• Lung cancer
• Machine learning
• SBRT
• Symptomatic RP

• Humans
• Radiation Pneumonitis/etiology
• Lung Neoplasms/radiotherapy
• Female
• Male
• Aged
• Carcinoma, Non-Small-Cell Lung/radiotherapy
• Middle Aged
• Tomography, X-Ray Computed/methods
• Radiosurgery/methods
• Radiosurgery/adverse effects
• Radiotherapy Dosage
• Aged, 80 and over
• Retrospective Studies
• Prognosis
• Imaging, Three-Dimensional

• Dynamic nomogram
• Lung cancer
• Symptomatic pneumonia

• Humans
• Lung Neoplasms/radiotherapy
• Lung Neoplasms/complications
• Nomograms
• Radiation Pneumonitis/diagnosis
• Radiation Pneumonitis/epidemiology
• Radiation Pneumonitis/etiology
• Retrospective Studies
• Radiotherapy Dosage
• Pneumonia/etiology
• Pneumonia/complications

• 2019B1101 Zhongshan Social Welfare Science and Technology Research Project

• Adverse events (AEs)
• Clinical trials
• Immune checkpoint inhibitor (ICI)
• RT
• Real-world retrospective data
• Treatment strategy

• Humans
• Bayes Theorem
• Immunotherapy/adverse effects
• Incidence
• Lung Neoplasms/drug therapy
• Lung Neoplasms/radiotherapy
• Network Meta-Analysis
• Pneumonia/epidemiology
• Pneumonia/etiology
• Retrospective Studies

• Humans
• Radiation Pneumonitis/etiology
• Retrospective Studies
• Radiation Oncology
• Esophageal Neoplasms/radiotherapy
• Calibration

• Lung cancer
• Machine learning
• Multiomics
• Radiation pneumonitis
• Survival outcome

• Humans
• Radiation Pneumonitis/diagnosis
• Radiation Pneumonitis/etiology
• Retrospective Studies
• Multiomics
• Lung Neoplasms/radiotherapy
• Risk Factors

• 2020Q11 Youth Science Foundation of Xiangya Hospital
• 2022LNJJ10 National Clinical Research Center for Geriatric Disorders, Xiangya Hospital, Central South University

• dosimetric comparison
• non-small cell lung cancer
• radiation side effects
• radiotherapy technique

This study was designed to establish radiation pneumonitis (RP) prediction models using dosiomics and/or deep learning-based radiomics (DLR) features based on 3D dose distribution.

A total of 140 patients with non-small cell lung cancer who received stereotactic body radiation therapy (SBRT) were retrospectively included in this study. These patients were randomly divided into the training (n = 112) and test (n = 28) sets. Besides, 107 dosiomics features were extracted by Pyradiomics, and 1316 DLR features were extracted by ResNet50. Feature visualization was performed based on Spearman’s correlation coefficients, and feature selection was performed based on the least absolute shrinkage and selection operator. Three different models were constructed based on random forest, including (1) a dosiomics model (a model constructed based on dosiomics features), (2) a DLR model (a model constructed based on DLR features), and (3) a hybrid model (a model constructed based on dosiomics and DLR features). Subsequently, the performance of these three models was compared with receiver operating characteristic curves. Finally, these dosiomics and DLR features were analyzed with Spearman’s correlation coefficients.

In the training set, the area under the curve (AUC) of the dosiomics, DLR, and hybrid models was 0.9986, 0.9992, and 0.9993, respectively; the accuracy of these three models was 0.9643, 0.9464, and 0.9642, respectively. In the test set, the AUC of these three models was 0.8462, 0.8750, and 0.9000, respectively; the accuracy of these three models was 0.8214, 0.7857, and 0.8571, respectively. The hybrid model based on dosiomics and DLR features outperformed other two models. Correlation analysis between dosiomics features and DLR features showed weak correlations. The dosiomics features that correlated DLR features with the Spearman’s rho |ρ| ≥ 0.8 were all first-order features.

