Voxel-by-voxel correlation between radiologically radiation induced lung injury and dose after image-guided, intensity modulated radiotherapy for lung tumors

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.

Fast Deformable Image Registration for Real-Time Target Tracking During Radiation Therapy Using Cine MRI and Deep Learning

PURPOSE

We developed a deep learning (DL) model for fast deformable image registration using 2-dimensional sagittal cine magnetic resonance imaging (MRI) acquired during radiation therapy and evaluated its potential for real-time target tracking compared with conventional image registration methods.

METHODS AND MATERIALS

Our DL model uses a pair of cine MRI images as input and provides a motion vector field (MVF) as output. The MVF is then applied to align the input images. A retrospective study was conducted to train and evaluate our model using cine MRI data from patients undergoing treatment for abdominal and thoracic tumors. For each treatment fraction, MR-linear accelerator delivery log files, tracking videos, and cine image files were analyzed. Individual MRI frames were temporally sampled to construct a large set of image registration pairs used to evaluate multiple methods. The DL model was optimized using 5-fold cross validation, and model outputs (transformed images and MVFs) using test set images were saved for comparison with 3 conventional registration methods (affine, b-spline, and demons). Evaluation metrics were 3-fold: (1) registration error, (2) MVF stability (both spatial and temporal), and (3) average computation time.

RESULTS

We analyzed >21 hours of cine MRI (>629,000 frames) acquired during 86 treatment fractions from 21 patients. In a test set of 10,320 image registration pairs, DL registration outperformed conventional methods in both registration error (affine, b-spline, demons, DL; root mean square error: 0.067, 0.040, 0.036, 0.032; paired t test demons vs DL: t[20] = 4.2, P < .001) and computation time per frame (51, 1150, 4583, 8 ms). Among deformable methods, spatial stability of resulting MVFs was comparable; however, the DL model had significantly improved temporal consistency.

CONCLUSIONS

DL-based image registration can leverage large-scale MR cine data sets to outperform conventional registration methods and is a promising solution for real-time deformable motion estimation in radiation therapy.

The relationship between radiation dose and bevacizumab-related imaging abnormality in patients with brain tumors: A voxel-wise normal tissue complication probability (NTCP) analysis

PURPOSE

Bevacizumab-related imaging abnormality (BRIA), appearing as areas of restricted diffusion on magnetic resonance imaging (MRI) and representing atypical coagulative necrosis pathologically, has been observed in patients with brain tumors receiving radiotherapy and bevacizumab. We investigated the role of cumulative radiation dose in BRIA development in a voxel-wise analysis.

METHODS

Patients (n = 18) with BRIA were identified. All had high-grade gliomas or brain metastases treated with radiotherapy and bevacizumab. Areas of BRIA were segmented semi-automatically on diffusion-weighted MRI with apparent diffusion coefficient (ADC) images. To avoid confounding by possible tumor, hypoperfusion was confirmed with perfusion imaging. ADC images and radiation dose maps were co-registered to a high-resolution T1-weighted MRI and registration accuracy was verified. Voxel-wise normal tissue complication probability analyses were performed using a logistic model analyzing the relationship between cumulative voxel equivalent total dose in 2 Gy fractions (EQD2) and BRIA development at each voxel. Confidence intervals for regression model predictions were estimated with bootstrapping.

RESULTS

Among 18 patients, 39 brain tumors were treated. Patients received a median of 4.5 cycles of bevacizumab and 1-4 radiation courses prior to BRIA appearance. Most (64%) treated tumors overlapped with areas of BRIA. The median proportion of each BRIA region of interest volume overlapping with tumor was 98%. We found a dose-dependent association between cumulative voxel EQD2 and the relative probability of BRIA (β0 = -5.1, β1 = 0.03 Gy-1, γ = 1.3).

CONCLUSIONS

BRIA is likely a radiation dose-dependent phenomenon in patients with brain tumors receiving bevacizumab and radiotherapy. The combination of radiation effects and tumor microenvironmental factors in potentiating BRIA in this population should be further investigated.

Radiation pneumonitis prediction after stereotactic body radiation therapy based on 3D dose distribution: dosiomics and/or deep learning-based radiomics features

Background

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.

