Role of correlated noise in textural features extraction.

Predictive models of tumor response based on heterogeneity metrics in medical images, such as textural features, are highly suggestive. However, the demonstrated sensitivity of these features to noise does affect the model being developed. An in-depth analysis of the noise influence on the extraction of texture features was performed based on the assumption that an improvement in information quality can also enhance the predictive model. A heuristic approach was used that recognizes from the beginning that the noise has its own texture and it was analysed how it affects the quantitative signal data. A simple procedure to obtain noise image estimation is shown; one which makes it possible to extract the noise-texture features at each observation. The distance measured between the textural features in signal and estimated noise images allows us to determine the features affected in each observation by the noise and, for example, to exclude some of them from the model. A demonstration was carried out using synthetic images applying realistic noise models found in medical images. Drawn conclusions were applied to a public cohort of clinical images obtained using FDG-PET to show how the predictive model could be improved. A gain in the area under the receiver operating characteristic curve between 10 and 20% when noise texture information is used was shown. An improvement between 20 and 30% can be appreciated in the estimated model quality.

Local diagnostic reference levels for paediatric non-cardiac interventional radiology procedures.

PURPOSE: To establish local diagnostic reference levels (DRLs) for non-cardiac interventional procedures in paediatrics. METHODS: The type of procedure, the patient's weight and age and dose-related data from 279 interventions was recorded in a database completed by interventional radiologists, radiographers and technicians of the Medical Physics department. These procedures were classified into 14 categories and 6 weight ranges. Local DRLs were proposed for those ranges in which a sample of at least 15 patients could be gathered and were calculated as the third quartile (Q3) of the air kerma-area product (PKA) values. The Q3 of the fluoroscopy time (FT) and number of digital subtraction angiography (DSA) images were also obtained. Finally, the correlation between PKA and weight was analysed. RESULTS: Local DRLs are proposed for three types of procedures: hepatic/biliary interventions (5-15 kg, 1304 cGy·cm2; 15-30 kg, 2121 cGy·cm2), sclerotherapy procedures (15-30 kg, 704 cGy·cm2; 30-50 kg, 4049 cGy·cm2; 50-80 kg, 3734 cGy·cm2) and central venous catheter (CVC) procedures (5-15 kg, 84 cGy·cm2). Hepatic/biliary interventions showed a moderate correlation (r = 0.61), while sclerotherapy procedures presented a poor correlation (r = 0.34) between PKA and weight, possibly due to the PKA dependence on the complexity level. Regarding CVC procedures, a clearly higher correlation was found when the fluoroscopy PKA value was normalised to the FT (r = 0.85 vs r = 0.35). CONCLUSIONS: The results support the feasibility of establishing DRLs for the most common procedures (sclerotherapy, hepatic/biliary and CVC interventions) despite the small number of paediatric interventions.