Lung Size and the Risk of Radiation Pneumonitis

Dosiomics and radiomics-based prediction of pneumonitis after radiotherapy and immune checkpoint inhibition: The relevance of fractionation

OBJECTIVES

Post-therapy pneumonitis (PTP) is a relevant side effect of thoracic radiotherapy and immunotherapy with checkpoint inhibitors (ICI). The influence of the combination of both, including dose fractionation schemes on PTP development is still unclear. This study aims to improve the PTP risk estimation after radio(chemo)therapy (R(C)T) for lung cancer with and without ICI by investigation of the impact of dose fractionation on machine learning (ML)-based prediction.

MATERIALS AND METHODS

Data from 100 patients who received fractionated R(C)T were collected. 39 patients received additional ICI therapy. Computed Tomography (CT), RT segmentation and dose data were extracted and physical doses were converted to 2-Gy equivalent doses (EQD2) to account for different fractionation schemes. Features were reduced using Pearson intercorrelation and the Boruta algorithm within 1000-fold bootstrapping. Six single (clinics, Dose Volume Histogram (DVH), ICI, chemotherapy, radiomics, dosiomics) and four combined models (radiomics + dosiomics, radiomics + DVH + Clinics, dosiomics + DVH + Clinics, radiomics + dosiomics + DVH + Clinics) were trained to predict PTP. Dose-based models were tested using physical dose and EQD2. Four ML-algorithms (random forest (rf), logistic elastic net regression, support vector machine, logitBoost) were trained and tested using 5-fold nested cross validation and Synthetic Minority Oversampling Technique (SMOTE) for resampling in R. Prediction was evaluated using the area under the receiver operating characteristic curve (AUC) on the test sets of the outer folds.

RESULTS

The combined model of all features using EQD2 surpassed all other models (AUC = 0.77, Confidence Interval CI 0.76-0.78). DVH, clinical data and ICI therapy had minor impact on PTP prediction with AUC values between 0.42 and 0.57. All EQD2-based models outperformed models based on physical dose.

CONCLUSIONS

Radiomics + dosiomics based ML models combined with clinical and dosimetric models were found to be suited best for PTP prediction after R(C)T and could improve pre-treatment decision making. Different RT dose fractionation schemes should be considered for dose-based ML approaches.

A dynamic nomogram predicting symptomatic pneumonia in patients with lung cancer receiving thoracic radiation

PURPOSE

The most common and potentially fatal side effect of thoracic radiation therapy is radiation pneumonitis (RP). Due to the lack of effective treatments, predicting radiation pneumonitis is crucial. This study aimed to develop a dynamic nomogram to accurately predict symptomatic pneumonitis (RP ≥ 2) following thoracic radiotherapy for lung cancer patients.

METHODS

Data from patients with pathologically diagnosed lung cancer at the Zhongshan People's Hospital Department of Radiotherapy for Thoracic Cancer between January 2017 and June 2022 were retrospectively analyzed. Risk factors for radiation pneumonitis were identified through multivariate logistic regression analysis and utilized to construct a dynamic nomogram. The predictive performance of the nomogram was validated using a bootstrapped concordance index and calibration plots.

RESULTS

Age, smoking index, chemotherapy, and whole lung V5/MLD were identified as significant factors contributing to the accurate prediction of symptomatic pneumonitis. A dynamic nomogram for symptomatic pneumonitis was developed using these risk factors. The area under the curve was 0.89(95% confidence interval 0.83-0.95). The nomogram demonstrated a concordance index of 0.89(95% confidence interval 0.82-0.95) and was well calibrated. Furthermore, the threshold values for high- risk and low- risk were determined to be 154 using the receiver operating curve.

CONCLUSIONS

The developed dynamic nomogram offers an accurate and convenient tool for clinical application in predicting the risk of symptomatic pneumonitis in patients with lung cancer undergoing thoracic radiation.

Clinical implications of dose to functional lung volumes in the trimodality treatment of esophageal cancer

BACKGROUND

Trimodality treatment, i.e., neoadjuvant chemoradiotherapy (nCRT) followed by surgery, for locally advanced esophageal cancer (EC) improves overall survival but also increases the risk of postoperative pulmonary complications. Here, we tried to identify a relation between dose to functional lung volumes (FLV) as determined by 4D-CT scans in EC patients and treatment-related lung toxicity.

MATERIALS AND METHODS

All patients with EC undergoing trimodality treatment between 2017 and 2022 in UZ Leuven and scanned with 4D-CT-simulation were selected. FLVs were determined based on Jacobian determinants of deformable image registration between maximum inspiration and expiration phases. Dose/volume parameters of the anatomical lung volume (ALV) and FLV were compared between patients with versus without postoperative pulmonary complications. Results of pre- and post-nCRT pulmonary function tests (PFTs) were collected and compared in relation to radiation dose.

