Voxel-level machine learning with or without cloud-based support in medical imaging

Patent metadata

Field	Value
Publication number	US-9959486-B2
Application number	US-201414518138-A
Country	US
Kind code	B2
Filing date	Oct 20, 2014
Priority date	Oct 20, 2014
Publication date	May 1, 2018
Grant date	May 1, 2018

Abstract

A single level machine-learnt classifier is used in medical imaging. A gross or large structure is located using any approach, including non-ML approaches such as region growing or level-sets. Smaller portions of the structure are located using ML applied to relatively small patches (small relative to the organ or overall structure of interest). The classification of small patches allows for a simple ML approach specific to a single scale or at a voxel/pixel level. The use of small patches may allow for providing classification as a service (e.g., cloud-based classification) since partial image data is to be transmitted. The use of small patches may allow for feedback on classification and updates to the ML. The use of small patches may allow for the creation of a labeled library of classification partially based on ML. Given a near complete labeled library, a simple matching of patches or a lookup can replace ML classification for faster throughput.

First claim

We claim:

1. A method for use of machine-learnt classifier in medical imaging, the method comprising:
segmenting, by a processor, gross parts of an anatomic structure of a patient represented in medical imaging data;
locating, by the processor, a region adjacent and separate from the segmented gross parts of the anatomic structure, and locating the gross parts of the anatomic structure from the segmenting, where the region contains relatively smaller parts of the anatomic structure and contains tissue not of the anatomic structure, where the relatively smaller parts of the anatomical structure are smaller than the gross parts of the anatomical structure;
dividing, by the processor, the region represented in the medical imaging data into a plurality of patches;
classifying, with a machine-learnt classifier, each of the patches as including relatively smaller parts of the anatomical structure or not including relatively smaller parts of the anatomical structure, the classifying of each of the patches being independent of classifying the other patches;
merging, by the processor, locations for the patches classified as including relatively smaller parts of the anatomical structure to the gross parts of the anatomical structure; and
outputting, on a display, a segmented image of the anatomical structure including locations from the locating and the merged locations from the patches.

2. The method of claim 1 wherein locating comprises region growing.

3. The method of claim 1 wherein segmenting the anatomical structure comprises region growing and skeletonization.

4. The method of claim 1 wherein the anatomic structure is a lung, the gross and relatively smaller parts of the anatomic structure are airways, and wherein outputting comprises outputting an image of the gross and smaller airways.

5. The method of claim 1 wherein dividing comprises dividing into overlapping patches.

6. The method of claim 1 wherein classifying comprises classifying with the machine-learnt classifier comprising a neural network.

7. The method of claim 6 wherein classifying comprises classifying with the machine-learnt classifier comprising a deep learnt, sparse auto-encoder classifier.

8. The method of claim 1 wherein classifying comprises classifying into as including relatively smaller parts of the anatomical structure or not and at least one other anatomical structure or not.

9. The method of claim 1 wherein the patches comprise no more than 50 pixels or voxels along a longest dimension.

10. The method of claim 1 wherein merging comprises removing the locations for patches classified as including relatively smaller parts of the anatomical structure but not connected to other of the locations directly or through a line or curve fit.

11. The method of claim 1 wherein segmenting, locating, and dividing are performed by the processor at a local system and wherein classifying is performed with the machine-learnt classifier by a server remote from the local system.

12. The method of claim 1 further comprising:
receiving from a user input an indication of error in the classifying for at least one of the patches;
transmitting the at least one of the patches and a corrected classification to a remote server; and
updating the machine-learnt classifier using the at least one of the patches and the corrected classification.

13. The method of claim 12 further comprising:
collecting the patches and additional patches with verified classifications; and
replacing the classifying with the machine-learnt classifier with matching from the collection of the patches and the additional patches.

14. The method of claim 1 wherein merging comprises skeletonization or creation of a surface mesh of the merged gross and relatively smaller parts of the anatomic structure.

15. A method for use of voxel-level machine-learnt classifier in medical imaging, the method comprising:
locating, without using a machine trained operator, gross parts of a structure from data representing a patient and a region around and outside the gross parts of the structure;
dividing, by a processor, the data representing the patient in the region around and outside the gross parts of the structure into sub-sets;
classifying, by the processor using a machine trained classifier, the sub-sets of the data representing the patient within the region around the structure as representing a relatively smaller part of the structure in the region or not, where the relatively smaller part of the anatomical structure is smaller than the gross parts of the anatomical structure; and
expanding the structure with locations corresponding to the sub-sets classified as belonging to the structure by adding the relatively smaller part of the structure to the gross part of the structure.

16. The method of claim 15 wherein locating comprises locating with region growing and skeletonization, and wherein classifying comprises classifying with a neural network.

17. The method of claim 15 wherein locating and expanding are performed by another processor and wherein the processor for classifying is remote to the other processor and acts as a server of the other processor.

18. The method of claim 17 wherein the processor is configured to update the machine trained classifier in response to feedback about the classifying from the other processor.

19. The method of claim 15 wherein the structure is a lung, the gross and relatively smaller parts of the structure are parts of an airway tree of the lung.

Assignees

• Siemens Healthcare Gmbh

Inventors

• Kiraly Atilla Peter
• Odry Benjamin L

Classifications

• G06V30/194

  References adjustable by an adaptive method, e.g. learning · CPC title

• G06T7/11 Primary

  Region-based segmentation · CPC title

• G06V10/255

  Detecting or recognising potential candidate objects based on visual cues, e.g. shapes · CPC title

• G06V10/267

  by performing operations on regions, e.g. growing, shrinking or watersheds · CPC title

• G06K2209/05

  Physics · mapped topic