Cinematic rendering in the evaluation of complex vascular injury of the lower extremities: how we do it.

Lower extremity trauma is one of the most common injury patterns seen in emergency medical and surgical practice. Vascular injuries occur in less than one percent of all civilian fractures. However, if not treated promptly, such injuries can lead to ischemia and death. Computed tomography angiography (CTA) is the non-invasive imaging gold standard and plays a crucial part in the decision-making process for treating lower extremity trauma. A novel, FDA-approved 3D reconstruction technique known as cinematic rendering (CR) yields photorealistic reconstructions of lower extremity vascular injuries depicting clinically important aspects of those injuries, aiding in patient workup and surgical planning, and thus improving patient outcomes. In this article, we provide clinical examples of the use of CR in evaluating lower extremity vascular injuries, including the relationship of these injuries to adjacent osseous structures and overlying soft tissues, and its role in management of lower extremity trauma.

Detection of left ventricular wall motion abnormalities from volume rendering of 4DCT cardiac angiograms using deep learning.

Background: The presence of left ventricular (LV) wall motion abnormalities (WMA) is an independent indicator of adverse cardiovascular events in patients with cardiovascular diseases. We develop and evaluate the ability to detect cardiac wall motion abnormalities (WMA) from dynamic volume renderings (VR) of clinical 4D computed tomography (CT) angiograms using a deep learning (DL) framework. Methods: Three hundred forty-three ECG-gated cardiac 4DCT studies (age: 61 ± 15, 60.1% male) were retrospectively evaluated. Volume-rendering videos of the LV blood pool were generated from 6 different perspectives (i.e., six views corresponding to every 60-degree rotation around the LV long axis); resulting in 2058 unique videos. Ground-truth WMA classification for each video was performed by evaluating the extent of impaired regional shortening visible (measured in the original 4DCT data). DL classification of each video for the presence of WMA was performed by first extracting image features frame-by-frame using a pre-trained Inception network and then evaluating the set of features using a long short-term memory network. Data were split into 60% for 5-fold cross-validation and 40% for testing. Results: Volume rendering videos represent ~800-fold data compression of the 4DCT volumes. Per-video DL classification performance was high for both cross-validation (accuracy = 93.1%, sensitivity = 90.0% and specificity = 95.1%, κ: 0.86) and testing (90.9, 90.2, and 91.4% respectively, κ: 0.81). Per-study performance was also high (cross-validation: 93.7, 93.5, 93.8%, κ: 0.87; testing: 93.5, 91.9, 94.7%, κ: 0.87). By re-binning per-video results into the 6 regional views of the LV we showed DL was accurate (mean accuracy = 93.1 and 90.9% for cross-validation and testing cohort, respectively) for every region. DL classification strongly agreed (accuracy = 91.0%, κ: 0.81) with expert visual assessment. Conclusions: Dynamic volume rendering of the LV blood pool combined with DL classification can accurately detect regional WMA from cardiac CT.

New and emerging patient-centered CT imaging and image-guided treatment paradigms for maxillofacial trauma.

This article reviews the conceptual framework, available evidence, and practical considerations pertaining to nascent and emerging advances in patient-centered CT-imaging and CT-guided surgery for maxillofacial trauma. These include cinematic rendering-a novel method for advanced 3D visualization, incorporation of quantitative CT imaging into the assessment of orbital fractures, low-dose CT imaging protocols made possible with contemporary scanners and reconstruction techniques, the rapidly growing use of cone-beam CT, virtual fracture reduction with design software for surgical pre-planning, the use of 3D printing for fabricating models and implants, and new avenues in CT-guided computer-aided surgery.

Three-dimensional CT angiography with volume rendering for the dignosis of multiple intracranial aneurysms / 中国脑血管病杂志

Objective:To evaluate the importance of 3D-CTA with volume rendering for the diagnosis of multiple intracranial aneurysms. Methods: Axial source images were obtained by helical CT scanning and reconstruction of 3D-CTA images was done by volume rendering technique in conjunction with multiplanar reformation. Results: In the past one year,there were 10 patients diagnosed as having multiple intracranial aneurysms by 3D-CTA and altogether 24 aneurysms were visualized,including 10 small aneurysms(≤5mm.Three dimensional CT angiography with volume rendering demonstrated aneurysms very well and provided useful information concerning the site,shape,size and spatial relationship with the surrounding vessels and bone anatomy. Conclusion: Three-dimensional CT angiography with volume rendering is a quick,reliable,and relatively noninvasive method for diagnosing multiple intracranial aneurysms.It delineates detailed aneurysmal morphology,and provides useful information for planning microsurgical approaches.