A method for predictive modeling of tumor regression for lung adaptive radiotherapy

Abstract

The purpose of this work is to create a decision support methodology to predict when patients undergoing radiotherapy treatment for locally advanced lung cancer would potentially benefit from adaptive radiotherapy. The proposed methodology seeks to eliminate the manual subjective review by developing an automated statistical learning model to predict when tumor regression would trigger implementation of adaptive radiotherapy based on quantified anatomic changes observed in individual patients on-treatment cone beam computed tomographies (CTs). This proposed process seeks to improve the efficacy and efficiency of both the existing manual and automated adaptive review processes for locally advanced stage III lung cancer. Methods: A predictive algorithm was developed as a decision support tool to determine the potential utility of mid-treatment adaptive radiotherapy based on anatomic changes observed on 1158 daily CBCT images across 43 patients. The anatomic changes on each axial slice within specified regionsof-interest were quantified into a single value utilizing imaging similarity criteria comparing the daily CBCT to the initial simulation CT. The range of the quantified metrics for each fraction across all axial slices are reduced to specified quantiles, which are used as the predictive input to train a logistic regression algorithm. A "ground-truth" of the need for adaptive radiotherapy based on tumor regression was evaluated systematically on each of the daily CBCTs and used as the classifier in the logistic regression algorithm. Accuracy of the predictive model was assessed utilizing both a tenfold cross validation and an independent validation dataset, with the sensitivity, specificity, and fractional accuracy compared to the ground-truth. Results: The sensitivity and specificity for the individual daily fractions ranged from 87.9%-94.3% and 91.9%-98.6% for a probability threshold of 0.2-0.5, respectively. The corresponding average treatment fraction difference between the model predictions and assessed ART "ground-truth" ranged from À2.25 to À0.07 fractions, with the model predictions consistently predicting the potential need for ART earlier in the treatment course. By initially utilizing a lower probability threshold, the higher sensitivity minimizes the chance of false negative by alerting the clinician to review a higher number of questionable cases. Conclusions: The proposed methodology accurately predicted the first fraction at which individual patients may benefit from ART based on quantified anatomic changes observed in the on-treatment volumetric imaging. The generalizability of the proposed method has potential to expand to additional modes of adaptive radiotherapy for lung cancer patients with observed underlying anatomic changes.

A prediction model for dosimetric‐based lung adaptive radiotherapy

“…The achievement of good model performance, that is, ∼85% sensitivity and specificity, demonstrated that the proposed method was capable of identifying the patients of replanning need accurately and efficiently thereby could be implemented as an auxiliary tool to assist the clinicians making timely decisions on plan adaption along the treatment course. As aforementioned in Section 1, the representative approaches to determine adaptive replanning for the lung cancer patients were to assess the anatomical changes by comparing the CBCT to the pCT images either manually 19 or using an automated predictive model 21 based on a set of anatomical trigger criteria. Compared to these existing approaches, the novelty of the proposed methodology in this study was the association of the patient‐specific anatomy and anatomical changes with the need of replanning based on patient‐specific dose changes through our prediction model.…”

“…If certain changes are observed (e.g., appearance of atelectasis), the radiation oncologist would be notified to make decisions on further action 18–20 . To eliminate the uncertainties introduced by manual subjective ART review, several studies have been done on developing prediction models based on machine learning (ML) methods as the decision supporting tools to automatically identify the anatomical changes from the CBCTs that would violate certain anatomical triggering criteria and trigger plan adaptions 21,22 . Although the implementation of the anatomical‐based ART scheme is quick and less complicated comparing to the dosimetric‐based ART scheme, it is susceptible to subjective judgment due to the lack of connection between the observed anatomical changes and the patient‐specific dosimetric influences.…”

Machine-learning-based prediction of the effectiveness of the delivered dose by exhale-gated radiotherapy for locally advanced lung cancer: The additional value of geometric over dosimetric parameters alone

“…Furthermore, anatomical changes owing to tumor shrinkage can occur throughout the course of curativeintended radiation therapy. These make adaptations of the target volume necessary in order to protect normal tissue (17)(18)(19)(20)(21).…”

Early Prediction of Planning Adaptation Requirement Indication Due to Volumetric Alterations in Head and Neck Cancer Radiotherapy: A Machine Learning Approach

“…To that end, a large number of studies have investigated the statistical relationship between the need for ART and image-based characteristics [ 12 , 13 ]. Nevertheless, the development of early prediction multivariate models for ART application presents several challenges as a consequence of volume-related discrepancies, resulting from anatomical alterations in cancer patients treated with RT [ 14 , 15 ].…”