US 12,494,287 B1
Methods relating to medical diagnostics and to medical diagnostic systems
Simon Henry Connell, Johannesburg (ZA); Martin Nkululeko Hogan Cook, Johannesburg (ZA); and Richard Charles Andrew, Johannesburg (ZA)
Assigned to UNIVERSITY OF JOHANNESBURG, Auckland Park (ZA)
Appl. No. 17/924,819
Filed by UNIVERSITY OF JOHANNESBURG, Johannesburg (ZA)
PCT Filed May 13, 2021, PCT No. PCT/IB2021/054109
§ 371(c)(1), (2) Date Nov. 11, 2022,
PCT Pub. No. WO2021/229497, PCT Pub. Date Nov. 18, 2021.
Claims priority of application No. 2020/02707 (ZA), filed on May 13, 2020.
Int. Cl. G16H 50/50 (2018.01); A61B 6/00 (2006.01); A61B 6/03 (2006.01); A61B 6/42 (2024.01); G06T 11/00 (2006.01); G06V 10/764 (2022.01); G16H 50/20 (2018.01)
CPC G16H 50/20 (2018.01) [A61B 6/032 (2013.01); A61B 6/4258 (2013.01); A61B 6/5205 (2013.01); A61B 6/5258 (2013.01); G06T 11/003 (2013.01); G06V 10/764 (2022.01); G16H 50/50 (2018.01); G06T 2211/441 (2023.08)] 20 Claims
OG exemplary drawing
 
1. A method of processing data from a medical diagnostic system which comprises a detector arrangement configured to detect interaction of high energy particles with tissue, the method comprising:
detecting, by the detector arrangement of the medical diagnostic system, interactions of high energy particles with tissue to generate diagnostic data;
receiving the diagnostic data generated by the detector arrangement;
generating digital diagnostic data using a digital twin,
wherein the digital twin is a computer-implemented simulation of at least part of the medical diagnostic system, and is configured to simulate physical interaction between the particles, the tissue, and the detector arrangement;
training a machine-based classifier using the digital diagnostic data generated from the digital twin;
receiving a first set of experimental diagnostic data associated with tissue with an indication of pathologies of tissue with or without undesired material therein;
receiving a second set of experimental diagnostic data corresponding to one or both of quantitative and qualitative aspects of pathologies of tissue with or without undesirable material therein;
validating and optimizing the digital diagnostic data generated by the digital twin by benchmarking the digital diagnostic data against at least one of the first and second sets of experimental diagnostic data; and
processing the received diagnostic data with the trained machine-based classifier to produce a diagnostic output that facilitates and/or assists a medical diagnosis.