Prediction of Radiation Pneumonitis With Dose Distribution: A Convolutional Neural Network (CNN) Based Model

Abstract

Radiation pneumonitis (RP) is one of the major side effects of thoracic radiotherapy. The aim of this study is to build a dose distribution based prediction model, and investigate the correlation of RP incidence and high-order features of dose distribution. A convolution 3D (C3D) neural network was used to construct the prediction model. The C3D network was pre-trained for action recognition. The dose distribution was used as input of the prediction model. With the C3D network, the convolution operation was performed in 3D space. The guided gradient-weighted class activation map (grad-CAM) was utilized to locate the regions of dose distribution which were strongly correlated with grade≥2 and grade<2 RP cases, respectively. The features learned by the convolution filters were generated with gradient ascend to understand the deep network. The performance of the C3D prediction model was evaluated by comparing with three multivariate logistic regression (LR) prediction models, which used the dosimetric, normal tissue complication probability (NTCP) or dosiomics factors as input, respectively. All the prediction models were validated using 70 non-small cell lung cancer (NSCLC) patients treated with volumetric modulated arc therapy (VMAT). The area under curve (AUC) of C3D prediction model was 0.842. While the AUC of the three LR models were 0.676, 0.744 and 0.782, respectively. The guided grad-CAM indicated that the low-dose region of contralateral lung and high-dose region of ipsilateral lung were strongly correlated with the grade≥2 and grade<2 RP cases, respectively. The features learned by shallow filters were simple and globally consistent, and of monotonous color. The features of deeper filters displayed more complicated pattern, which was hard or impossible to give strict mathematical definition. In conclusion, we built a C3D model for thoracic radiotherapy toxicity prediction. The results demonstrate its performance is superior over the classical LR models. In addition, CNN also offers a new perspective to further understand RP incidence.

Multi‐institutional dose‐segmented dosiomic analysis for predicting radiation pneumonitis after lung stereotactic body radiation therapy

“…Moreover, PR curves were calculated with emphasis on the incidence of RP in the minor class. 30 For predicting RP after VMAT, Liang et al conducted a PR curve analysis using a convolution 3D neural network 33 ; the result was consistent with our dosiomic approach. In our study, the PR-AUC significantly improved when switching from the DVI models to the dosiomic and hybrid models.…”

Application of Radiomics for the Prediction of Radiation-Induced Toxicity in the IMRT Era: Current State-of-the-Art

“…The existence of a strict relationship between the dose distribution, a change of CT texture features before and after RT, and the risk of RILI development was firstly demonstrated by Cunliffe et al ( 66 ). Recently, this dosiomic approach was replicated through a convolutional deep-neural network analysis ( 67 , 68 ) in a cohort of 70 NSCLC patients treated with volumetric modulated arc therapy (VMAT), providing a high discriminative power (AUC of 0.84) over standard logistic regression models for the prediction of radiation pneumonitis. Taking into account the much less clinically relevant impact of radiation pneumonitis in the context of stereotactic body RT, limited data are available ( 69 , 70 ) in this context in comparison to conventionally-fractionated regimens.…”

The Application and Development of Deep Learning in Radiotherapy: A Systematic Review

“…The results showed that CNN performed better than the traditional model, with an AUC of 0.842. 59 Lee et al applied ML and bioinformatics tools to genome-wide data to predict and explain the late genitourinary system toxicity in prostate cancer patients after radiotherapy. 60 DL’s prediction of the efficacy and side effects of radiotherapy was able to screen out the possible beneficiaries of radiotherapy in clinical work and to prepare for possible side effects.…”