Author name cluster

Mar Tintoré

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

1 author row

YNICL Journal 2023 Journal Article

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

Llucia Coll
Deborah Pareto
Pere Carbonell-Mirabent
Álvaro Cobo-Calvo
Georgina Arrambide
Ángela Vidal-Jordana
Manuel Comabella
Joaquín Castilló

The application of convolutional neural networks (CNNs) to MRI data has emerged as a promising approach to achieving unprecedented levels of accuracy when predicting the course of neurological conditions, including multiple sclerosis, by means of extracting image features not detectable through conventional methods. Additionally, the study of CNN-derived attention maps, which indicate the most relevant anatomical features for CNN-based decisions, has the potential to uncover key disease mechanisms leading to disability accumulation. From a cohort of patients prospectively followed up after a first demyelinating attack, we selected those with T1-weighted and T2-FLAIR brain MRI sequences available for image analysis and a clinical assessment performed within the following six months (N = 319). Patients were divided into two groups according to expanded disability status scale (EDSS) score: ≥3.0 and < 3.0. A 3D-CNN model predicted the class using whole-brain MRI scans as input. A comparison with a logistic regression (LR) model using volumetric measurements as explanatory variables and a validation of the CNN model on an independent dataset with similar characteristics (N = 440) were also performed. The layer-wise relevance propagation method was used to obtain individual attention maps. The CNN model achieved a mean accuracy of 79% and proved to be superior to the equivalent LR-model (77%). Additionally, the model was successfully validated in the independent external cohort without any re-training (accuracy = 71%). Attention-map analyses revealed the predominant role of frontotemporal cortex and cerebellum for CNN decisions, suggesting that the mechanisms leading to disability accrual exceed the mere presence of brain lesions or atrophy and probably involve how damage is distributed in the central nervous system.

Details DOI

YNICL Journal 2022 Journal Article

T1/T2-weighted ratio in multiple sclerosis: A longitudinal study with clinical associations

Mateus Boaventura
Jaume Sastre-Garriga
Aran Garcia-Vidal
Angela Vidal-Jordana
Davide Quartana
René Carvajal
Cristina Auger
Manel Alberich

BACKGROUND: T1w/T2-w ratio has been proposed as a clinically feasible MRI biomarker to assess tissue integrity in multiple sclerosis. However, no data is available in the earliest stages of the disease and longitudinal studies analysing clinical associations are scarce. OBJECTIVE: To describe longitudinal changes in T1-w/T2-w in patients with clinically isolated syndrome (CIS) and multiple sclerosis, and to investigate their clinical associations. METHODS: T1-w/T2-w images were generated and the mean value obtained in the corresponding lesion, normal-appearing grey (NAGM) and white matter (NAWM) masks. By co-registering baseline to follow-up MRI, evolved lesions were assessed; and by placing the mask of new lesions to the baseline study, the pre-lesional tissue integrity was measured. RESULTS: We included 171 CIS patients and 22 established multiple sclerosis patients. In CIS, evolved lesions showed significant T1-w/T2-w increases compared to baseline (+7.6%, P < 0.001). T1-w/T2-w values in new lesions were lower than in pre-lesional tissue (-28.2%, P < 0.001), and pre-lesional tissue was already lower than baseline NAWM (-7.8%, P < 0.001). In CIS at baseline, higher NAGM T1-w/T2-w was associated with multiple sclerosis diagnosis, and longitudinal decreases in NAGM and NAWM T1-w/T2-w were associated with disease activity. In established multiple sclerosis, T1-w/T2-w was inversely correlated with clinical disability and disease duration. CONCLUSION: A decrease in T1-w/T2-w ratio precedes lesion formation. In CIS, higher T1-w/T2-w was associated with multiple sclerosis diagnosis. In established multiple sclerosis, lower T1-w/T2-w values were associated with clinical disability. The possible differential impact of chronic inflammation, iron deposition and demyelination should be considered to interpret these findings.

Details DOI

YNICL Journal 2019 Journal Article

SVM recursive feature elimination analyses of structural brain MRI predicts near-term relapses in patients with clinically isolated syndromes suggestive of multiple sclerosis

Viktor Wottschel
Declan T. Chard
Christian Enzinger
Massimo Filippi
Jette L. Frederiksen
Claudio Gasperini
Antonio Giorgio
Maria A. Rocca

Machine learning classification is an attractive approach to automatically differentiate patients from healthy subjects, and to predict future disease outcomes. A clinically isolated syndrome (CIS) is often the first presentation of multiple sclerosis (MS), but it is difficult at onset to predict who will have a second relapse and hence convert to clinically definite MS. In this study, we thus aimed to distinguish CIS converters from non-converters at onset of a CIS, using recursive feature elimination and weight averaging with support vector machines. We also sought to assess the influence of cohort size and cross-validation methods on the accuracy estimate of the classification. We retrospectively collected 400 patients with CIS from six European MAGNIMS MS centres. Patients underwent brain MRI at onset of a CIS according to local standard-of-care protocols. The diagnosis of clinically definite MS at one-year follow-up was the standard against which the accuracy of the model was tested. For each patient, we derived MRI-based features, such as grey matter probability, white matter lesion load, cortical thickness, and volume of specific cortical and white matter regions. Features with little contribution to the classification model were removed iteratively through an interleaved sample bootstrapping and feature averaging approach. Classification of CIS outcome at one-year follow-up was performed with 2-fold, 5-fold, 10-fold and leave-one-out cross-validation for each centre cohort independently and in all patients together. The estimated classification accuracy across centres ranged from 64.9% to 88.1% using 2-fold cross-validation and from 73% to 92.9% using leave-one-out cross-validation. The classification accuracy estimate was higher in single-centre, smaller data sets than in combinations of data sets, being the lowest when all patients were merged together. Regional MRI features such as WM lesions, grey matter probability in the thalamus and the precuneus or cortical thickness in the cuneus and inferior temporal gyrus predicted the occurrence of a second relapse in patients at onset of a CIS using support vector machines. The increased accuracy estimate of the classification achieved with smaller and single-centre samples may indicate a model bias (overfitting) when data points were limited, but also more homogeneous. We provide an overview of classifier performance from a range of cross-validation schemes to give insight into the variability across schemes. The proposed recursive feature elimination approach with weight averaging can be used both in single- and multi-centre data sets in order to bridge the gap between group-level comparisons and making predictions for individual patients.

Details DOI