RESULTS

Twelve out of 51 EC patients developed postoperative pulmonary complications. ALV was smaller while FLV10Gy and FLV20Gy were larger in patients with complications (respectively 3141 ± 858mL vs 3601 ± 635mL, p = 0.025; 360 ± 216mL vs 264 ± 139mL, p = 0.038; 166 ± 106mL vs 118 ± 63mL, p = 0.030). No differences in ALV dose-volume parameters were detected. Baseline FEV1 and TLC were significantly lower in patients with complications (respectively 90 ± 17%pred vs 102 ± 20%pred, p = 0.033 and 93 ± 17%pred vs 110 ± 13%pred, p = 0.001), though no other PFTs were significantly different between both groups. DLCO was the only PFT that had a meaningful decrease after nCRT (85 ± 17%pred vs 68 ± 15%pred, p < 0.001) but was not related to dose to ALV/FLV.

CONCLUSION

Small ALV and increasing FLV exposed to intermediate (10 to 20 Gy) dose are associated to postoperative pulmonary complications. Changes of DLCO occur during nCRT but do not seem to be related to radiation dose to ALV or FLV. This information could attribute towards toxicity risk prediction and reduction strategies for EC.

Radiation pneumonia predictive model for radiotherapy in esophageal carcinoma patients

BACKGROUND

The machine learning models with dose factors and the deep learning models with dose distribution matrix have been used to building lung toxics models for radiotherapy and achieve promising results. However, few studies have integrated clinical features into deep learning models. This study aimed to explore the role of three-dimension dose distribution and clinical features in predicting radiation pneumonitis (RP) in esophageal cancer patients after radiotherapy and designed a new hybrid deep learning network to predict the incidence of RP.

METHODS

A total of 105 esophageal cancer patients previously treated with radiotherapy were enrolled in this study. The three-dimension (3D) dose distributions within the lung were extracted from the treatment planning system, converted into 3D matrixes and used as inputs to predict RP with ResNet. In total, 15 clinical factors were normalized and converted into one-dimension (1D) matrixes. A new prediction model (HybridNet) was then built based on a hybrid deep learning network, which combined 3D ResNet18 and 1D convolution layers. Machine learning-based prediction models, which use the traditional dosiomic factors with and without the clinical factors as inputs, were also constructed and their predictive performance compared with that of HybridNet using tenfold cross validation. Accuracy and area under the receiver operator characteristic curve (AUC) were used to evaluate the model effect. DeLong test was used to compare the prediction results of the models.

RESULTS

The deep learning-based model achieved superior prediction results compared with machine learning-based models. ResNet performed best in the group that only considered dose factors (accuracy, 0.78 ± 0.05; AUC, 0.82 ± 0.25), whereas HybridNet performed best in the group that considered both dose factors and clinical factors (accuracy, 0.85 ± 0.13; AUC, 0.91 ± 0.09). HybridNet had higher accuracy than that of Resnet (p = 0.009).

CONCLUSION

Based on prediction results, the proposed HybridNet model could predict RP in esophageal cancer patients after radiotherapy with significantly higher accuracy, suggesting its potential as a useful tool for clinical decision-making. This study demonstrated that the information in dose distribution is worth further exploration, and combining multiple types of features contributes to predict radiotherapy response.

Machine learning in non-small cell lung cancer radiotherapy: A bibliometric analysis

Background

Machine learning is now well-developed in non-small cell lung cancer (NSCLC) radiotherapy. But the research trend and hotspots are still unclear. To investigate the progress in machine learning in radiotherapy NSCLC, we performed a bibliometric analysis of associated research and discuss the current research hotspots and potential hot areas in the future.

Methods

The involved researches were obtained from the Web of Science Core Collection database (WoSCC). We used R-studio software, the Bibliometrix package and VOSviewer (Version 1.6.18) software to perform bibliometric analysis.

Results

We found 197 publications about machine learning in radiotherapy for NSCLC in the WoSCC, and the journal Medical Physics contributed the most articles. The University of Texas MD Anderson Cancer Center was the most frequent publishing institution, and the United States contributed most of the publications. In our bibliometric analysis, “radiomics” was the most frequent keyword, and we found that machine learning is mainly applied to analyze medical images in the radiotherapy of NSCLC.

Results

The research we identified about machine learning in NSCLC radiotherapy was mainly related to the radiotherapy planning of NSCLC and the prediction of treatment effects and adverse events in NSCLC patients who were under radiotherapy. Our research has added new insights into machine learning in NSCLC radiotherapy and could help researchers better identify hot research areas in the future.

Machine Learning-Based Multiomics Prediction Model for Radiation Pneumonitis

Objective

The study aims to establish and validate an effective CT-based radiation pneumonitis (RP) prediction model using the multiomics method of radiomics and EQD2-based dosiomics.

