A machine learning approach to explore cognitive signatures in patients with temporo-mesial epilepsy

Roger, Elise; Torlay, Laurent; Gardette, Jeremy; Mosca, Chrystèle; Banjac, Sonja; Minotti, Lorella; Kahane, Philippe; Baciu, Monica

doi:10.1016/j.neuropsychologia.2020.107455

Cited by 19 publications

(12 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At rest, patients present a significant functional disturbance of major connector and provincial hubs (namely IFG and hippocampi), essential for relational binding (L∪M neuroperations; see Figure 5). These functional disturbances are indeed specifically related to poor performance in cognitive indicators requiring the associative linking of verbal information (see our previous works on TLE patients: Banjac et al, 2021;Roger et al, 2019Roger et al, , 2020. Moreover, the spatial pattern of functional alterations largely coincides with…”

Section: Figure 4: Features and Neural Foundation Of The L∪m Frameworkmentioning

confidence: 74%

Missing links: the functional unification of language and memory (L∪M)

Roger¹,

Banjac²,

Schotten³

et al. 2021

Preprint

View full text Add to dashboard Cite

The field of neurocognition is currently undergoing a significant change of perspective. Traditional neurocognitive models evolved into an integrative and dynamic vision of cognitive functioning. Dynamic integration assumes an interaction between cognitive domains traditionally considered to be distinct. Language and declarative memory are regarded as separate functions supported by different neural systems. However, they also share anatomical structures (notably, the inferior frontal gyrus, the supplementary motor area, the superior and middle temporal gyrus, and the hippocampal complex) and cognitive processes (such as semantic and working memory) that merge to endorse our quintessential daily lives. We propose a new model, "L∪M" (i.e., Language/union/Memory), that considers these two functions interactively. We fractionated language and declarative memory into three cognitive dimensions, Embodiment-Formulation-Internalization, that communicate reciprocally. We formalized their interactions at the brain level with a connectivity-based approach. This new taxonomy overcomes the modular view of cognitive functioning and reconciles functional specialization with plasticity in neurological disorders.

show abstract

Section: Figure 4: Features and Neural Foundation Of The L∪m Frameworkmentioning

confidence: 74%

Missing links: the functional unification of language and memory (L∪M)

Roger¹,

Banjac²,

Schotten³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…We included TLE patients with left (LTLE) and right (RTLE) origin of seizures. Since previous studies showed that these patients can differ regarding cognitive functioning and neural organization ( Besson et al, 2014 , de Campos et al, 2016 , Phuong et al, 2021 , Roger et al, 2020b ), before conducting the main analyses planned in this study, we tested whether the LTLE and RTLE patients in our sample significantly differed regarding their clinical characteristics (age, epilepsy duration, number of AEDs, hippocampal atrophy and gender), hippocampal volume, neuropsychological performance. We did not flip the images of patients in the L-R direction in line with recommendations ( Lee et al, 2018 ) since previous research found significant asymmetries in functional connectivity between two hemispheres mirrored over the longitudinal fissure ( Raemaekers et al, 2018 ).…”

Section: Methodsmentioning

confidence: 99%

“…Recent neurocognitive frameworks suggest that human behaviors are enabled by complex interactions between cognitive functions, instead of isolated involvement of each of them ( Kellermann et al, 2016 , Roger et al, 2020b , Van Der Maas et al, 2006 ). The evidence of integration can be found in everyday life such as recalling an old episode ( Larsen et al, 2002 , Park et al, 2011 ) or maintaining a conversation by relying on what is called the common ground ( Clark & Marshall, 1981 ).…”

Section: Introductionmentioning

confidence: 99%

“…When formulating an utterance during a conversation, interlocutors are relying on background information that they believe is shared by the participants in the conversation ( Stalnaker, 2002 ). Hence, language must rely on the declarative memory and previous studies described a wide language-and-memory network (LMN) ( Banjac et al, 2020 , Roger et al, 2020a , Roger et al, 2020b ). This perspective is in line with the current transition towards new integrative and dynamic neurocognitive and connectomic models ( Dick et al, 2014 , Garcia-Ramos et al, 2016 , Herbet and Duffau, 2020 , Kellermann et al, 2016 , Zamora-Lopez et al, 2011 , Zhou et al, 2020 ).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Reconfiguration dynamics of a language-and-memory network in healthy participants and patients with temporal lobe epilepsy

Banjac

Roger

Pichat

et al. 2021

NeuroImage: Clinical

View full text Add to dashboard Cite

Highlights Language and memory interact as a composite function based on the LMN network. LMN configuration is state- and condition-dependent (healthy–pathological). LMN reconfiguration is reflected in network segregation and integration changes. LMN reconfiguration in HC depends on flexibility of key language and memory regions. LMN reconfiguration in TLE shows increased segregation and closer modules.

show abstract

“…The main goal of [126] was to discover the cognitive signatures of mTLE patients also with lateralization information. For this, SVM and XGBoost were used to classify the extracted features to either left or right.…”

Section: ) Ml-based Approaches In Epilepsy Diagnosismentioning

confidence: 99%

Machine Learning and Deep Learning Approaches for Brain Disease Diagnosis: Principles and Recent Advances

et al. 2021

View full text Add to dashboard Cite

Brain is the controlling center of our body. With the advent of time, newer and newer brain diseases are being discovered. Thus, because of the variability of brain diseases, existing diagnosis or detection systems are becoming challenging and are still an open problem for research. Detection of brain diseases at an early stage can make a huge difference in attempting to cure it. In recent years, the use of artificial intelligence (AI) is surging through all spheres of science, and no doubt, it is revolutionizing the field of neurology. Application of AI in medical science has made brain disease prediction and detection more accurate and precise. In this study, we present a review on recent machine learning and deep learning approaches in detecting four brain diseases such as Alzheimer's disease (AD), brain tumor, epilepsy, and Parkinson's disease. 147 recent articles on four brain diseases are reviewed considering diverse machine learning and deep learning approaches, modalities, datasets etc. Twenty-two datasets are discussed which are used most frequently in the reviewed articles as a primary source of brain disease data. Moreover, a brief overview of different feature extraction techniques that are used in diagnosing brain diseases is provided. Finally, key findings from the reviewed articles are summarized and a number of major issues related to machine learning/deep learning-based brain disease diagnostic approaches are discussed. Through this study, we aim at finding the most accurate technique for detecting different brain diseases which can be employed for future betterment. INDEX TERMS Alzheimer's disease, brain tumor, deep learning, epilepsy, Parkinson's disease, machine learning NOMENCLATURE The most commonly used abbreviations in this survey are summarized in Table 1.

show abstract

A machine learning approach to explore cognitive signatures in patients with temporo-mesial epilepsy

Cited by 19 publications

References 60 publications

Missing links: the functional unification of language and memory (L∪M)

Missing links: the functional unification of language and memory (L∪M)

Reconfiguration dynamics of a language-and-memory network in healthy participants and patients with temporal lobe epilepsy

Machine Learning and Deep Learning Approaches for Brain Disease Diagnosis: Principles and Recent Advances

Contact Info

Product

Resources

About