Radiotherapy and radiation oncology play a key role in the clinical management of patients suffering from oncological diseases. In clinical routine, anatomic imaging such as contrast-enhanced CT and MRI are widely available and are usually used to improve the target volume delineation for subsequent radiotherapy. Moreover, these modalities are also used for treatment monitoring after radiotherapy. However, some diagnostic questions cannot be sufficiently addressed by the mere use standard morphological imaging. Therefore, positron emission tomography (PET) imaging gains increasing clinical significance in the management of oncological patients undergoing radiotherapy, as PET allows the visualization and quantification of tumoral features on a molecular level beyond the mere morphological extent shown by conventional imaging, such as tumor metabolism or receptor expression. The tumor metabolism or receptor expression information derived from PET can be used as tool for visualization of tumor extent, for assessing response during and after therapy, for prediction of patterns of failure and for definition of the volume in need of dose-escalation. This review focuses on recent and current advances of PET imaging within the field of clinical radiotherapy / radiation oncology in several oncological entities (neuro-oncology, head & neck cancer, lung cancer, gastrointestinal tumors and prostate cancer) with particular emphasis on radiotherapy planning, response assessment after radiotherapy and prognostication.
The five-miRNA-signature is a strong and independent prognostic factor for disease recurrence and survival of patients with HPV-negative HNSCC.
Deep learning models based on medical images play an increasingly important role for cancer outcome prediction. The standard approach involves usage of convolutional neural networks (CNNs) to automatically extract relevant features from the patient’s image and perform a binary classification of the occurrence of a given clinical endpoint. In this work, a 2D-CNN and a 3D-CNN for the binary classification of distant metastasis (DM) occurrence in head and neck cancer patients were extended to perform time-to-event analysis. The newly built CNNs incorporate censoring information and output DM-free probability curves as a function of time for every patient. In total, 1037 patients were used to build and assess the performance of the time-to-event model. Training and validation was based on 294 patients also used in a previous benchmark classification study while for testing 743 patients from three independent cohorts were used. The best network could reproduce the good results from 3-fold cross validation [Harrell’s concordance indices (HCIs) of 0.78, 0.74 and 0.80] in two out of three testing cohorts (HCIs of 0.88, 0.67 and 0.77). Additionally, the capability of the models for patient stratification into high and low-risk groups was investigated, the CNNs being able to significantly stratify all three testing cohorts. Results suggest that image-based deep learning models show good reliability for DM time-to-event analysis and could be used for treatment personalisation.
BackgroundDefinitive chemoradiotherapy (dCRT) is a standard treatment for patients with locally advanced head and neck cancer. There is a clinical need for a stratification of this prognostically heterogeneous group of tumors in order to optimize treatment of individual patients. We retrospectively reviewed all patients with head and neck squamous cell carcinoma (HNSCC) of the oral cavity, oropharynx, hypopharynx, or larynx, treated with dCRT from 09/2008 until 03/2016 at the Department of Radiation Oncology, LMU Munich. Here we report the clinical results of the cohort which represent the basis for biomarker discovery and molecular genetic research within the framework of a clinical cooperation group.MethodsPatient data were collected and analyzed for outcome and treatment failures with regard to previously described and established risk factors.ResultsWe identified 184 patients with a median follow-up of 65 months and a median age of 64 years. Patients received dCRT with a median dose of 70 Gy and simultaneous chemotherapy in 90.2% of cases, mostly mitomycin C / 5-FU in concordance with the ARO 95–06 trial. The actuarial 3-year overall survival (OS), local, locoregional and distant failure rates were 42.7, 29.8, 34.0 and 23.4%, respectively. Human papillomavirus-associated oropharynx cancer (HPVOPC) and smaller gross tumor volume were associated with significantly improved locoregional tumor control rate, disease-free survival (DFS) and OS in multivariate analysis. Additionally, lower hemoglobin levels were significantly associated with impaired DFS und OS in univariate analysis. The extent of lymph node involvement was associated with distant failure, DFS and OS. Moreover, 92 patients (50%) of our cohort have been treated in concordance with the ARO 95–06 study, corroborating the results of this study.ConclusionOur cohort is a large unselected monocentric cohort of HNSCC patients treated with dCRT. Tumor control rates and survival rates compare favorably with the results of previously published reports. The clinical data, together with the available tumor samples from biopsies, will allow translational research based on molecular genetic analyses.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.