109 hasAuthorship W3039539109A5075888012 @default.
- W3039539109 hasConcept C154945302 @default.
- W3039539109 hasConcept C41008148 @default.
- W3039539109 hasConcept C81363708 @default.
- W3039539109 hasConceptScore W3039539109C154945302 @default.
- W3039539109 hasConceptScore W3039539109C41008148 @default.
- W3039539109 hasConceptScore W3039539109C81363708 @default.
- W3039539109 hasLocation W30395391091 @default.
- W3039539109 hasOpenAccess W3039539109 @default.
- W3039539109 hasPrimaryLocation W30395391091 @default.
- W3039539109 hasRelatedWork W2285788670 @default.
- W3039539109 hasRelatedWork W2521062615 @default.
- W3039539109 hasRelatedWork W2735477435 @default.
- W3039539109 hasRelatedWork W2749468216 @default.
- W3039539109 hasRelatedWork W2901465038 @default.
- W3039539109 hasRelatedWork W2998526951 @default.
- W3039539109 hasRelatedWork W3090822330 @default.
- W3039539109 hasRelatedWork W3119610945 @default.
- W3039539109 hasRelatedWork W3181746755 @default.
- W3039539109 hasRelatedWork W4239686595 @default.
- W3039539109 isParatext "false" @default.
- W3039539109 isRetracted "false" @default.
- W3039539109 magId "3039539109" @default.
- W3039539109 workType "article" @default.