Predicting the Efficacy of SBRT for Lung Cancer with 18F-FDG PET/CT Radiogenomics.

PURPOSE: to develop a radiogenomic model on the basis of 18F-FDG PET/CT radiomics and clinical-parameter EGFR for predicting PFS stratification in lung-cancer patients after SBRT treatment. METHODS: A total of 123 patients with lung cancer who had undergone 18F-FDG PET/CT examination before SBRT from September 2014 to December 2021 were retrospectively analyzed. All patients' PET/CT images were manually segmented, and the radiomic features were extracted. LASSO regression was used to select radiomic features. Logistic regression analysis was used to screen clinical features to establish the clinical EGFR model, and a radiogenomic model was constructed by combining radiomics and clinical EGFR. We used the receiver operating characteristic curve and calibration curve to assess the efficacy of the models. The decision curve and influence curve analysis were used to evaluate the clinical value of the models. The bootstrap method was used to validate the radiogenomic model, and the mean AUC was calculated to assess the model. RESULTS: A total of 2042 radiomics features were extracted. Five radiomic features were related to the PFS stratification of lung-cancer patients with SBRT. T-stage and overall stages (TNM) were independent factors for predicting PFS stratification. AUCs under the ROC curve of the radiomics, clinical EGFR, and radiogenomic models were 0.84, 0.67, and 0.86, respectively. The calibration curve shows that the predicted value of the radiogenomic model was in good agreement with the actual value. The decision and influence curve showed that the model had high clinical application values. After Bootstrap validation, the mean AUC of the radiogenomic model was 0.850(95%CI 0.849-0.851). CONCLUSIONS: The radiogenomic model based on 18F-FDG PET/CT radiomics and clinical EGFR has good application value in predicting the PFS stratification of lung-cancer patients after SBRT treatment.

CT-based radiomics nomogram may predict who can benefit from adaptive radiotherapy in patients with local advanced-NSCLC patients.

BACKGROUND: Although adaptive radiotherapy (ART) has many advantages, ART is not universal in the clinical appliance due to the consumption of a lot of labor, and economic burden. It is necessary to explore a CT stimulation-based radiomics model for screening who can get more benefits from ART in locally advanced non-small cell lung cancer (NSCLC) patients. METHOD: 183 cases of NSCLC patients receiving concurrent chemoradiotherapy with an adaptive approach were enrolled as a primary cohort, while 28 cases from another hospital served as an independent external validation cohort. Tumor regression assessment was conducted based on GTV reduction (Criteria A) or according to RECIST Version 1.1(Criteria B). The radiomics features were extracted by the "PyRadiomics" package and further screened by the LASSO method. Then, logistic regression was used to establish the model. Bootstrap and external validation were applied to verify the stability of the model. The receiver operating characteristic (ROC) curve was delineated to assess the predictive efficacy of the radiomics model. Dose-volume histograms were quantitatively compared between the initial and composite ART plans. Clinical endpoints included overall survival (OS) and progression-free survival (PFS). RESULT: There were no significant differences in clinical features between tumor regression-resistant (RR) and tumor regression-sensitivity (RS) groups. The AUC values of the Criteria A model and Criteria B model were 0.767 and 0.771, respectively. Bootstrapping validation and external validation confirmed the stability of models. In all patients, there was a significant benefit of ART in the lung, heart, cord, and esophagus compared to non-ART, particularly in RS patients. Furthermore, PFS and OS from ART were significantly longer in RS as defined by Criterion B than in RR patients with the same ART application. CONCLUSION: CT-based radiomics can screen out the patients who can gain more benefits from ART, which contribute to guiding and popularizing the application of ART strategy in the clinic within economic benefits and feasibility.

Efficient dose-volume histogram-based pretreatment patient-specific quality assurance methodology with combined deep learning and machine learning models for volumetric modulated arc radiotherapy.

