CellScope: Optimising Papillary Thyroid Cancer Diagnosis
CWSF · 2026 Disease & Illness Bronze Medal
Overview
Diagnosing aggressive thyroid cancers like the tall-cell variant can be challenging because pathologists must determine whether the cancer cells are at least 3 times taller than they are wide and if they make up 30% or more of the tumour(6). This makes accurate diagnosis of borderline cases difficult when the cells are close to the cutoff(6). Extensive consultation also delays the diagnosis. I created an artificial intelligence tool that measures the shape of cancer cells on digital slides combined with genetic changes in the tumour. I built a model that analyzes these measurements together with clinical and genetic data as a screening tool. My results showed that aggressive thyroid cancers have statistically significant differences in cell shape, and using these measurements together with clinical and genetic data helped identify these cases accurately and quicker than manual review. This innovation could help pathologists diagnose dangerous thyroid cancers faster and more consistently.
Awards (2)
- Bronze Medal
- Selected for CWSF 2026
Competition history
- CWSF 2026
Related projects
ISEF · 2015
Improved Cancer Detection and Diagnosis through a Novel Combination of Cell Segmentation and Artificial Intelligence Techniques
ISEF · 2023
Machine Learning Augmented Histopathological Diagnosis of an Aggressive Variant of Liver Cancer
ISEF · 2014
Quantitative Analysis of Macro-Cellular Biomarkers in Early Stage Ductal Carcinoma in situ (DCIS) Immunohistochemical Cytopathology Images Using Machine Learning
ISEF · 2025
Combining Accessibility With Machine Learning: Utilizing Machine Learning to Create a User-Friendly Medical Application to Process and Detect Histopathological Images of Oral Squamous Cell Carcinoma
Closest projects by meaning, across every fair and year in the corpus.