Discrete color-based Euclidean-invariant signatures for feature tracking in a DIET breast cancer screening system

Brown, Richard G.; Hann, C.E.; Chase, J. Geoffrey; Ray, Lawrence A.

doi:10.1117/12.711815

Cited by 17 publications

(25 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The point locations are taken to be the centroids of the detected coloured blobs. The feature locations are then tracked using the Euclidean Invariant algorithm described in Brown et al [2007]. The motion of the feature points from one camera is depicted in Fig.…”

Section: Calibrationmentioning

confidence: 99%

“…The features are tracked using the novel Euclideaninvariant algorithm described in Brown et al [2007] which is based on a system of coloured fiducial points as mentioned in the previous section. This method of feature tracking uses the geometrically invariant properties of local configurations of the coloured point locations to match points between frames, rather than using image-based correlation techniques, the advantage being that points can be matched over a wider range of transformations, notably those involving a large translational component.…”

Section: Feature Trackingmentioning

confidence: 99%

See 1 more Smart Citation

Surface Reconstruction for a DIET breast cancer screening system

Brown

Hann

Chase

et al. 2008

IFAC Proceedings Volumes

Self Cite

View full text Add to dashboard Cite

This paper outlines a method for accurately tracking surface motion on an actuated breast as part of a Digital Image-based Elasto-Tomography (DIET) breast cancer screening project. The tracking method is validated in both simulation and experiment on a silicon breast phantom which has similar elasticity characteristics to human breast tissue. Given mean reprojection error ranges between 0.3 and 0.5 pixels for 2M pixel cameras the end result is sub-millimetre surface tracking of a silicon phantom actuated at 100 Hz. This highly accurate, fast and low cost method of tracking is thus well suited to a DIET system.

show abstract

Section: Calibrationmentioning

confidence: 99%

Section: Feature Trackingmentioning

confidence: 99%

Surface Reconstruction for a DIET breast cancer screening system

Brown

Hann

Chase

et al. 2008

IFAC Proceedings Volumes

Self Cite

View full text Add to dashboard Cite

show abstract

“…The markers purpose of applying these markers was to ensure robust motion tracking when optically imaged with the DIET system. 28,29,32,33,47,48,[62][63][64] During the imaging procedure each one of 250 these 13 phantoms, was individually mounted on a metallic plate (200 mm x 150 mm) and hung pendant through a hole in the DIET clinical prototype. The phantom was vibrated using harmonic sinusoidal actuation of 0.5 mm amplitude, over a range of 10-50 Hz at a step size of 1 Hz.…”

Section: Iif3 Phantom Imaging 245mentioning

confidence: 99%

“…[28][29][30][31] Low frequency (5-100 Hz) sinusoidal waves are induced in the breast and the resulting surface oscillations are captured in three dimensions (3D) by an array of digital cameras tracking randomly applied fiducial markers. 29,32,33 The surface motion is analyzed to detect disturbances in vibration patterns. Areas of higher stiffness within the breast result in a different surface vibration response compared to healthy tissue.…”

mentioning

confidence: 99%

Silicone breast phantoms for elastographic imaging evaluation

et al. 2013

View full text Add to dashboard Cite

New Zealand 15(Received 2 Purpose: Breast cancer is a major public health issue for women, and early detection significantly increases survival rate. Currently, there is increased research interest in elastographic soft-tissue 20 imaging techniques based on the correlation between pathology and mechanical stiffness.Anthropomorphic breast phantoms are critical for in-vitro validation of emerging elastographic technologies. This research develops heterogeneous breast phantoms for use in testing elastographic imaging modalities.Methods: Mechanical property estimation of eight different elastomers is performed to determine 25 storage moduli (E') and damping ratios (ζ) using a dynamic mechanical analyzer (DMA). Dynamic compression testing was carried out isothermally at room temperature over a range of 4-50 Hz.Silicone compositions with physiologically realistic storage modulus were chosen for mimicking skin adipose, cancerous tumors and pectoral muscles and 13 anthropomorphic breast phantoms were constructed for in vitro trials of Digital Image Elasto Tomography (DIET) breast cancer screening 30 system. A simpler fabrication was used to assess the possibility of multiple tumor detection using Magnetic Resonance Elastography (MRE).Results: Silicone materials with ranges of storage moduli (E') from 2 to 570 kPa and damping ratios (ζ) from 0.03 to 0.56 were identified. The resulting phantoms were tested in two different elastographic breast cancer diagnostic modalities. A significant contrast was successfully identified 35 between healthy tissues and cancerous tumors both in Magnetic Resonance Elastography (MRE) and Digital Image Elasto-tomography (DIET). Conclusions:The phantoms presented promise aid to researchers in elastographic imaging modalities for breast cancer detection and provide a foundation for silicone based phantom materials for mimicking soft tissues of other human organs. 40

show abstract

“…The features are tracked using the novel Euclidean-invariant algorithm described in [9] which is based on a system of coloured fiducial points as mentioned in the previous section. This method of feature tracking uses geometrically invariant properties of local configurations of the coloured point locations to match points between frames, rather than using imagebased correlation techniques.…”

Section: B Feature Trackingmentioning

confidence: 99%

Vision-based 3D surface motion capture for the DIET breast cancer screening system

Brown

Hann

Chase

2010

IJCAT

Self Cite

View full text Add to dashboard Cite

Abstract-Breast cancer is one of the most prevalent forms of cancer in the world today. The search for effective treatment and screening methods is a highly active area of research. The Digital Image-based ElastoTomography (DIET) project is a new breast cancer screening system under development, where surface motion from the mechanically actuated breast is measured in 3D, and used as input to an inverse problem solving for breast elasticity. Cancerous lesions appear as high contrast features, being an order of magnitude stiffer than healthy tissue.The 3D motion capture is measured by an array of digital cameras using computer vision techniques. This paper presents a computer vision imaging system for the capture of 3D breast surface motion for the DIET system, including the image acquisition system, camera calibration, and 3D surface and motion reconstruction.Results are presented for experiments performed with silicone gel phantoms, with conditions designed to replicate the clinical procedure. Full 3D surface motion is successfully captured using an array of 5 cameras. Some successful results from the DIET inverse problem are also presented to demonstrate the viability of the system in practice.

show abstract

Discrete color-based Euclidean-invariant signatures for feature tracking in a DIET breast cancer screening system

Cited by 17 publications

References 7 publications

Surface Reconstruction for a DIET breast cancer screening system

Surface Reconstruction for a DIET breast cancer screening system

Silicone breast phantoms for elastographic imaging evaluation

Vision-based 3D surface motion capture for the DIET breast cancer screening system

Contact Info

Product

Resources

About