Radiographic assessment with magnetic resonance imaging (MRI) is widely used to characterize gliomas, which represent 80% of all primary malignant brain tumors. Unfortunately, glioma biology is marked by heterogeneous angiogenesis, cellular proliferation, cellular invasion, and apoptosis. This translates into varying degrees of enhancement, edema, and necrosis, making reliable imaging assessment challenging. Deep learning, a subset of machine learning artificial intelligence, has gained traction as a method, which has seen effective employment in solving image-based problems, including those in medical imaging. This review seeks to summarize current deep learning applications used in the field of glioma detection and outcome prediction and will focus on (1) pre- and post-operative tumor segmentation, (2) genetic characterization of tissue, and (3) prognostication. We demonstrate that deep learning methods of segmenting, characterizing, grading, and predicting survival in gliomas are promising opportunities that may enhance both research and clinical activities.

Objectives: Five percent of patients with recurrent gastrointestinal (GI) hemorrhage have indeterminate origin by radiological and endoscopic examinations. To improve diagnostic accuracy and therapeutic embolization, the technique of provocative mesenteric angiography (PMA) has been developed. It involves the addition of pharmacologic agents to standard angiographic protocols to induce bleeding. Material and Methods: This is an institutional review board-approved, retrospective study of 20 patients who underwent PMA between 2014 and 2019. All patients had clinical evidence of GI hemorrhage without a definite source. PMA consisted of anticoagulation with 5000 units of heparin and selective transcatheter injection of up to 600 μg of nitroglycerine, followed by slow infusion of up to 24 mg of tissue plasminogen activator into the arterial distribution of the highest suspicion mesenteric artery. Results: Among the 20 patients who underwent PMA, 11/20 (55%) resulted in angiographically visible extravasation. Of these 11 patients, nine patients underwent successful embolization with coil or glue and were discharged upon achieving hemodynamic stability. Two patients spontaneously stopped bleeding. In our series, PMA resulted in the successful treatment of 9/20 (45%) patients with recurrent hemorrhage. No procedure-associated complications were reported with these 20 patients during the procedure and their course of hospitalization. Conclusion: In our experience, PMA is an effective and safe approach in localizing and treating the source of GI bleeding in about half of patients with an otherwise unidentifiable source.

Background and Purpose: Intracerebral hemorrhage (ICH) expansion is an independent predictor of mortality and functional outcome with each milliliter of expansion increasing the chance of functional dependence by up to 7%. Unfortunately, detection of ICH expansion is often subjective, inaccurate, and may misguide treatment pathways. Artificial intelligence with convolutional neural networks (CNNs) represents a powerful new technology for image analysis and quantification. This study compares the accuracy, sensitivity, and specificity between a CNN optimized for ICH volume quantification and a traditional ABC/2 method. Materials and Methods: We performed a retrospective analysis of ICH patients who have had at least one follow-up non-contrast head CT (NCCT) within 24 hours. ICH expansion was defined as >33% volume of expansion, corresponding to a 10% increase in diameter. Each ICH was manually segmented, which served as ground truth measurements. Comparison of ICH expansion was made using (1) a traditional ABC/2 estimative approach and (2) a previously validated hybrid 3D/2D mask ROI-based CNN for ICH evaluation, which was trained previously on over 10,000 patients. Accuracy, sensitivity, and specificity of the CNN and ABC/2 approaches were then compared. Results: A total of 230 patients were included for a total of 460 NCCTs. The average ICH volume was 44.8 mL. The average ICH volume for the CNN was 45.3 mL (Pearson 0.99) and for ABC/2 was 60.4 mL (Pearson 0.81). Accuracy, sensitivity, and specificity for ICH expansion detection was 100%, 100%, and 100% for the CNN and 93.0%, 74.2%, and 96.0% for ABC/2. On visual inspection, cases of false positives by ABC/2 approaches tended to demonstrate eccentric expansion (Figure 1). Conclusions: A customized deep learning tool is highly accurate in the detection of ICH expansion. This may have important implications clinically for management and surveillance as well as in a clinical trial setting.

Aim: Evaluate patients with colonic diverticulitis complicated by liver abscesses at a single center and provide review of literature.Methods: Patients with colonic diverticulitis and liver abscess were identified via an administrative database and imaging search engine at Cedars Sinai Medical Center (CSMC). Clinical manifestations, laboratory and imaging findings and treatment strategies were assessed.Results: We identified 10 patients with a median age of 59 and a 7:3 male: female ratio. The top presenting signs and symptoms were: fever (90%), malaise (70%), anorexia (60%), nausea (40%), and right upper quadrant abdominal pain (30%). Mean white blood cell count was 22.4 1000/UL, total bilirubin 2.59 mg/DL, and alkaline phosphatase 206.6 IU/L. Of the reported liver abscess cultures, 5 patients grew a single organism and 2 had multiple organisms. Most common bacteria genus was Streptococcus (n=4). Five patients had right hepatic abscesses, 3 had bilobar, and 2 had left hepatic abscesses. Four patients had locally complicated diverticulitis: 2 with paracolonic abscess and 2 with purulent peritonitis. Nine patients had CT-guided drainage of liver abscess, while 2 needed surgical drainage of liver abscess (one required both). Five patients had colectomy: 1 emergently and 4 electively. Two patients who did not have colectomy had recurrent diverticulitis, and underwent colectomy following recurrence.Conclusion: Majority of patients with diverticulitis with liver abscess were males presenting with fever, and leukocytosis. Most had right liver lobe abscesses and most underwent colectomies. Diverticulitis with liver abscess is likely best treated as locally complicated disease and should undergo colectomy.

Trauma remains a leading cause of death for all age groups, and nearly two-thirds of these individuals suffer thoracic trauma. Due to the various types of injuries, including vascular and nonvascular, interventional radiology plays a major role in the acute and chronic management of the thoracic trauma patient. Interventional radiologists are critical members in the multidisciplinary team focusing on treatment of the patient with thoracic injury. Through case presentations, this article will review the role of interventional radiology in the management of trauma patients suffering thoracic injuries.