BACKGROUND: Weak correlation between gamma passing rates and dose differences in target volumes and organs at risk (OARs) has been reported in several studies. Evaluation on the differences between planned dose-volume histogram (DVH) and reconstructed DVH from measurement was adopted and incorporated into patient-specific quality assurance (PSQA). However, it is difficult to develop a methodology allowing the evaluation of errors on DVHs accurately and quickly. PURPOSE: To develop a DVH-based pretreatment PSQA for volumetric modulated arc therapy (VMAT) with combined deep learning (DL) and machine learning models to overcome the limitation of conventional gamma index (GI) and improve the efficiency of DVH-based PSQA. METHODS: A DL model with a three-dimensional squeeze-and-excitation residual blocks incorporated into a modified U-net was developed to predict the measured PSQA DVHs of 208 head-and-neck (H&N) cancer patients underwent VMAT between 2018 and 2021 from two hospitals, in which 162 cases was randomly selected for training, 18 for validation, and 28 for testing. After evaluating the differences between treatment planning system (TPS) and PSQA DVHs predicted by DL model with multiple metrics, a pass or fail (PoF) classification model was developed using XGBoost algorithm. Evaluation of domain experts on dose errors between TPS and reconstructed PSQA DVHs was taken as ground truth for PoF classification model training. RESULTS: The prediction model was able to achieve a good agreement between predicted, measured, and TPS doses. Quantitative evaluation demonstrated no significant difference between predicted PSQA dose and measured dose for target and OARs, except for Dmean of PTV6900 (p = 0.001), D50 of PTV6000 (p = 0.014), D2 of PTV5400 (p = 0.009), D50 of left parotid (p = 0.015), and Dmax of left inner ear (p = 0.007). The XGBoost model achieved an area under curves, accuracy, sensitivity, and specificity of 0.89 versus 0.88, 0.89 versus 0.86, 0. 71 versus 0.71, and 0.95 versus 0.91 with measured and predicted PSQA doses, respectively. The agreement between domain experts and the classification model was 86% for 28 test cases. CONCLUSIONS: The successful prediction of PSQA doses and classification of PoF for H&N VMAT PSQA indicating that this DVH-based PSQA method is promising to overcome the limitations of GI and to improve the efficiency and accuracy of VMAT delivery.

Enhanced CT-Based Radiomics to Predict Micropapillary Pattern Within Lung Invasive Adenocarcinoma.

OBJECTIVE: We aimed to investigate whether enhanced CT-based radiomics can predict micropapillary pattern (MPP) of lung invasive adenocarcinoma (IAC) in the pre-op phase and to develop an individual diagnostic predictive model for MPP in IAC. METHODS: 170 patients who underwent complete resection for pathologically confirmed lung IAC were included in our study. Of these 121 were used as a training cohort and the other 49 as a test cohort. Clinical features and enhanced CT images were collected and assessed. Quantitative CT analysis was performed based on feature types including first order, shape, gray-level co-occurrence matrix-based, gray-level size zone matrix-based, gray-level run length matrix-based, gray-level dependence matrix-based, neighboring gray tone difference matrix-based features and transform types including Log, wavelet and local binary pattern. Receiver operating characteristic (ROC) and area under the curve (AUC) were used to value the ability to identify the lung IAC with MPP using these characteristics. RESULTS: Using quantitative CT analysis, one thousand three hundred and seventeen radiomics features were deciphered from R (https://www.r-project.org/). Then these radiomic features were decreased to 14 features after dimension reduction using the least absolute shrinkage and selection operator (LASSO) method in R. After correlation analysis, 5 key features were obtained and used as signatures for predicting MPP within IAC. The individualized prediction model which included age, smoking, family tumor history and radiomics signature had better identification (AUC=0.739) in comparison with the model consisting only of radiomics features (AUC=0.722). DeLong test showed that the difference in AUC between the two models was statistically significant (P<0.01). Compared with the simple radiomics model, the more comprehensive individual prediction model has better prediction performance. CONCLUSION: The use of radiomics approach is of great value in the diagnosis of tumors by non-invasive means. The individualized prediction model in the study, when incorporated with age, smoking and radiomics signature, had effective predictive performance of lung IAC with MPP lesions. The combination of imaging features and clinical features can provide additional diagnostic value to identify the micropapillary pattern in IAC and can affect clinical diagnosis and treatment.