Methods

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.

Results

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.

Conclusion

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

Predicting Local Failure after Partial Prostate Re-Irradiation Using a Dosiomic-Based Machine Learning Model

The aim of this study is to predict local failure after partial prostate re-irradiation for the treatment of isolated locally recurrent prostate cancer by using a machine learning classifier based on radiomic features from pre-treatment computed tomography (CT), positron-emission tomography (PET) and biological effective dose distribution (BED) of the radiotherapy plan. The analysis was conducted on a monocentric dataset of 43 patients with evidence of isolated intraprostatic recurrence of prostate cancer after primary external beam radiotherapy. All patients received partial prostate re-irradiation delivered by volumetric modulated arc therapy. The gross tumor volume (GTV) of each patient was manually contoured from planning CT, choline-PET and dose maps. An ensemble machine learning pipeline including unbalanced data correction and feature selection was trained using the radiomic and dosiomic features as input for predicting occurrence of local failure. The model performance was assessed using sensitivity, specificity, accuracy and area under receiver operating characteristic curves of the score function in 10-fold cross validation repeated 100 times. Local failure was observed in 13 patients (30%), with a median time to recurrence of 36.7 months (range = 6.1–102.4 months). A four variables ensemble machine learning model resulted in accuracy of 0.62 and AUC 0.65. According to our results, a dosiomic machine learning classifier can predict local failure after partial prostate re-irradiation.

Normal Lung Tissue CT Density Changes after Volumetric-Arc Radiotherapy (VMAT) for Lung Cancer

Radiation-induced lung injury remains a significant toxicity in thoracic radiotherapy. Because a precise diagnosis is difficult and commonly used assessment scales are unclear and subjective, there is a need to establish quantitative and sensitive grading methods. The lung tissue density change expressed in Hounsfield units (HUs) derived from CT scans seems a useful numeric surrogate. The study aimed to confirm a dose-response effect on HU value changes (ΔHU), their evolution in time, and the impact of selected clinical and demographic factors. We used dedicated, self-developed software to register and analyze 120 pairs of initial and follow-up CT scans of 47 lung cancer patients treated with dynamic arc radiotherapy. The differences in HU values between CT scans were calculated within discretized dose-bins limited by isodose lines. We have proved the dose-effect relationship, which is well described with a sigmoid model. We found the time evolution of HU changes to suit a typical clinical presentation of radiation-induced toxicity. Some clinical factors were found to correlate with ΔHU degree: planning target volume (PTV), V35 in the lung, patient’s age and a history of arterial hypertension, and initial lung ventilation intensity. Lung density change assessment turned out to be a sensitive and valuable method of grading post-RT lung toxicity.

Quantitative assessment of intra- and inter-modality deformable image registration of the heart, left ventricle, and thoracic aorta on longitudinal 4D-CT and MR images

Purpose

Magnetic resonance imaging (MRI)‐based investigations into radiotherapy (RT)‐induced cardiotoxicity require reliable registrations of magnetic resonance (MR) imaging to planning computed tomography (CT) for correlation to regional dose. In this study, the accuracy of intra‐ and inter‐modality deformable image registration (DIR) of longitudinal four‐dimensional CT (4D‐CT) and MR images were evaluated for heart, left ventricle (LV), and thoracic aorta (TA).

Methods and materials

Non‐cardiac‐gated 4D‐CT and T1 volumetric interpolated breath‐hold examination (T1‐VIBE) MRI datasets from five lung cancer patients were obtained at two breathing phases (inspiration/expiration) and two time points (before treatment and 5 weeks after initiating RT). Heart, LV, and TA were manually contoured. Each organ underwent three intramodal DIRs ((A) CT modality over time, (B) MR modality over time, and (C) MR contrast effect at the same time) and two intermodal DIRs ((D) CT/MR multimodality at same time and (E) CT/MR multimodality over time). Hausdorff distance (HD), mean distance to agreement (MDA), and Dice were evaluated and assessed for compliance with American Association of Physicists in Medicine (AAPM) Task Group (TG)‐132 recommendations.

