Deep recurrent model for individualized prediction of Alzheimer’s disease progression

Jung, Wonsik; Jun, Eunji; Suk, Heung-Il; Initiative, Alzheimer’s Disease Neuroimaging

doi:10.1016/j.neuroimage.2021.118143

Cited by 39 publications

(23 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Four experiments were made using multiple types of feature in graph nodes (exp. 6,7,8,9). The best performance of diagnosis and prognosis was obtained using , (exp.…”

Section: Combination Of Grading and Additional Featuresmentioning

confidence: 99%

See 1 more Smart Citation

Towards better Interpretable and Generalizable AD detection using Collective Artificial Intelligence

Nguyen¹,

Clément²,

Mansencal³

et al. 2022

Preprint

View full text Add to dashboard Cite

Accurate diagnosis and prognosis of Alzheimer's disease are crucial for developing new therapies and reducing the associated costs. Recently, with the advances of convolutional neural networks, deep learning methods have been proposed to automate these two tasks using structural MRI. However, these methods often suffer from a lack of interpretability and generalization and have limited prognosis performance. In this paper, we propose a novel deep framework designed to overcome these limitations. Our pipeline consists of two stages. In the first stage, 125 3D U-Nets are used to estimate voxelwise grade scores over the whole brain. The resulting 3D maps are then fused to construct an interpretable 3D grading map indicating the disease severity at the structure level. As a consequence, clinicians can use this map to detect the brain structures affected by the disease. In the second stage, the grading map and subject's age are used to perform classification with a graph convolutional neural network. Experimental results based on 2106 subjects demonstrated competitive performance of our deep framework compared to state-ofthe-art methods on different datasets for both AD diagnosis and prognosis. Moreover, we found that using a large number of U-Nets processing different overlapping brain areas improved the generalization capacity of the proposed methods.

show abstract

“…Four experiments were made using multiple types of feature in graph nodes (exp. 6,7,8,9). The best performance of diagnosis and prognosis was obtained using , (exp.…”

Section: Combination Of Grading and Additional Featuresmentioning

confidence: 99%

“…Brain atrophy is an important biomarker of Alzheimer's disease. Many studies state that this morphological change may occur before the first cognitive symptoms of AD [7,8,9,10]. Those anatomical changes can be identified with the help of structural magnetic resonance imaging (sMRI) [11].…”

Section: Introduction 1contextmentioning

confidence: 99%

Towards better Interpretable and Generalizable AD detection using Collective Artificial Intelligence

Nguyen¹,

Clément²,

Mansencal³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Without too much professional knowledge, deep learning can automatically implement the process of feature extraction from data, rather than engineering features manually. Jung et al [ 23 ] proposed a deep recurrent network that utilizes cognitive data from the Mini-Mental State Examination (MMSE), ADAS-cog11, and ADAS-cog13 as the inputs. Along with the MRI features, the model predicted individuals’ cognitive scores and clinical labels over time.…”

Section: Related Workmentioning

confidence: 99%

A Novel Coupling Model of Physiological Degradation and Emotional State for Prediction of Alzheimer’s Disease Progression

Yang

Wang²

2022

Brain Sciences

View full text Add to dashboard Cite

The prediction of Alzheimer’s disease (AD) progression plays a very important role in the early intervention of patients and the improvement of life quality. Cognitive scales are commonly used to assess the patient’s status. However, due to the complicated pathogenesis of AD and the individual differences in AD, the prediction of AD progression is challenging. This paper proposes a novel coupling model (P-E model) that takes into account the processes of physiological degradation and emotional state transition of AD patients. We conduct experiments on synthetic data to validate the effectiveness of the proposed P-E model. Next, we conduct experiments on 134 subjects with more than 10 follow-ups from the Alzheimer’s Disease Neuroimaging Initiative. The prediction performance of the P-E model is significantly better than other state-of-the-art methods, which achieves the mean squared error of 7.137 ± 0.035. The experimental results show that the P-E model can well characterize the non-monotonic properties of AD cognitive data and can also have a good predictive ability for time series data with individual differences.

show abstract

“…Although deep learning models have attested to remarkable performance in predicting AD progression using regular and complete observed samples, they are often hindered by sparse or irregular data in genuine clinical settings. Previous studies aiming to resolve this limitation have proposed several imputation techniques to generate complete data by filling in the missing values [4]- [6]. A novel and intriguing strategy for addressing irregularly sampled time-series data is through ordinary differential equations (ODEs) [7]- [11].…”

Section: Introductionmentioning

confidence: 99%

Deep Geometrical Learning for Alzheimer’s Disease Progression Modeling

Jeong

Jung

Sohn

et al. 2022

2022 IEEE International Conference on Data Mining (ICDM)

Self Cite

View full text Add to dashboard Cite

Deep recurrent model for individualized prediction of Alzheimer’s disease progression

Cited by 39 publications

References 43 publications

Towards better Interpretable and Generalizable AD detection using Collective Artificial Intelligence

Towards better Interpretable and Generalizable AD detection using Collective Artificial Intelligence

A Novel Coupling Model of Physiological Degradation and Emotional State for Prediction of Alzheimer’s Disease Progression

Deep Geometrical Learning for Alzheimer’s Disease Progression Modeling

Contact Info

Product

Resources

About