Automatic identification of a potential pleural effusion

Patent metadata

Field	Value
Publication number	US-10548555-B2
Application number	US-201514666684-A
Country	US
Kind code	B2
Filing date	Mar 24, 2015
Priority date	Apr 17, 2014
Publication date	Feb 4, 2020
Grant date	Feb 4, 2020

Abstract

A method for automatically identifying a potential pleural effusion in medical image data of a thorax of a patient from a scan by means of a medical scanner is provided. It includes at least the steps of accepting rib cage detection data of the rib cage of the patient from the image data, which rib cage detection data include rib cage extent data of a rib cage extent of the interior of the rib cage, accepting lung detection data of the lung of the patient from the image data, which lung detection data comprise lung extent data of a lung extent of the external boundary of the lung, accepting mediastinum detection data of all organs of the mediastinum in the thorax (Th) of the patient from the image data, which mediastinum detection data comprise mediastinum extent data of a mediastinum extent of the external boundary of the mediastinum, and subtracting the lung extent and the mediastinum extent from the rib cage extent while forming pleural effusion identification data.

First claim

The invention claimed is:

1. A method for automatically identifying a potential pleural effusion in medical image data of a thorax of a patient, including at least the following steps:
providing a medical scanner,
scanning a patient with the medical scanner so as to receive image data,
accepting rib cage detection data from the image data, wherein the rib cage detection data includes rib cage extent data of a rib cage extent of an interior of the rib cage of the patient,
accepting lung detection data from the image data, wherein the lung detection data includes lung extent data of a lung extent of the external boundary of the lung of the patient,
accepting mediastinum detection data from the image data, wherein the mediastinum detection data includes mediastinum extent data of a mediastinum extent of the external boundary of the mediastinum of all organs of the mediastinum in the thorax of the patient,
subtracting the lung extent and the mediastinum extent from the rib cage extent to form pleural effusion identification data, wherein the pleural effusion identification data comprises volume information;
comparing the volume information of the pleural effusion identification data with a volume threshold; and
outputting a signal when the volume information of the pleural effusion identification data indicates the potential pleural effusion exceeds the volume threshold, wherein the signal serves as an automatic warning that the potential pleural effusion is large and there is a need to act for an invasive treatment of the large potential pleural effusion.

2. The method as claimed in claim 1 , wherein additionally, diaphragm detection data are received from the image data, wherein the diaphragm detection data includes diaphragm extent data of a diaphragm extent of the diaphragm of the patient, which diaphragm extent delimits the rib cage extent in the rib cage detection data in the direction of the abdominal cavity of the patient.

3. The method as claimed in claim 2 , wherein at least one of:
the rib cage extent in the rib cage detection data,
the lung extent in the lung detection data,
the mediastinum extent in the mediastinum detection data, and
the diaphragm extent in the diaphragm detection data is represented by a surface contour model.

4. The method as claimed in claim 1 , wherein a detection verification, in relation to a potential pleural effusion, is performed in the pleural effusion identification data after the subtracting.

5. The method as claimed in claim 4 , wherein the pleural effusion identification data are adapted in accordance with a detection result of the detection verification.

6. The method as claimed in claim 4 wherein the detection verification comprises a matching with form data of pleural effusions from a pleural effusion form database.

7. The method as claimed in claim 4 , wherein the detection verification comprises a matching of measurement data in the region of the potential pleural effusion with measurement data typical for a scanning method of the scanner in the case of a pleural effusion.

8. The method as claimed claim 1 , wherein the pleural effusion identification data comprise yes/no-information in respect of the presence or absence of the potential pleural effusion.

9. The method as claimed in claim 1 , wherein a specification in respect of a volume or extent of a potential pleural effusion is derived from the pleural effusion identification data.

10. The method as claimed in claim 9 , wherein a signal is output to a user in the case of a volume of the potential pleural effusion exceeding a volume threshold defined in advance.

11. The method as claimed in claim 1 , wherein the pleural effusion identification data are matched to reference pleural effusion identification data from a database and match information is derived therefrom.

12. The method as claimed in claim 1 , wherein the image data is obtained from a scan by a computed tomography system.

13. An identification system for automatically identifying a potential pleural effusion in medical image data of a thorax of a patient, including at least a processor, wherein the processor further comprises:
a first acceptor, configured to receive, from the image data from the medical scanner, rib cage detection data including rib cage extent data of a rib cage extent of the interior of the rib cage of the patient,
a second acceptor, configured to receive, from the image data from the medical scanner, lung detection data including lung extent data of a lung extent of the external boundary of the lung cage of the patient,
a third acceptor, configured to receive, from the image data from the medical scanner, mediastinum detection data including mediastinum extent data of a mediastinum extent of an external boundary of the mediastinum of all organs of the mediastinum in the thorax of the patient,
a subtraction unit configured to, during operation, subtract the lung extent and the mediastinum extent from the rib cage extent to form pleural effusion identification data, wherein the pleural effusion identification data comprises volume information;
an evaluation unit configured to, during operation, compare the volume information of the pleural effusion identification data with a volume threshold; and
an output for outputting a signal when the volume information of the pleural effusion identification data indicates the potential pleural effusion exceeds the volume threshold, wherein the signal serves as an automatic warning that the potential pleural effusion is large and there is a need to act for an invasive treatment of the large potential pleural effusion.

14. A computer program product that is on a processor of a programmable identification system comprising a computer readable hardware storage device having computer readable program code stored therein, said program code executable by a processor of a computer system to implement the method as claimed in claim 1 , when the program product is executed on the identification system.

Assignees

• Siemens Ag

Inventors

• Dankerl Peter
• Hammon Matthias
• Kramer Martin
• Soza Grzegorz

Classifications

• G16H50/30

  for calculating health indices; for individual health risk assessment · CPC title

• G06T2207/30061

  Lung · CPC title

• G06T2207/10081

  Computed x-ray tomography [CT] · CPC title

• G06T7/0014

  using an image reference approach · CPC title

• G06T2207/20224

  Image subtraction · CPC title