Method and system for estimating a deflated lung shape for video assisted thoracic surgery in augmented and mixed reality

1. A method, implemented on a computing device having at least one processor, storage, and a communication platform capable of connecting to a network for surgical procedure assistance, comprising:

obtaining a first volume of air inside a lung of a patient based on a first image of the lung captured prior to a surgical procedure, wherein the lung has a first shape on the first image;

capturing a video image of the lung during the surgical procedure;

generating a model to estimate a deflation parameter based on a plurality of laparoscopic images;

computing, via the generated model and the video image, a second volume of air deflated from the lung based on the deflation parameter;

estimating a second shape of the lung based on the first shape of the lung, the first air volume inside the lung and second volume of air deflated from the lung;

updating a surgical plan based on the estimated second shape of the lung; and

registering, the estimated second shape of the lung on to the patient in a mixed reality view.

2. The method of claim 1 , wherein the second shape being estimated by condensing a plurality of voxels in the first image along a gravity direction.

3. The method of claim 1 , wherein the surgical procedure includes a video assisted thoracic surgery (VATS), and the first image includes a computed tomography (CT) image.

4. The method of claim 1 , further comprising:

obtaining an angle of rotation of the lung from a first position at which the first image was captured to a second position at which the video image was captured; and

adjusting the first shape of the lung on the first image based on the angle of rotation, wherein the second shape of the lung is estimated based on the adjusted first shape of the lung, the first volume, and the second volume.

5. The method of claim 1 , wherein computing the second volume of the air comprises:

generating the plurality of laparoscopic images, wherein each laparoscopic image is generated as a function of a deflation control parameter and a camera position;

training the model to learn a mapping of each laparoscopic image to the deflation control parameter and camera position; and

determining, based on the training, the deflation parameter associated with the video image.

6. The method of claim 1 , wherein estimating the second shape of the lung comprises:

calculating a third volume of air inside the lung during the surgical procedure based on the second volume; and

determining a ratio between the first volume and the third volume.

7. The method of claim 6 , wherein estimating the second shape of the lung further comprises:

estimating, for each voxel of the plurality of voxels included in the first shape of the lung on the first image, the first volume of air inside each voxel based on an intensity of each voxel;

calculating the second volume of air inside each voxel based on the first volume of air inside the voxel and the ratio; and

condensing the plurality of voxels along the gravity direction based on the second volume of air inside each voxel.

8. A system for surgical procedure assistance, comprising:

at least one processor configured to:

obtain a first volume of air inside a lung of a patient based on a first image of the lung captured prior to a surgical procedure, wherein the lung has a first shape on the first image;

capture a video image of the lung during the surgical procedure;

generate a model to estimate a deflation parameter based on a plurality of laparoscopic images;

compute, via the generated model and the video image, a second volume of air deflated from the lung based on the deflation parameter;

estimate a second shape of the lung based on the first shape of the lung, the first air volume inside the lung, and second volume of air deflated from the lung;

update a surgical plan based on the estimated second shape of the lung; and

register, the estimated second shape of the lung on to the patient in a mixed reality view.

9. The system of claim 8 , wherein the second shape being estimated by condensing a plurality of voxels in the first image along a gravity direction.

10. The system of claim 8 , wherein the surgical procedure includes a video assisted thoracic surgery (VATS), and the first image includes a computed tomography (CT) image.

11. The system of claim 8 , wherein the at least one processor is further configured to:

obtain an angle of rotation of the lung from a first position at which the first image was captured to a second position at which the video image was captured; and

adjust the first shape of the lung on the first image based on the angle of rotation, wherein the second shape of the lung is estimated based on the adjusted first shape of the lung, the first volume, and the second volume.

12. The system of claim 8 , wherein the at least one processor is further configured to:

generate the plurality of laparoscopic images, wherein each laparoscopic image is generated as a function of a deflation control parameter and a camera position;

train the model to learn a mapping of each laparoscopic image to the deflation control parameter and camera position; and

determine, based on the training, the deflation parameter associated with the video image.

13. The system of claim 8 , wherein the at least one processor is further configured to:

calculate a third volume of air inside the lung during the surgical procedure based on the second volume; and

determine a ratio between the first volume and the third volume.

14. The system of claim 13 , wherein the at least one processor is further configured to:

estimate, for each voxel of the plurality of voxels included in the first shape of the lung on the first image, the first volume of air inside each voxel based on an intensity of each voxel;

calculate the second volume of air inside each voxel based on the first volume of air inside the voxel and the ratio; and

condense the plurality of voxels along the gravity direction based on the second volume of air inside each voxel.