Eric Moulton
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Eric Moulton has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Ran Klein
Carleton University
2 shared publications - Robert A. Dekemp
Division of Cardiology, Department of Medicine, University of Ottawa Heart Institute, ON, Canada (R.A.d.).
2 shared publications - Amir Jabbarpour
Carleton University
1 shared publication Bertrand Lapergue
Department of Stroke Center and Diagnostic and Interventional Neuroradiology, University of Versailles and Saint Quentin en Yvelines, Foch Hospital, Suresnes, France
1 shared publication- Chad R.R.N. Hunter
University of Ottawa Heart Institute, Cardiac Imaging, Ottawa, ON, Canada
1 shared publication - Charlotte Rosso
Institut du Cerveau, ICM, Inserm U 1127, Centre National de la Recherche UMR 7225, Sorbonne Université, Paris, France (C.R., L.D., J.B., T.C., S.M., P.P., J.-C.L., E.R.).
1 shared publication
Latest Publications
- Open Access
- 15 October 2025
- Published by Elsevier in Journal of Nuclear Cardiology
- Vol. 53, 102531
Artificial intelligence–enabled parametric mapping of myocardial blood flow with 82Rb positron emission tomography compared to 18F-flurpiridaz perfusion imaging: A paired pilot study of image quality
- 15 October 2025
- Published by Elsevier in Journal of Nuclear Cardiology
- Vol. 53, 102531
Open AccessArtificial intelligence–enabled parametric mapping of myocardial blood flow with 82Rb positron emission tomography compared to 18F-flurpiridaz perfusion imaging: A paired pilot study of image quality
- Open Access
- 10 August 2024
- Published by Elsevier in Journal of Nuclear Cardiology
- Vol. 40, 102020
Parametric imaging of myocardial blood flow with 82Rb PET: An accuracy and image quality analysis
- 10 August 2024
- Published by Elsevier in Journal of Nuclear Cardiology
- Vol. 40, 102020
Open AccessParametric imaging of myocardial blood flow with 82Rb PET: An accuracy and image quality analysis
- Open Access
- 18 April 2023
- Published by Elsevier in Seminars in Nuclear Medicine
- Vol. 53 (6) , 752-765
The Past, Present, and Future Role of Artificial Intelligence in Ventilation/Perfusion Scintigraphy: A Systematic Review
- 18 April 2023
- Published by Elsevier in Seminars in Nuclear Medicine
- Vol. 53 (6) , 752-765
Open AccessThe Past, Present, and Future Role of Artificial Intelligence in Ventilation/Perfusion Scintigraphy: A Systematic Review
- 28 September 2022
- Published by SAGE Publications in Journal of Cerebral Blood Flow & Metabolism
- Vol. 43 (2) , 198-209
Interpretable deep learning for the prognosis of long-term functional outcome post-stroke using acute diffusion weighted imaging
Advances in deep learning can be applied to acute stroke imaging to build powerful and explainable prediction models that could supersede traditionally used biomarkers. We aimed to evaluate the performance and interpretability of a deep learning model based on convolutional neural networks (CNN) in predicting long-term functional outcome with diffusion-weighted imaging (DWI) acquired at day 1 post-stroke. Ischemic stroke patients (n = 322) were included from the ASTER and INSULINFARCT trials as well as the Pitié-Salpêtrière registry. We trained a CNN to predict long-term functional outcome assessed at 3 months with the modified Rankin Scale (dichotomized as good [mRS ≤ 2] vs. poor [mRS ≥ 3]) and compared its performance to two logistic regression models using lesion volume and ASPECTS. The CNN contained an attention mechanism, which allowed to visualize the areas of the brain that drove prediction. The deep learning model yielded a significantly higher area under the curve (0.83 95%CI [0.78–0.87]) than lesion volume (0.78 [0.73–0.83]) and ASPECTS (0.77 [0.71–0.83]) (p < 0.05). Setting all classifiers to the specificity as the deep learning model (i.e., 0.87 [0.82–0.92]), the CNN yielded a significantly higher sensitivity (0.67 [0.59–0.73]) than lesion volume (0.48 [0.40–0.56]) and ASPECTS (0.50 [0.41–0.58]) (p = 0.002). The attention mechanism revealed that the network learned to naturally attend to the lesion to predict outcome.
