Providing a prognosis data record

Patent metadata

Field	Value
Publication number	US-11468569-B2
Application number	US-202017016303-A
Country	US
Kind code	B2
Filing date	Sep 9, 2020
Priority date	Sep 11, 2019
Publication date	Oct 11, 2022
Grant date	Oct 11, 2022

Abstract

A method for providing a prognosis data record includes receiving a first image data record relating to an examination region of an examination object, and receiving an operating parameter of a medical object that is arranged at the examination region of the examination object and positioning information of the medical object that is arranged at the examination region. The prognosis data record is created by applying a trained function to input data. The input data is based on the first image data record, the at least one operating parameter, and the positioning information of the medical object. At least one parameter of the trained function is based on a comparison with a first comparison image data record. As compared with the first image data record, the first comparison image data record includes changes influenced by the medical object at the examination region. The prognosis data record is provided.

First claim

The invention claimed is:

1. A computer-implemented method for providing a prognosis data record relating to an examination object, the computer-implemented method comprising:
receiving a first image data record relating to an examination region of the examination object;
receiving at least one operating parameter of a medical object that is arranged at the examination region of the examination object and positioning information of the medical object that is arranged at the examination region of the examination object;
creating the prognosis data record, creating the prognosis data record comprising applying a trained function to input data, wherein the input data is based on the first image data record, the at least one operating parameter, and the positioning information of the medical object, wherein at least one parameter of the trained function is based on a comparison with a first comparison image data record, and wherein as compared with the first image data record, the first comparison image data record includes changes influenced by the medical object at the examination region; and
providing the prognosis data record,
wherein the prognosis data record includes:
probability information of a fluid bubble formation within the examination region of the examination object, characteristic form information of the fluid bubble formation, or the probability information and the characteristic form information of the fluid bubble formation;
probability information of a lesion formation within the examination region of the examination object, characteristic form information of the lesion formation, or the probability information and the characteristic form information of the lesion formation; or
a combination thereof.

2. The computer-implemented method of claim 1 , further comprising:
receiving an elastography data record relating to the examination region of the examination object; and
registering the elastography data record with the first image data record,
wherein the input data is also based on the elastography data record.

3. The computer-implemented method of claim 1 , further comprising:
receiving at least one second image data record relating to at least one section of the examination region of the examination object,
wherein the at least one second image data record maps a temporal change at the examination region of the examination object as a result of the medical object, and
wherein the input data is also based on the at least one second image data record.

4. The computer-implemented method of claim 1 , wherein the prognosis data record includes a validity range with respect to the at least one operating parameter.

5. The computer-implemented method of claim 1 , wherein the first image data record is recorded by a magnetic resonance system, a medical x-ray device, a computed tomography system, or any combination thereof.

6. The computer-implemented method of claim 1 , wherein receiving the first image data record comprises receiving, by an interface of a provision unit, the first image data record relating to the examination region of the examination object,
wherein receiving the at least one operating parameter of the medical object that is arranged at the examination region of the examination object and the positioning information of the medical object that is arranged at the examination region of the examination object comprises receiving, by the interface, the at least one operating parameter of the medical object that is arranged at the examination region of the examination object and the positioning information of the medical object that is arranged at the examination region of the examination object,
wherein creating the prognosis data record comprises creating, by a computing unit of the provision unit, the prognosis data record, and
wherein providing the prognosis data record comprises providing, by the interface, the prognosis data record.

7. The computer-implemented method of claim 3 , wherein the at least one second image data record is recorded by an ultrasound device.

8. The computer-implemented method of claim 3 , wherein receiving the at least one second image data record comprises receiving a plurality of second image data records in temporal sequence, and
wherein a prognosis data record is created in each case based on the second image data records previously received in the temporal sequence.

9. The computer-implemented method of claim 6 , wherein the provision unit is part of a medical device.

10. A computer-implemented method for providing a trained function, the computer-implemented method comprising:
receiving a first training image data record relating to an examination region of an examination object;
receiving at least one training operating parameter of a medical object that is arranged at the examination region of the examination object and training positioning information of the medical object that is arranged at the examination region of the examination object;
receiving a further training image data record relating to the examination region of the examination object, wherein the further training image data record is recorded after the first training image data record in time, wherein a change at the examination region of the examination object as a result of the medical object takes place after the recording of the first training image data record and before recording the further training image data record;
creating a comparison prognosis data record from the further training image data record, wherein as compared with the first training image data record, the comparison prognosis data record includes changes influenced by the medical object at the examination region;
creating a training prognosis data record, creating the training prognosis data record comprising applying the trained function to input data, wherein the input data is based on the first training image data record, the at least one training operating parameter, and the training positioning information of the medical object;
adjusting at least one parameter of the trained function based on a comparison of the comparison prognosis data record and the training prognosis data record; and
providing the trained function,
wherein the training prognosis data record includes:
probability information of a fluid bubble formation within the examination region of the examination object, characteristic form information of the fluid bubble formation, or the probability information and the characteristic form information of the fluid bubble formation;
probability information of a lesion formation within the examination region of the examination object, characteristic form information of the lesion formation, or the probability information and the characteristic form information of the lesion formation; or
a combination thereof.

11. The computer-implemented method of claim 10 , further comprising:
receiving a training elastography data record relating to the examination region of the examination object;
and registering the training elastography data record with the first training image data record,
wherein the input data is also based on the training elastography data record.

12. The computer-implemented method of claim 10 , further comprising receiving at least one second training image data record relating to at least one section of the examination region of the examination object,
wherein the at least one second training image data record maps a temporal change at the examination region of the examination object as a result of the medical object, and
wherein the input data is also based on the at least one second training image data record.

Assignees

• Siemens Healthcare Gmbh

Inventors

• Regensburger Alois
• Wiets Michael
• Walter Sabrina
• Alzaga Amilcar

Classifications

• G06V10/454 Primary

  Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN] · CPC title

• G06V10/82

  using neural networks · CPC title

• G06V10/764

  using classification, e.g. of video objects · CPC title

• G06T7/0016 Primary

  involving temporal comparison · CPC title

• G06N3/045 Primary

  Combinations of networks · CPC title