Radiation-Induced Lung Density Changes on CT Scan for NSCLC: No Impact of Dose-Escalation Level or Volume

Characterisation of quantitative imaging biomarkers for inflammatory and fibrotic radiation-induced lung injuries using preclinical radiomics

BACKGROUND AND PURPOSE

Radiomics is a rapidly evolving area of research that uses medical images to develop prognostic and predictive imaging biomarkers. In this study, we aimed to identify radiomics features correlated with longitudinal biomarkers in preclinical models of acute inflammatory and late fibrotic phenotypes following irradiation.

MATERIALS AND METHODS

Female C3H/HeN and C57BL6 mice were irradiated with 20 Gy targeting the upper lobe of the right lung under cone-beam computed tomography (CBCT) image-guidance. Blood samples and lung tissue were collected at baseline, weeks 1, 10 & 30 to assess changes in serum cytokines and histological biomarkers. The right lung was segmented on longitudinal CBCT scans using ITK-SNAP. Unfiltered and filtered (wavelet) radiomics features (n = 842) were extracted using PyRadiomics. Longitudinal changes were assessed by delta analysis and principal component analysis (PCA) was used to remove redundancy and identify clustering. Prediction of acute (week 1) and late responses (weeks 20 & 30) was performed through deep learning using the Random Forest Classifier (RFC) model.

RESULTS

Radiomics features were identified that correlated with inflammatory and fibrotic phenotypes. Predictive features for fibrosis were detected from PCA at 10 weeks yet overt tissue density was not detectable until 30 weeks. RFC prediction models trained on 5 features were created for inflammation (AUC 0.88), early-detection of fibrosis (AUC 0.79) and established fibrosis (AUC 0.96).

CONCLUSIONS

This study demonstrates the application of deep learning radiomics to establish predictive models of acute and late lung injury. This approach supports the wider application of radiomics as a non-invasive tool for detection of radiation-induced lung complications.

Mechanistic model of radiotherapy-induced lung fibrosis using coupled 3D agent-based and Monte Carlo simulations

BACKGROUND

Mechanistic modelling of normal tissue toxicities is unfolding as an alternative to the phenomenological normal tissue complication probability models. The latter, currently used in the clinics, rely exclusively on limited patient data and neglect spatial dose distribution information. Among the various approaches, agent-based models are appealing as they provide the means to include patient-specific parameters and simulate long-term effects in complex systems. However, Monte Carlo tools remain the state-of-the-art for modelling radiation transport and provide measurements of the delivered dose with unmatched precision.

METHODS

In this work, we develop and characterize a coupled 3D agent-based - Monte Carlo model that mechanistically simulates the onset of the radiation-induced lung fibrosis in an alveolar segment. To the best of our knowledge, this is the first such model.

RESULTS

Our model replicates extracellular matrix patterns, radiation-induced lung fibrosis severity indexes and functional subunits survivals that show qualitative agreement with experimental studies and are consistent with our past results. Moreover, in accordance with experimental results, higher functional subunits survival and lower radiation-induced lung fibrosis severity indexes are achieved when a 5-fractions treatment is simulated. Finally, the model shows increased sensitivity to more uniform protons dose distributions with respect to more heterogeneous ones from photon irradiation.

CONCLUSIONS

This study lays thus the groundwork for further investigating the effects of different radiotherapeutic treatments on the onset of radiation-induced lung fibrosis via mechanistic modelling.

An Agent-Based Model of Radiation-Induced Lung Fibrosis

Early- and late-phase radiation-induced lung injuries, namely pneumonitis and lung fibrosis (RILF), severely constrain the maximum dose and irradiated volume in thoracic radiotherapy. As the most radiosensitive targets, epithelial cells respond to radiation either by undergoing apoptosis or switching to a senescent phenotype that triggers the immune system and damages surrounding healthy cells. Unresolved inflammation stimulates mesenchymal cells' proliferation and extracellular matrix (ECM) secretion, which irreversibly stiffens the alveolar walls and leads to respiratory failure. Although a thorough understanding is lacking, RILF and idiopathic pulmonary fibrosis share multiple pathways and would mutually benefit from further insights into disease progression. Furthermore, current normal tissue complication probability (NTCP) models rely on clinical experience to set tolerance doses for organs at risk and leave aside mechanistic interpretations of the undergoing processes. To these aims, we implemented a 3D agent-based model (ABM) of an alveolar duct that simulates cell dynamics and substance diffusion following radiation injury. Emphasis was placed on cell repopulation, senescent clearance, and intra/inter-alveolar bystander senescence while tracking ECM deposition. Our ABM successfully replicates early and late fibrotic response patterns reported in the literature along with the ECM sigmoidal dose-response curve. Moreover, surrogate measures of RILF severity via a custom indicator show qualitative agreement with published fibrosis indices. Finally, our ABM provides a fully mechanistic alveolar survival curve highlighting the need to include bystander damage in lung NTCP models.

