A deep learning model can diagnose thymic epithelial tumors with high sensitivity for thymic carcinoma detection, according to findings published in Annals of Oncology. The researchers suggested that the tool could be used to improve diagnostic consistency and support decision-making in settings with limited thoracic pathology expertise as well as in more specialized settings.
“We created a tool that—in the hands of a nonexpert pathologist—is able to properly diagnose 100% of thymic carcinomas and outperform nonexpert diagnoses,” explained senior study author Marina Garassino, MD, Professor of Medicine at UChicago Medicine.
Background and Study Methods
Thymic epithelial tumors are a rare group of tumors that can be challenging to diagnose due to their heterogeneous histologic patterns. Historically there has been significant interobserver variability in the classification of these tumors, even with standardized World Health Organization (WHO) classification criteria. About half of all thymic epithelial tumors may be reclassified on a second opinion.
The researchers believed that deep learning could reduce the diagnostic variability surrounding thymic epithelial tumors.
They trained a deep learning–based model using a dataset of hematoxylin and eosin (H&E) whole-slide images from The Cancer Genome Atlas (n = 119 patients). A novel hierarchical loss function was included in the model architecture for clinically relevant tumor groupings according to treatment strategies and patient outcomes.
The model was then validated on a cohort of 112 cases from the University of Chicago, and the diagnoses of thymic epithelial tumors were confirmed by an expert thoracic pathologist.
Performance of the model was tested on a three-group hierarchical scheme and on the six WHO classes.
Key Findings
When tested on the three-group hierarchical classification, the model achieved 91.1% accuracy (Cohen's ĸ = 0.859), and 77.7% accuracy on WHO classification (Cohen's ĸ = 0.716).
The model achieved a sensitivity of 100% and an accuracy of 94.6% for detecting thymic carcinomas.
Sixty percent of the misclassifications were found within the same clinical management group, which limited the impact on therapeutic decision making.
Going forward, the research team is trying to validate the tool with larger, international datasets and to allow for data and slides that utilize different procedures.
“In a larger population, harmonizing these steps is the biggest challenge,” Dr. Garassino said. “So, in the future, we plan to expand the algorithm so that it can correct for such differences, which will make the tool even more widely usable.”
DISCLOSURES: The research was supported by grants from the National Institutes of Health and a scholarship “Pierluigi Galli and Eurovetro Recycling SRL” from Associazione TUTOR. The Department of Medicine, Section of Hematology/Oncology and Department of Pathology at The University of Chicago and the TCGA Research Network also supported the study. For full disclosures of the study authors, visit annalsofoncology.org.
