Transfer learning using freeze features for Alzheimer neurological disorder detection using ADNI dataset

Naz, Saeeda; Ashraf, Asfa; Zaib, Ahmad

doi:10.1007/s00530-021-00797-3

Cited by 76 publications

(45 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ensemble model achieved an obvious improvement in its accuracy (with a 97.52% accuracy) compared to just using the simple average of the networks' predictions. The authors of [37] used convolutional network topologies for binary classification using freeze characteristics taken from the ImageNet source data set. The results of the study showed that the VGG architecture gave an accuracy of 99.27% (MCI/AD), 98.89% (AD/CN) and 97.06% (MCI/CN).…”

Section: Related Workmentioning

confidence: 99%

An Intelligent System for Early Recognition of Alzheimer’s Disease Using Neuroimaging

Odusami

Maskeliūnas

Damaševičius

2022

Sensors

View full text Add to dashboard Cite

Alzheimer’s disease (AD) is a neurodegenerative disease that affects brain cells, and mild cognitive impairment (MCI) has been defined as the early phase that describes the onset of AD. Early detection of MCI can be used to save patient brain cells from further damage and direct additional medical treatment to prevent its progression. Lately, the use of deep learning for the early identification of AD has generated a lot of interest. However, one of the limitations of such algorithms is their inability to identify changes in the functional connectivity in the functional brain network of patients with MCI. In this paper, we attempt to elucidate this issue with randomized concatenated deep features obtained from two pre-trained models, which simultaneously learn deep features from brain functional networks from magnetic resonance imaging (MRI) images. We experimented with ResNet18 and DenseNet201 to perform the task of AD multiclass classification. A gradient class activation map was used to mark the discriminating region of the image for the proposed model prediction. Accuracy, precision, and recall were used to assess the performance of the proposed system. The experimental analysis showed that the proposed model was able to achieve 98.86% accuracy, 98.94% precision, and 98.89% recall in multiclass classification. The findings indicate that advanced deep learning with MRI images can be used to classify and predict neurodegenerative brain diseases such as AD.

show abstract

Section: Related Workmentioning

confidence: 99%

An Intelligent System for Early Recognition of Alzheimer’s Disease Using Neuroimaging

Odusami

Maskeliūnas

Damaševičius

2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Many studies have demonstrated that using transfer learning parameter initialization can significantly improve the performance of models compared to training from scratch ( Afzal et al, 2019 ; Mousavian et al, 2019 ; Naz et al, 2021 ). This study selected the Med3D network and its pretrained weights on eight segmented datasets ( Chen et al, 2019 ).…”

Section: Methodsmentioning

confidence: 99%

A Two-Stage Model for Predicting Mild Cognitive Impairment to Alzheimer’s Disease Conversion

Zhang

et al. 2022

Front. Aging Neurosci.

View full text Add to dashboard Cite

Early detection of Alzheimer’s disease (AD), such as predicting development from mild cognitive impairment (MCI) to AD, is critical for slowing disease progression and increasing quality of life. Although deep learning is a promising technique for structural MRI-based diagnosis, the paucity of training samples limits its power, especially for three-dimensional (3D) models. To this end, we propose a two-stage model combining both transfer learning and contrastive learning that can achieve high accuracy of MRI-based early AD diagnosis even when the sample numbers are restricted. Specifically, a 3D CNN model was pretrained using publicly available medical image data to learn common medical features, and contrastive learning was further utilized to learn more specific features of MCI images. The two-stage model outperformed each benchmark method. Compared with the previous studies, we show that our model achieves superior performance in progressive MCI patients with an accuracy of 0.82 and AUC of 0.84. We further enhance the interpretability of the model by using 3D Grad-CAM, which highlights brain regions with high-predictive weights. Brain regions, including the hippocampus, temporal, and precuneus, are associated with the classification of MCI, which is supported by the various types of literature. Our model provides a novel model to avoid overfitting because of a lack of medical data and enable the early detection of AD.

show abstract

“…As we all know, public databases like ImageNet [23] with a large number of well-labeled images have achieved significant success on many challenging computer vision tasks [24][25][26][27]. In the process of building the Tangut datasets, due to the complex structure, illegibility, and a limited number of translations, it is extremely difficult to label the category of a single character.…”

Section: Data Labeling Methodsmentioning

confidence: 99%

End‐to‐end Tangut character database building and recognition method

Cao

et al. 2022

IET Image Processing

View full text Add to dashboard Cite

Character recognition is an important research topic nowadays, and a large amount of excellent work has appeared. In contrast, research related to the recognition of Tangut characters is still in the initial stage. Creating databases and effective recognition methods that can support the recognition of Tangut characters remain a great challenge. In this paper, a labeling method based on Multi‐Model and Multi‐Prediction (MMMP) is proposed, which built a Tangut character database (TCD) and an enhanced database (called “TCD‐E”) covering 6077 classes, and five test sets were also built for specific tasks. To recognize Tangut characters effectively and quickly, a 5‐layer end‐to‐end Tangut Characters Recognition Network (TCRNet) based on CNN using shallow neural networks is designed. Its recognition accuracy on TCD‐E reaches 97.96%$\%$. Based on TCRNet, an end‐to‐end Similar Tangut Characters Recognition Network (STCRNet) is further proposed by improving the loss function by combining the softmax loss function with the central loss function, and its test accuracy on similar Tangut characters test set (called “TCD‐E‐S”) is 0.70%$\%$ higher than TCRNet. Experiments show that TCD and TCD‐E can provide data support for Tangut character recognition. The recognition accuracy of TCRNet and STCRNet surpasses the previous best results.

show abstract

Transfer learning using freeze features for Alzheimer neurological disorder detection using ADNI dataset

Cited by 76 publications

References 30 publications

An Intelligent System for Early Recognition of Alzheimer’s Disease Using Neuroimaging

An Intelligent System for Early Recognition of Alzheimer’s Disease Using Neuroimaging

A Two-Stage Model for Predicting Mild Cognitive Impairment to Alzheimer’s Disease Conversion

End‐to‐end Tangut character database building and recognition method

Contact Info

Product

Resources

About