Method and system for cross-modality case-based computer-aided diagnosis

Patent metadata

Field	Value
Publication number	US-10318709-B2
Application number	US-74760208-A
Country	US
Kind code	B2
Filing date	Dec 9, 2008
Priority date	Dec 21, 2007
Publication date	Jun 11, 2019
Grant date	Jun 11, 2019

Abstract

A system and method for cross-modality case-based computer-aided diagnosis comprises storing a plurality of cases, each case including at least one image of one of a plurality of modalities and non-image information, mapping a feature relationship between a feature from images of a first modality to a feature from images of a second modality, and storing the relationship.

First claim

What is claimed is:

1. A method, comprising:
storing, on a non-transitory computer readable storage medium, a plurality of cases, each case including at least one image of one of a plurality of modalities and non-image information;
identifying, by a processor, at least one of the plurality of cases that contains images of a volume of interest across at least two different modalities;
extracting, by the processor, image-based features of the volume of interest from each image;
mapping, by the processor, a relationship between the features of the volume of interest across the different modalities to infer trends of features across different modalities;
storing the feature relationship on the non-transitory computer readable storage medium;
searching, by the processor, the non-transitory computer readable storage medium, wherein the searching comprises comparing a feature from an image of a current case to a corresponding feature in the at least one image of each of the plurality of stored cases based on the feature relationship, wherein the searching of images is across the multiple different modalities; and
retrieving, by the processor, at least one case within a predetermined threshold of similarity to the current case from the non-transitory computer readable storage medium.

2. The method of claim 1 , wherein the non-image information includes one of patient identifying information, demographic information, patient clinical information, and family history.

3. The method of claim 1 , wherein the mapping of the feature relationship is based on one of a factor analysis and a multivariate regression analysis.

4. The method of claim 1 , further comprising:
simultaneously displaying the original image and the retrieved case.

5. The method of claim 1 , further comprising:
calculating a distance between the extracted feature of the original image and a corresponding feature from the plurality of cases.

6. The method of claim 1 , wherein the plurality of modalities are a film mammogram, an ultrasound, a CT scan, an MRI scan, a PET scan, an X-ray and a digital mammogram.

7. The method of claim 1 , wherein the features of the volume of interest are a spiculation, a density feature, a texture feature, an average gray value, a shape feature, and a surface feature of a lesion.

8. A system, comprising:
a memory storing a plurality of cases, each case including at least one image of one of a plurality of modalities and non-image information; and
a processor identifying at least one of the plurality of cases that contains images of a volume of interest across at least two different modalities; extracting image-based features of the volume of interest from each image; mapping a relationship between the features of the volume of interest across the different modalities to infer trends of features across different modalities; searching the non-transitory computer readable storage medium, wherein the searching comprises comparing a feature from an image of a current case to a corresponding feature in the at least one image of each of the plurality of stored cases based on the feature relationship, wherein the searching of images is across the multiple different modalities; and retrieving at least one case within a predetermined threshold of similarity to the current case from the non-transitory computer readable storage medium.

9. The system of claim 8 , wherein the processor maps the feature of the first modality to the feature of the second modality using one of factor analysis and multivariate regression analysis.

10. The system of claim 8 , wherein the processor retrieves the at least one case based on calculating a distance between the extracted feature and a corresponding feature of the plurality of cases.

11. The system of claim 8 , wherein the processor simultaneously displays the original image and the retrieved case.

12. The system of claim 8 , wherein the plurality of modalities are a film mammogram, an ultrasound, a CT scan, an MRI scan, a PET scan, an X-ray and a digital mammogram.

13. The system of claim 8 , wherein the features of the volume of interest are a spiculation, a density feature, a texture feature, an average gray value, a shape feature, and a surface feature of a lesion.

14. A system, comprising:
a means for storing a plurality of cases, each case including at least one image of one of a plurality of modalities and non-image information; and
a means for identifying at least one of the plurality of cases that contains images of a volume of interest across at least two different modalities; extracting image-based features of the volume of interest from each image; mapping a relationship between the features of the volume of interest across the different modalities to infer trends of features across different modalities; searching the non-transitory computer readable storage medium, wherein the searching comprises comparing a feature from an image of a current case to a corresponding feature in the at least one image of each of the plurality of stored cases based on the feature relationship, wherein the searching of images is across the multiple different modalities; and retrieving at least one case within a predetermined threshold of similarity to the current case from the non-transitory computer readable storage medium.

Assignees

• Agnihotri Lalitha
• Boroczky Lilla
• Koninklijke Philips Nv

Inventors

• Agnihotri Lalitha
• Boroczky Lilla
• Zhao Luyin

Classifications

• G16H50/70

  for mining of medical data, e.g. analysing previous cases of other patients · CPC title

• G16H50/20

  for computer-aided diagnosis, e.g. based on medical expert systems · CPC title

• G06F19/321 Primary

  Physics · mapped topic

• G16H30/40 Primary

  for processing medical images, e.g. editing · CPC title

• G16H30/20

  for handling medical images, e.g. DICOM, HL7 or PACS · CPC title