# CT-Based Radiomics for a priori Predicting Response to Chemoradiation in Locally Advanced Lung Adenocarcinoma

## TL;DR

This study explores using CT scans and radiomics to predict how lung cancer patients will respond to chemoradiation before treatment begins.

## Contribution

The novel contribution is a CT-based radiomics model that predicts chemoradiation response in lung adenocarcinoma patients before treatment.

## Key findings

- A three-feature model using KNN achieved 80% accuracy in predicting chemoradiation response.
- The model showed a recall of 84% and an area under the curve of 0.77.
- Results suggest radiomics can predict treatment response with estimated accuracies of 77–84%.

## Abstract

Responses to chemoradiation can vary significantly among patients with locally advanced non-small cell lung cancer (NSCLC). The early identification of tumors that do not respond to chemoradiation is important for personalized treatment and optimized outcomes. The aim of our retrospective study was to explore CT-based radiomics as a potential way of predicting tumor response prior to the start of chemoradiation. We trained, tested, and validated a model based on the data of fifty-seven NSCLC patients. This model was able to classify tumor response with acceptable accuracy and precision. Further studies will be needed to validate the present findings.

The standard treatment for patients with locally advanced non-small cell lung cancer (NSCLC) is concurrent chemoradiation. However, clinical responses are heterogeneous and generally not known until after the completion of therapy. Multiple studies have investigated imaging predictors (radiomics) for different cancer histologies, but little exists for NSCLC. The objective of this study was to develop a multivariate CT-based radiomics model to a priori predict responses to definitive chemoradiation in patients with lung adenocarcinoma. Methods: Patients diagnosed with locally advanced unresectable lung adenocarcinoma who had undergone chemoradiotherapy followed by at least one dose of maintenance durvalumab were included. The PyRadiomics Python library was used to determine statistical, morphological, and textural features from normalized patient pre-treatment CT images and their wavelet-filtered versions. A nested leave-one-out cross-validation was used for model building and evaluation. Results: Fifty-seven patients formed the study cohort. The clinical stage was IIIA-C in 98% of patients. All but one received 6000–6600 cGy of radiation in 30–33 fractions. All received concurrent platinum-based chemotherapy. Based on RECIST 1.1, 20 (35%) patients were classified as responders (R) to chemoradiation and 37 (65%) patients as non-responders (NR). A three-feature model based on a KNN k = 1 machine learning classifier was found to have the best performance, achieving a recall, specificity, accuracy, balanced accuracy, precision, negative predictive value, F1-score, and area under the curve of 84%, 70%, 80%, 77%, 84%, 70%, 84%, and 0.77, respectively. Conclusions: Our results suggest that a CT-based radiomics model may be able to predict chemoradiation response for lung adenocarcinoma patients with estimated accuracies of 77–84%.