TY - JOUR
T1 - RimNet
T2 - A deep 3D multimodal MRI architecture for paramagnetic rim lesion assessment in multiple sclerosis
AU - Barquero, Germán
AU - La Rosa, Francesco
AU - Kebiri, Hamza
AU - Lu, Po Jui
AU - Rahmanzadeh, Reza
AU - Weigel, Matthias
AU - Fartaria, Mário João
AU - Kober, Tobias
AU - Théaudin, Marie
AU - Du Pasquier, Renaud
AU - Sati, Pascal
AU - Reich, Daniel S.
AU - Absinta, Martina
AU - Granziera, Cristina
AU - Maggi, Pietro
AU - Bach Cuadra, Meritxell
N1 - Publisher Copyright:
© 2020 The Author(s)
PY - 2020
Y1 - 2020
N2 - Objectives: In multiple sclerosis (MS), the presence of a paramagnetic rim at the edge of non-gadolinium-enhancing lesions indicates perilesional chronic inflammation. Patients featuring a higher paramagnetic rim lesion burden tend to have more aggressive disease. The objective of this study was to develop and evaluate a convolutional neural network (CNN) architecture (RimNet) for automated detection of paramagnetic rim lesions in MS employing multiple magnetic resonance (MR) imaging contrasts. Materials and methods: Imaging data were acquired at 3 Tesla on three different scanners from two different centers, totaling 124 MS patients, and studied retrospectively. Paramagnetic rim lesion detection was independently assessed by two expert raters on T2*-phase images, yielding 462 rim-positive (rim+) and 4857 rim-negative (rim-) lesions. RimNet was designed using 3D patches centered on candidate lesions in 3D-EPI phase and 3D FLAIR as input to two network branches. The interconnection of branches at both the first network blocks and the last fully connected layers favors the extraction of low and high-level multimodal features, respectively. RimNet's performance was quantitatively evaluated against experts’ evaluation from both lesion-wise and patient-wise perspectives. For the latter, patients were categorized based on a clinically relevant threshold of 4 rim+ lesions per patient. The individual prediction capabilities of the images were also explored and compared (DeLong test) by testing a CNN trained with one image as input (unimodal). Results: The unimodal exploration showed the superior performance of 3D-EPI phase and 3D-EPI magnitude images in the rim+/- classification task (AUC = 0.913 and 0.901), compared to the 3D FLAIR (AUC = 0.855, Ps < 0.0001). The proposed multimodal RimNet prototype clearly outperformed the best unimodal approach (AUC = 0.943, P < 0.0001). The sensitivity and specificity achieved by RimNet (70.6% and 94.9%, respectively) are comparable to those of experts at the lesion level. In the patient-wise analysis, RimNet performed with an accuracy of 89.5% and a Dice coefficient (or F1 score) of 83.5%. Conclusions: The proposed prototype showed promising performance, supporting the usage of RimNet for speeding up and standardizing the paramagnetic rim lesions analysis in MS.
AB - Objectives: In multiple sclerosis (MS), the presence of a paramagnetic rim at the edge of non-gadolinium-enhancing lesions indicates perilesional chronic inflammation. Patients featuring a higher paramagnetic rim lesion burden tend to have more aggressive disease. The objective of this study was to develop and evaluate a convolutional neural network (CNN) architecture (RimNet) for automated detection of paramagnetic rim lesions in MS employing multiple magnetic resonance (MR) imaging contrasts. Materials and methods: Imaging data were acquired at 3 Tesla on three different scanners from two different centers, totaling 124 MS patients, and studied retrospectively. Paramagnetic rim lesion detection was independently assessed by two expert raters on T2*-phase images, yielding 462 rim-positive (rim+) and 4857 rim-negative (rim-) lesions. RimNet was designed using 3D patches centered on candidate lesions in 3D-EPI phase and 3D FLAIR as input to two network branches. The interconnection of branches at both the first network blocks and the last fully connected layers favors the extraction of low and high-level multimodal features, respectively. RimNet's performance was quantitatively evaluated against experts’ evaluation from both lesion-wise and patient-wise perspectives. For the latter, patients were categorized based on a clinically relevant threshold of 4 rim+ lesions per patient. The individual prediction capabilities of the images were also explored and compared (DeLong test) by testing a CNN trained with one image as input (unimodal). Results: The unimodal exploration showed the superior performance of 3D-EPI phase and 3D-EPI magnitude images in the rim+/- classification task (AUC = 0.913 and 0.901), compared to the 3D FLAIR (AUC = 0.855, Ps < 0.0001). The proposed multimodal RimNet prototype clearly outperformed the best unimodal approach (AUC = 0.943, P < 0.0001). The sensitivity and specificity achieved by RimNet (70.6% and 94.9%, respectively) are comparable to those of experts at the lesion level. In the patient-wise analysis, RimNet performed with an accuracy of 89.5% and a Dice coefficient (or F1 score) of 83.5%. Conclusions: The proposed prototype showed promising performance, supporting the usage of RimNet for speeding up and standardizing the paramagnetic rim lesions analysis in MS.
KW - Deep learning
KW - Multimodal network
KW - Multiple sclerosis
KW - Paramagnetic rim lesions
KW - Supervised classification
KW - Susceptibility-based MRI
UR - http://www.scopus.com/inward/record.url?scp=85091098475&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85091098475&partnerID=8YFLogxK
U2 - 10.1016/j.nicl.2020.102412
DO - 10.1016/j.nicl.2020.102412
M3 - Article
C2 - 32961401
AN - SCOPUS:85091098475
SN - 2213-1582
VL - 28
JO - NeuroImage: Clinical
JF - NeuroImage: Clinical
M1 - 102412
ER -