Radiation-induced lung damage in patients treated with stereotactic body radiotherapy after EGFR-TKIs: is there any difference from stereotactic body radiotherapy alone?

BACKGROUND: To quantitatively evaluate lung damage after treatment of epidermal growth factor receptor tyrosine kinase inhibitors (EGFR-TKIs) and stereotactic body radiotherapy (SBRT) in patients with nonsmall cell lung cancer (NSCLC), and compare that of SBRT only treatment. METHODS: Eligible patients from an IRB-approved prospective clinical trial had one month of EGFRTKIs treatment followed by SBRT (TKI + SBRT) and with 3-month follow-up high resolution CT. NSCLC patients treated with SBRT alone during the same time period without EGFR-TKIs or other systemic therapies were identified as controls. The lung damage was assessed clinically by pneumonitis and quantitatively using by CT intensity (Hounsfield unit, HU) changes. The mean HU values were extracted for regions of the lungs receiving the same dose range at 10 Gy intervals to generate dose-response curves (DRC). The relationship of HU changes and radiation dose was modeled using a Probit model. RESULTS: Four out of 20 (25%) TKI + SBRT patients and none of 19 (0%) SBRT alone patients had developed grade 2 and above pneumonitis (P=0.053), respectively. Sixty percent of TKI + SBRT patients and 30% SBRT alone patients had HU changes of the normal lung density >200 HU, respectively. There were significant differences in the DRC and in lung HU changes between the two groups (all P<0.05). The physical dose for a 50% complication risk (TD50) of CT lung damage was 52 Gy (CI: 46-59) in TKI + SBRT group versus 72 Gy (CI: 58-107) in SBRT alone group (P<0.01). CONCLUSIONS: Compared to patients treated with SBRT alone, patients treated with EGFR-TKIs followed by SBRT were more incline to develop radiation pneumonitis, and resulted in greater lung CT intensity changes and steeper dose-CT lung damage response relationship at 3 months post treatment. Future study with larger number of patients and longer follow-up period is warranted to validate this finding.

Intermediate Dose-Volume Parameters, Not Low-Dose Bath, Is Superior to Predict Radiation Pneumonitis for Lung Cancer Treated With Intensity-Modulated Radiotherapy.

PURPOSE: Although intensity-modulated radiotherapy (IMRT) is now a preferred option for conventionally fractionated RT in lung cancer, the commonly used cutoff values of the dosimetric constraints are still mainly derived from the data using three-dimensional conformal radiotherapy (3D-CRT). We aimed to compare the prediction performance among different dosimetric parameters for acute radiation pneumonitis (RP) in patients with lung cancer received IMRT. METHODS: A total of 236 patients treated with IMRT were retrospectively reviewed in two independent groups of lung cancer from January 2014 to August 2018. The primary endpoint was grade 2 or higher acute RP (RP2). Dose metrics were generated from the bilateral lung volume outside GTV (VdoseG) and PTV (VdoseP). The associations of RP2 with clinical variables, dose-volume parameters and mean lung dose (MLD) were analyzed by univariate and multivariate logistic regression. The power of discrimination among each predictor was assessed by employing the bootstrapped area under the receiver operating characteristic curve (AUC), net reclassification improvement (NRI), and the integrated discrimination improvement (IDI). RESULTS: Thirty-four (14.4%) out of 236 patients developed acute RP2 after the end of IMRT. The clinical parameters were identified as less important predictors for RP2 based on univariate and multivariate analysis. In both studied groups, the significance of association was more convincing in V20P, V30P, and MLDP (smaller Ps) than V5G and V5P. The largest bootstrapped AUC was identified for the V30P. We found a trend of better discriminating performance for the V20P and V30P, and MLDP than the V5G and V5P according to the higher values in AUC, IDI, and NRI analysis. To limit RP2 incidence less than 20%, the V30P cutoff was 14.5%. CONCLUSIONS: This study identified the intermediate dose-volume parameters V20P and V30P with better prediction performance for acute RP2 than low-dose metrics V5G and V5P. Among all studied predictors, the V30P had the best discriminating power, and should be considered as a supplement to the traditional dose constraints in lung cancer treated with IMRT.