Medical system having movable components and a control device for preventing component collisions

• US 5,878,112 A
• Filed: 06/24/1997
• Issued: 03/02/1999
• Est. Priority Date: 06/25/1996
• Status: Expired due to Term

• Current Assignee: Siemens AG
• Original Assignee: Siemens AG
• Inventors: Koertge, Detlef
• Primary Examiner(s): Wong, Don
• Assistant Examiner(s): Bruce, David Vernon
• Application Number:
  US08/881,350
• Time in Patent Office: 616 Days
• Field of Search: 378/8, 378/95, 378/209, 600/407, 600/408, 600/415
• US Class Current: 378/209
• CPC Class Codes: A61B 6/102 Protection against mechanical damage, e.g. anti-collision devices
• CPC Class Codes: F16P 3/12 with means, e.g. feelers, which in case of the presence of a body part of a person in or near the danger zone influence the control or operation of the machine F16P3/08 takes precedence

Abstract

A medical system, such as an X-ray diagnostic device, having adjustable components, including a patient table, and having a monitoring device for determining the relative positions of the components and preventing collisions between them. Signals indicating the positions, the directions of motion and the speeds of movement of the components are fed directly from the drives and sensors of the components to the monitoring device. Calculations for controlling the components are carried out by a neural network, which has been appropriately trained in a learning phase.

Claims

1. A medical system comprising:

a plurality of adjustable components, including a table for supporting a patient;

a plurality of drives and sensors respectively connected to said adjustable components; and

a control device, connected to said drives and sensors, for determining respective positions of said components and preventing collisions between said respective components, said control device comprising a neural network,

wherein said control device gathers data for respective positions, respective directions of motion and respective speeds of movement of said components directly from said plurality of drives and sensors of said components, and

wherein said neural network carries out processing for controlling said components in accordance with the gathered data, following training of said neural network in a learning phase.

2. The medical system according to claim 1, wherein said neural network is a single layer radial base function network.

3. The medical system according to claim 1, wherein the medical system is an X-ray diagnostic device, and said plurality of adjustable components comprises said patient table and a C-bracket supporting a radiation source and a radiation receiver.

4. The medical system according to claim 1, wherein said neural network outputs data for controlling said components, in accordance with the processing of the gathered data, continually during operation of said control device.

5. A method for preventing component collisions in a medical system, the components being movable, relative to other system components and structures, in at least one degree of freedom in accordance with respective drive signals output by respective component drive sources, comprising:

outputting positional information, including at least one of location information, direction information, and speed information, for each degree of freedom of each movable component, the positional information being output from signal outputs connected either to the respective component drive sources or to the components;

supplying the positional information as input variables directly from the signal outputs to a neural network previously trained in a learning phase;

processing the input variables in the neural network, for determining positions of the respective components and generating control signals; and

outputting the control signals to the respective component drive sources for preventing component collisions in the medical system.