Systems and methods for storing compressed images
Method for storing a compressed digital image includes performing an artificial intelligence (“AI”) diagnostic test on the digital image; determining an uncompressed diagnostic result associated with the digital image based on the AI diagnostic test; generating one or more compressed digital images by compressing the digital image, each compressed digital image having a respective compression ratio; decompressing each compressed digital image to generate a respective decompressed digital image; performing the diagnostic test on each decompressed digital image; determining a decompressed diagnostic result associated with each decompressed digital image based on the respective diagnostic test; identifying one or more decompressed digital images having a respective decompressed diagnostic result that is the same as the uncompressed diagnostic result; selecting from the identified one or more decompressed digital images, the decompressed digital image associated with the highest compression ratio; and storing the compressed digital image associated with the selected decompressed digital image.
1. A method of storing a compressed digital image, comprising:
receiving, at one or more computing devices, a digital image;
performing, at the one or more computing devices, an artificial intelligence (“AI”) diagnostic test on the digital image;
determining, at the one or more computing devices, an uncompressed diagnostic result associated with the digital image based on the AI diagnostic test;
generating, at the one or more computing devices, one or more compressed digital images by compressing the digital image, each compressed digital image having a respective compression ratio;
decompressing, at the one or more computing devices, each compressed digital image to generate a respective decompressed digital image;
performing, at the one or more computing devices, the AI diagnostic test on each decompressed digital image;
determining, at the one or more computing devices, a decompressed diagnostic result associated with each decompressed digital image based on the respective AI diagnostic test;
identifying, at the one or more computing devices, one or more decompressed digital images having a respective decompressed diagnostic result that is the same as the uncompressed diagnostic result;
selecting, at the one or more computing devices and from the identified one or more decompressed digital images, the decompressed digital image associated with the highest compression ratio; and
storing, at the one or more computing devices, the compressed digital image associated with the selected decompressed digital image.
2. The method of claim 1 , wherein the digital record comprises a medical image record.
3. The method of claim 2 , wherein the medical image record comprises a Digital Imaging and Communications in Medicine (“DICOM”) Service-Object Pair Instance.
4. The method of claim 1 , wherein each compressed digital image is generated using a respective loss-less or lossy compression technique.
5. The method of claim 1 , wherein for each compressed digital image, the compression ratio is calculated by dividing an uncompressed file size of the uncompressed image by a compressed file size of the compressed digital image.
6. The method of claim 1 , further comprising deleting the digital image.
7. The method of claim 1 , further comprising deleting the selected decompressed digital image.
8. The method of claim 1 , further comprising deleting each non-selected decompressed digital image and each associated compressed digital image.
9. One or more computer readable non-transitory storage media embodying software that is operable when executed to:
receive a digital image;
perform an artificial intelligence (“AI”) diagnostic test on the digital image;
determine an uncompressed diagnostic result associated with the digital image based on the AI diagnostic test;
generate one or more compressed digital images by compressing the digital image, each compressed digital image having a respective compression ratio;
decompress each compressed digital image to generate a respective decompressed digital image;
perform the AI diagnostic test on each decompressed digital image;
determine a decompressed diagnostic result associated with each decompressed digital image based on the respective AI diagnostic test;
identify one or more decompressed digital images having a respective decompressed diagnostic result that is the same as the uncompressed diagnostic result;
select from the identified one or more decompressed digital images, the decompressed digital image associated with the highest compression ratio; and
store the compressed digital image associated with the selected decompressed digital image.
10. The media of claim 9 , wherein the digital record comprises a medical image record.
11. The media of claim 10 , wherein the medical image record comprises a Digital Imaging and Communications in Medicine (“DICOM”) Service-Object Pair Instance.
12. The media of claim 9 , wherein each compressed digital image is generated using a respective loss-less or lossy compression technique.
13. The media of claim 9 , wherein for each compressed digital image, the compression ratio is calculated by dividing an uncompressed file size of the uncompressed image by a compressed file size of the compressed digital image.
14. The media of claim 9 , further comprising deleting the digital image.
15. The media of claim 9 , further comprising deleting the selected decompressed digital image.
16. The media of claim 9 , further comprising deleting each non-selected decompressed digital image and each associated compressed digital image.
17. A system comprising: one or more processors; and a memory coupled to the processors comprising instructions executable by the processors, the processors being operable when executing the instructions to:
receive a digital image;
perform an artificial intelligence (“AI”) diagnostic test on the digital image;
determine an uncompressed diagnostic result associated with the digital image based on the AI diagnostic test;
generate one or more compressed digital images by compressing the digital image, each compressed digital image having a respective compression ratio;
decompress each compressed digital image to generate a respective decompressed digital image;
perform the AI diagnostic test on each decompressed digital image;
determine a decompressed diagnostic result associated with each decompressed digital image based on the respective AI diagnostic test;
identify one or more decompressed digital images having a respective decompressed diagnostic result that is the same as the uncompressed diagnostic result;
select from the identified one or more decompressed digital images, the decompressed digital image associated with the highest compression ratio; and
store the compressed digital image associated with the selected decompressed digital image.
18. The system of claim 17 , wherein the digital record comprises a medical image record.
19. The system of claim 18 , wherein the medical image record comprises a Digital Imaging and Communications in Medicine (“DICOM”) Service-Object Pair Instance.
20. The system of claim 17 , wherein each compressed digital image is generated using a respective loss-less or lossy compression technique.
21. The system of claim 17 , wherein for each compressed digital image, the compression ratio is calculated by dividing an uncompressed file size of the uncompressed image by a compressed file size of the compressed digital image.
22. The system of claim 17 , further comprising deleting the digital image.
23. The system of claim 17 , further comprising deleting the selected decompressed digital image.
24. The system of claim 17 , further comprising deleting each non-selected decompressed digital image and each associated compressed digital image.