Scott Doyle
University at Buffalo, NY·Biomedical Engineering
Oral cavity cancer is first treated with surgery. Afterward, pathologists look at the removed tissue under a microscope to judge how likely the cancer is to return.
- Fields
Biomedical Engineering
Computer Science
Medicine & Clinical Research
- Topics
oral cavity cancer
oral cancer
head and neck cancer
- Grants
- 1 known grant, through Mar 2027
What they work on
- Develop an AI image-analysis pipeline that predicts recurrence risk for Stage I/II oral cavity cancer from pathology slides, using active learning to recognize tissue structures and new measures of the tumor–host interface.
- Identify candidate treatment targets, such as the local immune response and angiogenesis (new blood vessel growth), from patterns found by the Quantitative Risk Model.
- Demonstrate robust model performance across a multi-site patient cohort collected from seven national and international centers.
- Map Quantitative Risk Model outputs onto synoptic pathology reports, the standardized pathology checklists, and build an AI-assisted report-filling tool for clinical workflows.
More about the research
That judgment is qualitative and can be ambiguous. Even among patients with early, Stage I/II disease treated by surgery alone, 25–37% develop a local recurrence. Better predictions could show which patients need more aggressive treatment.
Why it matters
Patients with early-stage oral cavity cancer who are likely to relapse after surgery could be identified sooner. Doctors could then direct aggressive combined therapy toward them and spare others unnecessary treatment. Because results feed into the standard reports pathologists already use, the tool could fit into clinical practice. The treatment targets it identifies could also guide the design of future clinical trials.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Hua Li
Washington University in St Louis, MO·Biomedical Engineering
Develop a learning-based prognostic model that predicts cervical cancer treatment response and outcome by integrating RNA biomarkers, radiologic and histologic images, and clinicopathologic data from about 600 patients at two institutions.
Tammara Watts
Duke University, NC·Medicine & Clinical Research
Identify ancestry-associated driver genes in HPV-negative oropharyngeal cancers from Black and White patients and relate them to treatment response, recurrence and overall survival.
Maneesh Dave
University of California-Davis, CA·Biomedical Engineering
Build inflammation Digital Pathology Tools (iDPT), machine learning and pathomics modules that preprocess, annotate and quantify inflammation, using about 700 digitized H&E-stained slides from mouse models of IBD and GvHD.
The school
University at Buffalo: 32 labs on PI Pages, $542M a year on research, 316 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.