Systems, methods and devices for analyzing quantitative information obtained from radiological images

Patent metadata

Field	Value
Publication number	US-9721340-B2
Application number	US-201414912150-A
Country	US
Kind code	B2
Filing date	Aug 13, 2014
Priority date	Aug 13, 2013
Publication date	Aug 1, 2017
Grant date	Aug 1, 2017

Abstract

An example method for analyzing quantitative information obtained from radiological images includes identifying a ROI or a VOI in a radiological image, segmenting the ROI or the VOI from the radiological image and extracting quantitative features that describe the ROI or the VOI. The method also includes creating a radiological image record including the quantitative features, imaging parameters of the radiological image and clinical parameters and storing the radiological image record in a data structure containing a plurality of radiological image records. In addition, the method includes receiving a request with the patient's radiological image or information related thereto, analyzing the data structure to determine a statistical relationship between the request and the radiological image records and generating a patient report with a diagnosis, a prognosis or a recommended treatment regimen for the patient's disease based on a result of analyzing the data structure.

First claim

What is claimed:

1. A method for analyzing quantitative information obtained from radiological images, comprising:
identifying a region of interest (ROI) or a volume of interest (VOI) in a radiological image;
segmenting the ROI or the VOI from the radiological image;
extracting a plurality of quantitative features that describe the ROI or the VOI from the radiological image;
creating a radiological image record comprising the quantitative features describing the ROI or the VOI from the radiological image, one or more imaging parameters related to the radiological image and one or more clinical parameters;
storing the radiological image record in a data structure comprising a plurality of radiological image records;
receiving a request related to a patient's radiological image, the request comprising the patient's radiological image or information related to the patient's radiological image;
analyzing the data structure to determine a statistical relationship between the request and the plurality of radiological image records;
generating a patient report comprising at least one of a diagnosis, a prognosis or a recommended treatment regimen for the patient's disease based on a result of analyzing the data structure; and
transmitting the patient report in response to the request, wherein the patient report further comprises one or more of a probability for at least one of the diagnosis, the prognosis, the recommended treatment regimen for the patient's disease, or a reliability coefficient associated with the probability for at least one of the diagnosis, the prognosis or the recommended treatment regimen for the patient's disease.

2. The method of claim 1 , wherein the quantitative features that describe the ROI or the VOI in the radiological image includes one or more of a shape-based feature, a texture-based feature, a habitat feature, an intensity feature or a position-based feature.

3. The method of claim 1 , wherein the one or more imaging parameters related to the radiological image comprise at least one of a resolution parameter, a reconstruction parameter and an acquisition parameter and the one or more imaging parameters related to the radiological image are included in a DICOM header of the radiological image.

4. The method of claim 1 , wherein the clinical parameters comprise at least one of a disease type, a disease stage, a treatment history or a clinical outcome.

5. The method of claim 4 , wherein the treatment history comprises a treatment regimen, wherein the treatment regimen is at least one of a prescribed drug, a clinical trial or a medical procedure or wherein the treatment history further comprises information about the prescribed drug including at least one of a name, a strength or a number of refills of the prescribed drug or wherein the treatment history further comprises information about a change in a disease and a treatment regimen prescribed in response to the change in the disease, wherein the change in the disease is a relapse of the disease or a healing of the disease.

6. The method of claim 4 , wherein the clinical outcome comprises at least one of a response to therapy, a time to progression, a progression-free survival, a disease-free survival or an overall survival, or wherein the clinical outcome comprises at least one of an objective assessment of response to therapy or a subjective assessment of response to therapy.

7. The method of claim 1 , wherein the radiological image record further comprises one or more of molecular, genetic, genomic, proteomic data, or demographic data.

8. The method of claim 1 , wherein analyzing the data structure to determine a statistical relationship between the request and the plurality of radiological image records comprises using a pattern recognition technique to identify patterns relevant to the patient's disease that are present in the data structure.

9. The method of claim 8 , wherein the pattern recognition technique is a distance matching algorithm.

10. The method of claim 1 , wherein the request related to the patient's radiological image comprises the patient'radiological image, the method further comprising:
identifying a ROI or a VOI in the patient's radiological image;
segmenting the ROI or the VOI from the patient's radiological image;
extracting a plurality of quantitative features that describe the ROI or the VOI from the patient's radiological image, wherein the information related to the patient's radiological image comprises the plurality of quantitative features that describe the ROI or the VOI from the patient's radiological image and one or more imaging parameters related to the patient's radiological image.

11. The method of claim 1 , wherein the request related to the patient's radiological image comprises the information related to the patient's radiological image, and wherein the information related to the patient's radiological image comprises one or more of a plurality of quantitative features that describe a ROI or a VOI in the patient's radiological image and one or more imaging parameters related to the patient's radiological image, or the patient's molecular, genetic, genomic or proteomic, tissue data or the patient's demographic data.

12. The method of claim 1 , wherein extracting a plurality of quantitative features that describe the ROI or the VOI in the radiological image further comprises extracting a plurality of quantitative features that describe an area at least partially surrounding the ROI or the VOI in the radiological image.

13. The method of claim 1 , wherein the ROI or the VOI in the radiological image is segmented from the radiological image using at least one of a region-growing algorithm, a level set algorithm, a graph cut algorithm, an active contour algorithm and a livewire algorithm.

14. The method of claim 1 , further comprising:
stripping confidential patient information from the radiological image; and
assigning the radiological image a de-identified number, wherein the radiological image record further comprises the de-identified number.

15. The method of claim 1 , wherein the radiological image is obtained by at least one of computed tomography (CT), magnetic resonance imaging (MRI) or positron emission tomography (PET).

16. A method for analyzing quantitative information obtained from radiological images, comprising:
identifying a ROI or a VOI in a patient's radiological image;
segmenting the ROI or the VOI from the patient's radiological image;
extracting a plurality of quantitative features that describe the ROI or the VOI from the patient's radiological image;
transmitting a request comprising the plurality of quantitative features that describe the ROI or the VOI from the patient's radiological image and one or more imaging parameters related to the patient's radiological image; and
receiving a patient report in response to the request, the patient report comprising at least one of a diagnosis, a prognosis or a recommended treatment regimen for the patient's disease, wherein the patient report is obtained by analyzing a data structure comprising a plurality of radiological image records to determine a statistical relationship between the request and the plurality of radiological image records, and wherein each of the plurality of radiological image records stored in the data structure comprises a plurality of quantitative features that describe a ROI or a VOI in each respective radiological image, one or more imaging parameters related to each respective radiological image and one or more clinical parameters.

17. The method of claim 16 ,

Assignees

• H Lee Moffitt Cancer Ct & Res
• Univ Leland Stanford Junior
• Stichting Maastricht Radiation Oncology ‘Maastro Clinic’

Inventors

• Gillies Robert J
• Eschrich Steven A
• Gatenby Robert A
• Lambin Philippe
• Dekker Andreas L A J
• Napel Sandy A
• Plevritis Sylvia K
• Rubin Daniel L

Classifications

• A61B6/469

  for selecting a region of interest [ROI] · CPC title

• A61B6/463

  characterised by displaying multiple images or images and diagnostic data on one display · CPC title

• G16H50/30

  for calculating health indices; for individual health risk assessment · CPC title

• A61B6/5217

  extracting a diagnostic or physiological parameter from medical diagnostic data · CPC title

• G06T7/0012 Primary

  Biomedical image inspection · CPC title