Materials and Methods

The study performed a retrospective analysis on 91 nonsmall cell lung cancer patients who received radiotherapy from 2019 to 2021 in our hospital. The patients with RP grade ≥1 were labeled as 1, and those with RP grade < 1 were labeled as 0. The whole lung excluding clinical target volume (lung-CTV) was used as the region of interest (ROI). The radiomic and dosiomic features were extracted from the lung-CTV area's image and dose distribution. Besides, the equivalent dose of the 2 Gy fractionated radiation (EQD₂) model was used to convert the physical dose to the isoeffect dose, and then, the EQD2-based dosiomic (eqd-dosiomic) features were extracted from the isoeffect dose distribution. Four machine learning (ML) models, including DVH, radiomics combined with DVH (radio + DVH), radiomics combined with dosiomics (radio + dose), and radiomics combined with eqd-dosiomics (radio + eqdose), were established to construct the prediction model via eleven different classifiers. The fivefold cross-validation was used to complete the classification experiment. The area under the curve (AUC) of the receiver operating characteristics (ROC), accuracy, precision, recall, and F1-score were calculated to assess the performance level of the prediction models.

Results

Compared with the DVH, radio + DVH, and radio + dose model, the value of the training AUC, accuracy, and F1-score of radio + eqdose was higher, and the difference was statistically significant (p < 0.05). Besides, the average value of the precision and recall of radio + eqdose was higher, but the difference was not statistically significant (p > 0.05).

Conclusion

The performance of using the ML-based multiomics method of radiomics and eqd-dosiomics to predict RP is more efficient and effective.

Predictors of high-grade radiation pneumonitis following radiochemotherapy for locally advanced non-small cell lung cancer: analysis of clinical, radiographic and radiotherapy-related factors

Purpose:

In this study, the relation between radiation pneumonitis (RP) and a wide spectrum of clinical, radiographic and treatment-related factors was investigated. As scoring of low-grade RP can be subjective, RP grade ≥3 (RP ≥ G3) was chosen as a more objective and clinically significant endpoint for this study.

Methods and Materials:

105 consecutive patients with locally advanced non-small cell lung cancer underwent conventionally fractionated radio-(chemo-)therapy to a median dose of 64 Gy. A retrospective analysis of 25 clinical (gender, race, pulmonary function, diabetes, statin use, smoking history), radiographic (emphysema, interstitial lung disease) and radiotherapy dose- and technique-related factors was performed to identify predictors of RP ≥ G3. Following testing of all variables for statistical association with RP using univariate analysis (UVA), a forward selection algorithm was implemented for building a multivariate predictive model (MVA) with limited sample size.

Results:

Median follow-up of surviving patients was 33 months (9–132 months). RP ≥ G3 was diagnosed in 10/105 (9·5%) patients. Median survival was 28·5 months. On UVA, predictors for RP ≥ G3 were diabetes, lower lobe location, planning target volume, volumetric modulated arc therapy (VMAT), lung V5 Gy (%), lung Vspared5 Gy (mL), lung V20 Gy (%) and heart V5 Gy (% and mL). On MVA, VMAT was the only significant predictor for RP ≥ G3 (p = 0·042). Lung V5 Gy and lung V20 Gy were borderline significant for RP ≥ G3. Patients with RP ≥ 3 had a median survival of 10 months compared to 29·5 months with RP < G3 (p = 0·02).

Conclusions:

In this study, VMAT was the only factor that was significantly correlated with RP ≥ G3. Avoiding RP ≥ G3 is important as a toxicity per se and as a risk factor for poor survival. To reduce RP, caution needs to be taken to reduce low-dose lung volumes in addition to other well-established dose constraints.

A Comparison of Isotoxic Dose-escalated Radiotherapy in Lung Cancer with Moderate Deep Inspiration Breath Hold, Mid-ventilation and Internal Target Volume Techniques

AIMS

With interest in normal tissue sparing and dose-escalated radiotherapy in the treatment of inoperable locally advanced non-small cell lung cancer, this study investigated the impact of motion-managed moderate deep inspiration breath hold (mDIBH) on normal tissue sparing and dose-escalation potential and compared this to planning with a four-dimensional motion-encompassing internal target volume or motion-compensating mid-ventilation approach.

MATERIALS AND METHODS

Twenty-one patients underwent four-dimensional and mDIBH planning computed tomography scans. Internal and mid-ventilation target volumes were generated on the four-dimensional scan, with mDIBH target volumes generated on the mDIBH scan. Isotoxic target dose-escalation guidelines were used to generate six plans per patient: three with a target dose cap and three without. Target dose-escalation potential, normal tissue complication probability and differences in pre-specified dose-volume metrics were evaluated for the three motion-management techniques.

