Decoding brain functional connectivity implicated in AD and MCI

Gupta, Sukrit; Chan, Yi Hao; Rajapakse, Jagath C.

doi:10.1101/697003

Cited by 3 publications

(6 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This issue is acute in the case of medical imaging applications where there are issues with scanner variability, scan acquisition settings, subject demography, and heterogeneity in disease characteristics across subjects. Therefore, it is important to decode the trained network using model interpretability approaches and validate the important features learned by the network [ 126 ]. It also becomes important to report testing results with an external dataset whose samples were not used for training.…”

Section: Challenges and Conclusionmentioning

confidence: 99%

3D Deep Learning on Medical Images: A Review

Singh

Wang

Gupta

et al. 2020

Sensors

Self Cite

389

150

View full text Add to dashboard Cite

The rapid advancements in machine learning, graphics processing technologies and the availability of medical imaging data have led to a rapid increase in the use of deep learning models in the medical domain. This was exacerbated by the rapid advancements in convolutional neural network (CNN) based architectures, which were adopted by the medical imaging community to assist clinicians in disease diagnosis. Since the grand success of AlexNet in 2012, CNNs have been increasingly used in medical image analysis to improve the efficiency of human clinicians. In recent years, three-dimensional (3D) CNNs have been employed for the analysis of medical images. In this paper, we trace the history of how the 3D CNN was developed from its machine learning roots, we provide a brief mathematical description of 3D CNN and provide the preprocessing steps required for medical images before feeding them to 3D CNNs. We review the significant research in the field of 3D medical imaging analysis using 3D CNNs (and its variants) in different medical areas such as classification, segmentation, detection and localization. We conclude by discussing the challenges associated with the use of 3D CNNs in the medical imaging domain (and the use of deep learning models in general) and possible future trends in the field.

show abstract

Section: Challenges and Conclusionmentioning

confidence: 99%

3D Deep Learning on Medical Images: A Review

Singh

Wang

Gupta

et al. 2020

Sensors

Self Cite

389

150

View full text Add to dashboard Cite

show abstract

“…A decoder can identify a subset of distinguishing input features and weights that are important to classify samples. We proposed a brain decoding strategy in [16], where we obtained the salience scores for input features and hidden layer nodes. In the proposed scheme, a fraction µ of nodes with the lowest salience scores c k from layers k ∈ {0, .…”

Section: Lean: Layerwise Elimination Of Accessory Nodesmentioning

confidence: 99%

“…We demonstrated this approach in [16] for the first time by using feedforward DNN. We successfully adopted DeepLIFT in decoding brain functional connectivity in [16], which efficiently computes salience scores for input features in a single pass and then recursively eliminate irrelevant. Such an approach only focuses on input features and does not optimize the DNN architecture.…”

Section: Decoding the Brain Functional Connectome Associated With Bramentioning

confidence: 99%

“…In recent works [16], the authors used feature salience scores to remove less salient features. In order to find salient features, DeepLIFT [44] was used to compute salience scores of both input features and hidden layer nodes.…”

Section: Introductionmentioning

confidence: 99%

“…Deep learning techniques make no assumptions about application specific a priori knowledge and therefore give consistent and unbiased decoding based on neuroimaging data. Recent applications of neural networks on neuroimaging data have derived the importance of input features in the classification task to uncover biomarkers for neurological diseases [16,19] or reveal task-related brain functional modulations [27]. Identifying disease-specific biomarkers aids in building models and classifying and predicting the progression or occurrence of unknown diseases in individuals.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Obtaining leaner deep neural networks for decoding brain functional connectome in a single shot

Gupta

Chan

Rajapakse

2020

Preprint

Self Cite

View full text Add to dashboard Cite

Neuroscientific knowledge points to the presence of redundancy in the correlations of brain's functional activity. These redundancies can be removed to mitigate the problem of overfitting when deep neural network (DNN) models are used to classify neuroimaging datasets. We propose an algorithm that removes insignificant nodes of DNNs in a layerwise manner and then adds a subset of correlated features in a single shot. When performing experiments with functional MRI datasets for classifying patients from healthy controls, we were able to obtain simpler and more generalizable DNNs. The obtained DNNs maintained a similar performance as the full network with only around 2% of the initial trainable parameters. Further, we used the trained network to identify salient brain regions and connections from functional connectome for multiple brain disorders. The identified biomarkers were found to closely correspond to previously known disease biomarkers. The proposed methods have cross-modal applications in obtaining leaner DNNs that seem to fit the data better. The corresponding code is available at https: //github.com/SCSE-Biomedical-Computing-Group/LEAN_CLIP. Keywords: Alzheimer's disease, attention deficit hyperactivity disorder, brain decoding, deep neural networks, feature selection, major depressive disorder, mild cognitive impairment 1 These authors contributed equally. 2 Data used in preparation of this article were obtained from the ADNI database (adni. loni.usc.edu). As such, the investigators within the ADNI contributed to the design and implementation of ADNI and/or provided data but did not participate in analysis or writing of this report. A complete list of the ADNI investigators can be found at

show abstract

Sparse Deep Neural Network for Encoding and Decoding the Structural Connectome

Singh,

Gupta,

Rajapakse

2024

IEEE J. Transl. Eng. Health Med.

View full text Add to dashboard Cite

Brain state classification by applying deep learning techniques on neuroimaging data has become a recent topic of research. However, unlike domains where the data is low dimensional or there are large number of available training samples, neuroimaging data is high dimensional and has few training samples. To tackle these issues, we present a sparse feedforward deep neural architecture for encoding and decoding the structural connectome of the human brain. We use a sparsely connected element-wise multiplication as the first hidden layer and a fixed transform layer as the output layer. The number of trainable parameters and the training time is significantly reduced compared to feedforward networks. We demonstrate superior performance of this architecture in encoding the structural connectome implicated in Alzheimer’s disease (AD) and Parkinson’s disease (PD) from DTI brain scans. For decoding, we propose recursive feature elimination (RFE) algorithm based on DeepLIFT, layer-wise relevance propagation (LRP), and Integrated Gradients (IG) algorithms to remove irrelevant features and thereby identify key biomarkers associated with AD and PD. We show that the proposed architecture reduces 45.1% and 47.1% of the trainable parameters compared to a feedforward DNN with an increase in accuracy by 2.6 % and 3.1% for cognitively normal (CN) vs AD and CN vs PD classification, respectively. We also show that the proposed RFE method leads to a further increase in accuracy by 2.1% and 4% for CN vs AD and CN vs PD classification, while removing approximately 90% to 95% irrelevant features. Furthermore, we argue that the biomarkers (i.e., key brain regions and connections) identified are consistent with previous literature. We show that relevancy score-based methods can yield high discriminative power and are suitable for brain decoding. We also show that the proposed approach led to a reduction in the number of trainable network parameters, an increase in classification accuracy, and a detection of brain connections and regions that were consistent with earlier studies.

show abstract

Decoding brain functional connectivity implicated in AD and MCI

Cited by 3 publications

References 14 publications

3D Deep Learning on Medical Images: A Review

3D Deep Learning on Medical Images: A Review

Obtaining leaner deep neural networks for decoding brain functional connectome in a single shot

Sparse Deep Neural Network for Encoding and Decoding the Structural Connectome

Contact Info

Product

Resources

About