Search

This editorial is in response to the three latest clinical consensus guidelines authored by the Critical Care Committee of the American Association for the Surgery of Trauma. Herein, we discuss their main findings and recommendations and their impact on the practice of Surgical Critical Care.

Objective: This study evaluated the performance of automated machine-learning to diagnose non-alcoholic fatty liver disease (NAFLD) by ultrasound and compared these findings to radiologist performance.Methods: 96 patients with histologic (33) or proton density fat fraction MRI (63) diagnosis of NAFLD and 100 patients without evidence of NAFLD were retrospectively identified. The “Fatty Liver” label included 96 patients with 405 images and the “Not Fatty Liver” label included 100 patients with 500 images. These 905 images made up a “Comprehensive Image” group. A “Radiology Selected Image” group was then created by selecting only images considered diagnostic by a blinded radiologist, resulting in 649 images. Cloud AutoML Visionbeta (Google LLC, Mountain View, CA) was used for machine learning. The models were evaluated against three blinded radiologists.Results: The “Comprehensive Image” group model demonstrated a sensitivity of 88.6% (73.3-96.8%) and a specificity of 95.3% (84.2-99.4%). Radiologist performance on this image group included a sensitivity of 81.0% (74.3-87.6%) and specificity of 86.0% (72.6-99.5%). The model’s overall accuracy was 92.3% (84.0-97.1%), compared with mean individual performance (83.8%, 78.4-89.1%). The “Radiology Selected Image” group model demonstrated a sensitivity of 88.6% (73.3 - 96.8%) and specificity of 87.9% (71.8-96.6%). Mean radiologist sensitivity was 92.4% (86.9-97.9%) and specificity was 91.9% (83.4-100%). The model’s overall accuracy was 88.2% (78.1-94.8%) which was comparable to the individual radiologist performance (92.2%, 90.1-94.2%) and consensus performance (95.6%, 87.6-99.1%).Conclusions: An automated machine-learning algorithm may accurately detect NAFLD on ultrasound.

Abstract Background Peptic ulcer perforation in the early post-cesarean period is rare but may result in maternal mortality. Case presentation Four cases of post-cesarean peptic ulcer perforation are presented. In all four patients, presentations include peritoneal signs such as acute abdominal pain and progressive distention, hemodynamic instability and intraperitoneal free fluid by ultrasound. Laparotomy and repair were done in all 4 cases. There were 2 maternal deaths. We also have reviewed English literature for the similar cases reported from 1940 to March 2019. Conclusion New onset tachycardia, abdominal pain and progressive distension after cesarean section without congruent changes in hemoglobin should raise concerns for intra-abdominal emergencies including perforated peptic ulcer. Early use of ultrasound should be considered to assist in diagnosis. Coordinated care by an obstetrician and a general surgeon is necessary in presence of any unusual postoperative abdominal pain. Early recognition of the disease is imperative to limit the surgical delay and to improve the outcomes.

Advances in modern clinical ultrasound include developments in ultrasound signal processing, imaging techniques and clinical applications. Improvements in ultrasound processing include contrast and high-fidelity ultrasound imaging to expand B-mode imaging and microvascular (or microluminal) discrimination. Similarly, volumetric sonography, automated or intelligent ultrasound, and fusion imaging developed from the innate limitations of planar ultrasound, including user-operator technical dependencies and complex anatomic spatial prerequisites. Additionally, ultrasound techniques and instrumentation have evolved towards expanding access amongst clinicians and patients. To that end, portability of ultrasound systems has become paramount. This has afforded growth into the point-of-care ultrasound and remote or tele-ultrasound arenas. In parallel, advanced applications of ultrasound imaging have arisen. These include high frequency superficial sonograms to diagnose dermatologic pathologies as well as various intra-cavitary or lesional interrogations by contrast-enhanced ultrasound. Properties such as realtime definition and ease-of-access have spurned procedural and interventional applications for vascular access. This narrative review provides an overview of these advances and potential future directions of ultrasound.

The mainstay of treatment for unresectable hepatocellular carcinoma is locoregional therapy including percutaneous ablation and transarterial chemo- and radioembolization. While monitoring for tumor response after transarterial chemoembolization is crucial, current imaging strategies are suboptimal. The standard of care is contrast-enhanced magnetic resonance imaging or computed tomography imaging performed at least 4 to 6 weeks after therapy. We present a case in which contrast-enhanced ultrasound identified a specific extra-hepatic collateral from the gastroduodenal artery supplying residual viable tumor and assisting with directed transarterial management. Keywords: Transarterial chemoembolization, Contrast-enhanced ultrasound, Hepatocellular carcinoma