Deep learning reveals Alzheimer's disease onset in MCI subjects: Results from an international challenge

Amoroso, Nicola; Diacono, Domenico; Fanizzi, Annarita; Rocca, Marianna La; Lombardi, Angela; Guaragnella, Cataldo; Bellotti, R.; Tangaro, Sabina; Initiative, Alzheimer’s Disease Neuroimaging

doi:10.1016/j.jneumeth.2017.12.011

Cited by 112 publications

(55 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the different data, processes, assessment and classification techniques used do not always allow a completely fair comparison. This is why it is important to organize International challenges [ 12 , 31 ] to validate different methodologies with a common set of data and evaluation procedures. Apart the differences due to the previously enclosed reasons, in Table 3 it can be observed that our performances are comparable with the state-of-the-art [ 32 , 33 ] although the optimization of the diagnostic accuracy was not the primary goal of this work.…”

Section: Discussionmentioning

confidence: 99%

Salient networks: a novel application to study Alzheimer disease

et al. 2018

Self Cite

View full text Add to dashboard Cite

BackgroundExtracting fundamental information from data, thus underlining hidden structures or removing noisy information, is one of the most important aims in different scientific fields especially in biological and medical sciences. In this article, we propose an innovative complex network application able to identify salient links for detecting the effect of Alzheimer’s disease on brain connectivity. We first build a network model of brain connectivity from structural Magnetic Resonance Imaging (MRI) data, then we study salient networks retrieved from the original ones.ResultsInvestigating informative power of the salient skeleton features in combination with those of the original networks we obtain an accuracy of for the distinction of Alzheimer disease (AD) patients from normal controls (NC). This performance significantly overcomes accuracy of the original network features. Moreover salient networks are able to correctly discriminate normal controls (NC) from AD patients and NC from subjects with mild cognitive impairment that will convert to AD (cMCI). These evaluations, performed on an independent dataset, give an accuracy of and respectively for NC-AD and NC-cMCI classifications. Therefore, most of the informative content of the original networks is kept after the 92 and 82 reduction respectively in the number of nodes and links. In addition, the present approach, applied to a publicly available MRI dataset from the Alzheimer Disease Neuroimaging Initiative (ADNI), brings out also some interesting aspects related to the topologies and hubs of the networks.ConclusionsThe experimental results demonstrate how salient networks can highlight important brain network characteristics and structural pathological changes, while reducing considerably data complexity and computational requirements.

show abstract

Section: Discussionmentioning

confidence: 99%

Salient networks: a novel application to study Alzheimer disease

et al. 2018

Self Cite

View full text Add to dashboard Cite

show abstract

“…Deep neural networks (DNNs) are commonly used to classify data in different fields (LeCun et al, 2015 ; Amoroso et al, 2018 ; Wang et al, 2018 ). DNNs are non-linear methods that allow the learning of complex patterns among features, thus providing a complex non-linear classification of input data (Graepel et al, 2010 ).…”

Section: The Application Of Deep Learning Methods In Psychologymentioning

confidence: 99%

“…Different machine learning methods, such as the random forest algorithm, allow researchers to find best features/variables to explain differences among two or groups of participants (Amoroso et al, 2018 ). There are several ways to conduct feature selection.…”

Section: The Application Of Deep Learning Methods In Psychologymentioning

confidence: 99%

Applying Big Data Methods to Understanding Human Behavior and Health

Moustafa

Diallo

Amoroso

et al. 2018

Front. Comput. Neurosci.

Self Cite

View full text Add to dashboard Cite

“…Developing computer aided diagnosis systems is desirable, as they can provide a non-invasive, low-cost tool-support to the traditional neuropsychological assessment performed by expert clinicians. Moreover, a great variety of state-of-the-art machine learning approaches, has shown outstanding performance for early detection and automated classification of Alzheimer's disease (AD) [12,13].Recently, we investigated the usefulness in this context of an uncommon graph measure, that is communicability. Communicability quantifies the ease of communications between node pairs in a network by considering not only the shortest path connecting them, but all possible available routes [14].…”

mentioning

confidence: 99%

mentioning

confidence: 99%

Machine Learning and DWI Brain Communicability Networks for Alzheimer’s Disease Detection

et al. 2020

Self Cite

View full text Add to dashboard Cite

Signal processing and machine learning techniques are changing the clinical practice based on medical imaging from many perspectives. A major topic is related to (i) the development of computer aided diagnosis systems to provide clinicians with novel, non-invasive and low-cost support-tools, and (ii) to the development of new methodologies for the analysis of biomedical data for finding new disease biomarkers. Advancements have been recently achieved in the context of Alzheimer’s disease (AD) diagnosis through the use of diffusion weighted imaging (DWI) data. When combined with tractography algorithms, this imaging modality enables the reconstruction of the physical connections of the brain that can be subsequently investigated through a complex network-based approach. A graph metric particularly suited to describe the disruption of the brain connectivity due to AD is communicability. In this work, we develop a machine learning framework for the classification and feature importance analysis of AD based on communicability at the whole brain level. We fairly compare the performance of three state-of-the-art classification models, namely support vector machines, random forests and artificial neural networks, on the connectivity networks of a balanced cohort of healthy control subjects and AD patients from the ADNI database. Moreover, we clinically validate the information content of the communicability metric by performing a feature importance analysis. Both performance comparison and feature importance analysis provide evidence of the robustness of the method. The results obtained confirm that the whole brain structural communicability alterations due to AD are a valuable biomarker for the characterization and investigation of pathological conditions.

show abstract

Deep learning reveals Alzheimer's disease onset in MCI subjects: Results from an international challenge

Abstract: DNNs reach a classification accuracy significantly higher than other machine learning strategies; on the other hand, fuzzy logic is particularly accurate with cMCI, suggesting a combination of these approaches could lead to interesting future perspectives.

Cited by 112 publications

References 29 publications

Salient networks: a novel application to study Alzheimer disease

Salient networks: a novel application to study Alzheimer disease

Applying Big Data Methods to Understanding Human Behavior and Health

Machine Learning and DWI Brain Communicability Networks for Alzheimer’s Disease Detection

Contact Info

Product

Resources

About