PET in lung cancerCombined PET/CT image characteristics for radiotherapy tumor response in lung cancer
Section snippets
Patient population
The study was approved by the Washington University School of Medicine Institutional Review Board. Patients with new diagnosis of NSCLC confined to the thorax who had not previously received thoracic irradiation were candidates for definitive therapy with either conventionally fractionated radiation therapy (RT) or stereotactic body radiosurgery (SBRT) as a component of their treatment and had an archived treatment plan, were eligible to participate. Patients were treated between 2003 and 2007
Experimental results
For 27 patients, thirty-two variables were extracted from both PET and CT pre-treatment images. The univariate correlations between PET/CT features and clinical endpoints of loco-regional or local control have been summarized in Table 2, Table 3 and Supplementary Figure S2.
For loco-regional recurrence, IVH variables had a high correlation with treatment outcomes over a wide range of values (x) as shown in the Supplementary Figure. For PET features without motion correction, IVH slope had the
Discussion
Our ability to cure patients with locally advanced NSCLC is severely limited by our ability to control disease locally. As a result, more aggressive treatment strategies are indicated. However, treatment related toxicity limits our ability to intensify treatment. As such, improved tools to predict tumor control and risk for toxicity would allow us to individualize treatment. For example, one could advocate escalating treatment in a patient predicted to be a poor responder with low likelihood
Conclusions
We have demonstrated an alternative feature-based approach to evaluate radiation treatment outcomes using PET and CT images in unresectable NSCLC patients. Our study demonstrates that multimodality image-feature modeling holds promise in planning individualized treatment by integrating information from multiple imaging modalities or multiple tracers if available. Combination with dosimetric variables improved performance in some cases; however, validation on larger prospective datasets is still
Conflict of Interest Statement
None.
Acknowledgements
The authors would like to thank Dr. Joseph Deasy for CERR support. This work was supported in part by the Barnes-Jewish Hospital Foundation (6661-01) and the CIHR-MOP-114910.
References (27)
- et al.
Final results of phase III trial in regionally advanced unresectable non-small cell lung cancer: Radiation Therapy Oncology Group, Eastern Cooperative Oncology Group, and Southwest Oncology Group
Chest
(2000) - et al.
Impact of tumor control on survival in carcinoma of the lung treated with irradiation
Int J Radiat Oncol Biol Phys
(1986) - et al.
Early FDG–PET imaging after radical radiotherapy for non-small-cell lung cancer: Inflammatory changes in normal tissues correlate with tumor response and do not confound therapeutic response evaluation
Int J Radiat Oncol Biol Phys
(2004) - et al.
Metabolic control probability in tumour subvolumes or how to guide tumour dose redistribution in non-small cell lung cancer (NSCLC): An exploratory clinical study
Radiother Oncol
(2009) - et al.
Early CT and FDG-metabolic tumour volume changes show a significant correlation with survival in stage I-III small cell lung cancer: A hypothesis generating study
Radiother Oncol
(2011) - et al.
Development and external validation of a predictive model for pathological complete response of rectal cancer patients including sequential PET-CT imaging
Radiother Oncol
(2011) - et al.
Diagnostic performance of response assessment FDG–PET/CT in patients with head and neck squamous cell carcinoma treated with high-precision definitive (chemo)radiation
Radiother Oncol
(2010) - et al.
Exploring feature-based approaches in PET images for predicting cancer treatment outcomes
Pattern Recogn
(2009) - et al.
Respiratory motion in position emission tomography/computed tomography
A Review. Semin Nucl Med
(2008) - et al.
Impact of FDG–PET on radiation therapy volume delineation in non-small-cell lung cancer
Int J Radiat Oncol Biol Phys
(2004)
Multi-variable modeling of radiotherapy outcomes including dose-volume and clinical factors
Int J Radiat Oncol Biol Phys
Cancer Statistics, 2008
CA Cancer J Clin
Cited by (178)
Data and model aggregation for radiomics applications: Emerging trend and open challenges
2023, Information FusionArtificial intelligence-assisted selection and efficacy prediction of antineoplastic strategies for precision cancer therapy
2023, Seminars in Cancer BiologyRadiomics for Predicting Lung Cancer Outcomes Following Radiotherapy: A Systematic Review
2022, Clinical OncologyImmunotherapy treatment outcome prediction in metastatic melanoma through an automated multi-objective delta-radiomics model
2021, Computers in Biology and Medicine