RESULTS

The mean total lung volume was significantly greater with mDIBH compared with four-dimensional scans. Lung dose (mean and V21 Gy) and mean heart dose were significantly reduced with mDIBH in comparison with four-dimensional-based approaches, and this translated to a significant reduction in heart and lung normal tissue complication probability with mDIBH. In 20/21 patients, the trial target prescription dose cap of 79.2 Gy was achievable with all motion-management techniques.

CONCLUSION

mDIBH aids lung and heart dose sparing in isotoxic dose-escalated radiotherapy compared with four-dimensional planning techniques. Given concerns about lung and cardiac toxicity, particularly in an era of consolidation immunotherapy, reduced normal tissue doses may be advantageous for treatment tolerance and outcome.

Pulmonary dose tolerance in hemithorax radiotherapy for Ewing sarcoma of the chest wall: Are we overestimating the risk of radiation pneumonitis?

BACKGROUND

Children with chest wall Ewing sarcoma with malignant pulmonary effusion or pleural stranding require hemithorax radiation, often with plans that exceed lung constraints. We investigated disease control and pneumonitis in children requiring hemithorax radiation.

PROCEDURE

Eleven children (median age 13 years) received hemithorax radiotherapy. Symptomatic radiation pneumonitis was considered National Cancer Institute Common Terminology Criteria for Adverse Events (CTCAE) grade 1+ with respiratory symptoms. Mean lung dose (MLD), volume of lung exposed to a dose ≥5 Gy (V5), ≥20 Gy (V20), and ≥35 Gy (V35) were recorded. Adult and pediatric lung constraints were obtained from Quantitative Analysis of Normal Tissue Effects in the Clinic (QUANTEC) guidelines and Children's Oncology Group (COG) protocols, respectively.

RESULTS

Median hemithorax dose was 15 Gy (1.5 Gy/fraction). Median total dose was 51 Gy (1.8 Gy/fraction). Most plans delivered both protons and photons. The ipsilateral MLD, V5, and V20 were 27.2 Gy, 100%, and 48.3%; the bilateral MLD, V20, and V35 were 14.1 Gy, 22.8%, and 14.3%, respectively. One hundred percent, 36%, and 91% of treatments exceeded recommended adult ipsilateral lung constraints of V5 <65%, V20 <52%, and MLD of 22 Gy; 64%, 45%, and 82% exceeded COG bilateral lung constraints of V20 <20%, MLD <15 Gy, and MLD <12 Gy, respectively; 82% of treatments exceeded the COG ipsilateral lung constraint of V20 <30%. At a median 36 months (range 12-129), the symptomatic radiation pneumonitis incidence was 0%. Two patients progressed with nonpulmonary metastatic disease and died at a median 12 months following radiotherapy.

CONCLUSIONS

Existing guidelines may overestimate pneumonitis risk, even among young children receiving multiagent chemotherapy. For children with chest wall Ewing sarcoma and other thoracic malignancies, more data are needed to refine pediatric dose-effect models for pulmonary toxicity.

Construction and Verification of a Radiation Pneumonia Prediction Model Based on Multiple Parameters

Objective:

Patients with lung cancer are at risk of radiation pneumonia (RP) after receiving radiotherapy. We established a prediction model according to the critical indicators extracted from radiation pneumonia patients.

Materials and Methods:

74 radiation pneumonia patients were involved in the training set. Firstly, the clinical data, hematological and radiation dose parameters of the 74 patients were screened by Logistics regression univariate analysis according to the level of radiation pneumonia. Next, Stepwise regression analysis was utilized to construct the regression model. Then, the influence of continuous variables on RP was tested by smoothing function. Finally, the model was externally verified by 30 patients in validation set and visualized by R code.

Results:

In the training set, there was 40 patients suffered≥ level 2 acute radiation pneumonia. Clinical data (diabetes), blood indexes (lymphocyte percentage, basophil percentage, platelet count) and radiation dose (V15 > 40%, V20 > 30%, V35 >18%, V40 > 15%) were related to radiation pneumonia (P < 0.05). Particularly, stepwise regression analysis indicated that the history of diabetes, the basophils percentage, platelet count and V20 could be the best combination used for predicting radiation pneumonia. The column chart was obtained by fitting the regression model with the combined indicator. The receiver operating characteristic (ROC) curve showed that the AUC in the development term was 0.853, the AUC was 0.656 in the validation term. And calibration curves of both groups showed the high stability in efficiently diagnostic. Furthermore, the DCA curve showed that the model had a satisfactory positive net benefit.

Conclusion:

The combination of the basophils percentage, platelet count and V20 is available to build a predictive model of radiation pneumonia for patients with advanced lung cancer.

