FEATURE-BASED REGISTRATION OF SECTIONAL IMAGES

• US 20100215227A1
• Filed: 11/16/2007
• Published: 08/26/2010
• Est. Priority Date: 11/16/2006
• Status: Active Grant

• Current Assignee: Visiopharm A/S
• Original Assignee: Visiopharm A/S
• Inventors: Rasmussen, Steen T., Bjerrum, Kim A., Hansen, John Dore, Grunkin, Michael
• Granted Patent: US 8,229,194 B2
• Time in Patent Office: Days
• US Class Current: 382/128
• CPC Class Codes: G06T 2207/30004 Biomedical image processing
• CPC Class Codes: G06T 3/153 using elastic snapping
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06T 7/33 using feature-based methods
• 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

Abstract

The present invention relates to a method and a system for obtaining and analysing image pairs, obtained as sections of specimen. The invention facilitates registration of two corresponding images, one from each section of the specimen. The invention includes performing a registration process of the two images thereby obtaining a mathematical transformation rule and afterwards using said transformation rule for each image field identified in one image allowing that the corresponding image field in the other image may be identified as well. After the corresponding image pairs have been obtained using the method of the present invention, the sections can be assessed, such as by identifying the counting events for at least one type of object on the image fields within at least one corresponding image pair, optionally using automatic means.

Claims

1-43. -43. (canceled)

44. A method for obtaining at least one corresponding image pair from at least two adjacent sections A and B of a specimen, said method comprising the steps of:

a) obtaining a superimage of at least part of section A and a superimage of at least part of section B, wherein a superimage is an image of a section comprising all image fields and an image field is an area of the image to be analysed,

b) carrying out an image registration process on the two superimages by establishing correspondence between features of the two related superimages, so as to obtain a mathematical transformation rule,

c) identifying an image field within section A,

d) using said mathematical transformation rule to identify an area within section B, said area comprising an image field within section B corresponding to said image field within section A, and adding a minimum guard zone to each border of said area in section B,

e) obtaining an image of said image field within section A identified in step c) and obtaining an image of said image field within section B identified in step d) and carrying out a second registration process on the two images to obtain a registered corresponding image pair,

f) optionally repeating steps c)-e) one or more times to obtain one or more different corresponding image pair(s) of one or more different image fields in the two sections A and B,

g) storing a digitized version of said registered corresponding image pair(s) in a computer-readable storage means,

wherein the superimages of step a) are obtained using a lower resolution than the resolution used to obtain the images of step e).

45. The method according to claim 44, wherein the superimages are obtained using a magnification of at least 2.5×

.

46. The method according to claim 44, wherein the minimum guard zone is calculated using the following formula:

$\frac{\left(\begin{array}{c}\mathrm{working}<br><br><br><br>\mathrm{magnification}<br><br><br><br>\mathrm{of}<br><br>\\ \mathrm{said}<br><br><br><br>\mathrm{area}<br><br><br><br>\mathrm{in}<br><br><br><br>\mathrm{step}<br><br><br><br>d\end{array}\right)}{\left(\mathrm{superimage}<br><br><br><br>B<br><br><br><br>\mathrm{magnification}\right)}\times <br><br>\left(\begin{array}{c}\mathrm{margin}<br><br><br><br>\mathrm{of}<br><br><br><br>\mathrm{registration}<br><br><br><br>\mathrm{error}<br><br>\\ \mathrm{of}<br><br><br><br>\mathrm{superimage}<br><br><br><br>B<br><br><br><br>\mathrm{in}<br><br><br><br>\mathrm{pixels}\end{array}\right)$

wherein the area of said area in step d) is at least 1.5 times the area of said image field within section B.

47. The method according to claim 44, wherein a guard zone is also added to each border of the image field within section A.

48. The method according to claim 47, comprising the additional step of carrying out a second registration process on the two corresponding image fields and guard zones obtained in step d) to obtain a registered corresponding image pair.

49. The method according to claim 44, wherein said transformation rule includes a rotation rule and/or a translation rule and/or a warp rule, which is carried out on at least part of the section.

50. The method according to claim 44, wherein the first image field is identified at random and the subsequent image fields are identified using a pre-defined function.

51. The method according to claim 44, wherein said image field of section A is selected in the specimen by a human operator.

52. The method according to claim 44, wherein counting events are presented to a human operator as suggested counting events based on image analysis of the image field pairs.

53. A method for assessing at least two adjacent sections of a specimen, said method comprising the steps of:

i) providing at least one corresponding image pair according to the method of claim 52;

ii) identifying the counting events for at least one type of object on said image fields within at least one corresponding image pair, optionally using automatic means.

54. The method according to claim 53, comprising the additional step of:

quantifying the amount or number of said counting events on the images of said image field(s) within section A and said image field(s) within section B.

55. The method according to claim 54, wherein said quantification includes calculating the number of counting events and/or objects per volume of tissue.

56. An automated system for carrying out the method according to claim 44, comprising, in combination:

a database capable of including a plurality of digital images of a plurality of biological specimens;

a software module for analyzing a plurality of pixels from a digital image of a biological specimen;

a control module comprising instructions for carrying out the method of claim 44.

57. The automated system according to claim 56, wherein said system comprises a slide loader, a barcode reader, a microscope and a stage.

58. A software program comprising instructions for carrying out the method according to claim 44.