A5080250783- Radiomics and Machine Learning in Medical Imaging
- Advanced Radiotherapy Techniques
- Lung Cancer Diagnosis and Treatment
- Head and Neck Cancer Studies
- Advanced Neural Network Applications
- Medical Imaging and Analysis
- AI in cancer detection
- Brain Tumor Detection and Classification
- Medical Imaging Techniques and Applications
- Cancer Immunotherapy and Biomarkers
- Cardiac Imaging and Diagnostics
- CAR-T cell therapy research
- Prostate Cancer Diagnosis and Treatment
- Coronary Interventions and Diagnostics
- Spectroscopy Techniques in Biomedical and Chemical Research
- Medical Image Segmentation Techniques
- Advanced Image Processing Techniques
- Spectroscopy and Chemometric Analyses
- Immunotherapy and Immune Responses
- Memory and Neural Mechanisms
- Biosensors and Analytical Detection
- Glioma Diagnosis and Treatment
- Chalcogenide Semiconductor Thin Films
- AI-based Problem Solving and Planning
- Image Processing Techniques and Applications
Polytechnique Montréal
2020-2024
Nanchang Institute of Technology
2024
University of California, Santa Barbara
2020-2024
Centre Hospitalier de l’Université de Montréal
2020-2024
ImaginAb (United States)
2023
Montreal Heart Institute
2023
University of California, San Francisco
2023
Université de Montréal
2018-2023
Saint John's Health Center
2022
California Polytechnic State University
2020
Head and neck radiotherapy induces important toxicity, its efficacy tolerance vary widely across patients. Advancements in delivery techniques, along with the increased quality frequency of image guidance, offer a unique opportunity to individualize based on imaging biomarkers, aim improving radiation while reducing toxicity. Various artificial intelligence models integrating clinical data radiomics have shown encouraging results for toxicity cancer control outcomes prediction head...
Abstract The coronary angiogram is the gold standard for evaluating severity of artery disease stenoses. Presently, assessment conducted visually by cardiologists, a method that lacks standardization. This study introduces DeepCoro, ground-breaking AI-driven pipeline integrates advanced vessel tracking and video-based Swin3D model was trained validated on dataset comprised 182,418 angiography videos spanning 5 years. DeepCoro achieved notable precision 71.89% in identifying segments...
A new narrow bandgap non-fullerene electron acceptor was designed, synthesized, and characterized for near-infrared organic photovoltaics.
Abstract In radiation oncology, predicting patient risk stratification allows specialization of therapy intensification as well selecting between systemic and regional treatments, all which helps to improve outcome quality life. Deep learning offers an advantage over traditional radiomics for medical image processing by salient features from training data originating multiple datasets. However, while their large capacity combine high-level imaging prediction, they lack generalization be used...
With the emergence of online MRI radiotherapy treatments, MR-based workflows have increased in importance clinical workflow. However proper dose planning still requires CT images to calculate attenuation due bony structures. In this paper, we present a novel deep image synthesis model that generates an unsupervised manner from diagnostic for planning. The proposed based on generative adversarial network (GAN) consists learning new invariant representation generate synthetic (sCT) high...
Deep neural networks are commonly used for automated medical image segmentation, but models will frequently struggle to generalize well across different imaging modalities. This issue is particularly problematic due the limited availability of annotated data, both in target as source modality, making it difficult deploy these on a larger scale. To overcome challenges, we propose new semi-supervised training strategy called MoDATTS. Our approach designed accurate cross-modality 3D tumor...
Head and neck radiotherapy planning requires electron densities from different tissues for dose calculation. Dose calculation imaging modalities such as MRI remains an unsolved problem since this modality does not provide information about the density of electrons.
The early initiation of binge-drinking and biological sex are critical risk factors for the development affective disturbances cognitive decline, as well neurodegenerative diseases including Alzheimer's disease. Further, a history excessive alcohol consumption alters normal age-related changes in pattern protein expression brain, which may relate to an acceleration decline. Here, we aimed disentangle interrelation between during adolescence, aging on manifestation negative affect, decline...
Cancer control outcomes of lung cancer are hypothesized to be affected by several confounding factors, including tumor heterogeneity and patient history, which have been mitigate the dose delivery effectiveness when treated with radiation therapy. Providing an accurate predictive model identify patients at risk would enable tailored follow-up strategies during treatment.
In medical imaging, radiological scans of different modalities serve to enhance sets features for clinical diagnosis and treatment planning. This variety enriches the source information that could be used outcome prediction. Deep learning methods are particularly well-suited feature extraction from high-dimensional inputs such as images. this work, we apply a CNN classification network augmented with FCN preprocessor sub-network public TCIA head neck cancer dataset. The training goal is...
Adaptive radiotherapy is a growing field of study in cancer treatment due to it's objective sparing healthy tissue. The standard care several institutions includes longitudinal cone-beam computed tomography (CBCT) acquisitions monitor changes, but have yet be used improve tumor control while managing side-effects. aim this demonstrate the clinical value pre-treatment CBCT acquired daily during radiation therapy for head and neck cancers downstream task predicting severe toxicity occurrence:...
Adaptive radiotherapy is a growing field of study in cancer treatment due to it's objective sparing healthy tissue. The standard care several institutions includes longitudinal cone-beam computed tomography (CBCT) acquisitions monitor changes, but have yet be used improve tumor control while managing side-effects. aim this demonstrate the clinical value pre-treatment CBCT acquired daily during radiation therapy for head and neck cancers downstream task predicting severe toxicity occurrence:...
<title>Abstract</title> The coronary angiogram is the gold standard for evaluating severity of artery disease stenoses. Presently, assessment conducted visually by cardiologists, a method that lacks standardization. This study introduces DeepCoro, ground-breaking AI-driven pipeline integrates advanced vessel tracking and video-based Swin3D model was trained validated on large dataset comprised 182,418 angiographies spanning 4 years. DeepCoro achieved notable precision 71.89% in identifying...
Prostate cancer is one of the most prevalent cancers in men, where diagnosis confirmed through biopsies analyzed with histopathology. A diagnostic T2-w MRI often registered to intra-operative transrectal ultrasound (TRUS) for effective targeting suspicious lesions during image-guided biopsy procedures or needle-based therapeutic interventions such as brachytherapy. However, this process remains challenging and time-consuming an interventional environment. The present work proposes automated...
Abstract Background: Immunotherapy (IOT) of cancer depends on intratumoral CD8+ cells overcoming multiple obstacles to their localization and function. cell content its changes with treatment are important understand tumor immunobiology, prognosis, guide therapy. Trial design: ImaginAb has developed an imaging agent, 89Zr-crefmirlimab berdoxam (formerly 89Zr-Df-IAB22M2C/89Zr-Df-crefmirlimab), 80 kDa minibody lacking a functional Fc domain, conferring high affinity CD8, conjugated via...
Traditional pairwise medical image registration techniques are based on computationally intensive frameworks due to numerical optimization procedures. While there is increasing adoption of deep neural networks improve deformable registration, achieving a clinically suitable solution remains scarce. One the primary difficulties lies in choice tractable distance functions assess similarity. Recent works have explored Wasserstein as loss function generative networks. In this work, we evaluate...