TY - JOUR
T1 - GAMER MRI
T2 - Gated-attention mechanism ranking of multi-contrast MRI in brain pathology
AU - Lu, Po Jui
AU - Yoo, Youngjin
AU - Rahmanzadeh, Reza
AU - Galbusera, Riccardo
AU - Weigel, Matthias
AU - Ceccaldi, Pascal
AU - Nguyen, Thanh D.
AU - Spincemaille, Pascal
AU - Wang, Yi
AU - Daducci, Alessandro
AU - La Rosa, Francesco
AU - Bach Cuadra, Meritxell
AU - Sandkühler, Robin
AU - Nael, Kambiz
AU - Doshi, Amish
AU - Fayad, Zahi A.
AU - Kuhle, Jens
AU - Kappos, Ludwig
AU - Odry, Benjamin
AU - Cattin, Philippe
AU - Gibson, Eli
AU - Granziera, Cristina
N1 - Funding Information:
We would like to acknowledge all the patients and healthy controls in this project. This project is supported by Swiss National Funds PZ00P3_154508, PZ00P3_131914 and PP00P3_176984. Francesco La Rosa and Meritxell Bach Cuadra are supported by the European Union's Horizon 2020 research and innovation program under the Marie Sklodowska-Curie project TRABIT (agreement No 765148) and by the Centre d'Imagerie BioMedicale (CIBM). We would also thank the Mount Sinai Hospital for providing the stroke dataset and Basel University Hospital for acquiring the MS dataset. The concepts and information presented in this paper are based on research results and GAMER MRI is not commercially available.
Funding Information:
We would like to acknowledge all the patients and healthy controls in this project. This project is supported by Swiss National Funds PZ00P3_154508, PZ00P3_131914 and PP00P3_176984. Francesco La Rosa and Meritxell Bach Cuadra are supported by the European Union's Horizon 2020 research and innovation program under the Marie Sklodowska-Curie project TRABIT (agreement No 765148) and by the Centre d'Imagerie BioMedicale (CIBM). We would also thank the Mount Sinai Hospital for providing the stroke dataset and Basel University Hospital for acquiring the MS dataset. The concepts and information presented in this paper are based on research results and GAMER MRI is not commercially available.
Funding Information:
Part of the work was performed while Po-Jui Lu was doing internship in Siemens Healthineers, Princeton, USA. Youngjin Yoo, Pascal Ceccaldi and Eli Gibson are employed by Siemens Healthineers, Princeton, USA. Benjamin Odry is employed by Covera Health, New York, USA. Matthias Weigel has received research funding by Biogen for developing spinal cord MRI. Kambiz Nael has consulted for Olea Medical outside the scope of this work. Zahi Fayad has a research grant from Siemens Healthineers and is founder and board member of Trained Therapeutix Discovery.
Publisher Copyright:
© 2020 The Author(s)
PY - 2021/1
Y1 - 2021/1
N2 - Introduction: During the last decade, a multitude of novel quantitative and semiquantitative MRI techniques have provided new information about the pathophysiology of neurological diseases. Yet, selection of the most relevant contrasts for a given pathology remains challenging. In this work, we developed and validated a method, Gated-Attention MEchanism Ranking of multi-contrast MRI in brain pathology (GAMER MRI), to rank the relative importance of MR measures in the classification of well understood ischemic stroke lesions. Subsequently, we applied this method to the classification of multiple sclerosis (MS) lesions, where the relative importance of MR measures is less understood. Methods: GAMER MRI was developed based on the gated attention mechanism, which computes attention weights (AWs) as proxies of importance of hidden features in the classification. In the first two experiments, we used Trace-weighted (Trace), apparent diffusion coefficient (ADC), Fluid-Attenuated Inversion Recovery (FLAIR), and T1-weighted (T1w) images acquired in 904 acute/subacute ischemic stroke patients and in 6,230 healthy controls and patients with other brain pathologies to assess if GAMER MRI could produce clinically meaningful importance orders in two different classification scenarios. In the first experiment, GAMER MRI with a pretrained convolutional neural network (CNN) was used in conjunction with Trace, ADC, and FLAIR to distinguish patients with ischemic stroke from those with other pathologies and healthy controls. In the second experiment, GAMER MRI with a patch-based CNN used Trace, ADC and T1w to differentiate acute ischemic stroke lesions from healthy tissue. The last experiment explored the performance of patch-based CNN with GAMER MRI in ranking the importance of quantitative MRI measures to distinguish two groups of lesions with different pathological characteristics and unknown quantitative MR features. Specifically, GAMER MRI was applied to assess the relative importance of the myelin water fraction (MWF), quantitative susceptibility mapping (QSM), T1 relaxometry map (qT1), and neurite density index (NDI) in distinguishing 750 juxtacortical lesions from 242 periventricular lesions in 47 MS patients. Pair-wise permutation t-tests were used to evaluate the differences between the AWs obtained for each quantitative measure. Results: In the first experiment, we achieved a mean test AUC of 0.881 and the obtained AWs of FLAIR and the sum of AWs of Trace and ADC were 0.11 and 0.89, respectively, as expected based on previous knowledge. In the second experiment, we achieved a mean test F1 score of 0.895 and a mean AW of Trace = 0.49, of ADC = 0.28, and of T1w = 0.23, thereby confirming the findings of the first experiment. In the third experiment, MS lesion classification achieved test balanced accuracy = 0.777, sensitivity = 0.739, and specificity = 0.814. The mean AWs of T1map, MWF, NDI, and QSM were 0.29, 0.26, 0.24, and 0.22 (p < 0.001), respectively. Conclusions: This work demonstrates that the proposed GAMER MRI might be a useful method to assess the relative importance of MRI measures in neurological diseases with focal pathology. Moreover, the obtained AWs may in fact help to choose the best combination of MR contrasts for a specific classification problem.