The hybrid features based on dosiomics and DLR features from 3D dose distribution could improve the performance of RP prediction after SBRT.

• dosiomics
• multi-omics
• radiation pneumonitis
• radiomics
• radiotherapy

Radiation pneumonitis is a common and serious complication of radiotherapy for thoracic tumours. Although radiotherapy technology is constantly improving, the incidence of radiation pneumonitis is still not low, and severe cases can be life-threatening. Once radiation pneumonitis develops into radiation fibrosis (RF), it will have irreversible consequences, so it is particularly important to prevent the occurrence and development of radiation pneumonitis. Immune checkpoint inhibitors (ICIs) have rapidly altered the treatment landscape for multiple tumour types, providing unprecedented survival in some patients, especially for the treatment of non-small cell lung cancer (NSCLC). However, in addition to its remarkable curative effect, ICls may cause immune-related adverse events. The incidence of checkpoint inhibitor pneumonitis (CIP) is 3% to 5%, and its mortality rate is 10% to 17%. In addition, the incidence of CIP in NSCLC is higher than in other tumour types, reaching 7%–13%. With the increasing use of immune checkpoint inhibitors (ICls) and thoracic radiotherapy in the treatment of patients with NSCLC, ICIs may induce delayed radiation pneumonitis in patients previously treated with radiation therapy, or radiation activation of the systemic immune system increases the toxicity of adverse reactions, which may lead to increased pulmonary toxicity and the incidence of pneumonitis. In this paper, the data about the occurrence of radiation pneumonitis, immune pneumonitis, and combined treatment and the latest related research results will be reviewed.

• immune pneumonitis
• pneumonitis after combination therapy
• radiation pneumonitis
• treatment and management of pneumonitis

Immunotherapy has been administered to many patients with non-small-cell lung cancer (NSCLC). However, only few studies have examined toxicity in patients receiving an immune checkpoint inhibitor (ICI) after concurrent chemoradiotherapy (CCRT). Therefore, we performed a retrospective study to determine factors that predict radiation pneumonitis (RP) in these patients.

We evaluated the size of the planning target volume, mean lung dose (MLD), and the lung volume receiving more than a threshold radiation dose (VD) in 106 patients. The primary endpoint was RP ≥ grade 2, and toxicity was evaluated.

After CCRT, 51/106 patients were treated with ICI. The median follow-up period was 11.5 months (range, 3.0–28.2), and RP ≥ grade 2 occurred in 47 (44.3%) patients: 27 and 20 in the ICI and non-ICI groups, respectively. Among the clinical factors, only the use of ICI was associated with RP (p = 0.043). Four dosimetric variables (MLD, V20, V30, and V40) had prognostic significance in univariate analysis for occurrence of pneumonitis (hazard ratio, p-value; MLD: 2.3, 0.009; V20: 2.9, 0.007; V30: 2.3, 0.004; V40: 2.5, 0.001). Only V20 was a significant risk factor in the non-ICI group, and MLD, V30, and V40 were significant risk factors in the ICI group. The survival and local control rates were superior in the ICI group than in the non-ICI group, but no significance was observed.

Patients receiving ICI after definitive CCRT were more likely to develop RP, which may be related to the lung volume receiving high-dose radiation. Therefore, several factors should be carefully considered for patients with NSCLC.

The online version contains supplementary material available at 10.1186/s13014-021-01930-2.

• Concurrent chemoradiotherapy
• Dosimetric factor
• Immunotherapy
• Non-small-cell lung cancer
• Radiation therapy
• Tumor microenvironment

The purpose of this study is to investigate whether there are predictors and cutoff points that can predict the acceptable lung dose using intensity-modulated radiation therapy (IMRT) and volume-modulated arc therapy (VMAT) in radiotherapy for upper ang middle esophageal cancer.

