Discrete Colour-based Euclidean-Invariant Signatures for Feature Tracking in a DIET Breast Cancer Screening System

Simple item page
dc.contributor.authorBrown, R.G.
dc.contributor.authorHann, C.E.
dc.contributor.authorChase, Geoff
dc.contributor.authorRay, L.
dc.date.accessioned2008-07-21T04:28:50Z
dc.date.available2008-07-21T04:28:50Z
dc.date.issued2007en
dc.description.abstractA Digital Image-based Elasto-Tomography (DIET) system for breast cancer screening has been proposed in which the elastic properties of breast tissue are recovered by solving an inverse problem on the surface motion of a breast under low frequency (50-100 Hz) mechanical actuation. The proposed means for capturing the surface motion of the breast in 3D is to use a stroboscope to capture images from multiple digital cameras at preselected phase angles. Photogrammetric techniques are then used to reconstruct matched point features in 3D. Since human skin lacks high contrast visual features, it is necessary to introduce artificial fiducials which can be easily extracted from digital images. The chosen fiducials are points in three different colours in differing proportions randomly applied to the skin surface. A three-dimensional signature which is invariant to locally Euclidean transformations between images is defined on the points of the lowest proportion colour. The approxi- mate local Euclidean invariance between adjacent frames enables these points to be matched using this signature. The remaining points are matched by interpolating the transformation of the matched points. This algorithm has significant performance gains over conventional gradient-based tracking algorithms because it utilises the intrinsic problem geometry. Successful results are presented for simulated image sequences and for images of a mechanically actuated viscoelastic gel phantom with tracking errors within 3 pixels. The errors in the phantom sequence correspond to less than 0.3 mm error in space, which is more than sufficient accuracy for the DIET system.en
dc.identifier.citationBrown, R.G., Hann, C.E., Chase, J.G., Ray, L. (2007) Discrete Colour-based Euclidean-Invariant Signatures for Feature Tracking in a DIET Breast Cancer Screening System. San Diego, CA, USA: SPIE Medical Imaging Conference - Physiology, Function, and Structure from Medical Images, 17-22 Feb 2007.en
dc.identifier.urihttp://hdl.handle.net/10092/725
dc.language.isoen
dc.publisherUniversity of Canterbury. College of Engineering.en
dc.publisherUniversity of Canterbury. Mathematics and Statistics.en
dc.publisherUniversity of Canterbury. Mechanical Engineering.en
dc.relation.urihttp://spiedigitallibrary.aip.org/dbt/dbt.jsp?KEY=PSISDG&Volume=6511&Issue=1&bproc=symp&scode=MI07en
dc.rights.urihttps://hdl.handle.net/10092/17651en
dc.subjectBreast canceren
dc.subjectScreeningen
dc.subject.marsdenFields of Research::290000 Engineering and Technology::291500 Biomedical Engineering::291504 Biomechanical engineeringen
dc.titleDiscrete Colour-based Euclidean-Invariant Signatures for Feature Tracking in a DIET Breast Cancer Screening Systemen
dc.typeConference Contributions - Published
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
12606265_DIET Tracking - SPIE 2007 - Brown - PAPER.pdf
Size:
938.17 KB
Format:
Adobe Portable Document Format
Download
Collections
Engineering: Conference Contributions