AB - Introduction: During the last decade, a multitude of novel quantitative and semiquantitative MRI techniques have provided new information about the pathophysiology of neurological diseases. Yet, selection of the most relevant contrasts for a given pathology remains challenging. In this work, we developed and validated a method, Gated-Attention MEchanism Ranking of multi-contrast MRI in brain pathology (GAMER MRI), to rank the relative importance of MR measures in the classification of well understood ischemic stroke lesions. Subsequently, we applied this method to the classification of multiple sclerosis (MS) lesions, where the relative importance of MR measures is less understood. Methods: GAMER MRI was developed based on the gated attention mechanism, which computes attention weights (AWs) as proxies of importance of hidden features in the classification. In the first two experiments, we used Trace-weighted (Trace), apparent diffusion coefficient (ADC), Fluid-Attenuated Inversion Recovery (FLAIR), and T1-weighted (T1w) images acquired in 904 acute/subacute ischemic stroke patients and in 6,230 healthy controls and patients with other brain pathologies to assess if GAMER MRI could produce clinically meaningful importance orders in two different classification scenarios. In the first experiment, GAMER MRI with a pretrained convolutional neural network (CNN) was used in conjunction with Trace, ADC, and FLAIR to distinguish patients with ischemic stroke from those with other pathologies and healthy controls. In the second experiment, GAMER MRI with a patch-based CNN used Trace, ADC and T1w to differentiate acute ischemic stroke lesions from healthy tissue. The last experiment explored the performance of patch-based CNN with GAMER MRI in ranking the importance of quantitative MRI measures to distinguish two groups of lesions with different pathological characteristics and unknown quantitative MR features. Specifically, GAMER MRI was applied to assess the relative importance of the myelin water fraction (MWF), quantitative susceptibility mapping (QSM), T1 relaxometry map (qT1), and neurite density index (NDI) in distinguishing 750 juxtacortical lesions from 242 periventricular lesions in 47 MS patients. Pair-wise permutation t-tests were used to evaluate the differences between the AWs obtained for each quantitative measure. Results: In the first experiment, we achieved a mean test AUC of 0.881 and the obtained AWs of FLAIR and the sum of AWs of Trace and ADC were 0.11 and 0.89, respectively, as expected based on previous knowledge. In the second experiment, we achieved a mean test F1 score of 0.895 and a mean AW of Trace = 0.49, of ADC = 0.28, and of T1w = 0.23, thereby confirming the findings of the first experiment. In the third experiment, MS lesion classification achieved test balanced accuracy = 0.777, sensitivity = 0.739, and specificity = 0.814. The mean AWs of T1map, MWF, NDI, and QSM were 0.29, 0.26, 0.24, and 0.22 (p < 0.001), respectively. Conclusions: This work demonstrates that the proposed GAMER MRI might be a useful method to assess the relative importance of MRI measures in neurological diseases with focal pathology. Moreover, the obtained AWs may in fact help to choose the best combination of MR contrasts for a specific classification problem.
KW - Attention mechanism
KW - Deep learning
KW - Multiple sclerosis
KW - Quantitative MRI
KW - Relative importance order
KW - Stroke
UR - http://www.scopus.com/inward/record.url?scp=85098749028&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85098749028&partnerID=8YFLogxK
U2 - 10.1016/j.nicl.2020.102522
DO - 10.1016/j.nicl.2020.102522
M3 - Article
C2 - 33360973
AN - SCOPUS:85098749028
SN - 2213-1582
VL - 29
JO - NeuroImage: Clinical
JF - NeuroImage: Clinical
M1 - 102522
ER -