Discrete Colour-based Euclidean-Invariant Signatures for Feature Tracking in a DIET Breast Cancer Screening System (2007)
Type of ContentConference Contributions - Published
PublisherUniversity of Canterbury. College of Engineering.
University of Canterbury. Mathematics and Statistics.
University of Canterbury. Mechanical Engineering.
A 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.
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.
This citation is automatically generated and may be unreliable. Use as a guide only.
KeywordsBreast cancer; Screening
Showing items related by title, author, creator and subject.
Ismail HM; Pretty CG; Signal MK; Haggers M; Chase, Geoff (Bentham Science Publishers Ltd., 2019)Early detection of breast cancer, combined with effective treatment, can reduce mortality. Millions of women are diagnosed with breast cancer and many die every year globally. Numerous early detection screening tests have ...
Lotz, T.; Kashif, A.; Feng, S.; Biret, P.; Denais, Y.; Lottin, D.; Maillard, L.; Tirschler, T.; Chase, Geoff (University of Canterbury. Mechanical Engineering, 2011)Digital Image Elasto Tomography (DIET) is a noninvasive breast cancer screening modality that induces vibrations into a breast and images its surface motion with digital cameras. Disturbances seen in motion patterns are ...
Tissue actuation studies for a digital-imaged elasto-tomogarphy [i.e. tomography] (DIET) breast cancer screening system. Kinoshita, Shigeaki (University of Canterbury. Mechanical Engineering, 2005)Breast cancer is now the second leading cause of cancer death for women around the world . However, in New Zealand, according to the “Cancer Society of New Zealand’, breast cancer still has the dubious leadership of ...