Ultrasound Scanner 27 September 2017 By Erik N. Steen, Chief - - PowerPoint PPT Presentation

ultrasound scanner
SMART_READER_LITE
LIVE PREVIEW

Ultrasound Scanner 27 September 2017 By Erik N. Steen, Chief - - PowerPoint PPT Presentation

Session 23440 The Intelligent Cardiovascular Ultrasound Scanner 27 September 2017 By Erik N. Steen, Chief Engineer GEHC Cardiovascular Ultrasound This presentation partly describes ongoing research and development efforts. These efforts are not


slide-1
SLIDE 1

JB52083XX

Vivid is a trademark of General Electric Company.

The Intelligent Cardiovascular Ultrasound Scanner

27 September 2017 By Erik N. Steen, Chief Engineer GEHC Cardiovascular Ultrasound This presentation partly describes ongoing research and development efforts. These efforts are not products and may never become products

Session 23440

slide-2
SLIDE 2

Cardiologist

How can I be confident in my ability to manage my patient’s heart health when 10-15% of the patients have suboptimal echoes?

Interventional Cardiologist

I need a better understanding

  • f the anatomy and function

during structural heart repairs

slide-3
SLIDE 3

Vivid™ E95

Cardiovascular Ultrasound with

Vivid and cSound are trademarks of General Electric Company.

slide-4
SLIDE 4

4

cSound Intelligent processing

  • Channel data from many transmits collected into

GPU memory in real time

  • Image is computed in real time by software

algorithms

  • High performance
  • Great flexibility to change algorithms
slide-5
SLIDE 5

HDlive™ Ex Exam amples les from

  • m in

interventi ventions

  • ns

Vivid, cSound, HDlive are trademarks of General Electric company or one of it’s subsidiaries.

slide-6
SLIDE 6

Amyloidosis example (ACE+TCI vs vs Texture)

Texture

With cSound™, image reconstruction algorithms can be changed according to clinical needs

slide-7
SLIDE 7

Blood flow can be visualized in completely new ways

slide-8
SLIDE 8

Cardiologist

How can I be confident in my ability to manage my patient’s heart health when 10-15% of the patients have suboptimal echoes? I need a better understanding of the anatomy and function during structural heart repairs How can I become more efficient with the increased burden of cardiovascular disease and pressure on cost ?

slide-9
SLIDE 9

9

Automatic Doppler Measurements

Performing manual Doppler measurements (tracings) is time consuming

Active for the most common measurements: LVOT Vmax LVOT Trace AV Vmax AV Trace TR Vmax MV E/A Velocity E’

Auto Doppler may reduce scan time, improve consistency (less user dependent) and eventually make the exam more efficient

slide-10
SLIDE 10

Cardiologist

How can I be confident in my ability to manage my patient’s heart health when 10-15% of the patients have suboptimal echoes? I need a better understanding of the anatomy and function during structural heart repairs How can I become more efficient with the increased burden of cardiovascular disease and pressure on cost ? How can I make sure my cardiovascular ultrasound system is future-proof ?

slide-11
SLIDE 11

JB52083XX

Vivid is a trademark of General Electric Company.

Future development(*)

*Note: Technology in development that represents ongoing research and development efforts. These technologies are not products and may never become

  • products. Not for sale. Not cleared or approved by the U.S. FDA or any other global regulator for commercial availability
slide-12
SLIDE 12

12

Faster GPUs can be combined with new algorithms for greatly improved 3D imaging (*)

*Note: Technology in development that represents ongoing research and development efforts. These technologies are not products and may never become

  • products. Not for sale. Not cleared or approved by the U.S. FDA or any other global regulator for commercial availability
slide-13
SLIDE 13

13

cSound Intelligent workflow

  • Workflow is automatically optimized according to

cardiac view.

*Note: Technology in development that represents ongoing research and development efforts. These technologies are not products and may never become

  • products. Not for sale. Not cleared or approved by the U.S. FDA or any other global regulator for commercial availability
slide-14
SLIDE 14

14

Apical 4 chamber view Apical 2 chamber view Apical long axis view Parasternal long axis view Parasternal short axis view

Preliminary results

  • Data: >100.000 images from > 5000 loops with variable image quality & patient anatomy
  • 500 loops used for validation
  • Various network architectures investigated
  • Accuracy (CaffeNet): 96 % accuracy on frame level, 97 % accuracy on sequence level (using majority vote)
  • < 2 ms per frame inference time using a Quadro P4000 GPU

Automatic Cardiac View Recognition (*)

*Note: Technology in development that represents ongoing research and development efforts. These technologies are not products and may never become

  • products. Not for sale. Not cleared or approved by the U.S. FDA or any other global regulator for commercial availability