A5039187492- Medical Imaging and Analysis
- Radiomics and Machine Learning in Medical Imaging
- Medical Image Segmentation Techniques
- Scoliosis diagnosis and treatment
- Medical Imaging Techniques and Applications
- Advanced Neural Network Applications
- Advanced Radiotherapy Techniques
- Spinal Fractures and Fixation Techniques
- AI in cancer detection
- Hepatocellular Carcinoma Treatment and Prognosis
- MRI in cancer diagnosis
- Prostate Cancer Diagnosis and Treatment
- Spectroscopy Techniques in Biomedical and Chemical Research
- Advanced Fiber Optic Sensors
- Advanced X-ray and CT Imaging
- Spine and Intervertebral Disc Pathology
- Advanced MRI Techniques and Applications
- Optical Coherence Tomography Applications
- Brain Tumor Detection and Classification
- Photoacoustic and Ultrasonic Imaging
- Lung Cancer Diagnosis and Treatment
- Optical Imaging and Spectroscopy Techniques
- Spectroscopy and Chemometric Analyses
- Advanced Neuroimaging Techniques and Applications
- Soft Robotics and Applications
Centre Hospitalier Universitaire Sainte-Justine
2014-2024
Université de Montréal
2013-2024
Polytechnique Montréal
2015-2024
Centre Hospitalier de l’Université de Montréal
2016-2024
University of California, San Francisco
2018-2023
Montreal Heart Institute
2023
CARE Canada
2020
Philips (Canada)
2020
San Francisco VA Medical Center
2018
Philips (United States)
2009-2013
No AccessJournal of UrologyAdult Urology1 Oct 2011Magnetic Resonance Imaging/Ultrasound Fusion Guided Prostate Biopsy Improves Cancer Detection Following Transrectal Ultrasound and Correlates With Multiparametric Magnetic Imaging Peter A. Pinto, Paul H. Chung, Ardeshir R. Rastinehad, Angelo Baccala, Jochen Kruecker, Compton J. Benjamin, Sheng Xu, Pingkun Yan, Samuel Kadoury, Celene Chua, Julia K. Locklin, Baris Turkbey, Joanna Shih, Stacey P. Gates, Carey Buckner, Gennady Bratslavsky, W....
Deep learning is a class of machine methods that has been successful in computer vision. Unlike traditional require hand-engineered feature extraction from input images, deep learn the image features by which to classify data. Convolutional neural networks (CNNs), core for imaging, are multilayered artificial with weighted connections between neurons iteratively adjusted through repeated exposure training These have numerous applications radiology, particularly classification, object...
There has been a resurgent interest in intravoxel incoherent motion (IVIM) MR imaging to obtain perfusion as well diffusion information on lesions, which the was modeled Gaussian diffusion. However, it observed that this deviated from expected monoexponential decay at high b-values and reported prostate is contrary findings dynamic contrast-enhanced (DCE) MRI studies angiogenesis. Thus, work evaluate effect of different IVIM fractions (f) coefficients (D) for cancer detection. The results...
We propose a model for the joint segmentation of liver and lesions in computed tomography (CT) volumes. build from two fully convolutional networks, connected tandem trained together end-to-end. evaluate our approach on 2017 MICCAI Liver Tumour Segmentation Challenge, attaining competitive lesion detection scores across wide range metrics. Unlike other top performing methods, output post-processing is trivial, we do not use data external to challenge, simple single-stage that However, method...
We demonstrate a novel approach to enhance the precision of surgical needle shape tracking based on distributed strain sensing using optical frequency domain reflectometry (OFDR). The enhancement is provided by fibers with high scattering properties. Shape tools properties has seen increased attention in recent years. Most investigations made this field use fiber Bragg gratings (FBG), which can be used as discrete or quasi-distributed sensors. By truly (OFDR), preliminary results show that...
No AccessJournal of UrologyAdult Urology1 Mar 2011D'Amico Risk Stratification Correlates With Degree Suspicion Prostate Cancer on Multiparametric Magnetic Resonance Imaging Ardeshir R. Rastinehad, Angelo A. Baccala, Paul H. Chung, Juan M. Proano, Jochen Kruecker, Sheng Xu, Julia K. Locklin, Baris Turkbey, Joanna Shih, Gennady Bratslavsky, W. Marston Linehan, Neil D. Glossop, Pingkun Yan, Samuel Kadoury, Peter L. Choyke, Bradford J. Wood, and Pinto RastinehadArdeshir Rastinehad Urologic...
It is well known that it challenging to train deep neural networks and recurrent for tasks exhibit long term dependencies. The vanishing or exploding gradient problem a issue associated with these challenges. One approach addressing gradients use either soft hard constraints on weight matrices so as encourage enforce orthogonality. Orthogonal preserve norm during backpropagation may therefore be desirable property. This paper explores issues optimization convergence, speed stability when...
To evaluate the performance, agreement, and efficiency of a fully convolutional network (FCN) for liver lesion detection segmentation at CT examinations in patients with colorectal metastases (CLMs).This retrospective study evaluated an automated method using FCN that was trained, validated, tested 115, 15, 26 contrast material-enhanced containing 261, 22, 105 lesions, respectively. Manual by radiologist reference standard. Performance user-corrected segmentations compared manual...
In this paper we propose a deep learning approach for segmenting sub-cortical structures of the human brain in Magnetic Resonance (MR) image data. We draw inspiration from state-of-the-art Fully-Convolutional Neural Network (F-CNN) architecture semantic segmentation objects natural images, and adapt it to our task. Unlike previous CNN-based methods that operate on patches, model is applied full blown 2D image, without any alignment or registration steps at testing time. further improve...
Organ segmentation in medical imagery can be used to guide patient diagnosis, treatment and follow ups. In this paper, we present a fully automatic framework for kidney with convolutional networks (ConvNets) contrast-enhanced computerised tomography (CT) scans. our approach, ConvNet is trained using patch-wise approach predict the class membership of central voxel 2D patches. The kidneys then produced by densely running over each slice CT scan. Efficient predictions achieved transforming...
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...
Using external actuation sources to navigate untethered drug-eluting microrobots in the bloodstream offers great promise improving selectivity of drug delivery, especially oncology, but current field forces are difficult maintain with enough strength inside human body (>70-centimeter-diameter range) achieve this operation. Here, we present an algorithm predict optimal patient position respect gravity during endovascular microrobot navigation. Magnetic resonance navigation, using magnetic...
To assess the feasibility of combined electromagnetic device tracking and computed tomography (CT)/ultrasonography (US)/fluorine 18 fluorodeoxyglucose (FDG) positron emission (PET) fusion for real-time feedback during percutaneous intraoperative biopsies hepatic radiofrequency (RF) ablation.In this HIPAA-compliant, institutional review board-approved prospective study with written informed consent, 25 patients (17 men, eight women) underwent 33 three 36 FDG-avid targets between November 2007...
Quantifying spinal cord (SC) atrophy in neurodegenerative and traumatic diseases brings important diagnosis prognosis information for the clinician. We recently developed PropSeg method, which allows fast, accurate automatic segmentation of SC on different types MRI contrast (e.g., T <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> -, xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> - *-weighted sequences) any field view. However,...
We introduce a novel approach for segmenting articulated spine shape models from medical images. A nonlinear low-dimensional manifold is created training set of mesh to establish the patterns global variations. Local appearance captured neighborhoods in once overall representation converges. Inference with respect and parameters performed using higher-order Markov random field (HOMRF). Singleton pairwise potentials measure support data coherence space respectively, while cliques encode...
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...