Deciphering multiple sclerosis disability with deep learning attention maps on clinical MRI

Coll, Llucia; Pareto, Deborah; Carbonell‐Mirabent, Pere; Cobo‐Calvo, Álvaro; Arrambide, Georgina; Vidal-Jordana, Ángela; Comabella, Manuel; Castilló, Joaquín; Rodríguez‐Acevedo, Breogán; Zabalza, Ana; Galán, Ingrid; Midaglia, Luciana; Nos, Carlos; Salerno, Annalaura; Auger, Cristina; Alberich, Manel; Río, Jordi; Sastre‐Garriga, Jaume; Oliver, Arnau; Montalbán, Xavier; Tintoré, Mar; Lladó, Xavier; Tur, C

doi:10.1016/j.nicl.2023.103376

Cited by 10 publications

(8 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…L. Coll et al predicted a class of multiple sclerosis disability using whole-brain MRI scans as input by a 3D-CNN model, which achieved a mean accuracy of 79% and proved to be superior to the equivalent logistic regression model (77%). The model was also successfully validated in the independent external cohort without any re-training (accuracy = 71%) [81]. Perinatal arterial ischemic stroke has been linked to unfavorable neurological outcomes.…”

Section: Deep Learning Assisted Mrimentioning

confidence: 94%

Deep Learning Aided Neuroimaging and Brain Regulation

Ouyang²,

Yuan³

2023

Sensors

View full text Add to dashboard Cite

Currently, deep learning aided medical imaging is becoming the hot spot of AI frontier application and the future development trend of precision neuroscience. This review aimed to render comprehensive and informative insights into the recent progress of deep learning and its applications in medical imaging for brain monitoring and regulation. The article starts by providing an overview of the current methods for brain imaging, highlighting their limitations and introducing the potential benefits of using deep learning techniques to overcome these limitations. Then, we further delve into the details of deep learning, explaining the basic concepts and providing examples of how it can be used in medical imaging. One of the key strengths is its thorough discussion of the different types of deep learning models that can be used in medical imaging including convolutional neural networks (CNNs), recurrent neural networks (RNNs), and generative adversarial network (GAN) assisted magnetic resonance imaging (MRI), positron emission tomography (PET)/computed tomography (CT), electroencephalography (EEG)/magnetoencephalography (MEG), optical imaging, and other imaging modalities. Overall, our review on deep learning aided medical imaging for brain monitoring and regulation provides a referrable glance for the intersection of deep learning aided neuroimaging and brain regulation.

show abstract

Section: Deep Learning Assisted Mrimentioning

confidence: 94%

Deep Learning Aided Neuroimaging and Brain Regulation

Ouyang²,

Yuan³

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…These studies show the potential of AI algorithms to provide an accurate patient stratification that is both biologically reliable and prognostically meaningful. 42,44 Regarding the studies that have used attention maps, which reflect those anatomical regions that the DL model deems more relevant to make a given DL-based prediction, Eitel et al 11 found that posterior periventricular white matter regions were determinant for the diagnosis of MS. More recently, Coll et al 45 found that the areas identified as most relevant to classify patients into more or less disabled (i.e. EDSS ⩾ 3.0 vs EDSS < 3.0) were the frontotemporal cortex and cerebellum (Figure 5), suggesting that damage in these regions may be key to disability accrual (please see Table 5 for more details).…”

Section: Investigation Of Disease Mechanismsmentioning

confidence: 99%

“…As can be observed, the most relevant brain areas for the DL-based prediction were the frontal and cerebellar cortices. See Coll et al 45 for more details.…”

Section: Investigation Of Disease Mechanismsmentioning

confidence: 99%

Artificial intelligence applied to MRI data to tackle key challenges in multiple sclerosis

Collorone,

Coll,

Lorenzi

et al. 2024

Mult Scler

Self Cite

View full text Add to dashboard Cite

Artificial intelligence (AI) is the branch of science aiming at creating algorithms able to carry out tasks that typically require human intelligence. In medicine, there has been a tremendous increase in AI applications thanks to increasingly powerful computers and the emergence of big data repositories. Multiple sclerosis (MS) is a chronic autoimmune condition affecting the central nervous system with a complex pathogenesis, a challenging diagnostic process strongly relying on magnetic resonance imaging (MRI) and a high and largely unexplained variability across patients. Therefore, AI applications in MS have the great potential of helping us better support the diagnosis, find markers for prognosis to eventually design more powerful randomised clinical trials and improve patient management in clinical practice and eventually understand the mechanisms of the disease. This topical review aims to summarise the recent advances in AI applied to MRI data in MS to illustrate its achievements, limitations and future directions.

show abstract

“…Descubrieron que estas áreas se encontraban en las regiones de la sustancia blanca periventricular posterior 7 . Más recientemente, Coll et al 24 utilizaron mapas de atención derivados por CNN para descubrir las regiones cerebrales que el algoritmo de aprendizaje profundo había considerado más relevantes para la estratificación de personas con EM (n = 319) en discapacitadas (EDSS ≥ 3.0) o no discapacitadas (EDSS < 3.0) utilizando solo una imagen de RM estructural 24 . Su modelo de CNN logró una precisión promedio del 79%, superando a un modelo de regresión logística equivalente (77%).…”

Section: Investigación De Los Mecanismos De La Enfermedadunclassified

“…Los análisis de los mapas de atención (Fig. 2) revelaron el papel predominante de la corteza frontotemporal y el cerebelo en las decisiones de la CNN, lo que sugiere que los mecanismos que conducen a la acumulación de discapacidad podrían estar relacionados con el daño en esas regiones 24 .…”

Section: Investigación De Los Mecanismos De La Enfermedadunclassified

Inteligencia artificial en esclerosis múltiple

Tur,

Collorone

2023

KRANION

View full text Add to dashboard Cite

La inteligencia artificial (IA) es la rama de la ciencia que tiene como objetivo crear algoritmos capaces de llevar a cabo tareas que normalmente requieren inteligencia humana. La medicina ha experimentado un notable aumento en las aplicaciones de la IA gracias a computadoras cada vez más potentes y a la aparición de grandes repositorios de datos. La esclerosis múltiple (EM) es una enfermedad autoinmune crónica que afecta al sistema nervioso central con una patogénesis compleja, un proceso diagnóstico desafiante y una alta variabilidad entre personas, en gran parte inexplicada. Las aplicaciones de la IA en la EM tienen un gran potencial para respaldar mejor el diagnóstico, encontrar marcadores pronósticos y ayudar a comprender los mecanismos de la enfermedad. Esta revisión tiene como objetivo resumir los avances recientes de la IA en la EM para ilustrar sus logros, limitaciones y direcciones futuras.

show abstract

Deciphering multiple sclerosis disability with deep learning attention maps on clinical MRI

Cited by 10 publications

References 48 publications

Deep Learning Aided Neuroimaging and Brain Regulation

Deep Learning Aided Neuroimaging and Brain Regulation

Artificial intelligence applied to MRI data to tackle key challenges in multiple sclerosis

Inteligencia artificial en esclerosis múltiple

Contact Info

Product

Resources

About