A deep learning-based dual-omics prediction model for radiation pneumonitis

PURPOSE

Radiation pneumonitis (RP) is the main source of toxicity in thoracic radiotherapy. This study proposed a deep learning-based dual-omics model, which aims to improve the RP prediction performance by integrating more data points and exploring the data in greater depth.

MATERIALS AND METHODS

The bimodality data were the original dose (OD) distribution and the ventilation image (VI) derived from four-dimensional computed tomography (4DCT). The functional dose (FD) distribution was obtained by weighting OD with VI. A pre-trained three-dimensional convolution (C3D) network was used to extract the features from FD, VI, and OD. The extracted features were then filtered and selected using entropy-based methods. The prediction models were constructed with four most commonly used binary classifiers. Cross-validation, bootstrap, and nested sampling methods were adopted in the process of training and hyper-tuning.

RESULTS

Data from 217 thoracic cancer patients treated with radiotherapy were used to train and validate the prediction model. The 4DCT-based VI showed the inhomogeneous pulmonary function of the lungs. More than half of the extracted features were singular (of none-zero value for few patients), which were eliminated to improve the stability of the model. The area under curve (AUC) of the dual-omics model was 0.874 (95% confidence interval: 0.871-0.877), and the AUC of the single-omics model was 0.780 (0.775-0.785, VI) and 0.810 (0.804-0.811, OD), respectively.

CONCLUSIONS

The dual-omics outperformed single-omics for RP prediction, which can be contributed to: (1) using more data points; (2) exploring the data in greater depth; and (3) incorporating of the bimodality data.

Usefulness of Simple Original Interstitial Lung Abnormality Scores for Predicting Radiation Pneumonitis Requiring Steroidal Treatment After Definitive Radiation Therapy for Patients With Locally Advanced Non-Small Cell Lung Cancer

Purpose

Adjuvant durvalumab has become a standard treatment after chemoradiation therapy for patients with locally advanced non-small cell lung cancer (LA-NSCLC). Accordingly, predicting radiation pneumonitis (RP) requiring steroidal treatment (steroid-RP) is of utmost importance because steroidal administration is reported to weaken the effectiveness of immunotherapy. However, grade 2 RP was used as an index of RP in previous studies, but it is an ambiguous definition because it includes not only steroid-RP but also a mild cough requiring only a cough medicine. Therefore, in this study, steroid-RP was used for evaluating RP, and the purpose of this study was to investigate predictive factors of steroid-RP, including original simple interstitial lung abnormality scores (ILASs).

Methods and Materials

A total of 145 patients with LA-NSCLC who received definitive radiation therapy (DRT) in our institution from January 2014 to May 2017 were identified. Original ILASs, performance status, age, respiratory function, Brinkman index, concurrent administration of chemotherapy, and dose-volume histogram metrics of the lung were analyzed to evaluate their association with steroid-RP. Additionally, 3 diagnostic radiologists evaluated the patients' pre-DRT chest computed tomography images and determined the simple ILASs. ILASs were rated as follows: 0: none; 1: abnormality without honeycombing (ground-glass attenuation, fine reticular opacity, and microcysts); and 2: honeycombing.

Results

The median follow-up period was 729 days. Thirty-one patients (21.4%) experienced steroid-RP. In the univariate analysis, lung V5/V10/VS5, Brinkman index, and ILASs were significant predictive factors of steroid-RP. Additionally, multivariate analysis including Brinkman index ≥840, lung V5 ≥37%, and an ILAS ≥1 revealed that only an ILAS (P = .001) was an independent predictive factor of steroid-RP.

Conclusions

The original simple ILAS was an easy-to-use tool and a significant predictive factor of steroid-RP in DRT in patients with LA-NSCLC.

Effect of tumor and normal lung volumes on the lung volume-dose parameters of IMRT in non-small-cell lung cancer

OBJECTIVES

To explore the effect of tumor and normal lung volumes on lung volume-dose parameters in patients with non-small-cell lung cancer (NSCLC) who had undergone intensity-modulated radiation therapy (IMRT).

METHODS

The clinical data of 208 patients with NSCLC who underwent radical IMRT between June 2014 and June 2018 were retrospectively analyzed. A regression model curve was used to evaluate the effect of tumor and normal lung volumes on normal lung relative volumes receiving greater than 5 and 20 Gy (V5, V20), on mean lung dose (MLD), and on absolute volumes spared from greater than 5 and 20 Gy (AVS5, AVS20).

RESULTS

The V5, V20, and MLD of the bilateral lung were fitted to a quadratic equation curve with the change in tumor volume, which increased initially and then decreased when the tumor volume increased. The V5, V20, and MLD of the lung reached their apex when the tumor volumes were 288.07, 341.69, and 326.83 cm3, respectively. AVS5 and AVS20 decreased in a logarithmic curve with an increase in tumor volume. The V5, V20, and MLD of the small normal lung volume group were all significantly higher than those of the large normal lung volume group (p<0.001, p=0.004, p=0.002). However, the AVS5 and AVS20 of the small normal lung volume group were all significantly lower than those of the large normal lung volume group (p<0.001).