Random Walk Algorithm-Based Computer Tomography (CT) Image Segmentation Analysis Effect of Spiriva Combined with Symbicort on Immunologic Function of Non-Small-Cell Lung Cancer

The objective of this research was to explore the effect of the treatment regimen of Spiriva combined with Symbicort on the immune function of non-small-cell lung cancer (NSCLC) based on computed tomography (CT) imaging features. An automatic CT image segmentation algorithm (RW-CT) was constructed based on random walk (RW) and image segmentation technology. The image segmentation algorithm based on the Toboggan method (C-CT) was introduced to compare with the traditional RW algorithm. 60 subjects were divided into four groups: a Chinese combined with Western medicine group (treated with Spiriva combined with Symbicort, group C+W), a Chinese medicine group (treated with Spiriva, group C), a Western medicine group (treated with Symbicort, group W), and a model group for control (group M). The results show that the Dice coefficient of the RW-CT algorithm was obviously larger than that of the C-CT algorithm and the RW algorithm, while the Hausdorff distance (HD) of the RW-CT algorithm was much smaller than that of the other two algorithms ( $P<0.05$ ). The proportion of positive cells of hypoxia-inducible factor-1α (HIF-1α) in group C+W was the least (15%-23%), followed by the group W (21%-29%) and the group C (28%-37%), and that in the group M was the highest (39%-49%). There was a remarkable difference in the immunohistochemical scores (HIS) of vascular endothelial growth factor (VEGF) in the tumor tissues between group C+W and the group M ( $H=14.200$ , $P=0.001$ ), but there was no great difference from the group C and the group W ( $P>0.05$ ). There was a notable difference in the IHS of vascular endothelial factor recepto-2 (VEGFR-2) between the group C+W medication group and the group M ( $H=12.800$ , $P=0.002$ ), and there was no statistical difference between the group C and W ( $P>0.05$ ). In short, the RW-CT constructed based on RW was better than the traditional algorithms for CT image segmentation. The Spiriva combined with Symbicort could effectively inhibit the expression of VEGF, VEGFR-2, and HIF-1α in NSCLC and promote the immunologic function of the body.

Carbon Monoxide Diffusing Capacity (DLCO) Correlates with CT Morphology after Chemo-Radio-Immunotherapy for Non-Small Cell Lung Cancer Stage III

Introduction: Curatively intended chemo-radio-immunotherapy for non-small cell lung cancer (NSCLC) stage III may lead to post-therapeutic pulmonary function (PF) impairment. We hypothesized that the decrease in global PF corresponds to the increase in tissue density in follow-up CTs. Hence, the study aim was to correlate the dynamics in radiographic alterations to carbon monoxide diffusing capacity (DLCO) and FEV1, which may contribute to a better understanding of radiation-induced lung disease. Methods: Eighty-five patients with NSCLC III were included. All of them received two cycles of platinum-based induction chemotherapy followed by high dose radiation. Thereafter, durvalumab was administered for one year in 63/85 patients (74%). Pulmonary function tests (PFTs) were performed three months and six months after completion of radiotherapy (RT) and compared to baseline. At the same time points, patients underwent diagnostic CT (dCT). These dCTs were matched to the planning CT (pCT) using RayStation® Model Based Segmentation and deformable image registration. Differential volumes defined by specific isodoses were generated to correlate them with the PFTs. Results: In general, significant correlations between PFTs and differential volumes were found in the mid-dose range, especially for the volume of the lungs receiving between 65% and 45% of the dose prescribed (V65−45%) and DLCO (p<0.01). This volume range predicted DLCO after RT (p-value 0.03) as well. In multivariate analysis, DLCO (p-value 0.040) and FEV1 (p-value 0.014) predicted pneumonitis. Conclusions: The current analysis revealed a strong relation between the dynamics of DLCO and CT morphology changes in the mid-dose range, which convincingly indicates the importance of routinely used PFTs in the context of a curative treatment approach.

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.

