FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386850835> ?p ?o ?g. }

• W4386850835 abstract "Training deep Convolutional Neural Networks (CNNs) presents challenges in terms of memory requirements and computational resources, often resulting in issues such as model overfitting and lack of generalization. These challenges can only be mitigated by using an excessive number of training images. However, medical image datasets commonly suffer from data scarcity due to the complexities involved in their acquisition, preparation, and curation. To address this issue, we propose a compact and hybrid machine learning architecture based on the Morphological and Convolutional Neural Network (MCNN), followed by a Random Forest classifier. Unlike deep CNN architectures, the MCNN was specifically designed to achieve effective performance with medical image datasets limited to a few hundred samples. It incorporates various morphological operations into a single layer and uses independent neural networks to extract information from each signal channel. The final classification is obtained by utilizing a Random Forest classifier on the outputs of the last neural network layer. We compare the classification performance of our proposed method with three popular deep CNN architectures (ResNet-18, ShuffleNet-V2, and MobileNet-V2) using two training approaches: full training and transfer learning. The evaluation was conducted on two distinct medical image datasets: the ISIC dataset for melanoma classification and the ORIGA dataset for glaucoma classification. Results demonstrate that the MCNN method exhibits reliable performance in melanoma classification, achieving an AUC of 0.94 (95% CI: 0.91 to 0.97), outperforming the popular CNN architectures. For the glaucoma dataset, the MCNN achieved an AUC of 0.65 (95% CI: 0.53 to 0.74), which was similar to the performance of the popular CNN architectures. This study contributes to the understanding of mathematical morphology in shallow neural networks for medical image classification and highlights the potential of hybrid architectures in effectively learning from medical image datasets that are limited by a small number of case samples." @default.
• W4386850835 created "2023-09-20" @default.
• W4386850835 creator A5031562608 @default.
• W4386850835 creator A5075416557 @default.
• W4386850835 date "2023-09-19" @default.
• W4386850835 modified "2023-10-16" @default.
• W4386850835 title "Hybrid morphological-convolutional neural networks for computer-aided diagnosis" @default.
• W4386850835 cites W130099911 @default.
• W4386850835 cites W1930624869 @default.
• W4386850835 cites W1974969377 @default.
• W4386850835 cites W2002427601 @default.
• W4386850835 cites W2082704080 @default.
• W4386850835 cites W2083927153 @default.
• W4386850835 cites W2108598243 @default.
• W4386850835 cites W2134603844 @default.
• W4386850835 cites W2165698076 @default.
• W4386850835 cites W2581082771 @default.
• W4386850835 cites W2767635412 @default.
• W4386850835 cites W2783687327 @default.
• W4386850835 cites W2891706393 @default.
• W4386850835 cites W2895486342 @default.
• W4386850835 cites W2905307056 @default.
• W4386850835 cites W2911437338 @default.
• W4386850835 cites W2913223168 @default.
• W4386850835 cites W2939071985 @default.
• W4386850835 cites W2954996726 @default.
• W4386850835 cites W2956154037 @default.
• W4386850835 cites W2963366775 @default.
• W4386850835 cites W2963446712 @default.
• W4386850835 cites W2964273253 @default.
• W4386850835 cites W2964317695 @default.
• W4386850835 cites W2964350391 @default.
• W4386850835 cites W2964383635 @default.
• W4386850835 cites W3001283548 @default.
• W4386850835 cites W3007935259 @default.
• W4386850835 cites W3014666486 @default.
• W4386850835 cites W3020996329 @default.
• W4386850835 cites W3025948831 @default.
• W4386850835 cites W3034553879 @default.
• W4386850835 cites W3045506901 @default.
• W4386850835 cites W3089472426 @default.
• W4386850835 cites W3099733385 @default.
• W4386850835 cites W3103891644 @default.
• W4386850835 cites W3120795911 @default.
• W4386850835 cites W3136343426 @default.
• W4386850835 cites W3138881922 @default.
• W4386850835 cites W3152497941 @default.
• W4386850835 cites W3176923149 @default.
• W4386850835 cites W4223899585 @default.
• W4386850835 cites W4280492604 @default.
• W4386850835 cites W4288068240 @default.
• W4386850835 cites W4295312788 @default.
• W4386850835 cites W4307828581 @default.
• W4386850835 cites W4310396525 @default.
• W4386850835 cites W4362664427 @default.
• W4386850835 cites W642169424 @default.
• W4386850835 doi "https://doi.org/10.3389/frai.2023.1253183" @default.
• W4386850835 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37795497" @default.
• W4386850835 hasPublicationYear "2023" @default.
• W4386850835 type Work @default.
• W4386850835 citedByCount "0" @default.
• W4386850835 crossrefType "journal-article" @default.
• W4386850835 hasAuthorship W4386850835A5031562608 @default.
• W4386850835 hasAuthorship W4386850835A5075416557 @default.
• W4386850835 hasBestOaLocation W43868508351 @default.
• W4386850835 hasConcept C108583219 @default.
• W4386850835 hasConcept C115961682 @default.
• W4386850835 hasConcept C119857082 @default.
• W4386850835 hasConcept C150899416 @default.
• W4386850835 hasConcept C153180895 @default.
• W4386850835 hasConcept C154945302 @default.
• W4386850835 hasConcept C169258074 @default.
• W4386850835 hasConcept C22019652 @default.
• W4386850835 hasConcept C41008148 @default.
• W4386850835 hasConcept C50644808 @default.
• W4386850835 hasConcept C75294576 @default.
• W4386850835 hasConcept C81363708 @default.
• W4386850835 hasConcept C95623464 @default.
• W4386850835 hasConceptScore W4386850835C108583219 @default.
• W4386850835 hasConceptScore W4386850835C115961682 @default.
• W4386850835 hasConceptScore W4386850835C119857082 @default.
• W4386850835 hasConceptScore W4386850835C150899416 @default.
• W4386850835 hasConceptScore W4386850835C153180895 @default.
• W4386850835 hasConceptScore W4386850835C154945302 @default.
• W4386850835 hasConceptScore W4386850835C169258074 @default.
• W4386850835 hasConceptScore W4386850835C22019652 @default.
• W4386850835 hasConceptScore W4386850835C41008148 @default.
• W4386850835 hasConceptScore W4386850835C50644808 @default.
• W4386850835 hasConceptScore W4386850835C75294576 @default.
• W4386850835 hasConceptScore W4386850835C81363708 @default.
• W4386850835 hasConceptScore W4386850835C95623464 @default.
• W4386850835 hasLocation W43868508351 @default.
• W4386850835 hasLocation W43868508352 @default.
• W4386850835 hasOpenAccess W4386850835 @default.
• W4386850835 hasPrimaryLocation W43868508351 @default.
• W4386850835 hasRelatedWork W2005234362 @default.
• W4386850835 hasRelatedWork W2162970382 @default.
• W4386850835 hasRelatedWork W2889302474 @default.
• W4386850835 hasRelatedWork W2979740303 @default.
• W4386850835 hasRelatedWork W2981628807 @default.

• next