Computer vision technologies for rapid detection
A computing system includes a processor; and a memory having stored thereon an adjustment application comprising computer-executable instructions that, when executed, cause the computing system to: display a graphical user interface including a digital medical image of a patient; superimpose a bounding box; receive an adjustment of an area of interest; and provide an adjusted digital medical image. A non-transitory computer-readable medium includes computer-executable instructions that, when executed via one or more processors, cause a computer to: display a graphical user interface including a digital medical image of a patient; superimpose a bounding box; receive an adjustment of an area of interest; and provide an adjusted digital medical image. A computer-implemented method includes: displaying a graphical user interface including a digital medical image of a patient; superimposing a bounding box; receiving an adjustment of an area of interest; and providing an adjusted digital medical image.
1. A computing system for facilitating a clinician adjustment of a digital medical image corresponding to a patient used in conjunction with a machine learning model, comprising:
one or more processors; and
one or more memories having stored thereon an adjustment application comprising computer-executable instructions that, when executed, cause the computing system to:
train, via the one or more processors, the machine learning model to learn to detect acute respiratory distress syndrome based on an opacity of the digital medical image;
display, via the one or more processors, a graphical user interface including the digital medical image corresponding to the patient;
superimpose, over the digital medical image corresponding to the patient, a bounding box containing one or more areas of interest;
receive, via the one or more processors, an adjustment of at least one of the bounding box or the one or more areas of interest; and
provide, via the one or more processors, an adjusted digital medical image corresponding to the patient to the machine learning model, the adjusted digital medical image including the adjustment of at least one of the bounding box or the one or more areas of interest.
2. The computing system of claim 1 , the adjustment application comprising further instructions that, when executed by the one or more processors, cause the computing system to:
capture, via an imaging device, the digital medical image corresponding to the patient.
3. The computing system of claim 1 , wherein the adjustment of at least one of the bounding box or the one or more areas of interest is at least one of a repositioning, a rotation, an extension, an erasure, or a redrawing.
4. The computing system of claim 1 ,
wherein the machine learning model is a deep learning model being trained, and
the adjustment application comprising further instructions that, when executed by the one or more processors, cause the computing system to:
inject the adjusted digital medical image corresponding to the patient to an image processing pipeline;
reprocess the adjusted digital medical image; and
provide the adjusted digital medical image to the deep learning model to facilitate training of the deep learning model.
5. The computing system of claim 1 ,
wherein the machine learning model is a trained deep learning model being operated, and
the adjustment application comprising further instructions that, when executed by the one or more processors, cause the computing system to:
provide the adjusted digital medical image to the trained deep learning model to improve predictive accuracy of the deep learning model.
6. The computing system of claim 1 ,
wherein the digital medical image is a chest X-ray image, and
wherein the one or more areas of interest include one or more heat maps generated using a Gradient-weighted Class Activation Mapping (Grad-CAM) algorithm.
7. The computing system of claim 1 ,
wherein the digital medical image corresponds to a projectional radiography image, computed tomography (CT) scanning image or a magnetic resonance imaging (MRI) scanning image.
8. The computing system of claim 1 , wherein the machine learning model is trained to detect at least one of acute respiratory distress syndrome, trauma, sepsis, pneumonia, aspiration, congestive heart failure, hemothorax, pneumothorax, atelectasis, collapsed lung, pleural effusion or tuberculosis.
9. A non-transitory computer-readable medium having stored thereon computer-executable instructions that, when executed via one or more processors, cause a computer to:
train, via one or more processors, the machine learning model to learn to detect acute respiratory distress syndrome based on an opacity of the digital medical image;
display, via one or more processors, a graphical user interface including a digital medical image corresponding to a patient;
superimpose, over the digital medical image corresponding to the patient, a bounding box containing one or more areas of interest;
receive, via one or more processors, an adjustment of at least one of the bounding box or the one or more areas of interest; and
provide, via one or more processors, an adjusted digital medical image corresponding to the patient to a machine learning model, the adjusted digital medical image including the adjustment of at least one of the bounding box or the one or more areas of interest.
10. The non-transitory computer-readable medium of claim 9 , having stored thereon computer-executable instructions that, when executed via one or more processors, cause a computer to:
capture, via an imaging device, the digital medical image corresponding to the patient.
