Dose optimization based on outcome quality

• US 10,289,953 B2
• Filed: 12/07/2012
• Issued: 05/14/2019
• Est. Priority Date: 12/13/2011
• Status: Active Grant

• Current Assignee: Koninklijke Philips N.V.
• Original Assignee: Koninklijke Philips N.V.
• Inventors: Lee, Michael Chun-chieh, Cohen-Solal, Eric
• Primary Examiner(s): Smith, Paulinho E
• Application Number:
  US14/365,267
• Publication Number:
  US 20140304206A1
• Time in Patent Office: 2,349 Days
• Field of Search: None
• CPC Class Codes: A61B 6/032 Transmission computed tomography [CT]
• CPC Class Codes: A61B 6/542 involving control of exposure
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G16H 15/00 ICT specially adapted for medical reports, e.g. generation or transmission thereof
• CPC Class Codes: G16H 30/20 for handling medical images, e.g. DICOM, HL7 or PACS
• CPC Class Codes: G16H 40/40 for the management of medical equipment or devices, e.g. scheduling maintenance or upgrades

Abstract

A system includes a modeler that generates a model which models a quality of findings in radiologist reports as a function of deposited dose of scans from which the radiologist reports are created and a dose optimizer that determines an optimal dose value for a planned scan based on the model and one or more optimization rules. A method includes generating a model which models a quality of findings in radiologist reports as a function of deposited dose of scans from which the radiologist reports are created and determining an optimal dose value tar a planned scan based on the model and one or more optimization rules.

Claims

1. An imaging system, comprising:

a data acquisition system;

a console, including;

a memory storing a mathematical model; and

a processor configured to;

extract radiology reports and ionizing radiation dose measurements from stored patient studies;

generate, with the mathematical model, a model which models a quality of findings in the radiology reports as a function of deposited dose of scans from the ionizing radiation dose measurements, wherein the quality of findings corresponds to a positive finding rate; and

determine an optimal radiation dose value based on the model and one or more optimization rules;

estimate a radiation dose value for a planned scan; and

control the data acquisition system to acquire projection data indicative of an examination region based on the planned scan in response to the estimated radiation dose value for the planned scan not exceeding the determined optimal radiation dose value, and

an image reconstruction system configured to reconstruct the projection data to generate volumetric image data of the examination region.

2. The system of claim 1, wherein the processor models the quality of findings graphically in a regression curve.

3. The system of claim 1, wherein the one or more optimization rules defines the optimal dose value as a predetermined percentage between a maximum quality and a minimum quality.

4. The system of claim 2, wherein the processor models the quality of findings as:

y=A/(1+exp(−

(dose−

B)/C)+D, where y represents the quality, D represents a minimum value of the regression curve, A represents a maximum excursion from D, B represents a radiation dose at which y is at a half-maximal value, and C defines a steepness of a transition between the minimum and maximum values.

5. The system of claim 1, wherein the processor individually evaluates groups of related imaging studies and generates the model for a group of the groups based on a result of an evaluation of that group.

6. The system of claim 5, wherein the evaluation is based on a sub-set of sections of the radiology reports.

7. The system of claim 5, wherein the evaluation of the group is normalized across interpreting radiologist.

8. The system of claim 5, wherein the evaluation is specific to a style of a particular interpreting radiologist.

9. The system of claim 5, wherein the evaluation determines at least one of a presence, an absence, or a frequency of one or more of:

a count of terms of uncertainty;

a statistical measures of uncertainty based on sentiment analysis;

a presence of positive findings;

a presence of negative findings;

a presence of comparison findings with prior report, a presence of recommended actions;

a strength of the recommendation;

an average number of distinct medical concepts, or other metric.

10. The system of claim 5, wherein the processor groups imaging related data extracted from a data repository into one or more groups and individually evaluates one or more of the groups.

11. The system of claim 10, wherein the processor groups the imaging related data based on one or more of imaging protocol, anatomy scanned, clinical indication, demographics, or interpreting radiologist.

12. The system of claim 1, wherein processor validates scan settings, of the planned scan, related to dose based on the optimal dose value.

