Case study: TLS Detect
Authors
More like this
Prediction of patient’s TLS status from H&E whole slide images in pan-cancer cohort
Context
Tertiary lymphoid structures (TLSs) are formations at sites with persistent inflammatory stimulation, including tumors. These ectopic lymphoid organs mainly consist of chemo-attracting B cells, T cells, and supporting dendritic cells (DCs).
TLS presence in the tumor compartment is considered a novel biomarker to stratify the overall survival risk of untreated cancer patients and as a marker of efficient immunotherapies for patients with solid tumors.1
However, the assessment of TLS by pathologists is time-consuming and often requires additional tissue sections using immunohistochemistry (IHC) or immunofluorescence stainings.
Methods
Based on a pan-tumor cohort of 675 WSI, Owkin has developed a deep learning method to predict the presence of TLS from routinely digitized H&E WSI.
The model scores regions of 112x112μm² by their relevance for TLS status and aggregates scores to make the final prediction.
Results
This model is able to predict TLS status at the patient level with an AUC of 0.87 in 5-fold cross validation on the pan-cancer cohort. Moreover the model is robust to the transfer on an external cohort of pancreatic patients and achieves an AUC of 0.86.
The prognostic value of the model was also evaluated. A survival analysis on the overall survival of patients led to a hazard ratio of 0.62 (ci: [0.44, 0.86] , p=0.018) between TLS positive patients and TLS negative patients, when classified using Owkin deep learning method.
This indicates that it is less likely to observe an event (death) in the TLS-positive group, compared to TLS-negative group.
Impact
- This novel deep learning method provides a simple and standardized approach to screen for presence of TLS from routine WSIs and couldsupport a larger adoption of assessment for this biomarker.
- Selecting high-value subgroups of patients that are most likely to respond to the ICI being tested is a key step for improving the statistical power of a trial.
- Better selection of trial participants will improve success rates across trial phases and ultimately faster regulatory approval and an improve access to ICI’s for more patients.
Citations
1. Ton N. Schumacher, Daniela S. Thommen ,Tertiary lymphoid structures in cancer. Science 375, eabf9419 (2022). DOI: 10.1126/science.abf9419