Automatic detection of medical image acquisition protocol
The disclosure relates to method and device for determining at least a portion of an anatomy from a set of medical images. Thereafter, the image acquisition protocol associated with the medical images is determined automatically based on the determined anatomy. The image acquisition protocol is automatically determined by extracting one or more features associated with the medical images characterizing the acquisition protocol. Thereafter, the medical images are classified based in the features. Further, the medical images are assigned with an acquisition protocol label based on the classification of the medical images. The medical images are displayed with the respective protocol labels. Further, medical images acquired with an identified image acquisition protocol at different time instances are displayed for comparative analysis.
1. A method of automatically detecting a medical imaging protocol, the method comprising:
receiving, by a processor, a set of medical images from at least one imaging device, the processor being separate from the at least one imaging device;
determining, by the processor, an anatomy of a body part in at least one medical image from the set of medical images;
extracting, by the processor, at least one feature associated with the at least one medical image;
detecting, by the processor, the at least one medical image as an outlier image based on the at least one feature that does not belong to a set of known image acquisition protocols;
automatically classifying, by the processor, the outlier image into at least one image acquisition protocol based on the at least one feature; and
identifying medical images acquired with the image acquisition protocol at different time instances from a medical image database.
2. The method of claim 1 , further comprising:
displaying the image acquisition protocol of the set of medical images on a display unit; and
providing a comparative view of the identified medical images acquired with the image acquisition protocol on the display unit for analysis.
3. The method of claim 1 , further comprising:
assigning the at least one medical image with an image acquisition protocol label based on the classification of the at least one medical image.
4. The method of claim 1 , wherein the at least one feature comprises a two-dimensional Local Binary Pattern (LBP), a three-dimensional LBP, and saliency weighted Histogram of the LBP.
5. The method of claim 1 , wherein the detecting of the at least one medical image as the outlier image comprises:
determining an error value associated with the at least one feature of the at least one medical image;
comparing the error value against a threshold value to determine when the at least one medical image is an outlier; and
displaying a result indicating the at least one medical image is an outlier.
6. The method of claim 1 , wherein the classification of the at least one medical image is performed using a probabilistic classifier and a non-probabilistic classifier.
7. The method of claim 1 , wherein the detecting of the outlier image is performed using at least one statistical transformation algorithm.
8. The method of claim 1 , wherein the anatomy of the at least one medical image is detected based on at least one landmark detection algorithm.
9. A device for automatically detecting a medical imaging protocol, the device comprising:
a processor;
a memory coupled with the processor, wherein the memory comprises processor executable instructions configured to:
receive at least one medical image from an imaging device, wherein the imaging device is separate from the device;
determine an anatomy of a body part in the at least one medical image from a set of medical images;
extract at least one feature associated with the at least one medical image;
detect the at least one medical image as an outlier image based on the at least one feature that does not belong to a set of known image acquisition protocols;
automatically classify the outlier image into at least one image acquisition protocol based on the at least one feature; and
identify medical images acquired with the image acquisition protocol at different time instances from a medical image database.
10. The device of claim 9 , further comprising:
a display unit,
wherein the processor executable instructions are further configured to:
display the image acquisition protocol of the set of medical images on the display unit; and
provide a comparative view of the identified medical images acquired with the image acquisition protocol on a display unit for analysis.
11. The device of claim 9 , wherein the processor executable instructions further comprise instructions configured to:
assign the identified medical images with an acquisition protocol label, wherein the acquisition protocol label is assigned based on the classification of the identified medical images.
12. The device of claim 9 , wherein the processor executable instructions configured for detecting the outlier image comprise instructions configured to:
determine an error value in a reconstruction feature space of a medical image of the identified medical images; and
label the medical image as an outlier based on the error value as compared with a threshold value.
13. The device of claim 9 , wherein the device is configured to receive magnetic resonance images from the imaging device.
14. The device of claim 9 , wherein the processor executable instructions are configured to use at least one of a probabilistic and a non-probabilistic classifier to classify the identified medical images.
15. The device of claim 12 , wherein the processor executable instructions are configured to use at least one statistical transformation algorithm to detect the outlier image.
16. The device of claim 9 , wherein the anatomy of the at least one medical image is detected based on landmark detection algorithms.