FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3197103570> ?p ?o ?g. }

• W3197103570 endingPage "5846" @default.
• W3197103570 startingPage "5846" @default.
• W3197103570 abstract "This study presents the first application of convolutional neural networks to high-frequency ultrasound skin image classification. This type of imaging opens up new opportunities in dermatology, showing inflammatory diseases such as atopic dermatitis, psoriasis, or skin lesions. We collected a database of 631 images with healthy skin and different skin pathologies to train and assess all stages of the methodology. The proposed framework starts with the segmentation of the epidermal layer using a DeepLab v3+ model with a pre-trained Xception backbone. We employ transfer learning to train the segmentation model for two purposes: to extract the region of interest for classification and to prepare the skin layer map for classification confidence estimation. For classification, we train five models in different input data modes and data augmentation setups. We also introduce a classification confidence level to evaluate the deep model’s reliability. The measure combines our skin layer map with the heatmap produced by the Grad-CAM technique designed to indicate image regions used by the deep model to make a classification decision. Moreover, we propose a multicriteria model evaluation measure to select the optimal model in terms of classification accuracy, confidence, and test dataset size. The experiments described in the paper show that the DenseNet-201 model fed with the extracted region of interest produces the most reliable and accurate results." @default.
• W3197103570 created "2021-09-13" @default.
• W3197103570 creator A5015682504 @default.
• W3197103570 creator A5019225526 @default.
• W3197103570 creator A5045904799 @default.
• W3197103570 creator A5068300275 @default.
• W3197103570 creator A5080746457 @default.
• W3197103570 date "2021-08-30" @default.
• W3197103570 modified "2023-10-16" @default.
• W3197103570 title "Deep Learning-Based High-Frequency Ultrasound Skin Image Classification with Multicriteria Model Evaluation" @default.
• W3197103570 cites W1965970425 @default.
• W3197103570 cites W1987869189 @default.
• W3197103570 cites W1992894246 @default.
• W3197103570 cites W1997763162 @default.
• W3197103570 cites W2003444435 @default.
• W3197103570 cites W2094286293 @default.
• W3197103570 cites W2158004511 @default.
• W3197103570 cites W2194775991 @default.
• W3197103570 cites W2295107390 @default.
• W3197103570 cites W2460255240 @default.
• W3197103570 cites W2467131677 @default.
• W3197103570 cites W2531409750 @default.
• W3197103570 cites W2600174524 @default.
• W3197103570 cites W2606534623 @default.
• W3197103570 cites W2625644029 @default.
• W3197103570 cites W2734349601 @default.
• W3197103570 cites W2735666957 @default.
• W3197103570 cites W2740028789 @default.
• W3197103570 cites W2789895747 @default.
• W3197103570 cites W2800458096 @default.
• W3197103570 cites W2899366209 @default.
• W3197103570 cites W2913559493 @default.
• W3197103570 cites W2934946272 @default.
• W3197103570 cites W2947263797 @default.
• W3197103570 cites W2952570739 @default.
• W3197103570 cites W2962858109 @default.
• W3197103570 cites W2991269671 @default.
• W3197103570 cites W3007943565 @default.
• W3197103570 cites W3020996329 @default.
• W3197103570 cites W3023925071 @default.
• W3197103570 cites W3033169887 @default.
• W3197103570 cites W3036165397 @default.
• W3197103570 cites W3081494544 @default.
• W3197103570 cites W3083973122 @default.
• W3197103570 cites W3091853163 @default.
• W3197103570 cites W3103010481 @default.
• W3197103570 cites W3128528820 @default.
• W3197103570 cites W3137548130 @default.
• W3197103570 cites W3156682058 @default.
• W3197103570 doi "https://doi.org/10.3390/s21175846" @default.
• W3197103570 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/8434172" @default.
• W3197103570 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34502735" @default.
• W3197103570 hasPublicationYear "2021" @default.
• W3197103570 type Work @default.
• W3197103570 sameAs 3197103570 @default.
• W3197103570 citedByCount "6" @default.
• W3197103570 countsByYear W31971035702022 @default.
• W3197103570 countsByYear W31971035702023 @default.
• W3197103570 crossrefType "journal-article" @default.
• W3197103570 hasAuthorship W3197103570A5015682504 @default.
• W3197103570 hasAuthorship W3197103570A5019225526 @default.
• W3197103570 hasAuthorship W3197103570A5045904799 @default.
• W3197103570 hasAuthorship W3197103570A5068300275 @default.
• W3197103570 hasAuthorship W3197103570A5080746457 @default.
• W3197103570 hasBestOaLocation W31971035701 @default.
• W3197103570 hasConcept C108583219 @default.
• W3197103570 hasConcept C115961682 @default.
• W3197103570 hasConcept C119857082 @default.
• W3197103570 hasConcept C121332964 @default.
• W3197103570 hasConcept C124101348 @default.
• W3197103570 hasConcept C150899416 @default.
• W3197103570 hasConcept C153180895 @default.
• W3197103570 hasConcept C154945302 @default.
• W3197103570 hasConcept C163258240 @default.
• W3197103570 hasConcept C2780009758 @default.
• W3197103570 hasConcept C41008148 @default.
• W3197103570 hasConcept C43214815 @default.
• W3197103570 hasConcept C62520636 @default.
• W3197103570 hasConcept C75294576 @default.
• W3197103570 hasConcept C81363708 @default.
• W3197103570 hasConcept C89600930 @default.
• W3197103570 hasConceptScore W3197103570C108583219 @default.
• W3197103570 hasConceptScore W3197103570C115961682 @default.
• W3197103570 hasConceptScore W3197103570C119857082 @default.
• W3197103570 hasConceptScore W3197103570C121332964 @default.
• W3197103570 hasConceptScore W3197103570C124101348 @default.
• W3197103570 hasConceptScore W3197103570C150899416 @default.
• W3197103570 hasConceptScore W3197103570C153180895 @default.
• W3197103570 hasConceptScore W3197103570C154945302 @default.
• W3197103570 hasConceptScore W3197103570C163258240 @default.
• W3197103570 hasConceptScore W3197103570C2780009758 @default.
• W3197103570 hasConceptScore W3197103570C41008148 @default.
• W3197103570 hasConceptScore W3197103570C43214815 @default.
• W3197103570 hasConceptScore W3197103570C62520636 @default.
• W3197103570 hasConceptScore W3197103570C75294576 @default.
• W3197103570 hasConceptScore W3197103570C81363708 @default.
• W3197103570 hasConceptScore W3197103570C89600930 @default.
• W3197103570 hasFunder F4320324727 @default.

• next