Dynamic self-learning medical image method and system

1. A method for creating and using a dynamic self-learning medical image network system, the method comprising:

receiving, from a first node that displays one or more medical images to a user, initial user interaction data pertaining to one or more user interactions with the one or more initially obtained medical images;

training a deep learning algorithm based at least in part on the initial user interaction data received from the node, wherein the initial user interaction data received from the node is weighted based on a rate of diagnostic accuracy of the user; and

transmitting an instance of the trained deep learning algorithm to the first node and/or to one or more additional nodes, wherein at each respective node to which the instance of the trained deep learning algorithm is transmitted, the trained deep learning algorithm is applied to respective one or more subsequently obtained medical images in order to obtain a result.

2. The method of claim 1 , wherein the initial user interaction data comprises one or more of:

(a) an actual or estimated portion of at least one of the one or more medical images that was focused upon by at least one user;

(b) at least one annotation on at least one of the one or more initially obtained medical images;

(c) a selection of one of more pixels associated with at least one of the one or more initially obtained medical images;

(d) an actual or estimated amount of time one or more users spent viewing one or more of the initially obtained medical images; and

(e) a description of a patient condition and/or written or recorded audio diagnostic findings.

3. The method of claim 1 , wherein the deep learning algorithm generates data models for detecting recurring patterns in medical images based on the initial user interaction data.

4. The method of claim 1 , wherein the deep learning algorithm generates data models for detecting a localization in medical images based on the initial user interaction data.

5. The method of claim 4 , wherein the localization comprises pixel or voxel coordinates.

6. The method of claim 1 , wherein the deep learning algorithm generates a set of task flows.

7. The method of claim 6 , wherein the rate of diagnostic accuracy of the user is low, and, in response, the deep learning algorithm modifies the set of task flows to provide the user with additional information.

8. The method of claim 1 , wherein the instance of the deep learning algorithm records a medical history associated with a patient; and

presents the medical history associated with the patient to the user.

9. The method of claim 1 , further comprising receiving, from the first node and/or one or more additional nodes, subsequent user interaction data pertaining to one or more subsequently obtained medical images, wherein the subsequent user interaction data is used to modify the trained deep learning algorithm if it is determined that the subsequent user interaction data satisfies a predetermined threshold confidence level indicating that the trained deep learning algorithm should be modified.

10. The method of claim 9 , wherein the predetermined threshold level requires a predetermined number of users to corroborate a particular detail.

11. The method of claim 9 , wherein the predetermined threshold level is determined based on data pooled from a plurality of users.

12. The method of claim 9 , further comprising running one or more data-mining algorithms on the subsequent user interaction data to determine the complexity of the subsequent user interaction data.

13. The method of claim 12 , wherein the predetermined threshold level is a level of complexity of the subsequent user interaction data.

14. The method of claim 1 , wherein the instance of the trained deep learning algorithm is a partial instance.

15. A dynamic self-learning medical image network system, comprising: a plurality of nodes; and

a central brain server configured to receive initial user interaction data from one or more nodes of the plurality,

wherein the initial user interaction data pertains to one or more user interactions with one or more initially obtained medical images,

train a deep learning algorithm based at least in part on the initial user interaction data received from the node, wherein the initial user interaction data received from the node is weighted based on a rate of diagnostic accuracy of the user, and

transmit an instance of the trained deep learning algorithm to each node of the plurality,

wherein each node of the plurality is configured to apply the instance of the trained deep learning algorithm to one or more subsequently obtained medical images in order to obtain a result.

16. The system of claim 15 , wherein the initial user interaction data comprises one or more of:

(a) an actual or estimated portion of at least one of the one or more medical images that was focused upon by at least one user;

(b) at least one annotation on at least one of the one or more initially obtained medical images;

(c) a selection of one of more pixels associated with at least one of the one or more initially obtained medical images;

(d) an actual or estimated amount of time one or more users spent viewing one or more of the initially obtained medical images; and

(e) a description of a patient condition and/or written or recorded audio diagnostic findings.

17. The system of claim 15 , wherein at least one node of the plurality is a user interaction device.

18. The system of claim 15 , wherein at least one node of the plurality is not a user interaction device.

19. The system of claim 18 , wherein the at least one node is an intelligent workstation.

20. The system of claim 15 , further comprising a central brain network, wherein the central brain server is communicatively coupled to the central brain network.

21. The system of claim 20 , wherein the central brain server is one of a plurality of central brain servers.