Results

Mean values of HD, MDA, and Dice under all registration scenarios for each region of interest ranged between 8.7 and 16.8 mm, 1.0 and 2.6 mm, and 0.85 and 0.95, respectively, and were within the TG‐132 recommended range (MDA < 3 mm, Dice > 0.8). Intramodal DIR showed slightly better results compared to intermodal DIR. Heart and TA demonstrated higher registration accuracy compared to LV for all scenarios except for HD and Dice values in Group A. Significant differences for each metric and tissue of interest were noted between Groups B and D and between Groups B and E. MDA and Dice significantly differed between LV and heart in all registrations except for MDA in Group E.

Conclusions

DIR of the heart, LV, and TA between non‐cardiac‐gated longitudinal 4D‐CT and MRI across two modalities, breathing phases, and pre/post‐contrast is acceptably accurate per AAPM TG‐132 guidelines. This study paves the way for future evaluation of RT‐induced cardiotoxicity and its related factors using multimodality DIR.

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.

Artificial Intelligence and the Medical Physicist: Welcome to the Machine

Artificial intelligence (AI) is a branch of computer science dedicated to giving machines or computers the ability to perform human-like cognitive functions, such as learning, problem-solving, and decision making. Since it is showing superior performance than well-trained human beings in many areas, such as image classification, object detection, speech recognition, and decision-making, AI is expected to change profoundly every area of science, including healthcare and the clinical application of physics to healthcare, referred to as medical physics. As a result, the Italian Association of Medical Physics (AIFM) has created the “AI for Medical Physics” (AI4MP) group with the aims of coordinating the efforts, facilitating the communication, and sharing of the knowledge on AI of the medical physicists (MPs) in Italy. The purpose of this review is to summarize the main applications of AI in medical physics, describe the skills of the MPs in research and clinical applications of AI, and define the major challenges of AI in healthcare.

Prediction of Radiation Pneumonitis With Machine Learning in Stage III Lung Cancer: A Pilot Study

Background:

Radiation pneumonitis (RP) is a dose-limiting toxicity in lung cancer radiotherapy (RT). As risk factors in the development of RP, patient and tumor characteristics, dosimetric parameters, and treatment features are intertwined, and it is not always possible to associate RP with a single parameter. This study aimed to determine the algorithm that most accurately predicted RP development with machine learning.

Methods:

Of the 197 cases diagnosed with stage III lung cancer and underwent RT and chemotherapy between 2014 and 2020, 193 were evaluated. The CTCAE 5.0 grading system was used for the RP evaluation. Synthetic minority oversampling technique was used to create a balanced data set. Logistic regression, artificial neural networks, eXtreme Gradient Boosting (XGB), Support Vector Machines, Random Forest, Gaussian Naive Bayes and Light Gradient Boosting Machine algorithms were used. After the correlation analysis, a permutation-based method was utilized for as a variable selection.

Results:

RP was seen in 51 of the 193 cases. Parameters affecting RP were determined as, total(t)V5, ipsilateral lung D_max, contralateral lung D_max, total lung D_max, gross tumor volume, number of chemotherapy cycles before RT, tumor size, lymph node localization and asbestos exposure. LGBM was found to be the algorithm that best predicted RP at 85% accuracy (confidence interval: 0.73-0.96), 97% sensitivity, and 50% specificity.

Conclusion:

When the clinical and dosimetric parameters were evaluated together, the LGBM algorithm had the highest accuracy in predicting RP. However, in order to use this algorithm in clinical practice, it is necessary to increase data diversity and the number of patients by sharing data between centers.

Prevention and treatment of radiation-induced lung injury

Radiation-induced lung injury (RILI) is a common complication in cancer patients receiving local thoracic radiation and bone marrow transplantation conditioning. It is divided into early-stage radiation pneumonitis and advanced radiation fibrosis of the lung. This severely hampers the quality of life and survival of cancer patients. Meanwhile, RILI is a major factor limiting radiation doses in clinical practice, which affects the local control of cancer. Unfortunately, the mechanism of RILI is still not well defined, and there are no treatment options available for these patients. In this review we summarize the methods and agents used for the treatment and prevention of RILI, with the aim of increasing understanding of RILI.

