Dr. Caroline Reinhold

Academic title(s): 

Professor - Department of Diagnostic Radiology
Associate Member - Department of Medicine, Division of Experimental Medicine; Department of Obstetrics & Gynecology; Department of Oncology (Medical Physics); Department of Experimental Surgery

Dr. Caroline Reinhold
Contact Information
Address: 

McGill University Health Centre (MUHC)
Augmented Intelligence & Precision Health Laboratory
(AIPHL)
5252 de Maisonneuve Boulevard West,
Montréal, Qc, H4A 3S5

Phone: 
(514) 934-1934 ext. 37681
Email address: 
caroline.reinhold [at] mcgill.ca
Current research: 

My research in recent years has focused on quantitative image analysis and artificial intelligence (AI). I co-founded and am Co-Director of the Augmented Intelligence Precision Health Laboratory (AIPHL) of the MUHC Research Institute which consists of a multi-disciplinary team of scientists and clinicians, including computer scientists and machine learning experts, working within the hospital system to develop unique non-invasive image-based signatures that form the basis of AI clinical assistant tools for precision medicine. The AIPHL lab is involved in the inception, development, and validation of clinical AI applications in partnership with other academic teams and industry. A major area of clinical translation includes oncology and cardiovascular disease, through precision diagnostics and therapeutics. Advanced biomedical imaging technologies and clinical imaging features, molecular genomic, proteomic, and other clinical information are used for precision health and biomarker development. Therefore, one of the major areas of interest and strength is to lead translation of machine learning algorithms for implementation in the clinical setting.

Projects: 
  1. Using artificial intelligence to analyze emergency medical images, for fast prioritization of life-threatening conditions like strokes, collapsed lung or perforated bowels in remote Quebec communities.
  2. Deep Learning to differentiate uterine leiomyosarcomas from atypical leiomyomas at MRI.
  3. Deep learning for pre-operative risk stratification using MRI in patients with proven endometrial carcinoma.
  4. MRI Characteristics of the Microcystic, Elongated, and Fragmented (MELF) Pattern in Endometrial Cancer.
Selected publications: 
Research areas: 
Bioinformatics
Biomedical Engineering
Cancer
Cardiovascular diseases
Digestive Diseases
Epidemiology
Genetic diseases
Person-Centred Outcome
Renal diseases
Reproduction
Surgery
Back to top