Predicting Response to Neoadjuvant Chemoradiotherapy in Esophageal Cancer with Textural Features Derived from Pretreatment 18F-FDG PET/CT Imaging

A Postreconstruction Harmonization Method for Multicenter Radiomic Studies in PET

Several reports have shown that radiomic features are affected by acquisition and reconstruction parameters, thus hampering multicenter studies. We propose a method that, by removing the center effect while preserving patient-specific effects, standardizes features measured from PET images obtained using different imaging protocols. Methods: Pretreatment ¹⁸F-FDG PET images of patients with breast cancer were included. In one nuclear medicine department (department A), 63 patients were scanned on a time-of-flight PET/CT scanner, and 16 lesions were triple-negative (TN). In another nuclear medicine department (department B), 74 patients underwent PET/CT on a different brand of scanner and a different reconstruction protocol, and 15 lesions were TN. The images from department A were smoothed using a gaussian filter to mimic data from a third department (department A-S). The primary lesion was segmented to obtain a lesion volume of interest (VOI), and a spheric VOI was set in healthy liver tissue. Three SUVs and 6 textural features were computed in all VOIs. A harmonization method initially described for genomic data was used to estimate the department effect based on the observed feature values. Feature distributions in each department were compared before and after harmonization. Results: In healthy liver tissue, the distributions significantly differed for 4 of 9 features between departments A and B and for 6 of 9 between departments A and A-S (P < 0.05, Wilcoxon test). After harmonization, none of the 9 feature distributions significantly differed between 2 departments (P > 0.1). The same trend was observed in lesions, with a realignment of feature distributions between the departments after harmonization. Identification of TN lesions was largely enhanced after harmonization when the cutoffs were determined on data from one department and applied to data from the other department. Conclusion: The proposed harmonization method is efficient at removing the multicenter effect for textural features and SUVs. The method is easy to use, retains biologic variations not related to a center effect, and does not require any feature recalculation. Such harmonization allows for multicenter studies and for external validation of radiomic models or cutoffs and should facilitate the use of radiomic models in clinical practice.

Increased FDG uptake on late-treatment PET in non-tumour-affected oesophagus is prognostic for pathological complete response and disease recurrence in patients undergoing neoadjuvant radiochemotherapy

PURPOSE

Early side effects including oesophagitis are potential prognostic factors in patients undergoing radiochemotherapy (RCT) for locally advanced oesophageal cancer (LAEC). We assessed the prognostic value of ¹⁸F-fluorodeoxyglucose (FDG) uptake within irradiated non-tumour-affected oesophagus (NTO) during restaging positron emission tomography (PET) as a surrogate for inflammation/oesophagitis.

METHODS

This retrospective evaluation included 64 patients with LAEC who had completed neoadjuvant RCT and had successful oncological resection. All patients underwent FDG PET/CT before and after RCT. In the restaging PET scan maximum and mean standardized uptake values (SUV_max, SUV_mean) were determined in the tumour and NTO. Univariate Cox regression with respect to overall survival, local control, distant metastases and treatment failure was performed. Independence of clinically relevant parameters was tested in a multivariate Cox regression analysis.

RESULTS

Increased FDG uptake, measured in terms of SUV_mean in NTO during restaging was significantly associated with complete pathological remission (p = 0.002) and did not show a high correlation with FDG response of the tumour (rho < 0.3). In the univariate analysis, increased SUV_max and SUV_mean in NTO was associated with improved overall survival (p = 0.011, p = 0.004), better local control (p = 0.051, p = 0.044), a lower rate of treatment failure (p < 0.001 for both) and development of distant metastases (p = 0.012, p = 0.001). In the multivariate analysis, SUV_max and SUV_mean in NTO remained a significant prognostic factor for treatment failure (p < 0.001, p = 0.004) and distant metastases (p = 0.040, p = 0.011).

CONCLUSIONS

FDG uptake in irradiated normal tissues measured on restaging PET has significant prognostic value in patients undergoing neoadjuvant RCT for LAEC. This effect may potentially be of use in treatment personalization.