Imaging and reporting combination in medical imaging
Since the final output for medical imaging is the radiology report, the quality of which is largely dependent on the radiologist, there is a need for a comprehensive system for both medical imaging and reporting. Imaging and radiology reporting are combined. Image acquisition, reading of the images, and reporting are linked, allowing feedback of readings to control acquisition so that the final reporting is more comprehensive. Clinical findings typically associated with reporting may be used automatically to feedback for further or continuing acquisition without requiring a radiologist. A clinical identification may be used to determine what image processing to perform for reading, and/or raw (i.e., non-reconstructed) scan data from the imaging system are provided for integrated image processing with report generation.
1. A method for imaging and generating a radiology report in a medical system, the method comprising:
scanning, by a medical imaging scanner, a patient;
receiving, by an image processor, a clinical identification of a reason for the scanning for the patient and first scan data from the scanning, the image processor being in a different building than the medical imaging scanner;
selecting image processing for the first scan data from the scanning, the image processing selected based on the clinical identification, wherein the image processing comprises operating on the first scan data after the scanning and wherein the selecting is performed after the scanning to acquire the first scan data;
image processing, by the image processor, the first scan data from the scanning using the selected image processing, the image processing relating the first scan data to scan settings from a clinical finding for pathology generated by the image processing;
feeding back the scan settings to the medical imaging scanner based on the imaging processing, wherein the scan settings are to be used by the medical imaging scanner;
rescanning, by the medical imaging scanner as configured by the scan settings, the patient, the rescanning by the medical imaging scanner different than the scanning due to the configuration by the scan settings;
generating, by a machine-learned network implemented by the image processor, the radiology report in response to the first scan data, the feedback information, and/or second scan data from the rescanning, the radiology report having narrative text characterizing the patient; and
outputting the radiology report.
2. The method of claim 1 wherein generating comprises generating with a deep machine-learned text generator as the machine-learned network, and wherein the image processor and the deep machine-learned text generator are in the different building than the medical imaging scanner, wherein the image processor receives the first scan data and clinical identification from the medical imaging scanner, and wherein the image processor performs the selecting.
3. The method of claim 2 wherein scanning comprises scanning with a computed tomography system, a magnetic resonance system, or a nuclear medicine system, and wherein image processing the first scan data comprises receiving the first scan data as projection data, k-space data, or lines of response data and reconstructing to an object space based on the clinical identification.
4. The method of claim 1 wherein image processing comprises filtering, denoising, detecting, classifying, and/or segmenting from the first scan data.
5. The method of claim 1 wherein image processing comprises determining the clinical finding, wherein feeding back the information comprises feeding back the scan settings for the medical imaging scanner, and wherein rescanning comprises rescanning with the scan settings based on the clinical finding.
6. The method of claim 1 wherein generating comprises generating by a machine-learned natural language network.
7. The method of claim 1 wherein image processing comprises determining the clinical finding with a machine-learned network, and wherein generating the clinical report comprises generating the clinical report with the clinical finding and another clinical finding from image processing of the second scan data from the rescanning.
8. The method of claim 1 wherein image processing comprises checking the second data for quality, and wherein feeding back the information comprises feeding back a request to perform the rescanning based on the check of the quality.
9. The method of claim 1 wherein receiving the clinical identification comprises receiving a symptom, and wherein selecting comprises selecting based on the symptom.
10. The method of claim 1 wherein generating the radiology report comprises generating the narrative text including a pathology, severity of the pathology, and location of the pathology.
11. The method of claim 1 wherein outputting comprises outputting to an electronic medical records database, a referring physician, and/or the patient.
12. A system for imaging and generating a radiology report, the system comprising:
a medical imager configured to scan a patient, the configuration being for a clinical application;
a processor configured to receive scan data from the medical imager, then select image processing for the previously received scan data, then apply the image processing to the scan data, then determine a clinical finding from the image processing, the clinical finding being a medical opinion for a type of pathology or disease, then control the medical imager with scan settings based on the clinical finding, the scan settings determined from a relation of the clinical finding to the scan settings, and then generate the radiology report from the clinical finding with a machine-learned network, the processor in a different building than the medical imager; and
an interface configured to output the radiology report.
13. The system of claim 12 wherein the processor is a server at a different facility than the medical imager.
14. The system of claim 12 wherein the processor is configured to apply the image processing as reconstruction, quality assurance of the scan, filtering, denoising, detection, segmentation, classification, quantification, and/or prediction.
15. The system of claim 12 wherein the medical imager is configured to output a clinical identification tag for the clinical application, and wherein the processor is configured to apply the image processing selected based on the clinical identification tag.
16. The system of claim 12 wherein the medical imager is configured to provide the scan data from the scan without reconstruction, and wherein the processor is configured to reconstruct as part of the application of the image processing.
17. The system of claim 12 wherein the interface comprises a computer network interface for output to a medical records database.
18. A method for imaging and generating a radiology report in a medical system, the method comprising:
receiving first and second scan data from first and second medical scanners, the first and second scan data representing first and second patients and being without reconstruction into a three-dimensional object space, the receiving being at a server or workstation in a different location than the first and second medical scanners;
obtaining first and second clinical indication tags for the first and second scan data, the first and second clinical indication tags being first and second, different reasons for scanning of the first and second patients, respectively, to have been performed; then
image processing, including reconstruction, of the first and second scan data by the server or workstation in the different location than the first and second medical scanners, the image processing including the reconstruction of the first scan data different than the reconstruction of the second scan data based on the first and second clinical indication tags for the previously performed scans to acquire the first and second scan data being different, the image processing determining first and second clinical findings for pathologies of the first and second patients, respectively, from the reconstructions of the first and second scan data;
generating first and second radiology reports from information provided by the image processing, the first and second radiology reports including the first and second clinical findings, respectively; and
outputting the first and second radiology reports.
19. The method of claim 18 wherein generating comprises generating without display of any images from the first and second scan data to a human after receiving and through the image processing and the generating.