Student Information

Binit PokharelFollow

Faculty

Schulich School of Medicine and Dentistry, Dept. of Pathology

Supervisor Name

Dr. Matthew Cecchini

Keywords

Tumour TMB Artificial Intelligence Lung Cancer Computational Models

Loading...

Media is loading
 

Description

A high tumour mutational burden is a promising biomarker for identifying lung cancer patients who would benefit from risky but potentially highly beneficial immunotherapy treatment. However, the cost and time it takes to obtain it make it difficult to implement in the clinic. Previous work by our collaborators has shown that this biomarker can be estimated based on scans of hematoxylin and eosin histology slides of squamous cell carcinoma tumours using a machine learning model, and that a focus on cancerous regions within the tumour yields the best results. In future work, the contours completed in our research project will be used to filter the input to the machine learning model, allowing for the expansion of those experiments to more patients and centres.

Creative Commons License

Creative Commons Attribution-Noncommercial 4.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial-Share Alike 4.0 License.

Document Type

Video

Share

COinS
 

Development of Tumour Contours to Support Generation of a Novel Algorithm to Predict Tumour Mutational Burden in Squamous Lung Cancer

A high tumour mutational burden is a promising biomarker for identifying lung cancer patients who would benefit from risky but potentially highly beneficial immunotherapy treatment. However, the cost and time it takes to obtain it make it difficult to implement in the clinic. Previous work by our collaborators has shown that this biomarker can be estimated based on scans of hematoxylin and eosin histology slides of squamous cell carcinoma tumours using a machine learning model, and that a focus on cancerous regions within the tumour yields the best results. In future work, the contours completed in our research project will be used to filter the input to the machine learning model, allowing for the expansion of those experiments to more patients and centres.