Incomplete multi-modal representation learning for Alzheimer’s disease diagnosis

Liu, Yanbei; Fan, Lianxi; Zhang, Changqing; Zhou, Tao; Xiao, Zhitao; Geng, Lei; Shen, Dinggang

doi:10.1016/j.media.2020.101953

Cited by 55 publications

(20 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar to the problems encountered by Liu et al [9], the author is also actively exploring solutions to the problem of incomplete data, such as using semi-supervised learning or unsupervised learning. The authors also notice that the experiment focuses on binary classification, and the task of multiple classification has not been involved, and plan to focus on it in future research.…”

Section: Discussionmentioning

confidence: 98%

“…They proposed a three-stage deep feature learning and fusion framework, and proved the superiority of using multimodality data through experiments. In 2021, for Alzheimers disease diagnosis with incomplete modalities, Liu et al [9] proposed an Auto-Encoder which can complement the missing data in the kernel space. This can help solve the problem of incomplete medical data.…”

Section: Multimodality Diagnosis Of Alzheimer's Diseasementioning

confidence: 99%

See 1 more Smart Citation

Computer-Aided Diagnosis of Alzheimer’s Disease via Deep Learning Models and Radiomics Method

et al. 2021

View full text Add to dashboard Cite

This paper focused on the problem of diagnosis of Alzheimer’s disease via the combination of deep learning and radiomics methods. We proposed a classification model for Alzheimer’s disease diagnosis based on improved convolution neural network models and image fusion method and compared it with existing network models. We collected 182 patients in the ADNI and PPMI database to classify Alzheimer’s disease, and reached 0.906 AUC in training with single modality images, and 0.941 AUC in training with fusion images. This proved the proposed method has better performance in the fusion images. The research may promote the application of multimodal images in the diagnosis of Alzheimer’s disease. Fusion images dataset based on multi-modality images has higher diagnosis accuracy than single modality images dataset. Deep learning methods and radiomics significantly improve the diagnosing accuracy of Alzheimer’s disease diagnosis.

show abstract

Section: Discussionmentioning

confidence: 98%

Section: Multimodality Diagnosis Of Alzheimer's Diseasementioning

confidence: 99%

Computer-Aided Diagnosis of Alzheimer’s Disease via Deep Learning Models and Radiomics Method

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Our model can use multiple nIDPs as supervision targets and can predict unseen nIDPs. Compared to nonlinear approaches (e.g., (Zhang et al, 2012a;Zhou et al, 2020;Liu et al, 2020)), our approach can explicitly discover a low-dimensional linear latent space as new image-derived phenotypes. We performed a comprehensive comparison of SuperBigFLICA with the hand-curated IDPs currently being created by our group on behalf of UK Biobank, and modes of unsupervised BigFLICA, and found a significantly improved performance on predicting nIDPs.…”

Section: Discussionmentioning

confidence: 99%

“…Various studies have proposed (semi-)supervised approaches for IDP discovery, e.g., Qi et al (2017) developed a multimodal fusion with reference approach and applied it to find multimodal modes related to schizophrenia (Sui et al, 2018) and major depressive disorder (Qi et al, 2018). Another line of research focused on complex nonlinear approaches, such as multiple kernel learning (Zhang et al, 2012a;Zhou et al, 2020;Liu et al, 2020), graph-based transductive learning (Wang et al, 2017) and neural networks such as multilayer perceptrons (Lu et al, 2018;Lee et al, 2019), which proved successful in predicting neurological disorders such as Alzheimer's disease. However, two caveats still exist in the above approaches.…”

Section: Introductionmentioning

confidence: 99%

Supervised Phenotype Discovery from Multimodal Brain Imaging

Gong

Bai

Zheng

et al. 2021

Preprint

View full text Add to dashboard Cite

Data-driven discovery of image-derived phenotypes (IDPs) from large-scale multimodal brain imaging data has enormous potential for neuroscientific and clinical research by linking IDPs to subjects' demographic, behavioural, clinical and cognitive measures (i.e., non-imaging derived phenotypes or nIDPs). However, current approaches are primarily based on unsupervised approaches, without use of information in nIDPs. In this paper, we proposed Supervised BigFLICA (SuperBigFLICA), a semi-supervised, multimodal, and multi-task fusion approach for IDP discovery, which simultaneously integrates information from multiple imaging modalities as well as multiple nIDPs. SuperBigFLICA is computationally efficient and largely bypasses the need for parameter tuning. Using the UK Biobank brain imaging dataset with around 40,000 subjects and 47 modalities, along with more than 17,000 nIDPs, we showed that SuperBigFLICA enhances the prediction power of nIDPs, benchmarked against IDPs derived by conventional expert-knowledge and unsupervised-learning approaches (with average nIDP prediction accuracy improvements of up to 46%). It also enables learning of generic imaging features that can predict new nIDPs. Further empirical analysis of the SuperBigFLICA algorithm demonstrates its robustness in different prediction tasks and the ability to derive biologically meaningful IDPs in predicting health outcomes and cognitive nIDPs, such as fluid intelligence and hypertension scores.

show abstract

“…Measures for that have been proposed and applied to scientific and engineering disciplines. We actually found a large number of such applications by a survey for only the last 5 years, some of which are about the following: Medicine on cancer, Alzheimer's disease, and Covid-19 [1]- [3]. Brain science and engineering using electroencephalogram, electromyogram, and so on [4], [5].…”

Section: A Background Of Variable Dependence Detectionmentioning

confidence: 99%

NNR-GL: A Measure to Detect Co-Nonlinearity Based on Neural Network Regression Regularized by Group Lasso

et al. 2021

View full text Add to dashboard Cite

For finding keys to understand and elucidate a phenomenon, it is essential to detect dependences among variables, and so measures for that have been proposed. Correlation coefficient and its variants are most common, but they only detect a linear dependence (co-linearity) between two variables. Some recent measures can detect a nonlinear dependence (co-nonlinearity) by means of kernelization or segmentation. They are supposed to handle two variables only and open to discussion with regard to performance in detection and difficulty in setup. There is room for a novel measure based on Neural Networks (NNs), since usual NNs aim at prediction but not at variable dependence detection. For the high-performance detection of co-nonlinearities among multi variables, we propose a measure called NNR-GL based on Neural Network Regression (NNR) regularized by Group Lasso (GL). NNR-GL embodies the detection through multi-input single-output regression by NNR and regularization on the input layer by GL. NNR-GL then calculates how strong the detected co-nonlinearities are by unifying the regression performance and the weights on input variables. We conducted experiments using artificial data to examine the behaviors and fundamental effectiveness of NNR-GL. The performance was estimated by a comprehensive detection performance criterion (CDP-AUC in short), which is the mean of area under curves representing true positive and true negative detections. NNR-GL achieved the values of CDP-AUC from 0.7472 to 0.9681, where 0 means complete failure and 1 means complete success in detection. These values were consistently higher than those from 0.5972 to 0.9259 of the conventional measures for all the different conditions of dependence, data size, and noise rate. Consequently, the effectiveness and robustness of NNR-GL were clearly confirmed.

show abstract

Incomplete multi-modal representation learning for Alzheimer’s disease diagnosis

Cited by 55 publications

References 27 publications

Computer-Aided Diagnosis of Alzheimer’s Disease via Deep Learning Models and Radiomics Method

Computer-Aided Diagnosis of Alzheimer’s Disease via Deep Learning Models and Radiomics Method

Supervised Phenotype Discovery from Multimodal Brain Imaging

NNR-GL: A Measure to Detect Co-Nonlinearity Based on Neural Network Regression Regularized by Group Lasso

Contact Info

Product

Resources

About