Resmed Pty Ltd

Annalise Ai Pty Ltd

Harrison-ai Medical Pty Ltd

Benjamin Matthew Austin

Liam Holley

Etienne Veschambre

Marc Justin Nothrop

Dang-Dinh-Ang Tran

David Huang

David Vuong

Xavier Holt

Aaron Lee

Marco Amoroso

Jarrel Seah

Jeffrey Wardman

A method of an apparatus control pressure in the patient interface. A vent valve may be used with a respiratory device, where the vent valve may selectively block fluid communication between components, such as the flow generator, the patient interface, and/or the vent. An expiratory flow model may be used to determine an expiratory characteristic such as an expiratory flow rate or pressure in the patient interface where an indicative measure may not be available. The expiratory flow model may receive inputs based on a measure of the patient's respiration, such as the tidal volume, peak inspiratory flow rate or length of inspiration. The expiratory characteristic may be used by a controller to control a pressure in the patient interface to provide respiratory therapy to a patient at or close to a target pressure.

Control for pressure of a patient interface

Disclosed are methods, apparatus and systems for treating a respiratory disorder in a patient. The apparatus comprises a pressure generator configured to generate a flow of air so as to provide ventilatory support to the patient; a transducer configured to generate a flow signal representing a property of the flow of air; and a controller configured to analyse the flow signal to estimate the inspiratory volume and the expiratory volume of a breath of the patient and servo-control the degree of ventilatory support to adjust an estimated tidal volume toward a target tidal volume. A gain of the servo-control is dependent on a difference between the estimated inspiratory volume and the estimated expiratory volume. The method comprises operating an apparatus or system in a similar manner.

Methods and apparatus for treatment of respiratory disorders

This disclosure relates to detecting visual findings in anatomical images. Methods comprise inputting anatomical images into a neural network to output a feature vector and computing an indication of visual findings being present in the images by a dense layer of the neural network that takes as input the feature vector and outputs an indication of whether each of the visual findings is present in the anatomical images. The neural network is trained on a training dataset including anatomical images, and labels associated with the anatomical images and each of the visual findings. The visual findings may be organised as a hierarchical ontology tree. The neural network may be trained by evaluating the performance of neural networks in detecting the visual findings and a negation pair class which comprises anatomical images where a first visual finding is identified in the absence of a second visual finding.

Systems and methods for automated analysis of medical images

Growing community of inventors

Sydney, Australia

Benjamin Matthew Austin