ĂŰĚŇ´«Ă˝app

Trey Chernoff

Title: 
(he/him)
Trey Chernoff
Contact Information
Email address: 
trey.chernoff [at] mail.mcgill.ca
Address: 

Medical Physics, Cedars Cancer Centre DS1.4556

McGill University Health Centre

1001 boul. DĂ©carie

Montreal, QC H4A 3J1

Group: 
M.Sc. Graduate
Degree(s): 

BSc Honours, Physics (Regina '23)

MSc, Medical Physics (McGill, in progress)

Location: 
Glen Hospital
Graduate supervision: 

Supervisor: Dr. John Kildea

Research areas: 
Informatics
Current research: 

Most cancer patients experience severe pain at some point during their illness. Unfortunately, this pain is often underestimated and poorly managed by healthcare professionals until it becomes very intense. This inadequate pain management can negatively impact both the physical and mental well-being of patients. Identifying cancer pain early on is difficult but crucial for preventing severe discomfort. This research aims to detect pain early by analyzing medical images of patients. To develop an algorithm for this purpose, we will use two computer science techniques: one to gather data about pain from medical records, and another to extract information from medical images. We will use the first technique to quantify the pain levels documented in patients’ medical notes and the second technique to analyze radiographic images to assess tumour characteristics, such as volume and shape. We will then validate our model using pain scores collected from future cancer patients through a mobile app created by our team (). A key innovation of our model will be its ability to predict pain from radiographic images before it actually occurs. We aim to accomplish this feat by expanding upon the research previously conducted by Dr. Hossein Naseri, in that we will incorporate delta-radiomic features obtained from cone-beam CT data into a model that previously only utilized radiomic features from CT data.

Areas of interest: 

Radiomics, Deep learning, Bioinformatics, Natural language processing, Treatment planning.

Selected publications: 

Liu D, Tupor S, Singh J, Chernoff T, Leong N, Sadikov E, Amjad A, Zilles S. The challenges facing deep learning-based catheter localization for ultrasound guided high-dose-rate prostate brachytherapy. Med Phys. 2022 Apr;49(4):2442-2451. doi: 10.1002/mp.15522. Epub 2022 Feb 25. PMID: 35118676.

Selected talks and presentations: 
  • John McCrae Fellowship (2024)
  • 2nd Place - COMP ASM Science Spoken Succinctly Competition (2024)
  • McCall MacBain Scholarship Finalist Award (2023)
  • Ervin B. Podgorsak Fellowship (2023)
  • Petar C. Hein Memorial Scholarship in Physics (2022)
Back to top