Artificial intelligence (AI) is growing in all areas of medicine and was the topic of several advanced...
This section includes echocardiography (echo), transthoracic echo (TTE), transesophageal echo (TEE), echo contrast, transducers, ultrasound software and point of care ultrasound (POCUS). Ultrasound uses sound waves to create images and software to reconstruct the images. The trend in ultrasound the past decade has been toward smaller, more compact system with more advanced imaging features and increased framerates, event for 3-D and 4-D ultrasound. A big trend starting around 2018 has been the addition of artificial intelligence (AI) to speed workflows, increase reproducibility of diagnostic images regardless of sonographer skill, and automate tedious tasks such as qualification, contouring, anatomical identification and labeling and auto completion of sections on final reports.
An example of artificial intelligence on the GE Healthcare Vivid E95 system shown at ASE 2019 where the AI automatically pulls in an exam, identifies the left ventricle and myocardial boards and then calculates all the strain measurements in less than 10 seconds. While AI automation can greatly speed workflow, there are questions about the accuracy of AI for the next step in making diagnoses.
An example at HIMSS of deeper third-party software integration in enterprise imaging platforms was Siemens Healthcare showing a new, deep integration with echocardiography strain imaging analysis provider Epsilon Imaging. The integration eliminates the need for a separate login and the Epsilon software is now just a tool option available in the syngo system and it carries over data and images directly into the echo report.
A comparison of color-flow Doppler cardiac ultrasound showing blood flow, and blood speckle tracking revealing a more detailed and complex understanding of the flow. It shows the formation of a vortex that may play a role in future assessments for the efficiency of flow in the heart and vessels. Image from JASE, read more.
An example from the study of the Biosense Webster NuVision 3D/4D ICE imaging capability showing the left atrial appendage (LAA) visualization on 3D ICE. The system allows the user to place a false lighting source to be placed in different positions to change the lighting and shadows to better visualize the anatomy.
Images, or a digital twin mitral valve of a patient, created from cardiac ultrasound that were used to perform a virtual surgical procedure to test how the intervention would impact the patient prior to actually performing the procedure. The right image shows color coding for sheer stresses on the valve leaflets before and after the virtual surgery. The left image shows the model quantitation of leaflet coaptation at peak systole prior to the virtual surgery. Read the original article in Plos One.
An example of a strain echo from the study showing reduced peak longitudinal/reservoir left atrial strain in a COVID-19 patient who developed atrial fibrillation during admission. Average left atrial strain here is 20% (normal should be above 38%). Read the study.