Predicting Breast Cancer Subtypes Using Magnetic Resonance Imaging Based Radiomics With Automatic Segmentation.

OBJECTIVE: The aim of the study is to demonstrate whether radiomics based on an automatic segmentation method is feasible for predicting molecular subtypes. METHODS: This retrospective study included 516 patients with confirmed breast cancer. An automatic segmentation-3-dimensional UNet-based Convolutional Neural Networks, trained on our in-house data set-was applied to segment the regions of interest. A set of 1316 radiomics features per region of interest was extracted. Eighteen cross-combination radiomics methods-with 6 feature selection methods and 3 classifiers-were used for model selection. Model classification performance was assessed using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity. RESULTS: The average dice similarity coefficient value of the automatic segmentation was 0.89. The radiomics models were predictive of 4 molecular subtypes with the best average: AUC = 0.8623, accuracy = 0.6596, sensitivity = 0.6383, and specificity = 0.8775. For luminal versus nonluminal subtypes, AUC = 0.8788 (95% confidence interval [CI], 0.8505-0.9071), accuracy = 0.7756, sensitivity = 0.7973, and specificity = 0.7466. For human epidermal growth factor receptor 2 (HER2)-enriched versus non-HER2-enriched subtypes, AUC = 0.8676 (95% CI, 0.8370-0.8982), accuracy = 0.7737, sensitivity = 0.8859, and specificity = 0.7283. For triple-negative breast cancer versus non-triple-negative breast cancer subtypes, AUC = 0.9335 (95% CI, 0.9027-0.9643), accuracy = 0.9110, sensitivity = 0.4444, and specificity = 0.9865. CONCLUSIONS: Radiomics based on automatic segmentation of magnetic resonance imaging can predict breast cancer of 4 molecular subtypes noninvasively and is potentially applicable in large samples.

Interventional radiology followed by endoscopic drainage for pancreatic fluid collections associated with high bleeding risk: Two case reports.

BACKGROUND: Endoscopic ultrasound (EUS)-guided transluminal drainage is an advanced technique used to treat pancreatic fluid collections (PFCs). However, gastric varices and intervening vessels may be associated with a high risk of bleeding and are, therefore, listed as relative contraindications. Herein, we report two patients who underwent interventional embolization before EUS-guided drainage. CASE SUMMARY: Two 32-year-old males developed symptomatic PFCs after acute pancreatitis and came to our hospital for further treatment. One patient suffered from intermittent abdominal pain and vomiting, and computed tomography (CT) imaging showed an encapsulated cyst 7.93 cm × 6.13 cm in size. The other patient complained of a mass inside the abdomen, which gradually became enlarged. Gastric varices around the ideal puncture site were detected by EUS when we evaluated the possibility of endoscopic drainage in both patients. Interventional embolization was recommended as the first procedure to decrease the risk of bleeding. After that, EUS-guided transluminal drainage was successfully conducted, without vascular rupture. No postoperative complications occurred during hospitalization, and no recurrence was detected at the last follow-up CT scan performed at 1 mo. CONCLUSION: Interventional embolization is a safe, preoperative procedure that is performed before EUS-guided drainage in PFC patients with gastric varices or at high risk of bleeding.