Radiomics and deep learning in lung cancer

Lung malignancies have been extensively characterized through radiomics and deep learning. By providing a three-dimensional characterization of the lesion, models based on radiomic features from computed tomography (CT) and positron-emission tomography (PET) have been developed to detect nodules, distinguish malignant from benign lesions, characterize their histology, stage, and genotype. Deep learning models have been applied to automatically segment organs at risk in lung cancer radiotherapy, stratify patients according to the risk for local and distant recurrence, and identify patients candidate for molecular targeted therapy and immunotherapy. Moreover, radiomics has also been applied successfully to predict side effects such as radiation- and immunotherapy-induced pneumonitis and differentiate lung injury from recurrence. Radiomics could also untap the potential for further use of the cone beam CT acquired for treatment image guidance, four-dimensional CT, and dose-volume data from radiotherapy treatment plans. Radiomics is expected to increasingly affect the clinical practice of treatment of lung tumors, optimizing the end-to-end diagnosis-treatment-follow-up chain. The main goal of this article is to provide an update on the current status of lung cancer radiomics.

Radiomics for radiation oncologists: are we ready to go?

Radiomics have emerged as an exciting field of research over the past few years, with very wide potential applications in personalised and precision medicine of the future. Radiomics-based approaches are still however limited in daily clinical practice in oncology. This review focus on how radiomics could be incorporated into the radiation therapy pipeline, and globally help the radiation oncologist, from the tumour diagnosis to follow-up after treatment. Radiomics could impact on all steps of the treatment pipeline, once the limitations in terms of robustness and reproducibility are overcome. Major ongoing efforts should be made to collect and share data in the most standardised manner possible.

Evaluation of acute esophageal radiation-induced damage using magnetic resonance imaging: a feasibility study in mice

BACKGROUND

Thoracic and head and neck cancer radiation therapy (RT) can cause damage to nearby healthy organs such as the esophagus, causing acute radiation-induced esophageal damage (ARIED). A non-invasive method to detect and monitor ARIED can facilitate optimizing RT to avoid ARIED while improving local tumor control. Current clinical guidelines are limited to scoring the esophageal damage based on the symptoms of patients. Magnetic resonance imaging (MRI) is a non-invasive imaging modality that may potentially visualize radiation-induced organ damage. We investigated the feasibility of using T2-weighted MRI to detect and monitor ARIED using a two-phased study in mice.

METHODS

The first phase aimed to establish the optimal dose level at which ARIED is inducible and to determine the time points where ARIED is detectable. Twenty four mice received a single dose delivery of 20 and 40 Gy at proximal and distal spots of 10.0 mm (in diameter) on the esophagus. Mice underwent MRI and histopathology analysis with esophageal resection at two, three, and 4 weeks post-irradiation, or earlier in case mice had to be euthanized due to humane endpoints. In the second phase, 32 mice received a 40 Gy single dose and were studied at two, three, and 7 days post-irradiation. We detected ARIED as a change in signal intensity of the MRI images. We measured the width of the hyperintense area around the esophagus in all mice that underwent MRI prior to and after irradiation. We conducted a blind qualitative comparison between MRI findings and histopathology as the gold standard.

RESULTS/CONCLUSIONS

A dose of 40 Gy was needed to induce substantial ARIED. MRI detected ARIED as high signal intensity, visible from 2 days post-irradiation. Quantitative MRI analysis showed that the hyperintense area around the esophagus with severe ARIED was 1.41 mm wider than with no damage and MRI-only mice. The overall sensitivity and specificity were 56 and 43% respectively to detect any form of ARIED. However, in this study MRI correctly detected 100% of severe ARIED cases. Our two-phased preclinical study showed that MRI has the potential to detect ARIED as a change in signal intensity and width of enhancement around the esophagus.

Normal tissue complication probability (NTCP) models for modern radiation therapy

Mathematical models of normal tissue complication probability (NTCP) able to robustly predict radiation-induced morbidities (RIM) play an essential role in the identification of a personalized optimal plan, and represent the key to maximizing the benefits of technological advances in radiation therapy (RT). Most modern RT techniques pose, however, new challenges in estimating the risk of RIM. The aim of this report is to schematically review NTCP models in the framework of advanced radiation therapy techniques. Issues relevant to hypofractionated stereotactic body RT and ion beam therapy are critically reviewed. Reirradiation scenarios for new or recurrent malignances and NTCP are also illustrated. A new phenomenological approach to predict RIM is suggested.

