FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4210338317> ?p ?o ?g. }

• W4210338317 abstract "Melanoma is one of the most threatening types of skin cancer with a large-scale mortality rate. The early-stage diagnosis of melanoma can help prevent its proliferation to other body organs. In this regard, several Computer aided Diagnosis (CAD) approaches have been proposed by researchers which serve as a milestone in combatting this ugly disease. In this research work, we have proposed a Model Blending technique which is an ensemble of two pre-trained deep Convolutional Neural Networks (CNNs) namely DenseNet-201 and ResNet-50. The proposed ensemble approach plays a key role in accurate melanoma classification with reduced generalization error of the two Neural Networks (NNs). Region of Interest (ROI) segmentation and lesion classification are performed using multiple, standardized dermoscopy datasets accessed from PH², Med-Node and DermIs archives. We have applied advanced data purification techniques to remove occlusions, unwanted artifacts and to adjust low contrast or illumination effects. ROI (lesion) segmentation is done using the K-means clustering algorithm which precisely separates the foreground and background pixels of the images. Affine Image Transformation and Color Space Transformation approaches are applied to augment our image datasets. The ensemble model of ResNet-50 and DenseNet-201 performed binary lesion classification (benign or malignant) using a Majority Voting technique. Our proposed segmentation method displayed satisfactory results with a precision of 91&#x0025;, AUC 89&#x0025;, specificity 95.7&#x0025; and sensitivity score of 94&#x0025;. In the classification task, the pre-trained ensemble model recorded superior results as compared to other ultra-modern melanoma diagnosis approaches and achieved an accuracy of 95.2&#x0025;, specificity 96.7&#x0025;, sensitivity 92.8&#x0025; and AUC 98.5&#x0025; on multiple dermoscopy image datasets. The evaluation results are carefully analyzed and compared with other existing melanoma detection approaches which indicate the reliability and robustness of our model." @default.
• W4210338317 created "2022-02-08" @default.
• W4210338317 creator A5003828287 @default.
• W4210338317 creator A5018853081 @default.
• W4210338317 creator A5030892195 @default.
• W4210338317 date "2021-11-09" @default.
• W4210338317 modified "2023-10-17" @default.
• W4210338317 title "A Majority Voting based Ensemble Approach of Deep Learning Classifiers for Automated Melanoma Detection" @default.
• W4210338317 cites W2061253660 @default.
• W4210338317 cites W2113790176 @default.
• W4210338317 cites W2164273268 @default.
• W4210338317 cites W2564782580 @default.
• W4210338317 cites W2581082771 @default.
• W4210338317 cites W2593586875 @default.
• W4210338317 cites W2770842918 @default.
• W4210338317 cites W2810305204 @default.
• W4210338317 cites W2886533602 @default.
• W4210338317 cites W2910318609 @default.
• W4210338317 cites W2913373403 @default.
• W4210338317 cites W2947465563 @default.
• W4210338317 cites W3037272622 @default.
• W4210338317 cites W3089813167 @default.
• W4210338317 cites W3114688163 @default.
• W4210338317 cites W3160890506 @default.
• W4210338317 cites W3180110917 @default.
• W4210338317 cites W3180902710 @default.
• W4210338317 cites W3197894726 @default.
• W4210338317 doi "https://doi.org/10.1109/icic53490.2021.9692915" @default.
• W4210338317 hasPublicationYear "2021" @default.
• W4210338317 type Work @default.
• W4210338317 citedByCount "12" @default.
• W4210338317 countsByYear W42103383172022 @default.
• W4210338317 countsByYear W42103383172023 @default.
• W4210338317 crossrefType "proceedings-article" @default.
• W4210338317 hasAuthorship W4210338317A5003828287 @default.
• W4210338317 hasAuthorship W4210338317A5018853081 @default.
• W4210338317 hasAuthorship W4210338317A5030892195 @default.
• W4210338317 hasConcept C108583219 @default.
• W4210338317 hasConcept C115961682 @default.
• W4210338317 hasConcept C124504099 @default.
• W4210338317 hasConcept C153180895 @default.
• W4210338317 hasConcept C154945302 @default.
• W4210338317 hasConcept C41008148 @default.
• W4210338317 hasConcept C75294576 @default.
• W4210338317 hasConcept C81363708 @default.
• W4210338317 hasConcept C89600930 @default.
• W4210338317 hasConceptScore W4210338317C108583219 @default.
• W4210338317 hasConceptScore W4210338317C115961682 @default.
• W4210338317 hasConceptScore W4210338317C124504099 @default.
• W4210338317 hasConceptScore W4210338317C153180895 @default.
• W4210338317 hasConceptScore W4210338317C154945302 @default.
• W4210338317 hasConceptScore W4210338317C41008148 @default.
• W4210338317 hasConceptScore W4210338317C75294576 @default.
• W4210338317 hasConceptScore W4210338317C81363708 @default.
• W4210338317 hasConceptScore W4210338317C89600930 @default.
• W4210338317 hasLocation W42103383171 @default.
• W4210338317 hasOpenAccess W4210338317 @default.
• W4210338317 hasPrimaryLocation W42103383171 @default.
• W4210338317 hasRelatedWork W1522196789 @default.
• W4210338317 hasRelatedWork W2952813363 @default.
• W4210338317 hasRelatedWork W3029198973 @default.
• W4210338317 hasRelatedWork W3133861977 @default.
• W4210338317 hasRelatedWork W3167935049 @default.
• W4210338317 hasRelatedWork W3193565141 @default.
• W4210338317 hasRelatedWork W4226493464 @default.
• W4210338317 hasRelatedWork W4312417841 @default.
• W4210338317 hasRelatedWork W4315434538 @default.
• W4210338317 hasRelatedWork W4378678253 @default.
• W4210338317 isParatext "false" @default.
• W4210338317 isRetracted "false" @default.
• W4210338317 workType "article" @default.