Probabilistic edge detection in 3D optical microscopy images of tissue samples

Inspired by a state of the art 2D algorithm for edge detection in natural images, in this work we report the development of an accurate 3D probabilistic edge detector for fluorescence optical microscopy images of tissue samples. The method utilizes multi-orientation and multi-scale brightness, textural and spectral properties of the data to compute a probabilistic edge map. To demonstrate the strengths and accuracy of the proposed algorithm, comparisons of the edge maps produced by our algorithm and several other popular edge detectors on simulated and real 3D microscopic volumes are provided.

[1]  Zhuowen Tu,et al.  Supervised Learning of Edges and Object Boundaries , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[2]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[3]  Richard A. Robb,et al.  Image smoothing with Savtizky-Golai filters , 2003, SPIE Medical Imaging.

[4]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Johannes E. Schindelin,et al.  Fiji: an open-source platform for biological-image analysis , 2012, Nature Methods.

[6]  Petros Koumoutsakos,et al.  Edge detection in microscopy images using curvelets , 2009, BMC Bioinformatics.

[7]  Charless C. Fowlkes,et al.  Contour Detection and Hierarchical Image Segmentation , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Jitendra Malik,et al.  Learning to detect natural image boundaries using local brightness, color, and texture cues , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.