US 12,424,312 B2
Context-enhanced magnetic resonance (MR) workflow analysis and image reading
Joachim Dieter Schmidt, Hamburg (DE); and Thomas Erik Amthor, Hamburg (DE)
Assigned to KONINKLIJKE PHILIPS N.V., Eindhoven (NL)
Appl. No. 17/919,370
Filed by KONINKLIJKE PHILIPS N.V., Eindhoven (NL)
PCT Filed Apr. 25, 2021, PCT No. PCT/EP2021/060765
§ 371(c)(1), (2) Date Oct. 17, 2022,
PCT Pub. No. WO2021/219521, PCT Pub. Date Nov. 4, 2021.
Claims priority of provisional application 63/018,672, filed on May 1, 2020.
Prior Publication US 2023/0207112 A1, Jun. 29, 2023
Int. Cl. G16H 40/40 (2018.01); G06V 20/40 (2022.01); G06V 40/20 (2022.01); G11B 27/34 (2006.01); G16H 30/20 (2018.01); G16H 30/40 (2018.01)
CPC G16H 40/40 (2018.01) [G06V 20/44 (2022.01); G06V 20/46 (2022.01); G06V 40/20 (2022.01); G11B 27/34 (2013.01); G16H 30/20 (2018.01); G16H 30/40 (2018.01)] 19 Claims
OG exemplary drawing
 
1. A non-transitory computer readable medium storing instructions readable and executable by at least one electronic processor to perform a method of maintaining a machine log for a medical imaging device, the method comprising:
acquiring a video of a patient during a medical imaging examination;
detecting an activity in the video occurring from the medical imaging examination;
extracting at least one event annotation representing the detected activity in the video, wherein the at least one event annotation represents a human-related activity;
analyzing the acquired video of the detected activity occurred during the medical imaging examination;
recording machine log entries in the machine log of the medical imaging device, wherein the machine log entries are generated by the medical imaging device and include at least one of 1) sensor readings of sensors monitoring components of the medical imaging device, 2) error codes generated by the medical imaging device, and 3) information on phases of the medical imaging examination performed using the medical imaging device;
matching the extracted event annotations with machine log entries based on timestamps of the event annotations and timestamps of the machine log entries; and
annotating the machine log entries with the matched event annotations.