Eighty-two patients with T-shaped upper-middle esophageal cancer (UMEC) were enrolled in this retrospective study. Jaw-tracking IMRT plan (JT-IMRT), full-arc VMAT plan (F-VMAT), and pactial-arc VMAT plan (P-VMAT) were generated for each patient. Dosimetric parameters such as MLD and V20 of total lung were compared among the three plannings. Ten factors such as PCTV_inferior length and PCTV_inferior length/total lung length were calculated to find the predictors and cutoff points of the predictors. All patients were divided into two groups according to the cutoff points, and the dosimetric differences between the two groups of the three plans were compared. ANOVA, receiver operating characteristic (ROC) analysis, and Mann–Whitney U-test were performed for comparisons between datasets. A p <0.05 was considered statistically significant.

The quality of the targets of the three plannings was comparable. The total lung dose in P-VMAT was significantly lower than that in JT IMRT and F-VMAT. Monitor unit (MU) of F-VMAT and P-VMAT was significantly lower than that of JT IMRT. ROC analysis showed that among JT IMRT, F-VMAT, and P-VMAT, PCTV_i-L, and PCTV_i-L/TL_L had diagnostic power to predict the suitability of RT plans according to lung dose constraints of our department. For JT IMRT, the cutoff points of PCTV_i-L and PCTV_i-L/TL_L were 16.6 and 0.59. For F-VMAT, the cutoff points of PCTV_i-L and PCTV_i-L/TL_L were 16.75 and 0.62. For P-VMAT, the cutoff points of PCTV_i-L and PCTV_i-L/TL_L were 15.15 and 0.59. After Mann–Whitney U-test analysis, it was found that among the three plannings, the group with lower PCTV_i-L and PCTV_i-L/TL_L could significantly reduce the dose of total lung and heart (p <0.05).

PCTV_{i-L <}16.6 and PCTV_i-L/TL_L <0.59 for JT IMRT, PCTV_{i-L <}16.75 and PCTV_i-L/TL_L <0.62 for F-VMAT and PCTV_{i-L <}15.15, and PCTV_i-L/TL_L <0.59 for P-VMAT can predict whether patients with T-shaped UMEC can meet the lung dose limits of our department.

• cutoff point
• esophageal cancer
• intensity-modulated radiotherapy (IMRT)
• total lung dose predictor
• volumetric-modulated arc radiotherapy (VMAT)

• Lung cancer
• Non-small lung cancer
• Postoperative
• Radiotherapy

The safety of thoracic radiotherapy (TRT) after programmed death 1/programmed death ligand 1 (PD‐(L)1) inhibitor treatment in patients with lung cancer was scarcely reported. This retrospective study was conducted to evaluate the incidence, severity, and risk factors of symptomatic treatment‐related pneumonitis in patients with lung cancer who received this sequential combination.

We conducted a retrospective study of a cohort of patients with lung cancer who received TRT after at least two cycles of PD‐(L)1 inhibitor treatment between January 2018 and August 2020. Treatment‐related pneumonitis was evaluated and analyzed to illustrate the safety profile of this sequential combination. Potential risk factors were explored by univariate and multivariate logistic regression analyses.

Among the 828 patients with prior PD‐(L)1 inhibitor treatment, 96 patients receiving subsequent TRT were included in the analysis. Of these, 49 patients (51%) received radical TRT while 47 patients (49%) received palliative TRT. The median total dose was 52 Gy (IQR 50–60 Gy). The median time from the initiation of PD‐(L)1 inhibitor treatment to TRT was 4.8 months (1.6–14.1 months) with most of the patients (74%) administering no less than four cycles of PD‐(L)1 inhibitor. During follow‐up, 47 patients (48.96%) developed symptomatic treatment‐related pneumonitis (grade 2 n = 28, grade ≥3 n = 19) while six patients (6.25%) suffered from fatal toxicity. The median time of pneumonitis onset after completion of TRT was 35 days (0–177 days) with six patients developing during TRT. Pulmonary emphysema and lung V20 were demonstrated to be independent risk factors of symptomatic pneumonitis (OR: 5.67, 95% CI: 1.66–19.37, p = 0.006; OR: 3.49, 95% CI: 1.41–8.66, p = 0.007, respectively).

