Purpose To determine whether machine learning assisted-texture analysis of multi-energy virtual monochromatic image (VMI) datasets from dual-energy CT (DECT) can be used to differentiate metastatic head and neck squamous cell carcinoma (HNSCC) lymph nodes from lymphoma, inflammatory, or normal lymph nodes. Materials and methods A retrospective evaluation of 412 cervical nodes from 5 different patient groups (50 patients in total) having undergone DECT of the neck between 2013 and 2015 was performed: (1) HNSCC with pathology proven metastatic adenopathy, (2) HNSCC with pathology proven benign nodes (controls for (1)), (3) lymphoma, (4) inflammatory, and (5) normal nodes (controls for (3) and (4)). Texture analysis was performed with TexRAD® software using two independent sets of contours to assess the impact of inter-rater variation. Two machine learning algorithms (Random Forests (RF) and Gradient Boosting Machine (GBM)) were used with independent training and testing sets and determination of accuracy, sensitivity, specificity, PPV, NPV, and AUC. Results In the independent testing (prediction) sets, the accuracy for distinguishing different groups of pathologic nodes or normal nodes ranged between 80 and 95%. The models generated using texture data extracted from the independent contour sets had substantial to almost perfect agreement. The accuracy, sensitivity, specificity, PPV, and NPV for correctly classifying a lymph node as malignant (i.e. metastatic HNSCC or lymphoma) versus benign were 92%, 91%, 93%, 95%, 87%, respectively. Conclusion Machine learning assisted-DECT texture analysis can help distinguish different nodal pathology and normal nodes with a high accuracy.

No abstract

No abstract

Ultrasound-guided abdominal paracentesis is a procedure that is frequently performed by radiologists for both diagnostic and therapeutic purposes. This procedure has been shown to be safe with few complications. We report the case of a patient who underwent an ultrasound-guided therapeutic abdominal paracentesis for refractory ascites complicated by intraperitoneal hemorrhage leading to death. This case suggests that ultrasound-guided paracentesis may need to become a more standardized procedure and that in the event of hemorrhage, alternative treatment options such as embolization or surgical intervention should be utilized when manual compression fails.

6508 Background: While screening rates have improved among minorities, racial/ethnic disparities in diagnosis and treatment persist. Many steps in the diagnostic pathway can delay tissue diagnosis, and in usual practice breast biopsies are performed days to weeks after biopsy recommendation. The purpose of this study was to identify if racial/ethnic disparities exist in time from biopsy recommendation to biopsy, and if a same-day biopsy program (biopsy on the same day as the recommendation) eliminates these disparities. Methods: After IRB approval, we identified all diagnostic mammogram and ultrasound exams leading to biopsy pre- (September 2016-March 2017) and post- (September 2017-March 2018) implementation of our same-day biopsy program. We compared the distribution of age, race, language, insurance type, days to biopsy and proportion of same-day biopsies in pre- vs. post-implementation groups using the Wilcoxon test (for continuous variables) and the Pearson’s chi-squared test (for categorical variables). Multivariable linear and logistic models were estimated in pre and post periods to assess if days from biopsy recommendation to biopsy (linear) and having a same-day biopsy (logistic) were associated with age, race, language, and insurance type. Results: 663 and 482 patients underwent biopsy during pre- and post-implementation, respectively. Age, race, language, and insurance type were similar between time periods. For all patients, the same-day biopsy program decreased mean time from diagnostic examination to biopsy from 8 (IQR: 4-13) to 0 (IQR: 0-4) days (p < 0.001). During the pre time period, non-white patients and having government insurance were significantly associated with longer days to biopsy (non-white aCoef: 2.30 (95% CI: 0.58-4.03); insurance aCoef: 1.67 (95% CI: 0.02-3.32); p < 0.05), and increasing age and having government insurance were significantly associated with decreased odds of having a same-day biopsy (age aOR: 0.97 (95% CI 0.95-0.99); insurance aOR: 0.35 (95% CI 0.14-0.88); p < 0.05), after adjustment. During the post time period there was no evidence of these disparities. Conclusions: A same-day biopsy program eliminated racial/ethnic disparities in time from breast biopsy recommendation to biopsy.