Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313588382> ?p ?o ?g. }
- W4313588382 endingPage "167" @default.
- W4313588382 startingPage "167" @default.
- W4313588382 abstract "Mental deterioration or Alzheimer's (ALZ) disease is progressive and causes both physical and mental dependency. There is a need for a computer-aided diagnosis (CAD) system that can help doctors make an immediate decision. (1) Background: Currently, CAD systems are developed based on hand-crafted features, machine learning (ML), and deep learning (DL) techniques. Those CAD systems frequently require domain-expert knowledge and massive datasets to extract deep features or model training, which causes problems with class imbalance and overfitting. Additionally, there are still manual approaches used by radiologists due to the lack of dataset availability and to train the model with cost-effective computation. Existing works rely on performance improvement by neglecting the problems of the limited dataset, high computational complexity, and unavailability of lightweight and efficient feature descriptors. (2) Methods: To address these issues, a new approach, CAD-ALZ, is developed by extracting deep features through a ConvMixer layer with a blockwise fine-tuning strategy on a very small original dataset. At first, we apply the data augmentation method to images to increase the size of datasets. In this study, a blockwise fine-tuning strategy is employed on the ConvMixer model to detect robust features. Afterwards, a random forest (RF) is used to classify ALZ disease stages. (3) Results: The proposed CAD-ALZ model obtained significant results by using six evaluation metrics such as the F1-score, Kappa, accuracy, precision, sensitivity, and specificity. The CAD-ALZ model performed with a sensitivity of 99.69% and an F1-score of 99.61%. (4) Conclusions: The suggested CAD-ALZ approach is a potential technique for clinical use and computational efficiency compared to state-of-the-art approaches. The CAD-ALZ model code is freely available on GitHub for the scientific community." @default.
- W4313588382 created "2023-01-06" @default.
- W4313588382 creator A5012646380 @default.
- W4313588382 creator A5038718984 @default.
- W4313588382 creator A5056499722 @default.
- W4313588382 date "2023-01-03" @default.
- W4313588382 modified "2023-10-14" @default.
- W4313588382 title "CAD-ALZ: A Blockwise Fine-Tuning Strategy on Convolutional Model and Random Forest Classifier for Recognition of Multistage Alzheimer’s Disease" @default.
- W4313588382 cites W1581627189 @default.
- W4313588382 cites W2041677347 @default.
- W4313588382 cites W2525655278 @default.
- W4313588382 cites W2534299759 @default.
- W4313588382 cites W2592343442 @default.
- W4313588382 cites W2595499435 @default.
- W4313588382 cites W2762747243 @default.
- W4313588382 cites W2769782531 @default.
- W4313588382 cites W2774698027 @default.
- W4313588382 cites W2789337348 @default.
- W4313588382 cites W2790012920 @default.
- W4313588382 cites W2793556086 @default.
- W4313588382 cites W2793804994 @default.
- W4313588382 cites W2805494981 @default.
- W4313588382 cites W2886445457 @default.
- W4313588382 cites W2900386946 @default.
- W4313588382 cites W2901348195 @default.
- W4313588382 cites W2905035821 @default.
- W4313588382 cites W2906302663 @default.
- W4313588382 cites W2907148404 @default.
- W4313588382 cites W2911442010 @default.
- W4313588382 cites W2923463496 @default.
- W4313588382 cites W2929508119 @default.
- W4313588382 cites W2942882625 @default.
- W4313588382 cites W2944541202 @default.
- W4313588382 cites W2948184028 @default.
- W4313588382 cites W2950680182 @default.
- W4313588382 cites W2963168174 @default.
- W4313588382 cites W2964629181 @default.
- W4313588382 cites W2964657045 @default.
- W4313588382 cites W2968726102 @default.
- W4313588382 cites W2979487364 @default.
- W4313588382 cites W2990581109 @default.
- W4313588382 cites W2993219936 @default.
- W4313588382 cites W2995495466 @default.
- W4313588382 cites W2995864059 @default.
- W4313588382 cites W3005273529 @default.
- W4313588382 cites W3013699712 @default.
- W4313588382 cites W3023079706 @default.
- W4313588382 cites W3035162004 @default.
- W4313588382 cites W3040248281 @default.
- W4313588382 cites W3091780972 @default.
- W4313588382 cites W3100125480 @default.
- W4313588382 cites W3115069763 @default.
- W4313588382 cites W3123500501 @default.
- W4313588382 cites W3135876408 @default.
- W4313588382 cites W3136481290 @default.
- W4313588382 cites W3164454234 @default.
- W4313588382 cites W3167864582 @default.
- W4313588382 cites W3173195087 @default.
- W4313588382 cites W3196274803 @default.
- W4313588382 cites W3204772083 @default.
- W4313588382 cites W3210926952 @default.
- W4313588382 cites W3217378117 @default.
- W4313588382 cites W4205597106 @default.
- W4313588382 cites W4213002899 @default.
- W4313588382 cites W4220878282 @default.
- W4313588382 cites W4281701027 @default.
- W4313588382 cites W4306404621 @default.
- W4313588382 doi "https://doi.org/10.3390/diagnostics13010167" @default.
- W4313588382 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36611459" @default.
- W4313588382 hasPublicationYear "2023" @default.
- W4313588382 type Work @default.
- W4313588382 citedByCount "1" @default.
- W4313588382 countsByYear W43135883822023 @default.
- W4313588382 crossrefType "journal-article" @default.
- W4313588382 hasAuthorship W4313588382A5012646380 @default.
- W4313588382 hasAuthorship W4313588382A5038718984 @default.
- W4313588382 hasAuthorship W4313588382A5056499722 @default.
- W4313588382 hasBestOaLocation W43135883821 @default.
- W4313588382 hasConcept C108583219 @default.
- W4313588382 hasConcept C119857082 @default.
- W4313588382 hasConcept C124101348 @default.
- W4313588382 hasConcept C127413603 @default.
- W4313588382 hasConcept C138885662 @default.
- W4313588382 hasConcept C153180895 @default.
- W4313588382 hasConcept C154945302 @default.
- W4313588382 hasConcept C169258074 @default.
- W4313588382 hasConcept C194789388 @default.
- W4313588382 hasConcept C199639397 @default.
- W4313588382 hasConcept C200601418 @default.
- W4313588382 hasConcept C207685749 @default.
- W4313588382 hasConcept C22019652 @default.
- W4313588382 hasConcept C2776401178 @default.
- W4313588382 hasConcept C2780505938 @default.
- W4313588382 hasConcept C41008148 @default.
- W4313588382 hasConcept C41895202 @default.
- W4313588382 hasConcept C50644808 @default.
- W4313588382 hasConcept C81363708 @default.
- W4313588382 hasConcept C95623464 @default.