CONCLUSION

The effects of tumor volume and normal lung volume on dose-volume parameters should be considered. AVS5 is an important supplementary dose limitation parameter for patients whose tumor volume exceeds a certain boundary value (approximately 300 cm3).

Early variations in lymphocytes and T lymphocyte subsets are associated with radiation pneumonitis in lung cancer patients and experimental mice received thoracic irradiation

There were no ideal markers to predict the development of radiation pneumonitis (RP). We want to investigate the value of variations of lymphocytes and T lymphocyte subsets in predicting RP after radiotherapy (RT) of lung cancer based on previous clinical findings. A total of 182 lung cancer patients who received RT were retrospectively analyzed. Circulating lymphocytes and T lymphocyte subsets were measured before, during, and after RT. Patients were evaluated from the start of RT to 6 months post‐RT. A mice model with acute radiation‐induced lung injury was established and circulating lymphocytes were measured weekly until 8 weeks after irradiation. Univariate and multivariate analyses were adopted to identify risk factors of RP. Lymphocyte levels significantly decreased (P < .001) in patients before RP symptoms developed that also was able to be seen in the mice model and the values recovered during remission of symptoms. The decrease in lymphocyte count reflected the severity of RP. Meanwhile, CD4⁺ T lymphocyte count was significantly lower during the occurrence of symptoms in patients with RP than in those without RP (P < .001), and it improved along with RP recovery. Levels of lymphocytes and CD4⁺ T lymphocyte subsets proved as independent predictors of RP. Here we showed that lower peripheral blood levels of lymphocytes and CD4⁺ T lymphocyte were associated with an increased risk of RP, which was validated by this mice model, and thus are associated with differences in radiation‐induced lung toxicity among individuals and help identify those who are susceptible to developing RP after RT.

Advances in Preclinical Research Models of Radiation-Induced Cardiac Toxicity

Radiation therapy (RT) is an important component of cancer therapy, with >50% of cancer patients receiving RT. As the number of cancer survivors increases, the short- and long-term side effects of cancer therapy are of growing concern. Side effects of RT for thoracic tumors, notably cardiac and pulmonary toxicities, can cause morbidity and mortality in long-term cancer survivors. An understanding of the biological pathways and mechanisms involved in normal tissue toxicity from RT will improve future cancer treatments by reducing the risk of long-term side effects. Many of these mechanistic studies are performed in animal models of radiation exposure. In this area of research, the use of small animal image-guided RT with treatment planning systems that allow more accurate dose determination has the potential to revolutionize knowledge of clinically relevant tumor and normal tissue radiobiology. However, there are still a number of challenges to overcome to optimize such radiation delivery, including dose verification and calibration, determination of doses received by adjacent normal tissues that can affect outcomes, and motion management and identifying variation in doses due to animal heterogeneity. In addition, recent studies have begun to determine how animal strain and sex affect normal tissue radiation injuries. This review article discusses the known and potential benefits and caveats of newer technologies and methods used for small animal radiation delivery, as well as how the choice of animal models, including variables such as species, strain, and age, can alter the severity of cardiac radiation toxicities and impact their clinical relevance.

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

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.

High incidence of radiation pneumonitis in lung cancer patients with chronic silicosis treated with radiotherapy

Silica is an independent risk factor for lung cancer in addition to smoking. Chronic silicosis is one of the most common and serious occupational diseases associated with poor prognosis. However, the role of radiotherapy is unclear in patients with chronic silicosis. We conducted a retrospective study to evaluate efficacy and safety in lung cancer patients with chronic silicosis, especially focusing on the incidence of radiation pneumonitis (RP). Lung cancer patients with chronic silicosis who had been treated with radiotherapy from 2005 to 2018 in our hospital were enrolled in this retrospective study. RP was graded according to the National Cancer Institute's Common Terminology Criteria for Adverse Events (CTCAE), version 3.0. Of the 22 patients, ten (45.5%) developed RP ≥2. Two RP-related deaths (9.1%) occurred within 3 months after radiotherapy. Dosimetric factors V5, V10, V15, V20 and mean lung dose (MLD) were significantly higher in patients who had RP >2 (P < 0.05). The median overall survival times in patients with RP ≤2 and RP>2 were 11.5 months and 7.1 months, respectively. Radiotherapy is associated with excessive and fatal pulmonary toxicity in lung cancer patients with chronic silicosis.

