Interpretable Graph Convolutional Network Of Multi-Modality Brain Imaging For Alzheimer’s Disease Diagnosis

Zhou, Houliang; He, Lifang; Shen, Li; Chen, Brian

doi:10.1109/isbi52829.2022.9761449

Cited by 19 publications

(9 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For future studies, graph neural networks can be used to replace LR for the FC-based classification (Lei et al, 2022;Zhou et al, 2020) since they consider the functional network as a whole thus better preserving spatial information. However, this will also require more advanced explainability methods to interpret the classification results (Ying et al, 2019;Zhou et al, 2022).…”

Section: Discussionmentioning

confidence: 99%

Subject classification and cross-time prediction based on functional connectivity and white matter microstructure features in a rat model of Alzheimer’s using machine learning

Diao

Jelescu

2023

Preprint

View full text Add to dashboard Cite

Background: The pathological process of Alzheimer's disease (AD) typically takes up decades from onset to clinical symptoms. Early brain changes in AD include MRI-measurable features such as aItered functional connectivity (FC) and white matter degeneration. The ability of these features to discriminate between subjects without a diagnosis, or their prognostic value, is however not established. Methods: The main trigger mechanism of AD is still debated, although impaired brain glucose metabolism is taking an increasingly central role. Here we used a rat model of sporadic AD, based on impaired brain glucose metabolism induced by an intracerebroventricular injection of streptozotocin (STZ). We characterized alterations in FC and white matter microstructure longitudinally using functional and diffusion MRI. Those MRI-derived measures were used to classify STZ from control rats using machine learning, and the importance of each individual measure was quantified using explainable artificial intelligence methods. Results: Overall, combining all the FC and white matter metrics in an ensemble way was the best strategy to discriminate STZ rats, with a consistent accuracy over 0.85. However, the best accuracy early on was achieved using white matter microstructure features, and later on using FC. This suggests that consistent damage in white matter in the STZ group might precede FC. For cross-timepoint prediction, microstructure features also had the highest performance while, in contrast, that of FC was reduced by its dynamic pattern which shifted from early hyperconnectivity to late hypoconnectivity. Conclusions: Our study highlights the MRI-derived measures that best discriminate STZ vs control rats early in the course of the disease, with potential translation to humans.

show abstract

Section: Discussionmentioning

confidence: 99%

Subject classification and cross-time prediction based on functional connectivity and white matter microstructure features in a rat model of Alzheimer’s using machine learning

Diao

Jelescu

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Finding a reliable predictor of neurophysiological worsening (i.e., clinical behavioral observations or self-reported observations) has become critical in neuropsychiatry. A promising tool seems to be the identification and classification of AD using multi-modality neuroimaging data and an artificial intelligence approach [ 115 , 116 , 117 ]. Chen et al [ 115 ] provided an excellent overview of various types of machine learning and multimodal data fusion, as well as conceptual and practical challenges and opportunities for future psychiatric disease research.…”

Section: Neuroimaging In the Cognitive Impairmentmentioning

confidence: 99%

“…Chen et al [ 115 ] provided an excellent overview of various types of machine learning and multimodal data fusion, as well as conceptual and practical challenges and opportunities for future psychiatric disease research. The deep learning method has been sufficiently applied directly in AD using (1) resting-state electroencephalography [ 116 ], (2) a convolutional network of multi-modality brain imaging (i.e., MRI, 18 F-FDG PET, 18 F-florbetapir PET) [ 117 ], or by using (3) automated MRI-based software tools to assess entorhinal cortex thickness, hippocampal volume, and supramarginal gyrus thickness [ 118 ], all of which have high sensitivity and specificity for differentiating MCI from AD. Based on the multi-modal artificial machine learning algorithm, several non-unambiguous (i.e., non-specific, non-predictive, or non-distinguishable) neurological examinations ( Table 2 ) have the potential to become meaningful.…”

Section: Neuroimaging In the Cognitive Impairmentmentioning

confidence: 99%

Imaging Methods Applicable in the Diagnostics of Alzheimer’s Disease, Considering the Involvement of Insulin Resistance

