RESUMO
Purpose: To assess the potential of radiomic features in comparison to dual-energy CT (DECT) material decomposition to objectively stratify abdominal lymph node metastases. Materials and methods: In this retrospective study, we included 81 patients (m, 57; median age, 65 (interquartile range, 58.7-73.3) years) with either lymph node metastases (n = 36) or benign lymph nodes (n = 45) who underwent contrast-enhanced abdominal DECT between 06/2015-07/2019. All malignant lymph nodes were classified as unequivocal according to RECIST criteria and confirmed by histopathology, PET-CT or follow-up imaging. Three investigators segmented lymph nodes to extract DECT and radiomics features. Intra-class correlation analysis was applied to stratify a robust feature subset with further feature reduction by Pearson correlation analysis and LASSO. Independent training and testing datasets were applied on four different machine learning models. We calculated the performance metrics and permutation-based feature importance values to increase interpretability of the models. DeLong test was used to compare the top performing models. Results: Distance matrices and t-SNE plots revealed clearer clusters using a combination of DECT and radiomic features compared to DECT features only. Feature reduction by LASSO excluded all DECT features of the combined feature cohort. The top performing radiomic features model (AUC = 1.000; F1 = 1.000; precision = 1.000; Random Forest) was significantly superior to the top performing DECT features model (AUC = 0.942; F1 = 0.762; precision = 0.800; Stochastic Gradient Boosting) (DeLong < 0.001). Conclusion: Imaging biomarkers have the potential to stratify unequivocal lymph node metastases. Radiomics models were superior to DECT material decomposition and may serve as a support tool to facilitate stratification of abdominal lymph node metastases.
RESUMO
OBJECTIVES: CT is an essential diagnostic tool in health care. However, CT delivers relatively high levels of radiation which has been associated with an increased risk of childhood cancer. To address this, we evaluated patterns and time trends of CT use among children in Finland during the period in which changes in pediatric CT imaging practices were reported in several countries. METHODS: Data on CTs performed on children younger than 15 years were obtained from Finland's largest eight hospitals. CT data included the period 1996-2010 with an estimated coverage of more than 80 % of pediatric CT imaging in Finland. Joinpoint regression was used for trends analysis. CT radiation doses were estimated based on a Finnish dosimetry survey. RESULTS: A total of 48,807 pediatric CTs were performed in 1996-2010. More boys (55.5 %) were scanned than girls (42.8 %). CT numbers increased up to 2002, then decreased significantly (-6.9 % per year, 95 % CI: -10.4 to -3.2) towards 2005 and to a lesser extent thereafter, particularly among younger children. All CT types decreased in recent years, except for chest, spine, and extremities. The frequency of head CTs related to the diagnoses of intracranial injury, migraine and headache decreased towards the end of the study period. The estimated annual average effective dose from the three most common CT examinations was 0.004 mSv per child in the population. CONCLUSIONS: The frequency of pediatric CTs in Finland started to decrease after 2002. Apart from chest and orthopedic CTs, the utilization of pediatric CT imaging declined in recent years, most likely explained by improved awareness of medical radiation risks and reliance on alternative modalities such as MRI and ultrasound.