A Novel and Automated Approach to Classify Radiation Induced Lung Tissue Damage on CT Scans

Radiation-induced lung damage (RILD) is a common side effect of radiotherapy (RT). The ability to automatically segment, classify, and quantify different types of lung parenchymal change is essential to uncover underlying patterns of RILD and their evolution over time. A RILD dedicated tissue classification system was developed to describe lung parenchymal tissue changes on a voxel-wise level. The classification system was automated for segmentation of five lung tissue classes on computed tomography (CT) scans that described incrementally increasing tissue density, ranging from normal lung (Class 1) to consolidation (Class 5). For ground truth data generation, we employed a two-stage data annotation approach, akin to active learning. Manual segmentation was used to train a stage one auto-segmentation method. These results were manually refined and used to train the stage two auto-segmentation algorithm. The stage two auto-segmentation algorithm was an ensemble of six 2D Unets using different loss functions and numbers of input channels. The development dataset used in this study consisted of 40 cases, each with a pre-radiotherapy, 3-, 6-, 12-, and 24-month follow-up CT scans (n = 200 CT scans). The method was assessed on a hold-out test dataset of 6 cases (n = 30 CT scans). The global Dice score coefficients (DSC) achieved for each tissue class were: Class (1) 99% and 98%, Class (2) 71% and 44%, Class (3) 56% and 26%, Class (4) 79% and 47%, and Class (5) 96% and 92%, for development and test subsets, respectively. The lowest values for the test subsets were caused by imaging artefacts or reflected subgroups that occurred infrequently and with smaller overall parenchymal volumes. We performed qualitative evaluation on the test dataset presenting manual and auto-segmentation to a blinded independent radiologist to rate them as 'acceptable', 'minor disagreement' or 'major disagreement'. The auto-segmentation ratings were similar to the manual segmentation, both having approximately 90% of cases rated as acceptable. The proposed framework for auto-segmentation of different lung tissue classes produces acceptable results in the majority of cases and has the potential to facilitate future large studies of RILD.

Quantitative imaging for radiotherapy purposes

Quantitative imaging biomarkers show great potential for use in radiotherapy. Quantitative images based on microscopic tissue properties and tissue function can be used to improve contouring of the radiotherapy targets. Furthermore, quantitative imaging biomarkers might be used to predict treatment response for several treatment regimens and hence be used as a tool for treatment stratification, either to determine which treatment modality is most promising or to determine patient-specific radiation dose. Finally, patient-specific radiation doses can be further tailored to a tissue/voxel specific radiation dose when quantitative imaging is used for dose painting. In this review, published standards, guidelines and recommendations on quantitative imaging assessment using CT, PET and MRI are discussed. Furthermore, critical issues regarding the use of quantitative imaging for radiation oncology purposes and resultant pending research topics are identified.

Regional lung avoidance by CT numbers to reduce radiation-induced lung damage risk in non-small-cell lung cancer: a simulation study

Background: Selective avoidance aims at sparing functional lung regions. Here, we preferentially direct radiation to irreversibly nonfunctional lung areas based on planning CT imaging to reduce functional lung damage.Materials and methods: For 12 stage I-IV NSCLC patients, 5 lung substructures were segmented on the planning CT, combining voxels <-900HU, -900HU to -801HU, -800HU to -701HU, -700HU to -601HU and ≥-600HU (Level 1 to 5). Two VMAT plans were optimized: a reference plan blinded from substructures and a selective avoidance plan (AV) imposing gradually stricter constraints on Level 1-5, based on previously validated associations between lung subvolume baseline density and density increase (ΔHU) after treatment. Characteristics of treatment plans were evaluated, including subvolumes, dose, and predicted ΔHU (with reported 95% CI reflecting prediction model uncertainty).Results: Segmented substructures were on average 477 cc, 1157 cc, 484 cc, 69 cc, and 123 cc (Level 1-5). AV plans could spare Level 3-5, e.g., mean dose decrease of 3.5 Gy (range 0.6 Gy; 6.0 Gy) for Level 5, p<.001. This significantly reduced the average lung mass with predicted ΔHU>20HU by 12.5 g (95% CI: 5.4-16.9) and 27.1 g (95% CI: 10.2-32.9) for a median and upper 10th percentile patient susceptibility for damage simulation, respectively.Conclusions: Lung damage avoidance based on CT density is feasible and easy to implement. A biomarker providing a reliable selection of patients with high susceptibility for lung damage will be crucial to show the clinical relevance of this avoidance planning strategy.