1
|
Vicente EM, Grande Gutierrez N, Oakes JM, Cammin J, Gopal A, Kipritidis J, Modiri A, Mossahebi S, Mohindra P, Citron WK, Matuszak MM, Timmerman R, Sawant A. Integrating local and distant radiation-induced lung injury: Development and validation of a predictive model for ventilation loss. Med Phys 2024. [PMID: 38820385 DOI: 10.1002/mp.17187] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/18/2023] [Revised: 04/04/2024] [Accepted: 05/11/2024] [Indexed: 06/02/2024] Open
Abstract
BACKGROUND Investigations on radiation-induced lung injury (RILI) have predominantly focused on local effects, primarily those associated with radiation damage to lung parenchyma. However, recent studies from our group and others have revealed that radiation-induced damage to branching serial structures such as airways and vessels may also have a substantial impact on post-radiotherapy (RT) lung function. Furthermore, recent results from multiple functional lung avoidance RT trials, although promising, have demonstrated only modest toxicity reduction, likely because they were primarily focused on dose avoidance to lung parenchyma. These observations emphasize the critical need for predictive dose-response models that effectively incorporate both local and distant RILI effects. PURPOSE We develop and validate a predictive model for ventilation loss after lung RT. This model, referred to as P+A, integrates local (parenchyma [P]) and distant (central and peripheral airways [A]) radiation-induced damage, modeling partial (narrowing) and complete (collapse) obstruction of airways. METHODS In an IRB-approved prospective study, pre-RT breath-hold CTs (BHCTs) and pre- and one-year post-RT 4DCTs were acquired from lung cancer patients treated with definitive RT. Up to 13 generations of airways were automatically segmented on the BHCTs using a research virtual bronchoscopy software. Ventilation maps derived from the 4DCT scans were utilized to quantify pre- and post-RT ventilation, serving, respectively, as input data and reference standard (RS) in model validation. To predict ventilation loss solely due to parenchymal damage (referred to as P model), we used a normal tissue complication probability (NTCP) model. Our model used this NTCP-based estimate and predicted additional loss due radiation-induced partial or complete occlusion of individual airways, applying fluid dynamics principles and a refined version of our previously developed airway radiosensitivity model. Predictions of post-RT ventilation were estimated in the sublobar volumes (SLVs) connected to the terminal airways. To validate the model, we conducted a k-fold cross-validation. Model parameters were optimized as the values that provided the lowest root mean square error (RMSE) between predicted post-RT ventilation and the RS for all SLVs in the training data. The performance of the P+A and the P models was evaluated by comparing their respective post-RT ventilation values with the RS predictions. Additional evaluation using various receiver operating characteristic (ROC) metrics was also performed. RESULTS We extracted a dataset of 560 SLVs from four enrolled patients. Our results demonstrated that the P+A model consistently outperformed the P model, exhibiting RMSEs that were nearly half as low across all patients (13 ± 3 percentile for the P+A model vs. 24 ± 3 percentile for the P model on average). Notably, the P+A model aligned closely with the RS in ventilation loss distributions per lobe, particularly in regions exposed to doses ≥13.5 Gy. The ROC analysis further supported the superior performance of the P+A model compared to the P model in sensitivity (0.98 vs. 0.07), accuracy (0.87 vs. 0.25), and balanced predictions. CONCLUSIONS These early findings indicate that airway damage is a crucial factor in RILI that should be included in dose-response modeling to enhance predictions of post-RT lung function.
