Method and system for automatically turning on/off a light source for an endoscope during a surgery

1. A computer-implemented method for automatically turning on/off a light source of an endoscope camera during a surgical procedure, the method comprising:

receiving a first sequence of video images captured by the endoscope camera when the light source is turned on;

analyzing, by a computer, the first sequence of video images using a statistical classifier to classify each video image in the first sequence of video images as either a first class of image of being inside the patient's body or a second class of image of being outside of the patient's body;

determining, by the computer, whether the endoscope camera is inside a patient's body or outside of the patient's body based on the classified first sequence of video images, wherein the said determination includes determining if the first sequence of classified video images includes a first transitional event of transferring the endoscope camera from the inside of the patient's body to the outside of the patient's body; and

when the endoscope camera is determined to be outside of the patient's body, generating a first control signal for turning off the light source, wherein the first control signal is used to immediately turn off the light source.

2. The computer-implemented method of claim 1 , further comprising:

when the endoscope camera is determined to be inside the patient's body, continuing monitoring a state of the endoscope camera.

3. The computer-implemented method of claim 1 , wherein after the light source has been turned off, the method further comprises:

receiving a second sequence of video images captured by the endoscope camera when the light source is off;

processing the second sequence of video images to determine if the endoscope camera remains outside of the patient's body; and

if so, continuing monitoring the state of the endoscope camera,

otherwise, generating a second control signal for turning on the light source.

4. The computer-implemented method of claim 3 , wherein processing the second sequence of video images to determine if the endoscope camera remains outside of the patient's body includes:

using the statistical classifier to classify each video image in the second sequence of video images as the first class of image of being inside the patient's body or the second class of image of being outside of the patient's body; and

determining a state of the endoscope camera as being inside the patient's body or outside of the patient's body based on the classified second sequence of video images.

5. The computer-implemented method of claim 4 , wherein determining the state of the endoscope camera as being inside of the patient's body includes identifying a second transitional event of transferring the endoscope camera from outside of the patient's body to the inside of the patient's body based on the classified second sequence of video images.

6. The computer-implemented method of claim 1 , wherein while the light source remains turned off and the endoscope camera is outside of the patient's body, the method further comprises:

detecting that the endoscope camera is pointed at a white balancing object; and

generating a third control signal for turning on the light source for white balancing operation.

7. The computer-implemented method of claim 6 , wherein detecting that the endoscope camera is pointed at the white balancing object includes:

receiving a real-time video image captured by the endoscope camera when the light source is turned off; and

processing the video image to identify a predefined white balancing object within the video image.

8. The computer-implemented method of claim 1 , wherein the method further comprises training the statistical classifier by:

receiving a plurality of surgical videos, wherein each of the plurality of surgical videos contains video images of an endoscope being both inside and outside a patient's body;

for each of the plurality of surgical videos, labeling the corresponding video images as the first class of image or the second class of image; and

training the statistical classifier for distinguishing an input image as being the first class of image or the second class of image based on the labeled video images.

9. The computer-implemented method of claim 8 , wherein training the statistical classifier for distinguishing an input image includes training the statistical classifier based on a set of distinct image features, such as statistics of the color; texture; and contrast.

10. An apparatus for automatically turning on/off a light source of an endoscope camera during a surgical procedure, the apparatus comprising:

one or more processors; and

a memory coupled to the one or more processors; and

wherein the memory stores a set of instructions that, when executed by the one or more processors, cause the apparatus to:

receive a first sequence of video images captured by the endoscope camera when the light source is turned on;

analyze the first sequence of video images to determine whether the endoscope camera is inside a patient's body or outside of the patient's body, wherein the said determination includes determining if the first sequence of video images includes a first transitional event of transferring the endoscope camera from the inside of the patient's body to the outside of the patient's body; and

if it is determined that the endoscope camera is inside the patient's body, continue monitoring a state of the endoscope camera, or

if it is determined that the endoscope camera is outside of the patient's body, generate a first control signal for turning off the light source, wherein the first control signal is used to immediately turn off the light source.

11. The apparatus of claim 10 , further comprising:

using a machine-learning classifier to classify each video image in the first sequence of video images as a first class of image of being inside the patient's body or a second class of image of being outside of the patient's body; and

determining a state of the endoscope camera as being inside the patient's body or outside of the patient's body based on the classified first sequence of video images.

12. The apparatus of claim 11 , wherein the memory further stores a set of instructions that, when executed by the one or more processors, cause the apparatus to:

receive a second sequence of video images captured by the endoscope camera when the light source is off;

process the second sequence of video images to determine if the endoscope camera remains outside of the patient's body; and

if so, continue monitoring the state of the endoscope camera,

otherwise, generate a second control signal for turning on the light source.

13. The apparatus of claim 12 , wherein processing the second sequence of video images to determine if the endoscope camera remains outside of the patient's body further includes:

using the machine-learning classifier to classify each video image in the second sequence of video images as the first class of image of being inside the patient's body or the second class of image of being outside of the patient's body; and

determining a state of the endoscope camera as being inside the patient's body or outside of the patient's body based on the classified second sequence of video images.

14. The apparatus of claim 13 , wherein determining the state of the endoscope camera as being inside of the patient's body includes identifying a second transitional event of transferring the endoscope camera from outside of the patient's body to the inside of the patient's body.

15. The apparatus of claim 10 , wherein while the light source remains turned off and the endoscope camera is outside of the patient's body, the memory further stores a set of instructions that, when executed by the one or more processors, cause the apparatus to:

detect that the endoscope camera is pointed at a white balancing object; and

generate a third control signal for turning on the light source for white balancing operation.

16. The apparatus of claim 15 , wherein detecting that the endoscope camera is pointed at the white balancing object includes:

receiving a real-time video image captured by the endoscope camera when the light source is turned off; and

processing the video image to identify a predefined white balancing object within the video image.

17. 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 cause the light source in the light source module to be automatically turned on/off during a surgical procedure by:

receiving a first sequence of video images captured by the endoscope camera module when the light source is turned on;

determining, by the light-source control module, whether the endoscope camera module is inside a patient's body or outside of the patient's body by:

using an image classifier to classify each video image in the first sequence of video images as either a first class of image of being inside the patient's body or a second class of image of being outside of the patient's body; and

determining if the first sequence of classified video images includes a first transitional event of transferring the endoscope camera from the inside of the patient's body to the outside of the patient's body; and

if it is determined that the endoscope camera module is inside the patient's body, continuing monitoring a state of the endoscope camera, or

if it is determined that the endoscope camera module is outside of the patient's body, generating a first control signal for turning off the light source, wherein the control signal is used to immediately turn off the light source.

18. The endoscope system of claim 17 , wherein the light-source control module is further configured to cause the light source in the light source module to be automatically turned on/off during a surgical procedure by:

receiving a second sequence of video images captured by the endoscope camera module when the light source is turned off;

processing the second sequence of video images to determine if the endoscope camera module remains outside of the patient's body; and

if so, continuing monitoring the state of the endoscope camera module,

otherwise, generating a second control signal for turning on the light source.