13. The system of claim 12, wherein the processor compares the estimated radiation dose value of the planned scan and the optimal radiation dose value and displays a warning signal in response to the estimated dose value exceeding the optimal dose value.

14. The system of claim 12, wherein at least one of the estimated radiation dose value, the optimal radiation dose value or an accumulated dose value of the patient is visually presented via a monitor.

15. A method, comprising:

extracting, with a processor, radiology reports and ionizing radiation dose measurements from stored patient studies;

generating, with the processor, a model which models a quality of findings in radiologist reports as a function of deposited dose of scans from which the radiologist reports are created using the extracted radiology reports and ionizing radiation dose measurements;

determining, with the processor, an optimal radiation dose value based on the model, a group assignment for the planned scan, and one or more optimization rules, wherein the optimal radiation dose value corresponds to a radiation dose value of a scan at which a likelihood of improving a positive finding rate by increasing the radiation dose delivered is less than a predetermined threshold;

estimating, with the processor, a radiation dose value for a planned scan;

controlling, with the processor, data acquisition of an imaging system to acquire projection data indicative of an examination region based on the planned scan in response to the estimated radiation dose value for the planned scan not exceeding the optimal radiation dose value; and

reconstructing, with the processor, the projection data to generate volumetric image data of the examination region.

16. The method of claim 15, further comprising:

extracting imaging related data from a data repository into one or more groups, wherein the imaging related data includes image data and one or more of an imaging protocol, dose related imaging parameters, dose measurements, clinical indications, an identification of an interpreting radiologist, a radiologist report, patient demographics, an identification of the scanned anatomy corresponding to the image data;

grouping the extracted imaging related data into a plurality of groups, wherein the extracted imaging related data is grouped based on one or more of imaging protocol, anatomy scanned, clinical indication, demographics, or interpreting radiologist; and

evaluating, individually, one or more of the groups of related imaging studies, wherein the evaluation determines at least one of a presence, an absence, or a frequency of one or more of;

a count of terms of uncertainty;

a statistical measures of uncertainty based on sentiment analysis;

a presence of positive findings;

a presence of negative findings;

a presence of comparison findings with prior report;

a presence of recommended actions;

a strength of the recommendation;

an average number of distinct medical concepts, or other metric.

17. The method of claim 16, further comprising:

assigning the planned scan to a predetermined group of scans;

identifying and obtaining the optimal dose value for the predetermined group of scans;

comparing an estimated dose value of the planned scan and the obtained optimal dose value; and

generating a warning signal in response to the estimated dose value exceeding the optimal dose value.

18. The method of claim 15, wherein generating the model includes computing y=A/(1+exp(−

(dose−

B)/C)+D, where y represents the quality, D represents a minimum value of a regression function, A represents a maximum excursion from D, B represents a radiation dose at which y is at a half-maximal value, and C defines a steepness of a transition between the minimum and maximum values.

19. A system, comprising:

an imaging system configured to scan a patient based on predetermined scan parameters of a planned scan of a patient, wherein the predetermined scan parameters include at least one scan parameter that affects a dose delivered to the patient when the patient is scanned;

a console with a processor configured to;

determine a quality of findings in radiologist reports as a mathematical function of deposited dose of scans from which the radiologist reports are created, wherein the quality of findings corresponds to a positive finding rate;

determine an optimal dose value for a scan of the patient based on a relationship between the quality of findings and measured deposited dose of previously performed scans of patients;

generating a signal indicating whether the estimated dose value exceeds the optimal dose value; and

in response to the estimated dose value not exceeding the optimal dose value, control the imaging system to perform the scan based on the predetermined scan parameters to generate volumetric image data of the patient.

20. The system of claim 19, wherein the quality of findings is computed through:

y=A/(1+exp(−

(dose−

B)/C)+D, where y represents the quality, D represents a minimum value of a regression function, A represents a maximum excursion from D, B represents a radiation dose at which y is at a half-maximal value, and C defines a steepness of a transition between the minimum and maximum values.