TRT after PD‐(L)1 inhibitor treatment resulted in significantly increased incidence and severity of treatment‐related pneumonitis in patients with lung cancer. Intensive attention should be emphasized to the safety of this sequential combination in clinical practice.

• PD-(L)1 inhibitor
• lung cancer
• pneumonitis
• safety
• thoracic radiotherapy (TRT)

• Non small cell
• Post-operative radiotherapy
• Radiation techniques
• Toxicity

To evaluate the dosimetric and biological benefits of the fixed-jaw (FJ) intensity-modulated radiation therapy (IMRT) technique for patients with T-shaped esophageal cancer.

FJ IMRT plans were generated for thirty-five patients and compared with jaw tracking (JT) IMRT, static jaw (SJ) IMRT and JT volumetric modulated arc therapy (VMAT). Dosimetric parameters, tumor control probability (TCP) and normal tissue complication probability (NTCP), monitor units (MUs), delivery time and gamma passing rate, as a measure of dosimetric verification, were compared. The correlation between the length of PTV-C below the upper boundary of lung tissue (PTV-C_inferior) and dosimetric parameters and NTCP of the lung tissue were analyzed.

The homogeneity and conformity of the target in the four plans were basically equivalent. When compared to the JT IMRT and SJ IMRT plans, FJ IMRT plan led to a statistically significant improvement in the NTCP and low-middle dosimetric parameters of the lung, and the improvement had a moderately positive correlation with the length of PTV-C_inferior, with a correlation coefficient ranging from 0.523 to 0.797; the FJ IMRT plan exhibited better lung sparing in low-dose volumes than the JT VMAT plan. The FJ IMRT plan had similar MUs (888 ± 99) and delivery times (516.1 ± 54.7 s) as the JT IMRT plan (937 ± 194, 522 ± 5.6 s) but higher than SJ IMRT (713 ± 137, 488.8 ± 45.2 s) and JT VMAT plan (517 ± 59, 263.7 ± 43.3 s).

The FJ IMRT technique is superior in reducing the low-dose volumes of lung tissues for patients with T-shaped esophageal cancer.

• Fixed-jaw
• Jaw tracking
• Radiation pneumonitis
• Static jaw
• T-shaped esophageal cancer
• VMAT

• deep learning
• dose distribution
• dual-omics
• radiation pneumonitis
• ventilation image

• Cancer du poumon non à petites cellules
• Dose-volume histograms
• Histogrammes dose-volume
• Non-small cell lung cancer
• Pneumonectomie
• Pneumonectomy
• Pneumonite par irradiation
• Radiation pneumonitis

• Carcinoma, Non-Small-Cell Lung/radiotherapy
• Carcinoma, Non-Small-Cell Lung/surgery
• Female
• Humans
• Lung Neoplasms/radiotherapy
• Lung Neoplasms/surgery
• Male
• Middle Aged
• Nomograms
• Pneumonectomy
• Postoperative Care
• ROC Curve
• Radiation Pneumonitis/epidemiology
• Radiation Pneumonitis/etiology
• Radiation Pneumonitis/pathology
• Regression Analysis
• Retrospective Studies
• Sensitivity and Specificity
• Tumor Burden

Background: This study aims to establish lung biologically effective dose (BED)–based uniform dosimetric constraints for minimizing the risk of symptomatic radiation pneumonitis (SRP) from stereotactic body radiation therapy (SBRT) using variable fractionations in patients with lung tumors.

