The Image Biomarker Standardization Initiative validated consensus-based reference values for 169 radiomics features, thus enabling calibration and verification of radiomics software. Background Radiomic features may quantify characteristics present in medical imaging. However, the lack of standardized definitions and validated reference values have hampered clinical use. Purpos...

FDG-PET-derived textural features describing intra-tumor heterogeneity are increasingly investigated as imaging biomarkers. As part of the process of quantifying heterogeneity, image intensities (SUVs) are typically resampled into a reduced number of discrete bins. We focused on the implications of the manner in which this discretization is implemented. Two methods were evaluated: (1) R_D, dividing the SUV range into D equally spaced bins, where the intensity resolution (i.e. bin size) varies per image; and (2) R_B, maintaining a constant intensity resolution B. Clinical feasibility was assessed on 35 lung cancer patients, imaged before and in the second week of radiotherapy. Forty-four textural features were determined for different D and B for both imaging time points. Feature values depended on the intensity resolution and out of both assessed methods, R_B was shown to allow for a meaningful inter- and intra-patient comparison of feature values. Overall, patients ranked differently according to feature values–which was used as a surrogate for textural feature interpretation–between both discretization methods. Our study shows that the manner of SUV discretization has a crucial effect on the resulting textural features and the interpretation thereof, emphasizing the importance of standardized methodology in tumor texture analysis.

An overview of the Rapid Learning methodology, its results, and the potential impact on radiotherapy. Rapid Learning methodology is divided into four phases. In the data phase, diverse data are collected about past patients, treatments used, and outcomes. Innovative information technologies that support semantic interoperability enable distributed learning and data sharing without additional burden on health care professionals and without the need for data to leave the hospital. In the knowledge phase, prediction models are developed for new data and treatment outcomes by applying machine learning methods to data. In the application phase, this knowledge is applied in clinical practice via novel decision support systems or via extensions of existing models such as Tumour Control Probability models. In the evaluation phase, the predictability of treatment outcomes allows the new knowledge to be evaluated by comparing predicted and actual outcomes. Personalised or tailored cancer therapy ensures not only that patients receive an optimal treatment, but also that the right resources are being used for the right patients. Rapid Learning approaches combined with evidence based medicine are expected to improve the predictability of outcome and radiotherapy is the ideal field to study the value of Rapid Learning. The next step will be to include patient preferences in the decision making.

Repopulation of clonogenic tumor cells is inversely correlated with radiation treatment outcome in head and neck squamous cell carcinomas. A functional imaging tool to assess the proliferative activity of tumors could improve patient selection for treatment modifications and could be used for evaluation of early treatment response. The PET tracer 3′-deoxy-3′-¹⁸F-fluorothymidine (¹⁸F-FLT) can image tumor cell proliferation before and during radiotherapy, and it may provide biologic tumor information useful in radiotherapy planning. In the present study, the value of ¹⁸F-FLT PET in determining the lymph node status in squamous cell carcinoma of the head and neck was assessed, with pathology as the gold standard. Methods: Ten patients with newly diagnosed stage II–IV squamous cell carcinoma of the head and neck underwent ¹⁸F-FLT PET before surgical tumor resection with lymph node dissection. Emission ¹⁸F-FLT PET and CT images of the head and neck were recorded and fused, and standardized uptake values (SUVs) were calculated. From all 18 ¹⁸F-FLT PET-positive lymph node levels and from 8 ¹⁸F-FLT PET-negative controls, paraffin-embedded lymph node sections were stained and analyzed for the endogenous proliferation marker Ki-67 and for the preoperatively administered proliferation marker iododeoxyuridine. The sensitivity, specificity, positive predictive value, and negative predictive value were calculated for ¹⁸F-FLT PET. Results: Primary tumor sites were oral cavity (n = 7), larynx (n = 2), and maxillary sinus (n = 1). Nine of the 10 patients examined had ¹⁸F-FLT PET-positive lymph nodes (SUV_mean: median, 1.2; range, 0.8–2.9), but only 3 of these patients had histologically proven metastases. All metastatic lymph nodes showed Ki-67 and iododeoxyuridine staining in tumor cells. In the remaining 7 patients, there was abundant Ki-67 and iododeoxyuridine staining of B-lymphocytes in germinal centers in PET-positive lymph nodes, explaining the high rate of false-positive findings. The sensitivity, specificity, positive predictive value, and negative predictive value of ¹⁸F-FLT PET were 100%, 16.7%, 37.5%, and 100%, respectively. Conclusion: In head and neck cancer patients, ¹⁸F-FLT PET showed uptake in metastatic as well as in nonmetastatic reactive lymph nodes, the latter due to reactive B-lymphocyte proliferation. Because of the low specificity, ¹⁸F-FLT PET is not suitable for assessment of pretreatment lymph node status. This observation may also negatively influence the utility of ¹⁸F-FLT PET for early treatment response evaluation of small metastatic nodes.

Accelerated tumor cell proliferation is an important mechanism adversely affecting therapeutic outcome in head and neck cancer. 3′-deoxy-3′-¹⁸F-fluorothymidine (¹⁸F-FLT) is a PET tracer to noninvasively image tumor cell proliferation. The aims of this study were to monitor early tumor response based on repetitive ¹⁸F-FLT PET/CT scans and to identify subvolumes with high proliferative activity eligible for dose escalation. Methods: Ten patients with oropharyngeal tumors underwent an ¹⁸F-FLT PET/CT scan before and twice during radiotherapy. The primary tumor and metastatic lymph nodes (gross tumor volume, or GTV) were delineated on CT (GTV_CT) and after segmentation of the PET signal using the 50% isocontour of the maximum signal intensity or an adaptive threshold based on the signal-to-background ratio (GTV_SBR). GTVs were calculated, and similarity between GTV_CT and GTV_SBR was assessed. Within GTV_SBR, the maximum and mean standardized uptake value (SUV_max and SUV_mean, respectively) was calculated. Within GTV_CT, tumor subvolumes with high proliferative activity based on the 80% isocontour (GTV_80%) were identified for radiotherapy planning with dose escalation. Results: The GTV_CT decreased significantly in the fourth week but not in the initial phase of treatment. SUV_max and SUV_mean decreased significantly as early as 1 wk after therapy initiation and even further before the fourth week of treatment. For the primary tumor, the average (±SD) SUV_mean of the GTV_SBR was 4.7 ± 1.6, 2.0 ± 0.9, and 1.3 ± 0.2 for the consecutive scans (P < 0.0001). The similarity between GTV_CT and GTV_SBR decreased during treatment, indicating an enlargement of GTV_SBR outside GTV_CT caused by the increasing difficulty of segmenting tracer uptake in the tumor from the background and by proliferative activity in the nearby tonsillar tissue. GTV_80% was successfully identified in all primary tumors and metastatic lymph nodes, and dose escalation based on the GTV_80% was demonstrated to be technically feasible. Conclusion: ¹⁸F-FLT is a promising PET tracer for imaging tumor cell proliferation in head and neck carcinomas. Signal changes in ¹⁸F-FLT PET precede volumetric tumor response and are therefore suitable for early response assessment. Definition of tumor subvolumes with high proliferative activity and dose escalation to these regions are technically feasible.