Predicting the radiotherapeutic treatment response of non-small cell lung cancer

Abstract

Background and Objective:: Predicting the treatment response of a patient undergoing treatment for NSCLC (non-small cell lung cancer) is useful in the estimation of effectiveness of the treatment protocol. To assess the prognostic value of radiomic features extracted from CBCT (cone-beam computed tomography) images of NSCLC patients, an efficient classification model is developed. The study aims to predict the early response (predicting the response at the third week of the radiation therapy) of the patients using the first-week and third-week data, of the acquired CBCT images. Methods:: This retrospective study includes 99 NSCLC patients having undergone conventionally fractionated radiation therapy (RT) over six weeks. The radiomic features are computed using the Python pyradiomics package. Initially 107 radiomic features were chosen. A triage-based learning paradigm is implemented, wherein the machine decides upon the difficulty of a sample. If the machine recognizes an instance to be hard to classify, then it is left for human expert assistance, otherwise, a feed-forward neural network is trained which classifies a patient’s response to treatment. Results:: The proposed model achieves accuracy 0.75±0.03, precision 0.79±0.03, sensitivity 0.82±0.05, f-score 0.80±0.03 and specificity 0.61±0.08 to predict the patient’s early response. Using, ensemble learning technique an accuracy of 0.79±0.03, precision 0.91±0.06, sensitivity 0.80±0.08, f-score 0.84±0.03 and specificity 0.82±0.13 is achieved. Conclusion:: The experimental results revealed that the accuracy of proposed model is better than the state-of-the-art technique. The results show that CBCT radiomic features can prognosticate the tumor response for NSCLC patients.

Keywords

• NSCLC
• Radiomics
• RECIST
• CBCT
• Triage
• Neural network