Automatic detection of target tissues formed by linear structures from within three dimensional images
AssigneeFUJIFILM Corporation
InventorYoshiro Kitamura
Life of this patent
Estimating the term…
Abstract
[Objective] To improve detection performance of target tissues formed by linear structures within three dimensional images. [Constitution] The directions of principal axes of target tissues formed by linear structures or the directions of lines normal to tissues formed by planar structures within detection regions are calculated. Normalization processes are administered with respect to candidate target regions that include candidate target tissues based on the directions of the principal axes or the directions of the normal lines. Features of the normalized candidate target regions are calculated, and judgments are performed regarding whether the target tissues are included in the candidate target regions, employing the calculated features.
Claims15
An image processing apparatus, comprising:
- a detection region setting section, for setting detection regions within three dimensional images obtained by imaging subjects;
- a principal axis/normal line direction calculating section, for calculating one of the directions of the principal axes of candidate target tissues formed by linear structures within the detection regions or the directions of lines normal to candidate target tissues formed by planar structures within the detection regions;
- a normalization processing section, for administering normalizing processes which cut candidate target regions of a predetermined three dimensional shape along one of the directions of the principal axes or the directions of the normal lines, wherein each of the candidate target regions includes the candidate tissue which is scaled into a predetermined size and located along a predetermined direction;
- and
- a judging section, for calculating features of the normalized candidate target regions, and for judging whether target tissues are included in the candidate target regions using the calculated features.
An image processing method, comprising:
- setting detection regions within three dimensional images obtained by imaging subjects;
- calculating one of the directions of the principal axes of candidate target tissues formed by linear structures within the detection regions or the directions of lines normal to candidate target tissues formed by planar structures within the detection regions;
- administering normalizing processes which cut candidate target regions of a predetermined three dimensional shape along one of the directions of the principal axes or the directions of the normal lines, wherein each of the candidate target regions includes the candidate tissue which is scaled into a predetermined size and located along a predetermined direction;
- calculating features of the normalized candidate target regions;
- and
- judging whether target tissues are included in the candidate target regions using the calculated features.
A non-transitory computer readable recording medium having a program recorded therein, the program causing a computer to realize the functions of:
- setting detection regions within three dimensional images obtained by imaging subjects;
- calculating one of the directions of the principal axes of candidate target tissues formed by linear structures within the detection regions or the directions of lines normal to candidate target tissues formed by planar structures within the detection regions;
- administering normalizing processes which cut candidate target regions of a predetermined three dimensional shape along one of the directions of the principal axes or the directions of the normal lines, wherein each of the candidate target regions includes the candidate tissue which is scaled into a predetermined size and located along a predetermined direction;
- calculating features of the normalized candidate target regions;
- and
- judging whether target tissues are included in the candidate target regions using the calculated features.
Dependencies are inferred from the claim text.