Deep learning medical systems and methods for image reconstruction and quality evaluation
Methods and apparatus to automatically generate an image quality metric for an image are provided. An example method includes automatically processing a first medical image using a deployed learning network model to generate an image quality metric for the first medical image, the deployed learning network model generated from a digital learning and improvement factory including a training network, wherein the training network is tuned using a set of labeled reference medical images of a plurality of image types, and wherein a label associated with each of the labeled reference medical images indicates a central tendency metric associated with image quality of the image. The example method includes computing the image quality metric associated with the first medical image using the deployed learning network model by leveraging labels and associated central tendency metrics to determine the associated image quality metric for the first medical image.
1. An imaging system comprising:
at least one processor and at least one memory configured to implement a deployed learning network model, the deployed learning network model generated from a training network, wherein the training network is tuned using features extracted from a set of labeled reference medical images, and wherein a label associated with each of the labeled reference medical images indicates an image quality metric for the respective medical image, the features associated with a target value for the image quality metric, the at least one processor configured to at least:
automatically process a first medical image using the deployed learning network model to generate an image quality metric for the first medical image; and
compute the image quality metric associated with the first medical image using the deployed learning network model by leveraging the features and associated target value for the image quality metric to determine the associated image quality metric for the first medical image; and
a display to output the first medical image and the associated image quality metric.
2. The imaging system of claim 1 , wherein the image quality metric includes an image quality index.
3. The imaging system of claim 2 , wherein the image quality index is defined on a 5-point scale, wherein a low score on the 5-point scale indicates a low confidence to make a decision based on the first medical image and wherein a high score on the 5-point scale indicates a high confidence to make the decision based on the first medical image.
4. The imaging system of claim 1 , wherein the at least one processor is to compare the image quality metric to the target value to determine a reliability of the deployed learning network model.
5. The imaging system of claim 1 , wherein the deployed learning network model is to extract a plurality of features from the first medical image and evaluate a diagnostic quality of each of the extracted plurality of features to determine the image quality metric for the first medical image.
6. The imaging system of claim 1 , wherein the training network is tested using one or more unlabeled images before the deployed learning network model is generated from the training network.
7. The imaging system of claim 1 , wherein the features are calculated from image intensity values including at least one of mean, standard deviation, skewness, kurtosis, energy, contract, moment, or entropy.
8. The imaging system of claim 1 , wherein the training network is trained using a second medical image and at least one blurred variant of the second medical image.
9. An apparatus to automatically generate an image quality metric for a medical image, the apparatus comprising:
at least one processor and at least one memory configured to implement a deployed learning network model, the deployed learning network model generated from a training network, wherein the training network is tuned using features extracted from a set of labeled reference medical images, and wherein a label associated with each of the labeled reference medical images indicates an image quality metric for the respective medical image, the features associated with a target value for the image quality metric, the at least one processor configured to at least:
automatically process a first medical image using the deployed learning network model to generate an image quality metric for the first medical image;
compute the image quality metric associated with the first medical image using the deployed learning network model by leveraging the features and associated target value for the image quality metric to determine the associated image quality metric for the first medical image; and
output the first medical image and the associated image quality metric.
10. The apparatus of claim 9 , wherein the image quality metric includes an image quality index.
11. The apparatus of claim 10 , wherein the image quality index is defined on a 5-point scale, wherein a low score on the 5-point scale indicates a low confidence to make a decision based on the first medical image and wherein a high score on the 5-point scale indicates a high confidence to make the decision based on the first medical image.
12. The apparatus of claim 9 , wherein the at least one processor is to compare the image quality metric to the target value to determine a reliability of the deployed learning network model.
13. The apparatus of claim 9 , wherein the deployed learning network model is to extract a plurality of features from the first medical image and evaluate a diagnostic quality of each of the extracted plurality of features to determine the image quality metric for the first medical image.
14. The apparatus of claim 9 , wherein the training network is tested using one or more unlabeled images before the deployed learning network model is generated from the training network.
15. The apparatus of claim 9 , wherein the features are calculated from image intensity values including at least one of mean, standard deviation, skewness, kurtosis, energy, contract, moment, or entropy.
16. The apparatus of claim 9 , wherein the training network is trained using a second medical image and at least one blurred variant of the second medical image.
17. A non-transitory computer-readable storage medium including instructions which, when executed, cause at least one processor to at least:
automatically process a first medical image using a deployed learning network model to generate an image quality metric for the first medical image, the deployed learning network model generated from a training network, wherein the training network is tuned using features extracted from a set of labeled reference medical images, and wherein a label associated with each of the labeled reference medical images indicates an image quality metric for the respective medical image, the features associated with a target value for the image quality metric;
compute the image quality metric associated with the first medical image using the deployed learning network model by leveraging the features and associated target value for the image quality metric to determine the associated image quality metric for the first medical image; and
output the first medical image and the associated image quality metric.
18. The storage medium of claim 17 , wherein the image quality metric includes an image quality index.
19. The storage medium of claim 18 , wherein the image quality index is defined on a 5-point scale, wherein a low score on the 5-point scale indicates a low confidence to make a decision based on the first medical image and wherein a high score on the 5-point scale indicates a high confidence to make the decision based on the first medical image.
20. The storage medium of claim 17 , wherein the deployed learning network model is to extract a plurality of features from the first medical image and evaluate a diagnostic quality of each of the extracted plurality of features to determine the image quality metric for the first medical image.