Machine Learning to Build and Validate a Model for Radiation Pneumonitis Prediction in Patients with Non-Small Cell Lung Cancer

PURPOSE

Radiation pneumonitis is an important adverse event in patients with non-small cell lung cancer (NSCLC) receiving thoracic radiotherapy. However, the risk of radiation pneumonitis grade ≥ 2 (RP2) has not been well predicted. This study hypothesized that inflammatory cytokines or the dynamic changes during radiotherapy can improve predictive accuracy for RP2.

EXPERIMENTAL DESIGN

Levels of 30 inflammatory cytokines and clinical information in patients with stages I-III NSCLC treated with radiotherapy were from our prospective studies. Statistical analysis was used to select predictive cytokine candidates and clinical covariates for adjustment. Machine learning algorithm was used to develop the generalized linear model for predicting risk RP2.

RESULTS

A total of 131 patients were eligible and 17 (13.0%) developed RP2. IL8 and CCL2 had significantly (Bonferroni) lower expression levels in patients with RP2 than without RP2. But none of the changes in cytokine levels during radiotherapy was significantly associated with RP2. The final predictive GLM model for RP2 was established, including IL8 and CCL2 at baseline level and two clinical variables. Nomogram was constructed based on the GLM model. The model's predicting ability was validated in the completely independent test set (AUC = 0.863, accuracy = 80.0%, sensitivity = 100%, specificity = 76.5%).

CONCLUSIONS

By machine learning, this study has developed and validated a comprehensive model integrating inflammatory cytokines with clinical variables to predict RP2 before radiotherapy that provides an opportunity to guide clinicians.

Dosiomics: Extracting 3D Spatial Features From Dose Distribution to Predict Incidence of Radiation Pneumonitis

Radiation pneumonitis (RP) is one of the major toxicities of thoracic radiation therapy. RP incidence has been proven to be closely associated with the dosimetric factors and normal tissue control possibility (NTCP) factors. However, because these factors only utilize limited information of the dose distribution, the prediction abilities of these factors are modest. We adopted the dosiomics method for RP prediction. The dosiomics method first extracts spatial features of the dose distribution within ipsilateral, contralateral, and total lungs, and then uses these extracted features to construct prediction model via univariate and multivariate logistic regression (LR). The dosiomics method is validated using 70 non-small cell lung cancer (NSCLC) patients treated with volumetric modulated arc therapy (VMAT) radiotherapy. Dosimetric and NTCP factors based prediction models are also constructed to compare with the dosiomics features based prediction model. For the dosimetric, NTCP and dosiomics factors/features, the most significant single factors/features are the mean dose, parallel/serial (PS) NTCP and gray level co-occurrence matrix (GLCM) contrast of ipsilateral lung, respectively. And the area under curve (AUC) of univariate LR is 0.665, 0.710 and 0.709, respectively. The second significant factors are V₅ of contralateral lung, equivalent uniform dose (EUD) derived from PS NTCP of contralateral lung and the low gray level run emphasis of gray level run length matrix (GLRLM) of total lungs. The AUC of multivariate LR is improved to 0.676, 0.744, and 0.782, respectively. The results demonstrate that the univariate LR of dosiomics features has approximate predictive ability with NTCP factors, and the multivariate LR outperforms both the dosimetric and NTCP factors. In conclusion, the spatial features of dose distribution extracted by the dosiomics method effectively improves the prediction ability.

Interim Analysis of a Two-Institution, Prospective Clinical Trial of 4DCT-Ventilation-based Functional Avoidance Radiation Therapy

PURPOSE

Functional imaging has been proposed that uses 4DCT images to calculate 4DCT-based lung ventilation (4DCT-ventilation). We have started a 2-institution, phase 2 prospective trial evaluating the feasibility, safety, and preliminary efficacy of 4DCT-ventilation functional avoidance. The trial hypothesis is that the rate of grade ≥2 radiation pneumonitis could be reduced to 12% with functional avoidance, compared with a 25% rate of pneumonitis with a historical control. The trial employed a Simon 2-stage design with a planned futility analysis after 17 evaluable patients. The purpose of this work is to present the trial design and implementation, dosimetric data, and clinical results for the planned futility analysis.

METHODS AND MATERIALS

Eligible patients were patients with lung cancer who were prescribed doses of 45 to 75 Gy. For each patient, the 4DCT data were used to generate a 4DCT-ventilation image using the Hounsfield unit technique along with a compressible flow-based image registration algorithm. Two intensity modulated radiation therapy treatment plans were generated: (1) a standard lung plan and (2) a functional avoidance treatment plan that aimed to reduce dose to functional lung while meeting target and normal tissue constraints. Patients were treated with the functional avoidance plan and evaluated for thoracic toxicity (presented as rate and 95% confidence intervals [CI]) with a 1-year follow-up.

RESULTS

The V20 to functional lung was 21.6% ± 9.5% (mean ± standard deviation) with functional avoidance, representing a decrease of 3.2% (P < .01) relative to standard, nonfunctional treatment plans. The rates of grade ≥2 and grade ≥3 radiation pneumonitis were 17.6% (95% CI, 3.8%-43.4%) and 5.9% (95% CI, 0.1%-28.7%), respectively.