11. The non-transitory computer-readable medium of claim 9 , wherein the adjustment of at least one of the bounding box or the one or more areas of interest is at least one of a repositioning, a rotation, an extension, an erasure, or a redrawing.
12. The non-transitory computer-readable medium of claim 9 ,
wherein the machine learning model is a deep learning model being trained, and
the computer-readable medium having stored thereon computer-executable instructions that, when executed via one or more processors, cause a computer to:
inject the adjusted digital medical image corresponding to the patient to an image processing pipeline;
reprocess the adjusted digital medical image; and
provide the adjusted digital medical image to the deep learning model to facilitate training of the deep learning model.
13. The non-transitory computer-readable medium of claim 9 ,
wherein the machine learning model is a trained deep learning model being operated, and
the computer-readable medium having stored thereon computer-executable instructions that, when executed via one or more processors, cause a computer to:
provide the adjusted digital medical image to the trained deep learning model to improve predictive accuracy of the deep learning model.
14. The non-transitory computer-readable medium of claim 9 ,
wherein the digital medical image is a chest X-ray image, and
wherein the one or more areas of interest include one or more heat maps generated using a Gradient-weighted Class Activation Mapping (Grad-CAM) algorithm.
15. The non-transitory computer-readable medium of claim 9 , wherein the machine learning model is trained to detect at least one of acute respiratory distress syndrome, trauma, sepsis, pneumonia, aspiration, congestive heart failure, hemothorax, pneumothorax, atelectasis, collapsed lung, pleural effusion or tuberculosis.
16. The non-transitory computer-readable medium of claim 9 ,
wherein the digital medical image corresponds to a projectional radiography image, computed tomography (CT) scanning image or a magnetic resonance imaging (MRI) scanning image.
17. A computer-implemented method for facilitating a clinician adjustment of a digital medical image corresponding to a patient used in conjunction with a machine learning model, the method comprising:
training, via one or more processors, the machine learning model to learn to detect acute respiratory distress syndrome based on an opacity of the digital medical image;
displaying, via one or more processors, a graphical user interface including the digital medical image corresponding to a patient;
superimposing, over the digital medical image corresponding to the patient, a bounding box containing one or more areas of interest;
receiving, via one or more processors, an adjustment of at least one of the bounding box or the one or more areas of interest; and
providing, via one or more processors, an adjusted digital medical image corresponding to the patient to a machine learning model, the adjusted digital medical image including the adjustment of at least one of the bounding box or the one or more areas of interest.
18. The computer-implemented method of claim 17 , further comprising:
capture, via an imaging device, the digital medical image corresponding to the patient.
19. The computer-implemented method of claim 17 , wherein the adjustment of at least one of the bounding box or the one or more areas of interest is at least one of a repositioning, a rotation, an extension, an erasure, or a redrawing.
20. The computer-implemented method of claim 17 ,
wherein the machine learning model is a deep learning model being trained, and
further comprising:
injecting the adjusted digital medical image corresponding to the patient to an image processing pipeline;
reprocessing the adjusted digital medical image; and
providing the adjusted digital medical image to the deep learning model to facilitate training of the deep learning model.
21. The computer-implemented method of claim 17 ,
wherein the machine learning model is a trained deep learning model being operated, and
further comprising:
providing the adjusted digital medical image to the trained deep learning model to improve predictive accuracy of the deep learning model.
22. The computer-implemented method of claim 17 ,
wherein the digital medical image is a chest X-ray image, and
wherein the one or more areas of interest include one or more heat maps generated using a Gradient-weighted Class Activation Mapping (Grad-CAM) algorithm.
23. The computer-implemented method of claim 17 , wherein the machine learning model is trained to detect at least one of acute respiratory distress syndrome, trauma, sepsis, pneumonia, aspiration, congestive heart failure, hemothorax, pneumothorax, atelectasis, collapsed lung, pleural effusion or tuberculosis.
24. The computer-implemented method of claim 17 ,
wherein the digital medical image corresponds to a projectional radiography image, computed tomography (CT) scanning image or a magnetic resonance imaging (MRI) scanning image.