Recurrence patterns are significantly associated with the 18F‑FDG PET/CT radiomic features of patients with locally advanced non‑small cell lung cancer treated with chemoradiotherapy

A model for predicting the recurrence pattern of patients with locally advanced non-small cell lung cancer (LA-NSCLC) treated with chemoradiotherapy is of great importance for precision treatment. The present study analyzed whether the comprehensive quantitative values (CVs) of the fluorine-18(18F)-fluorodeoxyglucose (FDG) positron emission tomography (PET)/computed tomography (CT) radiomic features and metastasis tumor volume (MTV) combined with clinical characteristics could predict the recurrence pattern of patients with LA-NSCLC treated with chemoradiotherapy. Patients with LA-NSCLC treated with chemoradiotherapy were divided into training and validation sets. The recurrence profile of each patient, including locoregional recurrence (LR), distant metastasis (DM) and both LR/DM were recorded. In the training set of patients, the primary tumor prior radiotherapy with 18F-FDG PET/CT and both primary tumors and lymph node metastasis were considered as the regions of interest (ROIs). The CVs of ROIs were calculated using principal component analysis. Additionally, MTVs were obtained from ROIs. The CVs, MTVs and the clinical characteristics of patients were subjected to aforementioned analysis. Furthermore, for the validation set of patients, the CVs and clinical characteristics of patients with LA-NSCLC were also subjected to logistic regression analysis and the area under the curve (AUC) values calculated. A total of 86 patients with LA-NSCLC were included in the analysis, including 59 and 27 patients in the training and validation sets of patients, respectively. The analysis revealed 22 and 12 cases with LR, 24 and 6 cases with DM and 13 and 9 cases with LR/DM in the training and validation sets of patients, respectively. Histological subtype, CV2-5 and CV3-4 were identified as independent variables in the logistic regression analysis (P<0.05). In addition, the AUC values for diagnosing LR, DM and LR/DM were 0.873, 0.711 and 0.826, and 0.675, 0.772 and 0.708 in the training and validation sets of patients, respectively. Overall, the results demonstrated that the spatial and metabolic heterogeneity quantitative values from the primary tumor combined with the histological subtype could predict the recurrence pattern of patients with LA-NSCLC treated with chemoradiotherapy.

[1]  K. Kaira,et al.  Pattern of Local Failure and its Risk Factors of Locally Advanced Non-small Cell Lung Cancer Treated With Concurrent Chemo-radiotherapy , 2020, AntiCancer Research.

[2]  B. Loo,et al.  Predicting per-lesion local recurrence in locally advanced non-small cell lung cancer following definitive radiation therapy using pre- and mid-treatment metabolic tumor volume , 2020, Radiation oncology.

[3]  A. Bertaut,et al.  Outcomes of concurrent radiotherapy with weekly docetaxel and platinum-based chemotherapy in stage III non-small-cell lung cancer. , 2020, Cancer radiotherapie : journal de la Societe francaise de radiotherapie oncologique.

[4]  T. Mizowaki,et al.  Impact of histology on patterns of failure and clinical outcomes in patients treated with definitive chemoradiotherapy for locally advanced non-small cell lung cancer , 2019, International Journal of Clinical Oncology.

[5]  G. Persson,et al.  An investigative expansion of a competing risk model for first failure site in locally advanced non-small cell lung cancer , 2019, Acta oncologica.

[6]  T. Coroller,et al.  Deep Learning Predicts Lung Cancer Treatment Response from Serial Medical Imaging , 2019, Clinical Cancer Research.

[7]  J. Douillard,et al.  Patterns of locoregional failure in locally advanced non-small cell lung cancer treated with definitive conformal radiotherapy: Results from the Gating 2006 trial. , 2017, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[8]  Andriy Fedorov,et al.  Computational Radiomics System to Decode the Radiographic Phenotype. , 2017, Cancer research.

[9]  W. Curran,et al.  Standard-dose versus high-dose conformal radiotherapy with concurrent and consolidation carboplatin plus paclitaxel with or without cetuximab for patients with stage IIIA or IIIB non-small-cell lung cancer (RTOG 0617): a randomised, two-by-two factorial phase 3 study. , 2015, The Lancet. Oncology.

[10]  David R. Jones,et al.  Differences in patterns of recurrence in early-stage versus locally advanced non-small cell lung cancer. , 2014, The Annals of thoracic surgery.

[11]  Hung-Ming Wang,et al.  Development and Evaluation of an Open-Source Software Package “CGITA” for Quantifying Tumor Heterogeneity with Molecular Images , 2014, BioMed research international.

[12]  이근호,et al.  ROI(Region Of Interest)기반의 차등적 이미지 압축에 관한 연구 , 2014 .

[13]  M. Chatfield,et al.  Outcomes of chemoradiation for patients with locally advanced non‐small‐cell lung cancer , 2013, Internal medicine journal.

[14]  S. Ryu,et al.  ACR Appropriateness Criteria(®) non-spine bone metastases. , 2012, Journal of palliative medicine.

[15]  W. Sze,et al.  Palliative radiotherapy trials for bone metastases: a systematic review. , 2007, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[16]  Guido Gerig,et al.  User-guided 3D active contour segmentation of anatomical structures: Significantly improved efficiency and reliability , 2006, NeuroImage.

[17]  D. Tashkin,et al.  Physiologic characteristics of malignant unilateral main-stem bronchial obstruction. Diagnosis and Nd-YAG laser treatment. , 1988, The American review of respiratory disease.

[18]  T. Dilling,et al.  Analysis of Relapse Events After Definitive Chemoradiotherapy in Locally Advanced Non–Small‐Cell Lung Cancer Patients , 2019, Clinical lung cancer.

[19]  M. Suntharalingam,et al.  Single‐fraction radiotherapy versus multifraction radiotherapy for palliation of painful vertebral bone metastases—Equivalent efficacy, less toxicity, more convenient , 2013, Cancer.

[20]  Vicky Goh,et al.  Quantifying tumour heterogeneity in 18F-FDG PET/CT imaging by texture analysis , 2012, European Journal of Nuclear Medicine and Molecular Imaging.