Matches in SemOpenAlex for { <https://semopenalex.org/work/W4311372112> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W4311372112 endingPage "154" @default.
- W4311372112 startingPage "144" @default.
- W4311372112 abstract "AbstractArtificial intelligence (AI) based medical image recognition plays an role in assisting disease diagnosis systems. Recent research on deep learning techniques has provided fast and powerful approaches for image analysis and classification for pathologists in their diagnostic tasks. This paper presents a new approach to enhance the efficiency of the skin disease classification task. The method consists of three major parts as follows (1) Extracting skin damaged regions (region of interesting –ROI) based on the semantic segmentation technique, (2) morphological processing for refining the results of ROI extraction, (3) disease classification based on the deep convolution neural network (DCNN). In most of the previous approaches, disease diagnosis systems use image samples, which are taken from medical devices, producing very small, damaged regions in full images. In our approach, the segmentation task utilizes to extract only the damaged skin regions for disease diagnosis. Thusly, the advantage of the proposed method supports reducing the important data space and focuses on ROIs of the disease features for improving efficient diagnosis systems. The proposed method has been evaluated on the benchmark dataset of ISIC2018, which is already available online for both training and validation data. To ensure objectivity, some well-known backbones are used for feature extraction task such as DenseNet, MobileNet, EfficientNet models. The experimental results show that, by using the same feature extraction backbones, the proposed method outperforms the standard methods on some performed metrics (Recall, Accuracy, Precision, Specificity, and F1) with DenseNet (3.11%, 2.04%, 3.37%. 2.91%, and 3.49%), EfficientNet (1.04%, 0.71%, 0.05%, 0.77% and 1.10%), and MobileNet (4.15%, 1.66%, 6.10%, 1.34%, and 5.03%), respectively.KeywordsDeep learningImage processingMultiple classificationSemantic segmentation" @default.
- W4311372112 created "2022-12-25" @default.
- W4311372112 creator A5036304904 @default.
- W4311372112 creator A5047160220 @default.
- W4311372112 creator A5057436905 @default.
- W4311372112 creator A5085989249 @default.
- W4311372112 date "2022-12-15" @default.
- W4311372112 modified "2023-10-13" @default.
- W4311372112 title "Fusion of Segmentation and Classification for Improving Skin Disease Diagnosis" @default.
- W4311372112 cites W1901129140 @default.
- W4311372112 cites W1903029394 @default.
- W4311372112 cites W2097117768 @default.
- W4311372112 cites W2108598243 @default.
- W4311372112 cites W2126301712 @default.
- W4311372112 cites W2194775991 @default.
- W4311372112 cites W2412782625 @default.
- W4311372112 cites W2963150697 @default.
- W4311372112 cites W2963351448 @default.
- W4311372112 cites W2963446712 @default.
- W4311372112 cites W2971897287 @default.
- W4311372112 cites W2986479453 @default.
- W4311372112 cites W3019019053 @default.
- W4311372112 cites W3134320085 @default.
- W4311372112 cites W4205189720 @default.
- W4311372112 cites W4206292903 @default.
- W4311372112 doi "https://doi.org/10.1007/978-3-031-19694-2_13" @default.
- W4311372112 hasPublicationYear "2022" @default.
- W4311372112 type Work @default.
- W4311372112 citedByCount "0" @default.
- W4311372112 crossrefType "book-chapter" @default.
- W4311372112 hasAuthorship W4311372112A5036304904 @default.
- W4311372112 hasAuthorship W4311372112A5047160220 @default.
- W4311372112 hasAuthorship W4311372112A5057436905 @default.
- W4311372112 hasAuthorship W4311372112A5085989249 @default.
- W4311372112 hasConcept C108583219 @default.
- W4311372112 hasConcept C119857082 @default.
- W4311372112 hasConcept C127413603 @default.
- W4311372112 hasConcept C13280743 @default.
- W4311372112 hasConcept C153180895 @default.
- W4311372112 hasConcept C154945302 @default.
- W4311372112 hasConcept C185798385 @default.
- W4311372112 hasConcept C201995342 @default.
- W4311372112 hasConcept C205649164 @default.
- W4311372112 hasConcept C2780451532 @default.
- W4311372112 hasConcept C41008148 @default.
- W4311372112 hasConcept C52622490 @default.
- W4311372112 hasConcept C81363708 @default.
- W4311372112 hasConcept C89600930 @default.
- W4311372112 hasConceptScore W4311372112C108583219 @default.
- W4311372112 hasConceptScore W4311372112C119857082 @default.
- W4311372112 hasConceptScore W4311372112C127413603 @default.
- W4311372112 hasConceptScore W4311372112C13280743 @default.
- W4311372112 hasConceptScore W4311372112C153180895 @default.
- W4311372112 hasConceptScore W4311372112C154945302 @default.
- W4311372112 hasConceptScore W4311372112C185798385 @default.
- W4311372112 hasConceptScore W4311372112C201995342 @default.
- W4311372112 hasConceptScore W4311372112C205649164 @default.
- W4311372112 hasConceptScore W4311372112C2780451532 @default.
- W4311372112 hasConceptScore W4311372112C41008148 @default.
- W4311372112 hasConceptScore W4311372112C52622490 @default.
- W4311372112 hasConceptScore W4311372112C81363708 @default.
- W4311372112 hasConceptScore W4311372112C89600930 @default.
- W4311372112 hasLocation W43113721121 @default.
- W4311372112 hasOpenAccess W4311372112 @default.
- W4311372112 hasPrimaryLocation W43113721121 @default.
- W4311372112 hasRelatedWork W2279398222 @default.
- W4311372112 hasRelatedWork W2732542196 @default.
- W4311372112 hasRelatedWork W2773120646 @default.
- W4311372112 hasRelatedWork W2795329967 @default.
- W4311372112 hasRelatedWork W3018421652 @default.
- W4311372112 hasRelatedWork W3102253946 @default.
- W4311372112 hasRelatedWork W3144574764 @default.
- W4311372112 hasRelatedWork W4226289457 @default.
- W4311372112 hasRelatedWork W4293211451 @default.
- W4311372112 hasRelatedWork W4299822940 @default.
- W4311372112 isParatext "false" @default.
- W4311372112 isRetracted "false" @default.
- W4311372112 workType "book-chapter" @default.