- 28 September 2022
- Published by SAGE Publications in Journal of Cerebral Blood Flow & Metabolism
- Vol. 43 (2) , 198-209
Interpretable deep learning for the prognosis of long-term functional outcome post-stroke using acute diffusion weighted imaging
Advances in deep learning can be applied to acute stroke imaging to build powerful and explainable prediction models that could supersede traditionally used biomarkers. We aimed to evaluate the performance and interpretability of a deep learning model based on convolutional neural networks (CNN) in predicting long-term functional outcome with diffusion-weighted imaging (DWI) acquired at day 1 post-stroke. Ischemic stroke patients (n = 322) were included from the ASTER and INSULINFARCT trials as well as the Pitié-Salpêtrière registry. We trained a CNN to predict long-term functional outcome assessed at 3 months with the modified Rankin Scale (dichotomized as good [mRS ≤ 2] vs. poor [mRS ≥ 3]) and compared its performance to two logistic regression models using lesion volume and ASPECTS. The CNN contained an attention mechanism, which allowed to visualize the areas of the brain that drove prediction. The deep learning model yielded a significantly higher area under the curve (0.83 95%CI [0.78–0.87]) than lesion volume (0.78 [0.73–0.83]) and ASPECTS (0.77 [0.71–0.83]) (p < 0.05). Setting all classifiers to the specificity as the deep learning model (i.e., 0.87 [0.82–0.92]), the CNN yielded a significantly higher sensitivity (0.67 [0.59–0.73]) than lesion volume (0.48 [0.40–0.56]) and ASPECTS (0.50 [0.41–0.58]) (p = 0.002). The attention mechanism revealed that the network learned to naturally attend to the lesion to predict outcome.
- 6 March 2019
- Published by Springer Nature in Brain Structure and Function
- Vol. 224 (4) , 1-18
Connectivity between the visual word form area and the parietal lobe improves after the first year of reading instruction: a longitudinal MRI study in children
Shortly after reading instruction, a region in the ventral occipital temporal cortex (vOTC) of the left hemisphere, the Visual Word Form Area (VWFA), becomes specialized for written words. Its reproducible location across scripts suggests important anatomical constraints, such as specific patterns of connectivity, notably to spoken language areas. Here, we explored the structural connectivity of the emerging VWFA in terms of its specificity relative to other ventral visual regions and its stability throughout the process of reading instruction in ten children studied longitudinally over 2 years. Category-specific regions for words, houses, faces, and tools were identified in the left vOTC of each subject with functional MRI. With diffusion MRI and tractography, we reconstructed the connections of these regions at two time points (mean age ± standard deviation: 6.2 ± 0.3, 7.2 ± 0.4 years). We first showed that the regions for each visual category harbor their own specific connectivity, all of which precede reading instruction and remain stable throughout development. The most specific connections of the VWFA were to the dorsal posterior parietal cortex. We then showed that microstructural changes in these connections correlated with improvements in reading scores over the first year of instruction but not 1 year later in a subsample of eight children (age: 8.4 ± 0.3 years). These results suggest that the VWFA location depends on its connectivity to distant regions, in particular, the left inferior parietal region which may play a crucial role in visual field maps and eye movement dynamics in addition to attentional control in letter-by-letter reading and disambiguation of mirror-letters during the first stages of learning to read.
- 6 March 2019
- Published by Springer Nature in Brain Structure and Function
- Vol. 224 (4) , 1-18
Connectivity between the visual word form area and the parietal lobe improves after the first year of reading instruction: a longitudinal MRI study in children
Shortly after reading instruction, a region in the ventral occipital temporal cortex (vOTC) of the left hemisphere, the Visual Word Form Area (VWFA), becomes specialized for written words. Its reproducible location across scripts suggests important anatomical constraints, such as specific patterns of connectivity, notably to spoken language areas. Here, we explored the structural connectivity of the emerging VWFA in terms of its specificity relative to other ventral visual regions and its stability throughout the process of reading instruction in ten children studied longitudinally over 2 years. Category-specific regions for words, houses, faces, and tools were identified in the left vOTC of each subject with functional MRI. With diffusion MRI and tractography, we reconstructed the connections of these regions at two time points (mean age ± standard deviation: 6.2 ± 0.3, 7.2 ± 0.4 years). We first showed that the regions for each visual category harbor their own specific connectivity, all of which precede reading instruction and remain stable throughout development. The most specific connections of the VWFA were to the dorsal posterior parietal cortex. We then showed that microstructural changes in these connections correlated with improvements in reading scores over the first year of instruction but not 1 year later in a subsample of eight children (age: 8.4 ± 0.3 years). These results suggest that the VWFA location depends on its connectivity to distant regions, in particular, the left inferior parietal region which may play a crucial role in visual field maps and eye movement dynamics in addition to attentional control in letter-by-letter reading and disambiguation of mirror-letters during the first stages of learning to read.