Methods and Systems for Automatically Analyzing Clinical Images and Determining when Additional Imaging May Aid a Diagnosis
Methods and systems for automatically analyzing clinical images and determining when additional imaging may aid a diagnosis. One system includes at least one data source and a server. The server includes an electronic processor and an interface for communicating with the at least one data source. The electronic processor is configured to receive an image of a patient from the at least one data source over the interface. The electronic processor is also configured to automatically process the image to generate a diagnosis for the image. The electronic processor is also configured to automatically determine, based on the diagnosis, at least one additional image for supplementing the diagnosis. The electronic processor is also configured to automatically locate the at least one additional image for the patient and when the at least one additional image is available, automatically update the diagnosis based on the at least one additional image.
1 . A system for automatically analyzing clinical images and determining when additional imaging may aid a diagnosis, the system comprising:
at least one data source; and
a server including an electronic processor and an interface for communicating with the at least one data source, the electronic processor configured to
receive an image of a patient from the at least one data source over the interface;
automatically process the image to generate a diagnosis for the image;
automatically determine, based on the diagnosis, at least one additional image for supplementing the diagnosis;
automatically locate the at least one additional image for the patient; and
when the at least one additional image is available, automatically update the diagnosis based on the at least one additional image.
2 . The system of claim 1 , wherein the at least one additional image is generated before or after the image.
3 . The system of claim 1 , wherein the electronic processor is further configured to
receive training information from at least one data source, the training information including a plurality of images and graphical reporting associated with each of the plurality of images, each graphical reporting including a graphical marker designating a portion of one of the plurality of images and diagnostic information associated with the portion of the one of the plurality of images, and
perform machine learning to develop a model using the training information,
wherein the electronic processor is configured to process the image using the model to generate the diagnosis.
4 . The system of claim 1 , wherein the image was generated by a first imaging modality and wherein the at least one additional image was generated by a second imaging modality different than the first imaging modality.
5 . The system of claim 1 , wherein the image was generated using a first imaging parameter and wherein the at least one additional image was generated using a second imaging parameter different than the first imaging parameter.
6 . The system of claim 5 , wherein the first imaging parameter and the second imaging parameter includes at least one selected from a group consisting of a first indication of whether a contrast agent was used, a second indication of whether a radioactive isotope was used, a time after an agent or isotope was introduced, a magnetic resonance imaging (MRI) pulse sequence, and a computed tomography CT radiation level.
7 . The system of claim 1 , wherein the diagnosis includes a differential diagnosis.
8 . The system of claim 1 , wherein the image includes a first portion of the patient and the at least one additional image includes a second portion of the patient.
9 . The system of claim 1 , wherein the electronic processor is configured to automatically determine whether the at least one additional image is available for the patient by accessing at least one selected from a group consisting of a picture archiving and communications system (PACS), a vendor neutral archive, a radiology information system (RIS), an electronic medical record (EMR), a hospital information system (HIS), an image study ordering system, or a computer assisted detection (CAD) system.
10 . The system of claim 1 , wherein the electronic processor is configured to automatically determine whether the at least one additional image is available for the patient by prompting a user for the at least one additional image.
11 . The system of claim 1 , wherein the electronic processor is further configured to, when the at least one additional image is not available, take at least one automatic action to obtain the at least one additional image.
12 . The system of claim 11 , wherein the at least one automatic action includes generating and transmitting an electronic notification notifying a user of the at least one additional image.
13 . The system of claim 11 , wherein the at least one automatic action includes automatically placing an order for the at least one additional image.
14 . The system of claim 11 , wherein the electronic processor is further configured to monitor when the at least one additional image is available.