Spatial signature of dose patterns associated with acute radiation-induced lung damage in lung cancer patients treated with stereotactic body radiation therapy

Thoracic radiation therapy (RT) is often associated with lung side effects, whose etiology is still controversial. Our aim was to explore correlations between local dose in the thoracic anatomy and the radiation-induced lung damage (RILD). To this end, we designed a robust scheme for voxel-based analysis (VBA) to explore dose patterns associated with RILD in non-small-cell lung cancer (NSCLC) patients receiving stereotactic body RT (SBRT). We analyzed 106 NSCLC SBRT patients (median prescription dose: 50 Gy; range: [40-54] Gy) in 4 fractions (range: [3-5]) with clinical and dosimetric records suitable for the analysis. The incidence of acute G1 RILD (RTOG grade  ⩾  1) was 68%. Each planning CT and dose map was spatially normalized to a common anatomical reference using a B-spline inter-patient registration algorithm after masking the gross tumor volume. The tumor-subtracted dose maps were converted into biologically effective dose maps (α/β  =  3 Gy). VBA was performed according to a non-parametric permutation test accounting for multiple comparison, based on a cluster analysis method. The underlying general linear model of RILD was designed to include dose maps and each non-dosimetric variable significantly correlated with RILD. The clusters of voxels with dose differences significantly correlated with RILD at a given p -level (S _p) were generated. The only non-dosimetric variable significantly correlated with RILD was the chronic obstructive pulmonary disease (p   =  0.034). Patients with G1 RILD received significantly (p   ⩽  0.05) higher doses in two voxel clusters S _0.05 in the lower-left lung (14 cm³) and in an area (64 cm³) largely included within the ventricles. The applied VBA represents a powerful tool to probe the dose susceptibility of inhomogeneous organs in clinical radiobiology studies. The identified subregions with dose differences associated with G1 RILD in both the heart and lower lungs endorse a trend of previously reported hypotheses on lung toxicity radiobiology.

Deformable image registration for radiation therapy: principle, methods, applications and evaluation

Background: Deformable image registration (DIR) is increasingly used in the field of radiation therapy (RT) to account for anatomical deformations. The aims of this paper are to describe the main applications of DIR in RT and discuss current DIR evaluation methods. Methods: Articles on DIR published from January 2000 to October 2018 were extracted from PubMed and Science Direct. Our search was restricted to articles that report data obtained from humans, were written in English, and address DIR methods for RT. A total of 207 articles were selected from among 2506 identified in the search process. Results: At planning, DIR is used for organ delineation using atlas-based segmentation, deformation-based planning target volume definition, functional planning and magnetic resonance imaging-based dose calculation. In image-guided RT, DIR is used for contour propagation and dose calculation on per-treatment imaging. DIR is also used to determine the accumulated dose from fraction to fraction in external beam RT and brachytherapy, both for dose reporting and adaptive RT. In the case of re-irradiation, DIR can be used to estimate the cumulated dose of the two irradiations. Finally, DIR can be used to predict toxicity in voxel-wise population analysis. However, the evaluation of DIR remains an open issue, especially when dealing with complex cases such as the disappearance of matter. To quantify DIR uncertainties, most evaluation methods are limited to geometry-based metrics. Software companies have now integrated DIR tools into treatment planning systems for clinical use, such as contour propagation and fraction dose accumulation. Conclusions: DIR is increasingly important in RT applications, from planning to toxicity prediction. DIR is routinely used to reduce the workload of contour propagation. However, its use for complex dosimetric applications must be carefully evaluated by combining quantitative and qualitative analyses.

