Transfer Learning for Predicting Conversion from Mild Cognitive Impairment to Dementia of Alzheimer’s Type based on 3D-Convolutional Neural Network

Bae, Jinhyeong; Stock, Jane; Heywood, Ashley; Jung, Yongju; Jenkins, Lisanne M.; Katsaggelos, Aggelos K.; Popuri, Karteek; Beg, Faisal; Wang, Lei

doi:10.1101/2019.12.20.884932

Cited by 5 publications

(6 citation statements)

References 38 publications

(50 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The standard perturbation method has been widely used in the study of Alzheimer's disease [32,48,45,37] and related symptoms (amyloid-β pathology) [49]. However, most of the time, authors do not train their model with perturbed images.…”

Section: Perturbation Methods Applied To Neuroimagingmentioning

confidence: 99%

Interpretability of Machine Learning Methods Applied to Neuroimaging

Thibeau–Sutre¹,

Collin²,

Burgos³

et al. 2022

Preprint

View full text Add to dashboard Cite

Deep learning methods have become very popular for the processing of natural images, and were then successfully adapted to the neuroimaging field. As these methods are non-transparent, interpretability methods are needed to validate them and ensure their reliability. Indeed, it has been shown that deep learning models may obtain high performance even when using irrelevant features, by exploiting biases in the training set. Such undesirable situations can potentially be detected by using interpretability methods. Recently, many methods have been proposed to interpret neural networks. However, this domain is not mature yet. Machine learning users face two major issues when aiming to interpret their models: which method to choose, and how to assess its reliability? Here, we aim at providing answers to these questions by presenting the most common interpretability methods and metrics developed to assess their reliability, as well as their applications and benchmarks in the neuroimaging context. Note that this is not an exhaustive survey: we aimed to focus on the studies which we found to be the most representative and relevant.

show abstract

Section: Perturbation Methods Applied To Neuroimagingmentioning

confidence: 99%

Interpretability of Machine Learning Methods Applied to Neuroimaging

Thibeau–Sutre¹,

Collin²,

Burgos³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Therefore, some studies suggested a strategy used to address the classification of sMCI and pMCI classes, which is to employ a pretrained network trained on diverse cohorts, including CN, and AD to predict whether or not people with MCI will convert to AD. [14][15][16] Basaia et al 14 used a 3D convolutional neural network (3D CNN) based on a single cross-sectional sMRI to predicate MCI to AD conversation. In addition, this study investigated the limitations of using a single-center dataset.…”

Section: Impact Statementmentioning

confidence: 99%

“…The CNN-EL model achieved a 62.0% accuracy in distinguishing patients with MCI converters from those who will remain stable. Bae et al 16 used a CNN model that was first trained on sMRI scans of healthy individuals and those with AD to predict which individuals with MCI converted (MCI-C) and which did not convert (MCI-NC). Researchers used a classification task of NC versus AD as the source task for transfer learning to the target task, which is MCI-C versus MCI-NC.…”

Section: Impact Statementmentioning

confidence: 99%

“…The model's accuracy in predicting MCI-to-AD conversion was 82.4%. For various reasons, research studies 14,16 classify sMCI and pMCI using a model trained to differentiate between AD patients and HCs. It is more difficult to distinguish between sMCI and pMCI than between AD and CN.…”

Section: Impact Statementmentioning

confidence: 99%

“…This model will be used later to retrain MCI patients to recognize between sMCI and cMCI. We follow the same strategy followed by some studies [14][15][16] in the literature to address the classification of sMCI and pMCI classes: to employ a pretrained network trained on AD versus healthy individuals to predict whether or not people with MCI will convert to AD. The first dataset contains 89 3D T1-weighted magnetic resonance images from 89 subjects (45 patients with AD and 44 HCs), whereas the second dataset includes (467) 3D T1-weighted baseline sMRI scans for patients with probable MCI to track the progression of MCI conversion in more detail.…”

Section: Participants and Datasetsmentioning

confidence: 99%

See 2 more Smart Citations

A robust class decomposition-based approach for detecting Alzheimer’s progression

Alwuthaynani,

Abdallah,

Santos-Rodriguez

2023

Exp Biol Med (Maywood)

View full text Add to dashboard Cite

Computer-aided diagnosis of Alzheimer’s disease (AD) is a rapidly growing field with the possibility to be utilized in practice. Deep learning has received much attention in detecting AD from structural magnetic resonance imaging (sMRI). However, training a convolutional neural network from scratch is problematic because it requires a lot of annotated data and additional computational time. Transfer learning can offer a promising and practical solution by transferring information learned from other image recognition tasks to medical image classification. Another issue is the dataset distribution’s irregularities. A common classification issue in datasets is a class imbalance, where the distribution of samples among the classes is biased. For example, a dataset may contain more instances of some classes than others. Class imbalance is challenging because most machine learning algorithms assume that each class should have an equal number of samples. Models consequently perform poorly in prediction. Class decomposition can address this problem by making learning a dataset’s class boundaries easier. Motivated by these approaches, we propose a class decomposition transfer learning (CDTL) approach that employs VGG19, AlexNet, and an entropy-based technique to detect AD from sMRI. This study aims to assess the robustness of the CDTL approach in detecting the cognitive decline of AD using data from various ADNI cohorts to determine whether comparable classification accuracy for the two or more cohorts would be obtained. Furthermore, the proposed model achieved state-of-the-art performance in predicting mild cognitive impairment (MCI)-to-AD conversion with an accuracy of 91.45%.

show abstract

Interpretability of Machine Learning Methods Applied to Neuroimaging

et al. 2023

View full text Add to dashboard Cite

Deep learning methods have become very popular for the processing of natural images and were then successfully adapted to the neuroimaging field. As these methods are non-transparent, interpretability methods are needed to validate them and ensure their reliability. Indeed, it has been shown that deep learning models may obtain high performance even when using irrelevant features, by exploiting biases in the training set. Such undesirable situations can potentially be detected by using interpretability methods. Recently, many methods have been proposed to interpret neural networks. However, this domain is not mature yet. Machine learning users face two major issues when aiming to interpret their models: which method to choose and how to assess its reliability. Here, we aim at providing answers to these questions by presenting the most common interpretability methods and metrics developed to assess their reliability, as well as their applications and benchmarks in the neuroimaging context. Note that this is not an exhaustive survey: we aimed to focus on the studies which we found to be the most representative and relevant.

show abstract

Transfer Learning for Predicting Conversion from Mild Cognitive Impairment to Dementia of Alzheimer’s Type based on 3D-Convolutional Neural Network

Cited by 5 publications

References 38 publications

Interpretability of Machine Learning Methods Applied to Neuroimaging

Interpretability of Machine Learning Methods Applied to Neuroimaging

A robust class decomposition-based approach for detecting Alzheimer’s progression

Interpretability of Machine Learning Methods Applied to Neuroimaging

Contact Info

Product

Resources

About