Granted Patent B2

US 12,394,511 · App. 16/686,571 · Granted Aug 19, 2025

Inventors: Tatsuo Kawanaka (Tokyo, JP); Keiji Sugihara (Cary, NC)

Assignee: FUJIFILM HEALTHCARE AMERICAS CORPORATION

G16H30/20G16H10/60G16H50/20

Abstract

Claims (59)

1. A method for remote analysis of one or more medical image records, comprising:

receiving, at a workstation of a first user, a first medical image record having a first amount of data;

comparing, at the workstation of the first user, the first medical image record with each standard image of a standard image set to identify a similarity between the first medical image record and each of the standard images, wherein the standard image set comprises at least two standard images of an anatomical feature, each standard image comprising a generic image of the anatomical feature generated by a machine learning algorithm from a review of at least 1000 images of the anatomical feature including normal and abnormal images of the anatomical feature, each standard image associated with a respective index number;

calculating, if at least one respective similarity is above a threshold and at the workstation of the first user, a delta between the first medical image record and at least one of the standard images with the similarity above the threshold by comparing the first medical image record and the at least one standard with the similarity above the threshold, the delta having a second amount of data, the second amount of data being less than the first amount of data;

transferring the delta from the workstation of the first user and to one or more computing devices having a copy of the standard image set;

transferring a plurality of index numbers from the workstation of the first user and to the one or more computing device, wherein each of the plurality of index numbers is associated with a respective standard image;

combining, by the one or more computing devices, the delta and the at least one standard image with similarity above the threshold;

reconstructing, by the one or more computing devices, the first medical image record using the combination of the delta and the at least one standard image with similarity above the threshold to form a first reconstructed medical image record, the first reconstructed medical image record being identical to the first medical image record; and

analyzing, by the one or more computing devices, the first reconstructed medical image record.

2. The method of claim 1 , wherein the first medical image record comprises one or more Digital Imaging and Communications in Medicine (“DICOM”) Service-Object Pair (“SOP”) Instances.

3. The method of claim 1 , further comprising providing an alert to the user if the similarity is below a threshold.

4. The method of claim 1 , wherein comparing the first medical image record with each standard image comprises determining that the first medical image record and the standard image set each correspond with a similar anatomical feature.

5. The method of claim 1 , wherein analyzing the first reconstructed medical image record comprises determining a medical diagnosis.

6. The method of claim 5 , further comprising sending an alert to the workstation of the first user if the medical diagnosis is abnormal.

7. The method of claim 1 , wherein analyzing the first reconstructed medical image record comprises using an artificial intelligence (“AI”) engine stored on the one or more computing devices.

8. The method of claim 1 , further comprises sending, from the one or more computing devices and to the workstation of the first user, the analysis of the first medical image record.

9. One or more computer-readable non-transitory storage media embodying software that is operable when executed to:

receive, at a workstation of a first user, a first medical image record having a first amount of data;

compare, at the workstation of the first user, the first medical image record with each standard image of a standard image set to identify a similarity between the first medical image record and each of the standard images, wherein the standard image set comprises at least two standard images of an anatomical feature, each standard image comprising a generic image of the anatomical feature generated by a machine learning algorithm from a review of at least 1000 images of the anatomical feature including normal and abnormal images of the anatomical feature, each standard image associated with a respective index number;

identify, if at least one respective similarity is above a threshold and at the workstation of the first user, a delta between the first medical image record and at least one of the standard images with the similarity above the threshold by comparing the first medical image record and the at least one standard image with the similarity above the threshold, the delta having a second amount of data, the second amount of data being less than the first amount of data;

transfer the delta from the workstation of the first user and to one or more computing devices having a copy of the standard image set;

transfer a plurality of index numbers from the workstation of the first user and to the one or more computing device, wherein each of the plurality of index numbers is associated with a respective standard image;

combine, by the one or more computing devices, the delta and the first at least one standard image with similarity above the threshold;

reconstruct, by the one or more computing devices, the first medical image record using the combination of the delta and the at least one standard image with similarity above the threshold to form a first reconstructed medical image record, the first reconstructed medical image record being identical to the first medical image record; and

analyze, by the one or more computing devices, the first reconstructed medical image record.

