Automatically controlling an on/off state of a light source for an endoscope during a surgical procedure in an operating room
An endoscope system capable of automatically turning on/off a light source during a surgical procedure is disclosed. This endoscope system includes: an endoscope module; a light source module coupled to the endoscope module; and a light-source control module. Moreover, the light-source control module controls an ON/OFF state of the light source by: (1) receiving real-time video images captured by the endoscope module; (2) processing the real-time video images to determine whether the endoscope module is inserted into a patient's body or is outside of the patient's body; and (3) in response to determining the endoscope module being outside of the patient's body while the light source is turned on, generating a control signal to immediately turn off the light source to the endoscope module, thereby ensuring safety of people in the operating room and preventing sensitive information in the operating room from being captured by the endoscope module.
1. A computer-implemented method for controlling an on/off state of a light source of an endoscope during a surgical procedure, the method comprising:
receiving real-time video images captured by the endoscope;
determining, by a computer, a state of the endoscope, the state of the endoscope including a first state inside a patient's body or a second state outside the patient's body, wherein determining the state of the endoscope occurs when the light source is turned on and off;
detecting, by the computer, a transitional event based on the received real-time video images, wherein the transitional event includes a first transitional event from the second state to the first state, wherein detecting the transitional event based on the received real-time video images includes detecting the transitional event based on a single real-time video image or a sequence of real-time video images, wherein a machine-learning classifier identifies a correlation between the sequence of real-time video images and the transitional event; and
automatically generating, by the computer, a control signal upon detection of the transitional event, the control signal changing the on/off state of the light source.
2. The method of claim 1 , wherein determining the state of the endoscope includes applying a machine-learning classifier to classify the real-time video images as either a first class of real-time video images inside the patient's body or a second class of real-time video images outside the patient's body.
3. The method of claim 1 , wherein changing the on/off state of the light source in response to the first transitional event includes turning on the light source.
4. The method of claim 1 , wherein the transitional event further includes a second transitional event from the first state to the second state.
5. The method of claim 4 , wherein changing the on/off state of the light source in response to the second transitional event includes turning off the light source.
6. A non-transitory computer-readable medium to store instructions that, when executed by a processor of a computer system, cause the computer system to:
receive real-time video images captured by an endoscope;
determine a state of the endoscope, the state of the endoscope including a first state inside a patient's body or a second state outside the patient's body, wherein determining the state of the endoscope occurs when a light source of the endoscope is turned on and off;
detect a transitional event based on the received real-time video images, wherein the transitional event includes a first transitional event from the second state to the first state, wherein the processor executes the instructions to detect the transitional event based on the received real-time video images by detecting the transitional event based on a single real-time video image or a sequence of real-time video images, wherein a machine-learning classifier identifies a correlation between the sequence of real-time video images and the transitional event; and
automatically generate a control signal upon detection of the transitional event, the control signal changing an on/off state of the light source of the endoscope.
7. The non-transitory computer-readable medium of claim 6 , wherein the processor executes the instructions to determine the state of the endoscope by applying a machine-learning classifier to classify the real-time video images as either a first class of real-time video images inside the patient's body or a second class of real-time video images outside the patient's body.
8. The non-transitory computer-readable medium of claim 6 , wherein the processor executes the instructions to change the on/off state of the light source in response to the first transitional event by turning on the light source.
9. The non-transitory computer-readable medium of claim 6 , wherein the transitional event further includes a second transitional event from the first state to the second state.
10. The non-transitory computer-readable medium of claim 9 , wherein the processor executes the instructions to change the on/off state of the light source in response to the second transitional event by turning off the light source.
11. An endoscope system, comprising:
an endoscope camera module;
a light source module coupled to the endoscope camera module for providing a light source for the endoscope camera module; and
a light-source control module coupled to the endoscope camera module and the light source module, and configured to control an on/off state of the light source of an endoscope during a surgical procedure by:
receiving real-time video images captured by the endoscope;
determining a state of the endoscope, the state of the endoscope including a first state inside a patient's body or a second state outside the patient's body, wherein
determining the state of the endoscope occurs when the light source is turned on and off;
detecting a transitional event based on the received real-time video images, wherein the transitional event includes a first transitional event from the second state to the first state, wherein detecting the transitional event based on the received real-time video images includes detecting the transitional event based on a single real-time video image or a sequence of real-time video images, wherein a machine-learning classifier identifies a correlation between the sequence of real-time video images and the transitional event; and
automatically generating a control signal upon detection of the transitional event, the control signal changing the on/off state of the light source.
12. The endoscope system of claim 11 , wherein determining the state of the endoscope includes applying a machine-learning classifier to classify the real-time video images as either a first class of real-time video images inside the patient's body or a second class of real-time video images outside the patient's body.
13. The endoscope system of claim 11 , wherein changing the on/off state of the light source in response to the first transitional event includes turning on the light source.
14. The endoscope system of claim 11 , wherein the transitional event further includes a second transitional event from the first state to the second state, and changing the on/off state of the light source in response to the second transitional event by turning off the light source.