Method for moving cell detection from temporal image sequence model estimation

• US 8,045,783 B2
• Filed: 11/09/2006
• Issued: 10/25/2011
• Est. Priority Date: 11/09/2006
• Status: Active Grant

• Current Assignee: Leica Microsystems Gmbh (Danaher Corporation)
• Original Assignee: DRVision Technologies, LLC (Danaher Corporation)
• Inventors: Oh, Seho, Lee, Shih-Jong J.
• Primary Examiner(s): Ahmed; Samir
• Assistant Examiner(s): Liu; Li
• Application Number:
  US11/595,611
• Publication Number:
  US 20080112606A1
• Time in Patent Office: 1,811 Days
• Field of Search: None
• US Class Current: 382/133
• CPC Class Codes: G06T 2207/10056 Microscopic image
• CPC Class Codes: G06T 2207/30024 Cell structures in vitro; Tissue sections in vitro
• CPC Class Codes: G06T 7/254 involving subtraction of images
• CPC Class Codes: G06V 20/695 Preprocessing, e.g. image segmentation

Abstract

A computerized robust cell kinetic recognition method for moving cell detection from temporal image sequence receives an image sequence containing a current image. A dynamic spatial-temporal reference generation is performed to generate dynamic reference image output. A reference based object segmentation is performed to generate initial object segmentation output. An object matching and detection refinement is performed to generate kinetic recognition results output. The dynamic spatial-temporal reference generation step performs frame look ahead and the reference images contain a reference intensity image and at least one reference variation image.

Claims

1. A computerized object matching and detection refinement method for moving cell detection from temporal image sequence comprising the steps of:

a) Inputting an initial object segmentation from a temporal image sequence containing moving cells wherein objects are cells and the object segmentation is created by dynamic spatial-temporal reference method wherein the dynamic spatial-temporal reference generation method comprising the steps of;

(i) Inputting running interval image sequence;

(ii) Performing pixel statistics creation using the running interval image sequence to generate pixel statistics output;

(iii) Performing background time points detection using the running interval image sequence and the pixel statistics to generate background set output;

(iv) Performing reference image generation using the current image and the background set to generate reference intensity image output,

b) Inputting previous frame results;

c) Performing matching and shift estimation using the initial object segmentation and the previous frame results to generate either estimated shift and updated tracks or new cell detection output wherein the initial object segmentation is used to match the previous frame results using at least one of features such as location, static object morphology, intensity as well as object kinetic measurements such as velocity or acceleration;

d) Performing aligned combination using the previous frame results and either the estimated shift or zero shift for new cell to generate combined previous results output wherein the previous frame results corresponding to best match are aligned with current frame after shifting.

2. The object matching and detection refinement method of claim 1 further comprising the steps of

a) Performing sub-region cutting using the initial object segmentation to generate cut object components output;

b) Performing integration using the cut object components and the combined previous results to generate integrated mask output.

3. The object matching and detection refinement method of claim 2 further performing final refinement using the integrated mask to generate final object segmentation output.

4. The final refinement method of claim 3 performing structure guided processing.

5. The object matching and detection refinement method of claim 2 wherein the integration step including a conflict resolution step.

6. The object matching and detection refinement method of claim 2 wherein the integration step including using the cut object components that are close to the combined previous results.

7. The matching and shift estimation step of claim 1 further performing new cell detection.

8. The object matching and detection refinement method of claim 1 wherein the aligned combination performing a weighed combination wherein weights are goodness of matches indicating similarity between matches containing in the previous frame results.