A Low-Cost Three-Dimensional DenseNet Neural Network for Alzheimer’s Disease Early Discovery

Solano-Rojas, Braulio J.; Ricardo, Villalón-Fonseca

doi:10.3390/s21041302

Cited by 33 publications

(17 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This shows that the group convolution utilizing the same topology can improve the algorithmic performance, reduce the global information loss, enrich the lesion information extracted by the network, and avoid the errors caused by the singularity of feature extraction. Compared with the AD prediction algorithms based on DensNet proposed by Liu et al [ 28 ] and Solano-Rojas and Villalón-Fonseca [ 29 ], the algorithm proposed improves the classification accuracy by up to 21%. This indicates that the hybrid attention mechanism can capture the correlations between features, suppress redundant features, enhance the correlations between features and lesion regions, and perform adaptive feature extraction for regions with more information in PET images, thus further enhancing the recognition capability of the model.…”

Section: Experimental Results and Analysismentioning

confidence: 98%

Alzheimer’s Disease Prediction Algorithm Based on Group Convolution and a Joint Loss Function

Cheng

Wang

Wei

et al. 2022

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

Alzheimer’s disease (AD) can effectively predict by 18F-fluorodeoxyglucose positron emission tomography (18F-FDG PET) of the brain, but current PET images still suffer from indistinct lesion features, low signal-to-noise ratios, and severe artefacts, resulting in poor prediction accuracy for patients with mild cognitive impairment (MCI) and unclear lesion features. In this paper, an AD prediction algorithm based on group convolution and a joint loss function is proposed. First, a group convolutional backbone network based on ResNet18 is designed to extract lesion features from multiple channels, which makes the expression ability of the network improved to a great extent. Then, a hybrid attention mechanism is presented, which enables the network to focus on target regions and learn feature weights, so as to enhance the network’s learning ability of the lesion regions that are relevant to disease diagnosis. Finally, a joint loss function, that avoids the overfitting phenomenon, increases the generalization of the model, and improves prediction accuracy by adding a regularization loss function to the conventional cross-entropy function, is proposed. Experiments conducted on the public Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset show that the algorithm we proposed gives a prediction accuracy improvement of 2.4% over that of the current AD prediction algorithm, thus proving the effectiveness and availability of the new algorithm.

show abstract

Section: Experimental Results and Analysismentioning

confidence: 98%

Alzheimer’s Disease Prediction Algorithm Based on Group Convolution and a Joint Loss Function

Cheng

Wang

Wei

et al. 2022

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

show abstract

“…To the extent of making black boxes more interpretable, a few methods for explaining model behavior have been developed, contributing to the realization of the explainable AI [ 12 , 71 ]. Neurodegenerative disease research is only recently approaching explainable AI [ 72 , 73 , 74 , 75 ] and there are only a few works available where Guided Grad-CAM has been used to generate attention maps for DL neural networks [ 76 , 77 , 78 , 79 ]. To the best of our knowledge, this is the first work where a DL model for FTD detection is studied with explainable AI methods.…”

Section: Discussionmentioning

confidence: 99%

A Reproducible Deep-Learning-Based Computer-Aided Diagnosis Tool for Frontotemporal Dementia Using MONAI and Clinica Frameworks

Termine

Fabrizio

Caltagirone

et al. 2022

Life

View full text Add to dashboard Cite

Despite Artificial Intelligence (AI) being a leading technology in biomedical research, real-life implementation of AI-based Computer-Aided Diagnosis (CAD) tools into the clinical setting is still remote due to unstandardized practices during development. However, few or no attempts have been made to propose a reproducible CAD development workflow for 3D MRI data. In this paper, we present the development of an easily reproducible and reliable CAD tool using the Clinica and MONAI frameworks that were developed to introduce standardized practices in medical imaging. A Deep Learning (DL) algorithm was trained to detect frontotemporal dementia (FTD) on data from the NIFD database to ensure reproducibility. The DL model yielded 0.80 accuracy (95% confidence intervals: 0.64, 0.91), 1 sensitivity, 0.6 specificity, 0.83 F1-score, and 0.86 AUC, achieving a comparable performance with other FTD classification approaches. Explainable AI methods were applied to understand AI behavior and to identify regions of the images where the DL model misbehaves. Attention maps highlighted that its decision was driven by hallmarking brain areas for FTD and helped us to understand how to improve FTD detection. The proposed standardized methodology could be useful for benchmark comparison in FTD classification. AI-based CAD tools should be developed with the goal of standardizing pipelines, as varying pre-processing and training methods, along with the absence of model behavior explanations, negatively impact regulators’ attitudes towards CAD. The adoption of common best practices for neuroimaging data analysis is a step toward fast evaluation of efficacy and safety of CAD and may accelerate the adoption of AI products in the healthcare system.

show abstract

“…The study compared the performance of the proposed model with 2D-CNN and 3D-CNN, and it was demonstrated that 3D-CNN-SVM outperformed 2D-CNN and 3D-CNN. Solano-Rojas and Villalón-Fonseca [ 76 ] proposed a CNN based on DenseNet Bottleneck-Compressed architecture for AD diagnosis using MR images. The proposed model classified the input into five different categories, CN, EMCI, MCI, LMCI and AD, with an average accuracy of 86%.…”

Section: DL For Ad Diagnosismentioning

confidence: 99%

Deep Learning-Based Diagnosis of Alzheimer’s Disease

Saleem

Zahra

et al. 2022

JPM

View full text Add to dashboard Cite

Alzheimer’s disease (AD), the most familiar type of dementia, is a severe concern in modern healthcare. Around 5.5 million people aged 65 and above have AD, and it is the sixth leading cause of mortality in the US. AD is an irreversible, degenerative brain disorder characterized by a loss of cognitive function and has no proven cure. Deep learning techniques have gained popularity in recent years, particularly in the domains of natural language processing and computer vision. Since 2014, these techniques have begun to achieve substantial consideration in AD diagnosis research, and the number of papers published in this arena is rising drastically. Deep learning techniques have been reported to be more accurate for AD diagnosis in comparison to conventional machine learning models. Motivated to explore the potential of deep learning in AD diagnosis, this study reviews the current state-of-the-art in AD diagnosis using deep learning. We summarize the most recent trends and findings using a thorough literature review. The study also explores the different biomarkers and datasets for AD diagnosis. Even though deep learning has shown promise in AD diagnosis, there are still several challenges that need to be addressed.

show abstract

A Low-Cost Three-Dimensional DenseNet Neural Network for Alzheimer’s Disease Early Discovery

Cited by 33 publications

References 31 publications

Alzheimer’s Disease Prediction Algorithm Based on Group Convolution and a Joint Loss Function

Alzheimer’s Disease Prediction Algorithm Based on Group Convolution and a Joint Loss Function

A Reproducible Deep-Learning-Based Computer-Aided Diagnosis Tool for Frontotemporal Dementia Using MONAI and Clinica Frameworks

Deep Learning-Based Diagnosis of Alzheimer’s Disease

Contact Info

Product

Resources

About