Oxford University Innovation Ltd

Ultromics Limited

Ross Upton

Paul Leeson

Deborah Markham

Andrew Richard Parker

Edmund Wilkes

Arian Beqiri

Gary Woodward

Jurriath Azmathi Mumith

A system for diagnosing a heart condition comprises an imaging system () arranged to acquire two images of the heart at respective points in the cardiac cycle, and locating means, which may be manually operated or automatic, for locating a series of pairs of points on the images. Each pair of points indicates the respective positions of a single part of the heart in the two images. The system further comprises a processor () arranged to calculate from the positions of said pairs of points a value of at least one parameter of the deformation of the heart. It may further be arranged to compare the value of the at least one parameter with reference data to generate a diagnostic output.

Image-based diagnostic systems

An embodiment of the invention provides a system for automatically deriving a parameter of a human heart from ultrasound results. A first neural network is arranged to receive a plurality of echocardiographic images and to classify the images into one of at least a two-chamber view and a four-chamber view. A second neural network is arranged to receive echocardiographic images comprising a two- or four-chamber view and to identify the endocardial border of the left ventricle (LV) for each view. End-systole and end-diastole images are then identified and a parameter such as LV volume, ejection fraction, global longitudinal strain and regional longitudinal strain is calculated.

Assessing heart parameters using neural networks

The present disclosure relates to a system () for generating a diagnostic model. The system () includes a processor () configured to analyse a plurality of reference data sets. The reference data sets each include at least one image (). The analysis identities at least one feature in each image (). A metric is calculated in dependence on the at least one identified feature. Outcome data associated with at least some of the reference data sets is acquired. The diagnostic model is compiled in dependence on the at least one calculated metric and the associated outcome data. The present disclosure also relates to a method of generating a diagnostic model; and a non-transitory computer-readable medium.

Diagnostic modelling method and apparatus

The present disclosure relates to a system () for scoring motion of a heart wall (). The system () includes an imaging system () operable to acquire a first image () of the heart wall () at a first time and a second image () of the heart wall () at a second time. A processor () is provided to identify a first set of contour data in the first image (); and a second set of contour data in the second image (). The processor () defines at least one element (Ei) representing a cardiac cyclic change in a section of the heart wall () in dependence on the first and second sets of contour data. Each element (Ei) is analysed to generate at least one metric which is compared with a reference data model to score the motion of the corresponding section of the heart wall (). The disclosure also relates to a method of scoring motion of a heart wall (); and a non-transitory computer-readable medium.

Growing community of inventors

Oxford, United Kingdom

Ross Upton