Topological evolution of tumor imagery

• US 10,561,373 B2
• Filed: 01/31/2017
• Issued: 02/18/2020
• Est. Priority Date: 01/31/2017
• Status: Active Grant

• Current Assignee: Merative US LP
• Original Assignee: International Business Machines Corporation
• Inventors: Park, Sun Young, Sargent, Dustin
• Primary Examiner(s): Manuel, George
• Application Number:
  US15/421,023
• Publication Number:
  US 20180214086A1
• Time in Patent Office: 1,113 Days
• CPC Class Codes: A61B 2090/364 Correlation of different images or relation of image positions in respect to the body
• CPC Class Codes: A61B 2576/02 specially adapted for a particular organ or body part
• CPC Class Codes: A61B 2576/026 for the brain
• CPC Class Codes: A61B 5/004 adapted for image acquisition of a particular organ or body part A61B5/0082 takes precedence; arrangements for optical scanning A61B5/0062
• CPC Class Codes: A61B 5/055 involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
• CPC Class Codes: A61B 5/4842 Monitoring progression or stage of a disease
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• CPC Class Codes: A61B 5/7275 Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
• CPC Class Codes: A61B 6/032 Transmission computed tomography [CT]
• CPC Class Codes: A61B 6/486 involving generating temporal series of image data
• CPC Class Codes: A61B 6/5217 extracting a diagnostic or physiological parameter from medical diagnostic data
• CPC Class Codes: A61B 6/5247 combining images from an ionising-radiation diagnostic technique and a non-ionising radiation diagnostic technique, e.g. X-ray and ultrasound
• CPC Class Codes: A61B 8/085 for locating body or organic structures, e.g. tumours, calculi, blood vessels, nodules
• CPC Class Codes: A61B 8/5223 for extracting a diagnostic or physiological parameter from medical diagnostic data for algorithms to analyse biomedical images G06T7/0012
• CPC Class Codes: A61B 8/5261 combining images from different diagnostic modalities, e.g. ultrasound and X-ray
• CPC Class Codes: A61B 90/37 Surgical systems with images on a monitor during operation
• CPC Class Codes: G06F 18/2415 based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
• CPC Class Codes: G06T 2207/20084 Artificial neural networks [ANN]
• CPC Class Codes: G06T 2207/30016 Brain
• CPC Class Codes: G06T 2207/30096 Tumor; Lesion
• CPC Class Codes: G06T 7/0016 : involving temporal comparison
• CPC Class Codes: G06T 7/30 : Determination of transform parameters for the alignment of images, i.e. image registration
• CPC Class Codes: G06V 10/267 : by performing operations on regions, e.g. growing, shrinking or watersheds
• CPC Class Codes: G06V 2201/03 : Recognition of patterns in medical or anatomical images
• CPC Class Codes: G16H 30/20 : for handling medical images, e.g. DICOM, HL7 or PACS
• CPC Class Codes: G16H 30/40 : for processing medical images, e.g. editing
• CPC Class Codes: G16H 50/20 : for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

Topological evolution of a lesion within a time series of medical imagery is provided. In various embodiments, a time series of medical images is read. Each of the images depicts a subject anatomy and a lesion. The lesion has a size and a contour within each of the medical images. At least one anatomical label is read for the subject anatomy within each of the plurality of images. Based upon the contour of the lesion within each of the medical images and based on the at least one anatomical label, a further contour of the lesion is predicted outside of the time series.

Claims

1. A method comprising:

reading a time series of medical images, each of the images depicting a subject anatomy and a lesion, the lesion having a size and a contour within each of the medical images;

reading at least one anatomical label for the subject anatomy within each of the plurality of images;

based upon the contour of the lesion within each of the medical images and based on the at least one anatomical label, predicting a further contour of the lesion outside of the time series.

2. The method of claim 1, wherein predicting the further contour comprises:

applying a dynamic Bayesian network, a conditional random field, a support vector machine, or a recurrent neural network to the time series of medical images.

3. The method of claim 1, wherein predicting the further contour comprises:

applying a hidden Markov model to the time series of medical images.

4. The method of claim 1, wherein predicting the further contour comprises:

determining a plurality of characteristics of the lesion over the time series.

5. The method of claim 4, wherein the plurality of characteristics comprise:

size, shape, growth rate, shrinkage rate, intensity, texture, or neighboring tissue characteristics.

6. The method of claim 1, further comprising:

presenting to a user the further contour overlain on a further medical image corresponding to a time later than the time series.

7. The method of claim 1, further comprising:

aligning the medical images based on the at least one anatomical label.

8. The method of claim 7, wherein aligning the medical images comprises performing registration between the medical images.

9. The method of claim 1, further comprising:

predicting at least one additional lesion.

10. The method of claim 1, wherein applying the dynamic Bayesian network comprises:

dividing each of the medical images into a plurality of disjoint regions; and

determining whether the lesion is contained in each of the plurality of disjoint regions.

11. The method of claim 1, wherein applying the dynamic Bayesian network comprises:

dividing each of the medical images into a plurality of disjoint regions; and

determining at least one tissue characteristic for each of the plurality of disjoint regions.

12. The method of claim 1, wherein applying the dynamic Bayesian network comprises:

dividing each of the medical images into a plurality of disjoint regions; and

determining whether the lesion is contains in each of the plurality of disjoint regions.

13. The method of claim 1, wherein applying the dynamic Bayesian network comprises:

dividing each of the medical images into a plurality of disjoint regions; and

determining at least one tissue characteristic for each of the plurality of disjoint regions.

18. The system of claim 13, wherein applying the dynamic Bayesian network comprises:

dividing each of the medical images into a plurality of disjoint regions; and

determining whether the lesion is contained in each of the plurality of disjoint regions.

19. The system of claim 13, wherein applying the dynamic Bayesian network comprises:

dividing each of the medical images into a plurality of disjoint regions; and

determining at least one tissue characteristic for each of the plurality of disjoint regions.

14. A system comprising:

a data store comprising a time series of medical images, each of the images depicting a subject anatomy and a lesion, the lesion having a size and a contour within each of the medical images;

a computing node comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor of the computing node to cause the processor to perform a method comprising;

reading the time series of medical images;

reading at least one anatomical label for the subject anatomy within each of the plurality of images;

based upon the contour of the lesion within each of the medical images and based on the at least one anatomical label, predicting a further contour of the lesion outside of the time series.

15. The system of claim 14, wherein predicting the further contour comprises:

applying a dynamic Bayesian network to the time series of medical images.

16. The system of claim 15, wherein the dynamic Bayesian network comprises a hidden Markov model.

17. The system of claim 14, wherein predicting the further contour comprises:

determining a plurality of characteristics of the lesion over the time series.

20. A computer program product for topological evolution of a lesion, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to perform a method comprising:

reading a time series of medical images, each of the images depicting a subject anatomy and a lesion, the lesion having a size and a contour within each of the medical images;

reading at least one anatomical label for the subject anatomy within each of the plurality of images;

based upon the contour of the lesion within each of the medical images and based on the at least one anatomical label, predicting a further contour of the lesion outside of the time series.