Radiomics-Based Prediction of Treatment Response to TRuC-T Cell Therapy in Patients with Mesothelioma: A Pilot Study
Hubert Beaumont1, Antoine Iannessi1, Alexandre Thinnes1
1Median Technologies, 06560 Valbonne, France.
Background/Objectives:
T cell receptor fusion constructs (TRuCs), a next generation engineered T cell therapy, hold great promise. To accelerate the clinical development of these therapies, improving patient selection is a crucial pathway forward.
Methods:
We retrospectively analyzed 23 mesothelioma patients (85 target tumors) treated in a phase 1/2 single arm clinical trial (NCT03907852). Five imaging sites were involved, the settings for the evaluations were Blinded Independent Central Reviews (BICRs) with double reads. The reproducibility of 3416 radiomics and delta-radiomics (Δradiomics) was assessed. The univariate analysis evaluated correlations at the target tumor level with (1) tumor diameter response; (2) tumor volume response, according to the Quantitative Imaging Biomarker Alliance; and (3) the mean standard uptake value (SUV) response, as defined by the positron emission tomography response criteria in solid tumors (PERCISTs). A random forest model predicted the response of the target pleural tumors.
Results:
Tumor anatomical distribution was 55.3%, 17.6%, 14.1%, and 10.6% in the pleura, lymph nodes, peritoneum, and soft tissues, respectively. Radiomics/Δradiomics reproducibility differed across tumor localizations. Radiomics were more reproducible than Δradiomics. In the univariate analysis, none of the radiomics/Δradiomics correlated with any response criteria. With an accuracy ranging from 0.75 to 0.9, three radiomics/Δradiomics were able to predict the response of target pleural tumors. Pivotal studies will require a sample size of 250 to 400 tumors.
Conclusions:
The prediction of responding target pleural tumors can be achieved using a machine learning-based radiomics/Δradiomics analysis. Tumor-specific reproducibility and the average values indicated that using tumor models to create an effective patient model would require combining several target tumor models.
Insights
Machine learning-based radiomics and delta-radiomics can predict pleural tumor response in mesothelioma patients treated with T cell receptor fusion constructs (TRuCs). This approach aids in selecting patients for TRuC therapy, improving clinical development.
Area of Science:
- Oncology
- Radiology
- Biomedical Engineering
Background:
- T cell receptor fusion constructs (TRuCs) represent a promising engineered T cell therapy.
- Improving patient selection is critical for accelerating the clinical development of TRuC therapies.
Purpose of the Study:
- To assess the reproducibility of radiomics and delta-radiomics in mesothelioma.
- To evaluate the predictive capability of radiomics and delta-radiomics for treatment response.
- To develop a machine learning model for predicting pleural tumor response.
Main Methods:
- Retrospective analysis of 23 mesothelioma patients from a phase 1/2 clinical trial.
- Assessment of radiomics and delta-radiomics reproducibility across 3416 features.
- Univariate analysis of correlations with tumor response criteria (diameter, volume, SUV).
- Development of a random forest model to predict target pleural tumor response.
Main Results:
- Radiomics were more reproducible than delta-radiomics across different tumor localizations.
- No radiomics or delta-radiomics showed significant correlation with response criteria in univariate analysis.
- A machine learning model achieved 0.75-0.9 accuracy in predicting target pleural tumor response.
- Pivotal studies may require 250-400 tumors for validation.
Conclusions:
- Machine learning-based radiomics and delta-radiomics analysis can predict responding target pleural tumors.
- Tumor-specific reproducibility and average values suggest combining multiple target tumor models for effective patient modeling.
