Methods and systems for detecting acquisition errors in medical images

1. A system for detecting acquisition errors in an X-ray image, the system comprising a non-transitory computer-readable medium storing a preprocessing quality control module that, when executed by at least one electronic processor, is configured to generate associated classifications identifying characteristics of the medical image,

wherein the preprocessing quality control module comprises,

an anterior-posterior/posterior-anterior classifier developed by performing machine learning using a first set of training X-ray images, wherein the first set of training X-ray images are manually labeled with an anterior-posterior (AP) projection view or a posterior-anterior (PA) projection view;

an erect/supine classifier developed by performing machine learning using a second set of training X-ray images, wherein the second set of training X-ray images are manually labeled with erect or supine;

a clipped anatomy classifier developed by performing machine learning using a third set of training X-ray images, wherein a required anatomy is clipped out in each of the third set of training X-ray images using a deep learning based computer vision module;

an under/over exposure classifier developed by performing machine learning using a fourth set of training X-ray images, wherein the fourth set of training X-ray image are manually labeled with under or over exposure;

an patient rotation classifier developed by performing machine learning using a fifth set of training X-ray images, wherein the patient rotation classifier comprises a U-net based segmentation model trained to give heatmaps of clavicles and spinous processes;

an inspiration classifier developed by performing machine learning using a sixth set of training X-ray images, wherein the inspiration classifier comprises two U-net based segmentation models to segment the ribs and to segment the diaphragm respectively;

and

an ensemble model configured to combine the anterior-posterior/posterior-anterior classifier, the erect/supine classifier, the clipped anatomy classifier, the under/over exposure classifier, the patient rotation classifier, and the inspiration classifier to generate a final algorithm.

2. The system of claim 1 , wherein the preprocessing quality control module are developed using deep learning neural network models or deep learning neural network models followed by a rule engine.

3. The system of claim 2 , wherein the deep learning neural network models are ResNet based models.

4. The system of claim 1 , wherein the computer vision module comprises a U-Net based neural network trained to output anatomical ResNet masks corresponding to specific anatomies.

5. The system of claim 1 , wherein an ensemble model is configured to output a prediction on whether the X-ray image is diagnostically acceptable or diagnostically unacceptable.

6. The system of claim 5 , wherein the diagnostically acceptable image is passed to an abnormal detection module for further analysis.

7. The system of claim 5 , wherein the diagnostically unacceptable image is eliminated.

8. A method for detecting acquisition errors in an X-ray image, comprising

receiving the X-ray image captured via a medical imaging device;

determining a plurality of classifications of the X-ray image via a preprocessing quality control module developed with machine learning; and

outputting a prediction on whether the X-ray image is diagnostically acceptable or diagnostically acceptable;

wherein the preprocessing quality control module comprises,

an anterior-posterior/posterior-anterior classifier developed by performing machine learning using a first set of training X-ray images, wherein the first set of training X-ray images are manually labeled with an anterior-posterior (AP) projection view or a posterior-anterior (PA) projection view;

an erect/supine classifier developed by performing machine learning using a second set of training X-ray images, wherein the second set of training X-ray images are manually labeled with erect or supine;

a clipped anatomy classifier developed by performing machine learning using a third set of training X-ray images, wherein a required anatomy is clipped out in each of the third set of training X-ray images using a deep learning based computer vision module;

an under/over exposure classifier developed by performing machine learning using a fourth set of training X-ray images, wherein the fourth set of training X-ray image are manually labeled with under or over exposure;

an patient rotation classifier developed by performing machine learning using a fifth set of training X-ray images, wherein the patient rotation classifier comprises a U-net based segmentation model trained to give heatmaps of clavicles and spinous processes;

an inspiration classifier developed by performing machine learning using a sixth set of training X-ray images, wherein the inspiration classifier comprises two U-net based segmentation models to segment the ribs and to segment the diaphragm respectively;

and

an ensemble model configured to combine the anterior-posterior/posterior-anterior classifier, the erect/supine classifier, the clipped anatomy classifier, the under/over exposure classifier, the patient rotation classifier, and the inspiration classifier to generate a final algorithm.

9. The method of claim 8 , wherein the preprocessing quality control module are developed using deep learning neural network models or deep learning neural network models followed by a rule engine.

10. The method of claim 9 , wherein the deep learning neural network models are ResNet based models.

11. The method of claim 8 , wherein the computer vision module comprises a U-Net based neural network trained to output anatomical ResNet masks corresponding to specific anatomies.

12. The method of claim 8 , wherein the diagnostically acceptable image is passed to an abnormal detection module for further analysis.

13. The method of claim 8 , wherein the diagnostically unacceptable image is eliminated.