Jubilant Radiopharma, Kirkland, QC, Canada; University of Ottawa, School of Electrical Engineering and Computer Science, Ottawa, ON, Canada; University of Ottawa Heart Institute, Division of Cardiology, Ottawa, ON, Canada
Auto-generated profile, based on publicly available information
Eric Moulton
Jubilant Radiopharma, Kirkland, QC, Canada; University of Ottawa, School of Electrical Engineering and Computer Science, Ottawa, ON, Canada; University of Ottawa Heart Institute, Division of Cardiology, Ottawa, ON, Canada
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.
Ventilation-perfusion (V/Q) lung scans constitute one of the oldest nuclear medicine procedures, remain one of the few studies performed in the acute setting, and are amongst the few performed in the emergency setting. V/Q studies have witnessed a long fluctuation in adoption rates in parallel to continuous advances in image processing and computer vision techniques. This review provides an overview on the status of artificial intelligence (AI) in V/Q scintigraphy. To clearly assess the past, current, and future role of AI in V/Q scans, we conducted a systematic Ovid MEDLINE(R) literature search from 1946 to August 5, 2022 in addition to a manual search. The literature was reviewed and summarized in terms of methodologies and results for the various applications of AI to V/Q scans. The PRISMA guidelines were followed. Thirty-one publications fulfilled our search criteria and were grouped into two distinct categories: (1) disease diagnosis/detection (N = 22, 71.0%) and (2) cross-modality image translation into V/Q images (N = 9, 29.0%). Studies on disease diagnosis and detection relied heavily on shallow artificial neural networks for acute pulmonary embolism (PE) diagnosis and were primarily published between the mid-1990s and early 2000s. Recent applications almost exclusively regard image translation tasks from CT to ventilation or perfusion images with modern algorithms, such as convolutional neural networks, and were published between 2019 and 2022. AI research in V/Q scintigraphy for acute PE diagnosis in the mid-90s to early 2000s yielded promising results but has since been largely neglected and thus have yet to benefit from today's state-of-the art machine-learning techniques, such as deep neural networks. Recently, the main application of AI for V/Q has shifted towards generating synthetic ventilation and perfusion images from CT. There is therefore considerable potential to expand and modernize the use of real V/Q studies with state-of-the-art deep learning approaches, especially for workflow optimization and PE detection at both acute and chronic stages. We discuss future challenges and potential directions to compensate for the lag in this domain and enhance the value of this traditional nuclear medicine scan.
We aimed to develop a framework for generating 3D myocardial blood flow (MBF) images, computing their accuracy against clinically validated 2D polar MBF maps of the left ventricle, and evaluating their improvements in image quality over relative myocardial perfusion imaging (MPI). N=40 patients with a wide range of defect severities and uptake dynamics were retrospectively studied. The FlowQuantTM software was used to generate reference MPI and polar MBF maps and was adapted for voxel-wise MBF mapping. We evaluated agreement between parametric vs. polar values for MBF at rest and stress and for reserve (stress/rest MBF). We also assessed improvements in image quality, assessed by signal-to-noise ratio, contrast-to-noise ratio, tissue-to-blood ratio, and defect severity, from relative MPI to MBF. There was excellent agreement between 3D parametric and 2D polar-maps for all flow parameters (ICC>0.96) albeit with minimal bias (<8%) for rest and stress MBF at the patient level. Image quality substantially improved from MPI to MBF in every patient for all image quality metrics (p<0.0001) CONCLUSIONS: We developed a robust methodology for producing highly accurate 3D MBF images exhibiting considerably improved image quality compared to relative MPI commonly used in clinical practice.