CONCLUSIONS

Dosimetrically, functional avoidance achieved reduction in doses to functional lung while meeting target and organ at risk constraints. On the basis of Simon's 2-stage design and the 17.6% grade ≥2 pneumonitis rate, the trial met its futility criteria and has continued accrual.

Predictive relevance of ncRNAs in non-small-cell lung cancer patients with radiotherapy: a review of the published data

Radiotherapy is one of the most commonly used methods to treat non-small-cell lung cancer. However, radiotherapy, especially thoracic radiotherapy, is always accompanied by radiation-induced complications or radioresistance. In this regard, ncRNAs, including miRNAs and lncRNAs, have received considerable interest for their predictive relevance. This review article illustrates the recent findings about the possible involvement of ncRNAs, mainly miRNAs and lncRNAs, in radioresistance and radiation-induced complications and their potential use for predicting radiation-induced complications and radiotherapy response.

Exhaled Nitric Oxide Is Useful in Symptomatic Radioactive Pneumonia: A Retrospective Study

The aim was to defect the exhaled nitric oxide (eNO) prediction value of symptomatic radioactive pneumonia (SRP). 64 cases of lung cancer or esophagus cancer, who had the primary radiotherapy (intensity-modulated radiation therapy), were included from 2015 June to 2016 January. During the following, the patients were divided: the symptomatic radiation pneumonia group (SRP, with the CTCAE v4.0 score > 2) and the asymptomatic radiation pneumonia group (ASRP, with CTCAE v4.0 score ≤ 1). All the patients were measured eNO before and at the end of thoracic radiotherapy and gain the posttherapy eNO value and the eNO ratio (posttherapy eNO value/pretherapy eNO value), then the predictive values of eNO toward SRP were measured using the receiver-operating characteristic (ROC). 17 cases were included in the SRP group and the other 47 were included in the ASRP group. The posttherapy eNO was 29.35 (19~60) bbp versus 20.646 (11~37) (P < 0.001), and the ratio was 1.669 (0.61~3.5) versus 0.920 (0.35~1.5) (P < 0.01) (symptomatic versus asymptomatic). ROC showed that the cutoff value of SRP was 19.5 bbp (posttherapy eNO, area under concentration-time curve (AUC) = 0.879) and 1.305 (eNO ratio, AUC = 0.774), which meant that posttherapy eNO and eNO ratio were useful in finding SRP.

Temporal and spatial dose distribution of radiation pneumonitis after concurrent radiochemotherapy in stage III non-small cell cancer patients

Background and purpose

Radiation pneumonitis (RP) is the most common subacute side effect after concurrent chemoradiotherapy (CRT) for locally advanced non-small cell lung cancer. Several clinical and dose-volume (DV) parameters are associated with a distinct risk of symptomatic RP. The aim of this study was to assess the spatial dose distribution of the RP volume from first occurence to maximum volume expansion of RP.

Material and methods

Between 2007 and 2015, 732 patients with lung cancer were treated in an institution. Thirty-three patients met the following inclusion criteria: an RP grade II after CRT and a radiation dose ≥60 Gy and no prior medical history of cardiopulmonary comorbidities. The images of the first chest computed tomography (CT) confirming the diagnosis of RP and the CT images showing the maximum expansion of RP were merged with the treatment plan. The RP volume was delineated within the treatment plan, and a DV analysis was performed to evaluate the lung dose volume areas in which the RP manifested over time and whether dose volume changes within the RP volume occurred.

Results

A change from clinical diagnosis to maximum expansion of RP was observed as the RP at clinical appearance mainly manifested in the lower dose areas of the lung, whereas the RP volume at maximum expansion manifested in the higher dose areas, resulting in a significant shift of the assessed relative mean dose volume proportions within the RP volume. The mean relative dose volume proportion 0- ≤ 20 Gy decreased from 30.2% (range, 0–100) to 21.9% (range, 0–100; p = 0.04) at the expense of the dose volume > 40 Gy which increased from 39.2% (range, 0–100) to 49.8% (range, 0–100; p = 0.02), whereas the dose relative volume proportion > 20- ≤ 40 Gy showed no relevant change and slightly decreased from 30.6% (range, 0–85.7) to 28.3%, (range, 0–85.7; p = 0.34).

Conclusion

We observed a considerable increase in the relative dose proportions within the RP volume from diagnosis to maximum volume extent from low dose zones below 20 Gy to zones above 40 Gy. Although the clinical impact on RP remains unknown, a reduction of healthy healthy lung tissue receiving >40 Gy (V40) might be an additional parameter for irradiation planning in lung cancer patients.