Materials and Methods: A total of 102 patients with primary or oligometastatic lung tumors treated with SBRT in our institution were enrolled into this study. The associations between the clinical and dosimetric parameters and the incidences of SRP were analyzed using univariate and multivariate Cox regression hazard models. The receiver operating characteristic (ROC) curve was generated to evaluate the predictive performance of lung BED on the SRP risk compared with the physical dose.

Results: SRP occurred in 11 patients (10.8%). In univariate analysis, the mean lung dose (p = 0.002), V₅ (p = 0.005), V₂₀ (p < 0.001), and the percentage of non-target normal lung volume receiving more than a BED of 5–170 Gy (V_BED5−170, p < 0.05) were associated with SRP. Multivariate logistic regression analysis showed that there existed a significant statistical correlation between SRP and V_BED70 (p < 0.001), which performed better than V₅ or V₂₀ on the ROC curves, resulting in an optimal cut-off value of lung V_BED70 of 2.22%.

Conclusions: This retrospective study indicated that non-target lung BED may better predict SRP from patients with SBRT-treated lung cancer. Limiting the lung V_BED70 below 2.22% may be favorable to reduce the incidence of SRP, which warranted further prospective validation.

• biological effective dose (BED)
• lung cancer
• radiation pneumonitis
• risk factors
• stereotactic body radiation therapy (SBRT)

• Apneic oxygenation
• Fluoroscopy
• High frequency jet ventilation
• Lung immobilization
• Opto-electronic plethysmography
• Tumour surrogate marker

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.

• convolutional neural network
• deep learning
• dose distribution
• dosiomics
• pneumonitis prediction

• Lung cancer
• chronic silicosis
• dosimetric
• radiation pneumonitis
• radiotherapy

• Aged
• Chronic Disease
• Female
• Humans
• Incidence
• Lung Neoplasms/complications
• Lung Neoplasms/diagnostic imaging
• Lung Neoplasms/radiotherapy
• Male
• Middle Aged
• Prognosis
• Radiation Pneumonitis/diagnostic imaging
• Radiation Pneumonitis/epidemiology
• Radiation Pneumonitis/etiology
• Radiation Pneumonitis/physiopathology
• Respiratory Function Tests
• Silicosis/complications
• Silicosis/diagnostic imaging
• Survival Analysis
• Tomography, X-Ray Computed

We evaluated the effects of diabetes mellitus (DM) and DM-related serologic factors (HbA1c and fasting glucose) on the development of radiation pneumonitis in patients with lung cancer.

We retrospectively analyzed the clinical data of 123 patients with lung cancer treated with radiotherapy. Radiation pneumonitis was scored according to the toxicity criteria of the Radiation Therapy Oncology Group. We used binary logistic regression analysis to find significant predictive factors for the development of grade ≥3 radiation pneumonitis.

On univariable analysis, V20, mean lung dose, DM, HbA1c, and fasting glucose level were significantly associated with the development of grade ≥3 radiation pneumonitis. On multivariable analysis, V20, mean lung dose, DM, HbA1c, and fasting glucose level remained significant predictive factors for grade ≥3 radiation pneumonitis. The incidence of grade ≥3 radiation pneumonitis was 44.4% in patients with DM and 20.7% in patients without DM. The incidence of grade ≥3 radiation pneumonitis was 12.7% for HbA1c level ≤6.15% and 41.5% for HbA1c level >6.15%. The incidence of grade ≥3 radiation pneumonitis was 17.2% for fasting glucose level ≤121 mg/dL and 35.5% for fasting glucose level >121 mg/dL.

DM, HbA1c, and fasting glucose level are significant predictive factors for the development of grade ≥3 radiation pneumonitis in patients with lung cancer. Patients with DM, patients who have HbA1c >6.15%, and patients who have fasting glucose >121 mg/dL should be treated with greater caution.

• diabetes mellitus
• lung cancer
• radiation pneumonitis
• radiotherapy

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.

• dose distribution
• dosiomics
• logistic regression
• pneumonitis prediction
• radiomics