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

Patent metadata

Field	Value
Publication number	US-10339653-B2
Application number	US-201715664530-A
Country	US
Kind code	B2
Filing date	Jul 31, 2017
Priority date	Aug 13, 2013
Publication date	Jul 2, 2019
Grant date	Jul 2, 2019

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:
extracting, by a computing device, one or more quantitative features that describe a region of interest (ROI) or a volume of interest (VOI) in a radiological image;
storing the one or more quantitative features describing the ROI or the VOI from the radiological image as a radiological image record in a data structure accessible by the computing device, said data structure comprising one or more radiological image records;
receiving, by the computing device, 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, by the computing device, the data structure to determine a statistical relationship between the request and the one or more radiological image records; and
generating, by the computing device, 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.

2. The method of claim 1 , further comprising transmitting, by the computing device, 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.

3. The method of claim 1 , wherein the radiological image record further comprises one or more imaging parameters related to the radiological image and one or more clinical parameters.

4. 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.

5. The method of claim 3 , 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.

6. The method of claim 3 , wherein the clinical parameters comprise at least one of a disease type, a disease stage, a treatment history or a clinical outcome.

7. The method of claim 6 , 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.

8. The method of claim 6 , 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.

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

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

11. The method of claim 10 , wherein the pattern recognition technique is a distance matching algorithm.

12. 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, by the computing device, a ROI or a VOI in the patient's radiological image;
segmenting the ROI or the VOI from the patient's radiological image; and
extracting, by the computing device, one or more 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 one or more 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.

13. 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.

14. The method of claim 1 , wherein extracting, by the computing device, the one or more quantitative features that describe the ROI or the VOI in the radiological image further comprises extracting one or more quantitative features that describe an area at least partially surrounding the ROI or the VOI in the radiological image.

15. The method of claim 1 , wherein the ROI or the VOI in the radiological image is segmented from the radiological image by the computing device 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.

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

17. 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).

18. A method for analyzing quantitative information obtained from radiological images, comprising:
extracting, by a computing device, one or more quantitative features that describe a region of interest (ROI) or a volume of interest (VOI) from a patient's radiological image;
transmitting, by the computing device, a request comprising the one or more quantitative features that describe the ROI or the VOI from the patient's radiological image; and
receiving, by the computing device, 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 one or more radiological image records to determine a statistical relationship between the request and the one or more radiological image records, and wherein each of the one or more radiological image records stored in the data structure com

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

• G06T7/0012 Primary

  Biomedical image inspection · CPC title

• A61B6/469

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

• G16H50/30

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

• G06T7/11

  Region-based segmentation · CPC title

• A61B6/032

  Transmission computed tomography [CT] · CPC title