US 12,357,592 B2
Compositions and methods for monitoring the treatment of breast disorders
Per Hall, Stockholm (SE); and Mikael Eriksson, Täby (SE)
Appl. No. 16/962,797
Filed by Per Hall, Stockholm (SE); and Mikael Eriksson, Täby (SE)
PCT Filed Jan. 24, 2019, PCT No. PCT/IB2019/050606
§ 371(c)(1), (2) Date Jul. 16, 2020,
PCT Pub. No. WO2019/145896, PCT Pub. Date Aug. 1, 2019.
Claims priority of provisional application 62/622,029, filed on Jan. 25, 2018.
Prior Publication US 2020/0360312 A1, Nov. 19, 2020
Int. Cl. A61K 31/138 (2006.01); A61B 5/00 (2006.01); A61B 5/055 (2006.01); A61B 6/03 (2006.01); A61B 6/50 (2024.01); G06T 7/00 (2017.01); G06T 7/136 (2017.01); G06T 7/33 (2017.01); G16H 20/10 (2018.01); G16H 30/40 (2018.01); G16H 50/20 (2018.01); G16H 50/50 (2018.01)
CPC A61K 31/138 (2013.01) [A61B 5/004 (2013.01); A61B 5/055 (2013.01); A61B 6/032 (2013.01); A61B 6/502 (2013.01); G06T 7/0014 (2013.01); G06T 7/136 (2017.01); G06T 7/33 (2017.01); G06T 7/97 (2017.01); G16H 20/10 (2018.01); G16H 30/40 (2018.01); G16H 50/20 (2018.01); G16H 50/50 (2018.01); G06T 2207/20081 (2013.01); G06T 2207/30068 (2013.01)] 26 Claims
OG exemplary drawing
 
1. A method of treatment of a subject having or is at risk of having breast disorder, comprising:
(a) receiving, in a computer processing system, data input comprising a plurality of breast images of a subject and image metadata;
(b) applying an alignment algorithm to the plurality of breast images, the alignment algorithm comprising:
(i) labeling pixels in the plurality of breast images as breast area based on a polynomial fit to a corresponding region of one or more kernel images to generate a plurality of binary masks, thereby performing a thresholding method on the plurality of breast images marking the breast area in the plurality of breast images;
(ii) superimposing the breast area in each of the plurality of breast images in layers;
(iii) moving binary masks in breast area markings towards each other to an optimal position for alignment of the breast areas where pixel intensities of the binary masks show minimal difference relative to one another using least square means; and
(iv) generating by computer an aligned image from the optimal position comprising an area of mutual image information that is the resulting breast area of the aligned image; and
(c) administering a treatment regimen to the subject based on the aligned image.