10. The media of claim 9 , wherein the first medical image record comprises one or more Digital Imaging and Communications in Medicine (“DICOM”) Service-Object Pair (“SOP”) instances.

11. The media of claim 9 , wherein the software is further operable to provide an alert to the user if the similarity is below a threshold.

12. The media of claim 9 , wherein comparing the first medical image record with each standard image comprises determining that the first medical image record and the standard image set each correspond with a similar anatomical feature.

13. The media of claim 9 , wherein analyzing the first reconstructed medical image record comprises determining a medical diagnosis.

14. The media of claim 13 , further comprising sending an alert to the workstation of the first user if the medical diagnosis is abnormal.

15. The media of claim 9 , wherein analyzing the first reconstructed medical image record comprises using an artificial intelligence (“AI”) engine stored on the one or more computing devices.

16. The media of claim 9 , further comprises sending, from the one or more computing devices and to the workstation of the first user, the analysis of the first medical image record.

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, at a workstation of a first user, a first medical image record having a first amount of data;

compare, at the workstation of the first user, the first medical image record with each standard image of a standard image set to identify a similarity between the first medical image record and each of the standard images, wherein the standard image set comprises at least two standard images of an anatomical feature, each standard image comprising a generic image of the anatomical feature generated by a machine learning algorithm from a review of at least 1000 images of the anatomical feature including normal and abnormal images of the anatomical feature, each standard image associated with a respective index number;

identify, if at least one respective similarity is above a threshold and at the workstation of the first user, a delta between the first medical image record and at least one of the standard images with the similarity above the threshold by comparing the first medical image record and the at least one standard image with the similarity above the threshold, the delta having a second amount of data, the second amount of data being less than the first amount of data;

transfer the delta from the workstation of the first user and to one or more computing devices having a copy of the standard image set;

transfer a plurality index numbers from the workstation of the first user and to the one or more computing device, wherein each of the plurality of index numbers is associated with a respective standard image;

combine, by the one or more computing devices, the delta and the at least one standard image with similarity above the threshold;

reconstruct, by the one or more computing devices, the first medical image record using the combination of the delta and the at least one standard image with similarity above the threshold to form a first reconstructed medical image record, the first reconstructed medical image record being identical to the first medical image record; and

analyze, by the one or more computing devices, the first reconstructed medical image record.

18. A system for remote analysis of one or more medical image records, comprising:

a workstation including

a processor, including a pre-processing AI engine for processing a first medical image record, and

a memory storing a first copy of a standard image set, wherein the standard image set comprises at least two standard images of an anatomical feature, each standard image comprising a generic image of the anatomical feature generated by a machine learning algorithm from a review of at least 1000 images of the anatomical feature including normal and abnormal images of the anatomical feature, each standard image associated with a respective index number; and

one or more computing devices operationally coupled to the workstation, the one or more computing devices including

an AI engine, and

an AI engine storage storing a second copy of the standard image set; wherein the system is configured to

compare, at the workstation, a first medical image record with each standard image of the first copy of the standard image set to identify a similarity between the first medical image record and each of the standard images, wherein the first medical image record has a first amount of data;

calculate, if the similarity is above a threshold and at the workstation, a delta between the first medical image record and the first standard image by comparing the first medical image record and the first standard image, the delta having a second amount of data, the second amount of data being less than the first amount of data;

transfer the delta from the workstation and to the one or more computing devices;

transfer a plurality of index numbers from the workstation and to the one or more computing devices, wherein each of the plurality of index numbers is associated with a respective standard image;

combine, by the one or more computing devices, the delta and the at least one standard image with similarity above the threshold;

reconstruct, by the one or more computing devices, the first medical image record using the combination of the delta and the at least one standard image with similarity above the threshold to form a first reconstructed medical image record, the first reconstructed medical image record being identical to the first medical image record.

19. The system of claim 18 , wherein the workstation further comprises a transceiver for sending a delta to the server.

20. The system of claim 19 , wherein the delta is calculated by the pre-processing AI engine.

21. The system of claim 18 , wherein the workstation further comprises a graphical user interface.

22. The system of claim 18 , wherein the one or more computing devices further comprise a server processor.

23. The system of claim 18 , further comprising an imaging modality operationally coupled to the workstation to send the first medical image record from the imaging modality to the workstation.

Assignments (2)

Continuity (1)

References Cited (39)