PACE: A Probabilistic Atlas for Normal Tissue Complication Estimation in Radiation Oncology

In radiation oncology, the need for a modern Normal Tissue Complication Probability (NTCP) philosophy to include voxel-based evidence on organ radio-sensitivity (RS) has been acknowledged. Here a new formalism (Probabilistic Atlas for Complication Estimation, PACE) to predict radiation-induced morbidity (RIM) is presented. The adopted strategy basically consists in keeping the structure of a classical, phenomenological NTCP model, such as the Lyman-Kutcher-Burman (LKB), and replacing the dose distribution with a collection of RIM odds, including also significant non-dosimetric covariates, as input of the model framework. The theory was first demonstrated in silico on synthetic dose maps, classified according to synthetic outcomes. PACE was then applied to a clinical dataset of thoracic cancer patients classified for lung fibrosis. LKB models were trained for comparison. Overall, the obtained learning curves showed that the PACE model outperformed the LKB and predicted synthetic outcomes with an accuracy >0.8. On the real patients, PACE performance, evaluated by both discrimination and calibration, was significantly higher than LKB. This trend was confirmed by cross-validation. Furthermore, the capability to infer the spatial pattern of underlying RS map for the analyzed RIM was successfully demonstrated, thus paving the way to new perspectives of NTCP models as learning tools.

Assessment and agreement of the CT appearance pattern and its severity grading of radiation-induced lung injury after stereotactic body radiotherapy for lung cancer

Purpose

Radiographic severity of radiation-induced lung injury (RILI) has not been well-studied. The goal of this study was to assess the CT appearance pattern and severity of RILI without consideration of the clinical presentation.

Material and methods

A total of 49 patients, 41 with primary lung cancer and 8 with metastatic lung cancer, were treated by 4-fraction stereotactic body radiotherapy (SBRT). RILI after SBRT was separately assessed by two observers. The early and late CT appearance patterns and CT-based severity grading were explored.

Results

The median follow-up period was 39.0 months. In the early CT findings of observers 1 and 2, there was diffuse consolidation in 15 and 8, diffuse ground glass opacity (GGO) in 0 and 0, patchy consolidation and GGO in 17 and 20, patchy GGO in 3 and 3, and no changes in 10 and 14, respectively (kappa = 0.61). In late CT findings of observer 1 and 2, there were modified conventional pattern in 28 and 24, mass-like pattern in 8 and 11, scar-like pattern in 12 and 12, and no changes in 1 and 2, respectively (kappa = 0.63). In the results of the CT-based grading by observers 1 and 2, there were grade 0 in 1 and 2, grade 1 in 10 and 14, grade 2 in 31 and 29, grade 3 in 7 and 4, and none of grade 4 or more, respectively (kappa = 0.66). According to multivariate analyses (MVA), the significant predicting factors of grade 2 or more CT-based RILI were age (p = 0.01), oxygen dependence (p = 0.03) and interstitial shadow (p = 0.03).

Conclusions

The agreement of the CT appearance and CT-based grading between two observers was good. These indicators may be able to provide us with more objective information and a better understanding of RILI.

Image-Guided Fluorescence Endomicroscopy: From Macro- to Micro-Imaging of Radiation-Induced Pulmonary Fibrosis

Radiation-induced pulmonary fibrosis (RIPF) is a debilitating side effect of radiation therapy (RT) of several cancers including lung and breast cancers. Current clinical methods to assess and monitor RIPF involve diagnostic computed tomography (CT) imaging, which is restricted to anatomical macroscopic changes. Confocal laser endomicroscopy (CLE) or fluorescence endomicroscopy (FE) in combination with a fibrosis-targeted fluorescent probe allows to visualize RIPF in real-time at the microscopic level. However, a major limitation of FE imaging is the lack of anatomical localization of the endomicroscope within the lung. In this work, we proposed and validated the use of x-ray fluoroscopy-guidance in a rat model of RIPF to pinpoint the location of the endomicroscope during FE imaging and map it back to its anatomical location in the corresponding CT image. For varying endomicroscope positions, we observed a positive correlation between CT and FE imaging as indicated by the significant association between increased lung density on CT and the presence of fluorescent fiber structures with FE in RT cases compared to Control. Combining multimodality imaging allows visualization and quantification of molecular processes at specific locations within the injured lung. The proposed image-guided FE method can be extended to other disease models and is amenable to clinical translation for assessing and monitoring fibrotic damage.