Classification of Linear Structures in Mammograms Using Random Forests

Classification of linear structures, such as blood vessels, milk ducts, spiculations and fibrous tissue can be used to aid the automated detection and diagnosis of mammographic abnormalities We use a combination of dual-tree complex wavelet coefficients and random forest classification to detect and classify different types of linear structure Encouraging results are presented for synthetic linear structures added to real mammographic backgrounds, and spicules in real mammograms For spicule/non-spicule classification in real mammograms we report an area Az = 0.764 under the receiver operating characteristic.

[1]  Kristin Jane McLoughlin,et al.  Connective tissue representation for detection of microcalcifications in digital mammograms , 2002, SPIE Medical Imaging.

[2]  Michael Brady,et al.  A Multi-resolution CLS Detection Algorithm for Mammographic Image Analysis , 2004, MICCAI.

[3]  Rangaraj M. Rangayyan,et al.  Detection of architectural distortion in mammograms acquired prior to the detection of breast cancer using texture and fractal analysis , 2008, SPIE Medical Imaging.

[4]  Nico Karssemeijer,et al.  Detection of stellate distortions in mammograms , 1996, IEEE Trans. Medical Imaging.

[5]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[6]  Susan M. Astley,et al.  Statistical Modelling of Lines and Structures in Mammograms , 1997, IPMI.

[7]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[8]  Richard Baraniuk,et al.  The Dual-tree Complex Wavelet Transform , 2007 .

[9]  Michael Brady,et al.  Finding CLS Using Multiresolution Oriented Local Energy Feature Detection , 2003 .

[10]  Hans Bornefalk.  Use of phase and certainty information in automatic detection of stellate patterns in mammograms , 2004, SPIE Medical Imaging.

[11]  Susan M. Astley,et al.  Linear structures in mammographic images: detection and classification , 2004, IEEE Transactions on Medical Imaging.

[12]  Pierre Hellier,et al.  Level Set Methods in an EM Framework for Shape Classification and Estimation , 2004, International Conference on Medical Image Computing and Computer-Assisted Intervention.