| US 9,811,905 B2 | ||
| Anomaly detection in medical imagery | ||
| Sharon Alpert, Rehovot (IL); and Pavel Kisilev, Maalot (IL) | ||
| Assigned to International Business Machines Corporation, Armonk, NY (US) | ||
| Filed by International Business Machines Corporation, Armonk, NY (US) | ||
| Filed on Feb. 8, 2017, as Appl. No. 15/427,073. | ||
| Application 15/427,073 is a continuation of application No. 14/178,313, filed on Feb. 12, 2014. | ||
| Prior Publication US 2017/0148166 A1, May 25, 2017 | ||
| Int. Cl. G06K 9/00 (2006.01); G06T 7/00 (2017.01); G06T 5/40 (2006.01); G06T 7/13 (2017.01); G06K 9/46 (2006.01); G06K 9/62 (2006.01) | ||
| CPC G06T 7/0012 (2013.01) [G06K 9/4671 (2013.01); G06K 9/6267 (2013.01); G06T 5/40 (2013.01); G06T 7/13 (2017.01); G06T 2207/10088 (2013.01); G06T 2207/30068 (2013.01); G06T 2207/30096 (2013.01)] | 18 Claims |
| 1. A method comprising using at least one hardware processor for:
computing a patch distinctiveness score for each of multiple patches of a medical image;
computing a shape distinctiveness score for each of multiple regions of the medical image, wherein said computing of the shape
distinctiveness score comprises:
applying an edge detection algorithm to each of the multiple regions, to detect at least one pair of boundary edges in each
of at least some of the multiple regions,
for each pair of boundary edges (p, q):
(a) computing a length (lpq) of a vector (pq) and an orientation (ψpq) of the vector (pq),
(b) computing a normal (θp) to the boundary edge (p) and a normal (θq) to the boundary edge (q), and
(c) computing histograms for lpq, ψpq, θp and θq, and
computing the shape distinctiveness score for each of the at least some of the multiple regions, based on an entropy computation
of the histograms; and
computing a saliency map of the medical image, by combining the patch distinctiveness score and the shape distinctiveness
score.
|