Hnilicová

Kantorová

Šutovský

et al. 2023

IJMS

View full text Add to dashboard Cite

Alzheimer’s disease (AD) is an incurable neurodegenerative disease and the most frequently diagnosed type of dementia, characterized by (1) perturbed cerebral perfusion, vasculature, and cortical metabolism; (2) induced proinflammatory processes; and (3) the aggregation of amyloid beta and hyperphosphorylated Tau proteins. Subclinical AD changes are commonly detectable by using radiological and nuclear neuroimaging methods such as magnetic resonance imaging (MRI), computed tomography (CT), positron emission tomography (PET), and single-photon emission computed tomography (SPECT). Furthermore, other valuable modalities exist (in particular, structural volumetric, diffusion, perfusion, functional, and metabolic magnetic resonance methods) that can advance the diagnostic algorithm of AD and our understanding of its pathogenesis. Recently, new insights into AD pathoetiology revealed that deranged insulin homeostasis in the brain may play a role in the onset and progression of the disease. AD-related brain insulin resistance is closely linked to systemic insulin homeostasis disorders caused by pancreas and/or liver dysfunction. Indeed, in recent studies, linkages between the development and onset of AD and the liver and/or pancreas have been established. Aside from standard radiological and nuclear neuroimaging methods and clinically fewer common methods of magnetic resonance, this article also discusses the use of new suggestive non-neuronal imaging modalities to assess AD-associated structural changes in the liver and pancreas. Studying these changes might be of great clinical importance because of their possible involvement in AD pathogenesis during the prodromal phase of the disease.

show abstract

“…Traditionally, hand-crafted features based on prior expert knowledge, such as volume, activation, or attenuation of regions of interest are extracted to overcome the high dimensionality of imaging data. IDPs from brain imaging modalities have shown strong associations with morbidity and genetic risk for Alzheimer's disease [14][15][16]. Studies have also explored IDPs from computed tomography (CT) scans and magnetic resonance imaging and their associations with metabolic-related diseases [17][18][19].…”

Section: Introductionmentioning

confidence: 99%

Deep learning imaging phenotype can classify metabolic syndrome and is predictive of cardiometabolic disorders

Leiby,

Lee,

Shivakumar

et al. 2024

J Transl Med

View full text Add to dashboard Cite

Background Cardiometabolic disorders pose significant health risks globally. Metabolic syndrome, characterized by a cluster of potentially reversible metabolic abnormalities, is a known risk factor for these disorders. Early detection and intervention for individuals with metabolic abnormalities can help mitigate the risk of developing more serious cardiometabolic conditions. This study aimed to develop an image-derived phenotype (IDP) for metabolic abnormality from unenhanced abdominal computed tomography (CT) scans using deep learning. We used this IDP to classify individuals with metabolic syndrome and predict future occurrence of cardiometabolic disorders. Methods A multi-stage deep learning approach was used to extract the IDP from the liver region of unenhanced abdominal CT scans. In a cohort of over 2,000 individuals the IDP was used to classify individuals with metabolic syndrome. In a subset of over 1,300 individuals, the IDP was used to predict future occurrence of hypertension, type II diabetes, and fatty liver disease. Results For metabolic syndrome (MetS) classification, we compared the performance of the proposed IDP to liver attenuation and visceral adipose tissue area (VAT). The proposed IDP showed the strongest performance (AUC 0.82) compared to attenuation (AUC 0.70) and VAT (AUC 0.80). For disease prediction, we compared the performance of the IDP to baseline MetS diagnosis. The models including the IDP outperformed MetS for type II diabetes (AUCs 0.91 and 0.90) and fatty liver disease (AUCs 0.67 and 0.62) prediction and performed comparably for hypertension prediction (AUCs of 0.77). Conclusions This study demonstrated the superior performance of a deep learning IDP compared to traditional radiomic features to classify individuals with metabolic syndrome. Additionally, the IDP outperformed the clinical definition of metabolic syndrome in predicting future morbidities. Our findings underscore the utility of data-driven imaging phenotypes as valuable tools in the assessment and management of metabolic syndrome and cardiometabolic disorders.

show abstract

Interpretable Graph Convolutional Network Of Multi-Modality Brain Imaging For Alzheimer’s Disease Diagnosis

Cited by 19 publications

References 7 publications

Subject classification and cross-time prediction based on functional connectivity and white matter microstructure features in a rat model of Alzheimer’s using machine learning

Subject classification and cross-time prediction based on functional connectivity and white matter microstructure features in a rat model of Alzheimer’s using machine learning

Imaging Methods Applicable in the Diagnostics of Alzheimer’s Disease, Considering the Involvement of Insulin Resistance

Deep learning imaging phenotype can classify metabolic syndrome and is predictive of cardiometabolic disorders

Contact Info

Product

Resources

About