Collapse
Affiliation(s)
- Esther M Vicente
- Department of Radiation Oncology, University of Maryland School of Medicine, Baltimore, Maryland, USA
| | - Noelia Grande Gutierrez
- Mechanical Engineering Department, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA
| | - Jessica M Oakes
- Department of Bioengineering, Northeastern University, Boston, Massachusetts, USA
| | - Jochen Cammin
- Department of Radiation Oncology, University of Maryland School of Medicine, Baltimore, Maryland, USA
| | - Arun Gopal
- Department of Radiation Oncology, University of Maryland School of Medicine, Baltimore, Maryland, USA
| | - John Kipritidis
- Department of Radiotherapy, Northern Sydney Cancer Centre, Sydney, Australia
| | - Arezoo Modiri
- Department of Radiation Oncology, University of Maryland School of Medicine, Baltimore, Maryland, USA
| | - Sina Mossahebi
- Department of Radiation Oncology, University of Maryland School of Medicine, Baltimore, Maryland, USA
| | - Pranshu Mohindra
- Department of Radiation Oncology, University of Maryland School of Medicine, Baltimore, Maryland, USA
| | - Wendla K Citron
- Department of Radiation Oncology, University of Maryland School of Medicine, Baltimore, Maryland, USA
| | - Martha M Matuszak
- Department of Radiation Oncology, University of Michigan, Ann Arbor, Michigan, USA
| | - Robert Timmerman
- Department of Radiation Oncology, UT Southwestern Medical Center, Dallas, Texas, USA
| | - Amit Sawant
- Department of Radiation Oncology, University of Maryland School of Medicine, Baltimore, Maryland, USA
| |
Collapse
|
2
|
Zhou X, Pu Y, Zhang D, Guan Y, Lu Y, Zhang W, Fu C, Fang Q, Zhang H, Liu S, Fan L. Development of machine learning model to predict pulmonary function with low-dose CT-derived parameter response mapping in a community-based chest screening cohort. J Appl Clin Med Phys 2023; 24:e14171. [PMID: 37782241 PMCID: PMC10647993 DOI: 10.1002/acm2.14171] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/12/2023] [Revised: 09/14/2023] [Accepted: 09/20/2023] [Indexed: 10/03/2023] Open
Abstract
PURPOSE To construct and evaluate the performance of a machine learning-based low dose computed tomography (LDCT)-derived parametric response mapping (PRM) model for predicting pulmonary function test (PFT) results. MATERIALS AND METHODS A total of 615 subjects from a community-based screening population (40-74 years old) with PFT parameters, including the ratio of the first second forced expiratory volume to forced vital capacity (FEV1/FVC), the percentage of forced expiratory volume in the one second predicted (FEV1%), and registered inspiration-to-expiration chest CT scanning were enrolled retrospectively. Subjects were classified into a normal, high risk, and COPD group based on PFT. Data of 72 PRM-derived quantitative parameters were collected, including volume and volume percentage of emphysema, functional-small airways disease, and normal lung tissue. A machine-learning with random forest regression model and a multilayer perceptron (MLP) model were constructed and tested on PFT prediction, which was followed by evaluation of classification performance based on the PFT predictions. RESULTS The machine-learning model based on PRM parameters showed better performance for predicting PFT than MLP, with a coefficient of determination (R2 ) of 0.749 and 0.792 for FEV1/FVC and FEV1%, respectively. The Mean Squared Errors (MSE) for FEV1/FVC and FEV1% are 0.0030 and 0.0097 for the random forest model, respectively. The Root Mean Squared Errors (RMSE) for FEV1/FVC and FEV1% are 0.055 and 0.098, respectively. The sensitivity, specificity, and accuracy for differentiating between the normal group and high-risk group were 34/40 (85%), 65/72 (90%), and 99/112 (88%), respectively. For differentiating between the non-COPD group and COPD group, the sensitivity, specificity, and accuracy were 8/9 (89%), 112/112 (100%), 120/121 (99%), respectively. CONCLUSIONS The machine learning-based random forest model predicts PFT results in a community screening population based on PRM, and it identifies high risk COPD from normal populations with high sensitivity and reliably predicts of high-risk COPD.
Collapse
Affiliation(s)
- Xiuxiu Zhou
- Department of RadiologySecond Affiliated Hospital of PLA Naval Medical UniversityShanghaiChina
| | - Yu Pu
- Department of RadiologySecond Affiliated Hospital of PLA Naval Medical UniversityShanghaiChina
| | - Di Zhang
- Department of RadiologySecond Affiliated Hospital of PLA Naval Medical UniversityShanghaiChina
| | - Yu Guan
- Department of RadiologySecond Affiliated Hospital of PLA Naval Medical UniversityShanghaiChina
| | - Yang Lu
- Shanghai Aitrox Technology Corporation LimitedShanghaiChina
| | - Weidong Zhang
- Shanghai Aitrox Technology Corporation LimitedShanghaiChina
| | - Chi‐Cheng Fu
- Shanghai Aitrox Technology Corporation LimitedShanghaiChina
| | - Qu Fang
- Shanghai Aitrox Technology Corporation LimitedShanghaiChina
| | - Hanxiao Zhang
- Department of RadiologySecond Affiliated Hospital of PLA Naval Medical UniversityShanghaiChina
| | - Shiyuan Liu
- Department of RadiologySecond Affiliated Hospital of PLA Naval Medical UniversityShanghaiChina
| | - Li Fan
- Department of RadiologySecond Affiliated Hospital of PLA Naval Medical UniversityShanghaiChina
| |
Collapse
|
3
|
Carbon Monoxide Diffusing Capacity (DL CO) Correlates with CT Morphology after Chemo-Radio-Immunotherapy for Non-Small Cell Lung Cancer Stage III. Diagnostics (Basel) 2022; 12:diagnostics12051027. [PMID: 35626183 PMCID: PMC9139430 DOI: 10.3390/diagnostics12051027] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/23/2022] [Revised: 04/11/2022] [Accepted: 04/12/2022] [Indexed: 02/05/2023] Open
Abstract
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.
Collapse
|