System and method for visualizing placement of a medical tube or line

1. A medical image processing system, comprising:

a display;

a processor; and

a memory storing processor-executable code that when executed by the processor causes:

receiving an image of a region of interest of a patient with a medical tube or line disposed within the region of interest;

detecting the medical tube or line within the image;

detecting a reference landmark within the region of interest within the image, wherein the reference landmark is internal to the patient;

generating a combined image by superimposing a first graphical marker on the image that indicates an end of the medical tube or line and a second graphical marker on the image that indicates the reference landmark; and

displaying the combined image on the display.

2. The medical image processing system of claim 1 , wherein the processor-executable code when executed by the processor causes calculating a measured position of the end of the medical tube or line relative to the reference landmark, and wherein generating the combined image comprises superimposing a third graphical marker on the image that indicates the measured position.

3. The medical image processing system of claim 1 , wherein the processor-executable code when executed by the processor causes calculating respective confidence scores for one or more of a calculated distance between the end of the medical tube or line and the reference landmark, a determination as to whether a medical tube or line is present within the image, an accuracy of a detection of the end of the medical tube or line, or an accuracy of a detection of the reference landmark.

4. The medical image processing system of claim 1 , wherein the processor-executable code when executed by the processor causes determining whether the medical tube or line is properly placed relative to the reference landmark.

5. The medical image processing system of claim 4 , wherein the processor-executable code when executed by the processor causes providing a user-perceptible indication to a user when the medical tube or line is misplaced relative to the reference landmark.

6. The medical image processing system of claim 1 , wherein the medical tube or line comprises a chest tube, a nasogastric tube, endotracheal tube, vascular line, a peripherally inserted central catheter, or a catheter.

7. The medical image processing system of claim 1 , wherein the reference landmark comprises a carina, a chest cavity, a segmented lung, a diaphragm, or a stomach.

8. The medical image processing system of claim 1 , wherein detecting the medical tube or line within the image comprises utilizing one or more deep learning network models to detect the medical tube or line within the image.

9. The medical image processing system of claim 1 , wherein generating the combined image comprises superimposing on the image a colored graphical overlay over the medical tube or line to indicate the medical tube or line.

10. A method for medical image processing, comprising:

receiving, via a processor, an image of a region of interest of a patient with a medical tube or line disposed within the region of interest;

detecting, via the processor, the medical tube or line within the image;

detecting, via the processor, a reference landmark within the region of interest within the image, wherein the reference landmark is internal to the patient;

generating, via the processor, a combined image by superimposing a first graphical marker on the image that indicates an end of the medical tube or line and a second graphical marker on the image that indicates the reference landmark; and

causing, via the processor, display of the combined image on a display.

11. The method of claim 10 , comprises calculating, via the processor, a measured position of the end of the medical tube or line relative the reference landmark, and wherein generating the combined image comprises superimposing, via the processor, a third graphical marker on the image that indicates the measured position.

12. The method of claim 10 , comprises calculating, via the processor, respective confidence scores for one or more of a calculated distance between the end of the medical tube or line and the reference landmark, a determination as to whether a medical tube or line is present within the image, an accuracy of a detection of the end of the medical tube or line, or an accuracy of a detection of the reference landmark.

13. The method of claim 10 , comprising determining, via the processor, whether the medical tube or line is properly placed relative to the reference landmark.

14. The method of claim 13 , comprising providing, via the processor, a user-perceptible indication to a user when the medical tube or line is misplaced relative to the reference landmark.

15. The method of claim 10 , wherein detecting the medical tube or line within the image comprises utilizing, via the processor, one or more deep learning network models to detect the medical tube or line within the image.

16. A non-transitory, computer-readable medium, the computer-readable medium comprising processor-executable code configured to:

receive an image of a region of interest of a patient with a medical tube or line disposed within the region of interest;

detect the medical tube or line within the image and a reference landmark within the region of interest within the image, wherein the reference landmark is internal to the patient;

generate a combined image by superimposing a first graphical marker on the image that indicates an end of the medical tube or line and a second graphical marker on the image that indicates the reference landmark; and

display the combined image on a display.