3D-Arterial analysis software and CEUS in the assessment of severity and vulnerability of carotid atherosclerotic plaque: a comparison with CTA and histopathology.

PURPOSE: Our purpose is to assess Multiparametric Ultrasound (MPUS) efficacy for evaluation of carotid plaque vulnerability and carotid stenosis degree in comparison with Computed Tomography angiography (CTA) and histology. MATERIAL AND METHODS: 3D-Arterial Analysis is a 3D ultrasound software that automatically provides the degree of carotid stenosis and a colorimetric map of carotid plaque vulnerability. We enrolled 106 patients who were candidates for carotid endarterectomy. Prior to undergoing surgery, all carotid artery plaques were evaluated with Color-Doppler-US (CDUS), Contrast-Enhanced Ultrasound (CEUS), and 3D Arterial analysis (3DAA) US along with Computerized Tomographic Angiography (CTA) to assess the carotid artery stenosis degree. Post-surgery, the carotid specimens were fixed with 10% neutral buffered formalin solution, embedded in paraffin and used for light microscopic examination to assess plaque vulnerability morphological features. RESULTS: The results of the CTA examinations revealed 91 patients with severe carotid stenoses with a resultant diagnostic accuracy of 82.3% for CDUS, 94.5% for CEUS, 98.4% for 3DAA, respectively. The histopathological examination showed 71 vulnerable plaques with diagnostic accuracy values of 85.8% for CDUS, 93.4% for CEUS, 90.3% for 3DAA, 92% for CTA, respectively. CONCLUSIONS: The combination of CEUS and 3D Arterial Analysis may provide a powerful new clinical tool to identify and stratify "at-risk" patients with atherosclerotic carotid artery disease, identifying vulnerable plaques. These applications may also help in the postoperative assessment of treatment options to manage cardiovascular risks.

Prediction of Recurrence by Machine Learning in Salivary Gland Cancer Patients After Adjuvant (Chemo)Radiotherapy.

BACKGROUND/AIM: To investigate survival outcomes and recurrence patterns using machine learning in patients with salivary gland malignant tumor (SGMT) undergoing adjuvant chemoradiotherapy (CRT). PATIENTS AND METHODS: Consecutive SGMT patients were identified, and a data set included nine predictor variables and a dependent variable [disease-free survival (DFS) event] was standardized. The open-source R software was used. Survival outcomes were estimated by the Kaplan-Meier method. The random forest approach was used to select the important explanatory variables. A classification tree that optimally partitioned SGMT patients with different DFS rates was built. RESULTS: In total, 54 SGMT patients were included in the final analysis. Five-year DFS was 62.1%. The top two important variables identified were pathologic node (pN) and pathologic tumor (pT). Based on these explanatory variables, patients were partitioned in three groups, including pN0, pT1-2 pN+ and pT3-4 pN+ with 26%, 38% and 75% probability of recurrence, respectively. Accordingly, 5-year DFS rates were 73.7%, 57.1% and 34.3%, respectively. CONCLUSION: The proposed decision tree algorithm is an appropriate tool to partition SGMT patients. It can guide decision-making and future research in the SGMT field.