Search

Abstract: The purpose of this paper is to describe the experiments and methods that led to the geometrical interpretation of new-generation commercial PET-CT scanners, finalized to off-line PET-based treatment verification in ion beam therapy. Typically, the geometrical correspondence between the image domain (i.e., the dicom PET) and the sinogram domain (i.e., the PET raw data) is not explicitly described by scanner vendors. Hence, the proposed characterization can be applied to commercial PET-CT scanners used in biomedical research, for the development of technologies and methods requiring the use of PET raw data, without having access to confidential information from the vendors. [Copyright &y& Elsevier]

• Deep learning PET and CT-based DM and OS time-to-event models showed predictive capability. • PET-only achieved the best prognosis performance. • Unlike CT, GTV segmentation is not necessary for PET-based prognosis. Recent studies have shown that deep learning based on pre-treatment positron emission tomography (PET) or computed tomography (CT) is promising for distant metastasis (DM) and overall survival (OS) prognosis in head and neck cancer (HNC). However, lesion segmentation is typically required, resulting in a predictive power susceptible to variations in primary and lymph node gross tumor volume (GTV) segmentation. This study aimed at achieving prognosis without GTV segmentation, and extending single modality prognosis to joint PET/CT to allow investigating the predictive performance of combined- compared to single-modality inputs. We employed a 3D-Resnet combined with a time-to-event outcome model to incorporate censoring information. We focused on the prognosis of DM and OS for HNC patients. For each clinical endpoint, five models with PET and/or CT images as input were compared: PET-GTV, PET-only, CT-GTV, CT-only, and PET/CT-GTV models, where -GTV indicates that the corresponding images were masked using the GTV contour. Publicly available delineated CT and PET scans from 4 different Canadian hospitals (293) and the MAASTRO clinic (74) were used for training by 3-fold cross-validation (CV). For independent testing, we used 110 patients from a collaborating institution. The predictive performance was evaluated via Harrell's Concordance Index (HCI) and Kaplan-Meier curves. In a 5-year time-to-event analysis, all models could produce CV HCIs with median values around 0.8 for DM and 0.7 for OS. The best performance was obtained with the PET-only model, achieving a median testing HCI of 0.82 for DM and 0.69 for OS. Compared with the PET/CT-GTV model, the PET-only still had advantages of up to 0.07 in terms of testing HCI. The Kaplan-Meier curves and corresponding log-rank test results also demonstrated significant stratification capability of our models for the testing cohort. Deep learning-based DM and OS time-to-event models showed predictive capability and could provide indications for personalized RT. The best predictive performance achieved by the PET-only model suggested GTV segmentation might be less relevant for PET-based prognosis. [ABSTRACT FROM AUTHOR]

Abstract: Background and purpose: We report on the implementation of offline PET/CT-based treatment verification at the Heidelberg Ion Beam Therapy Centre (HIT) and present first clinical cases for post-activation measurements after scanned carbon ion irradiation. Key ingredient of this in-vivo treatment verification is the comparison of irradiation-induced patient activation measured by a PET scanner with a prediction simulated by means of Monte Carlo techniques. Material and methods: At HIT, a commercial full-ring PET/CT scanner has been installed in close vicinity to the treatment rooms. After selected irradiation fractions, the patient either walks to the scanner for acquisition of the activation data or is transported using a shuttle system. The expected activity distribution is obtained from the production of β+-active isotopes simulated by the FLUKA code on the basis of the patient-specific treatment plan, post-processed considering the time course of the respective treatment fraction, the estimated biological washout of the induced activity and a simplified model of the imaging process. Results: We present four patients with different indications of head, head/neck, liver and pelvic tumours. A clear correlation between the measured PET signal and the simulated activity pattern is observed for all patients, thus supporting a proper treatment delivery. In the case of a pelvic tumour patient it was possible to detect minor treatment delivery inaccuracies. Conclusions: The initial clinical experience proves the feasibility of the implemented strategy for offline confirmation of scanned carbon ion irradiation and therefore constitutes a first step towards a comprehensive PET/CT-based treatment verification in the clinical routine at HIT. [Copyright &y& Elsevier]