Detecting Irregular Curvilinear Structures in Gray Scale and Color Imagery using Multi-Directional Oriented Flux

We present here additional performance curves and comparative results on the evaluated datasets. The images shown in the links below are the maximum (or minimum) intensity projections (MIP) of the original image stacks and those of the algorithm results.

The results presented in the "Best Segmentations" columns are obtained by first finding the threshold value that maximizes the Jaccard index (equivalently the VOC measure defined in Eq.(4) of [26]). For this, we used η=0.4, as also mentioned in the manuscript. We then followed the procedure described in the last part of Section 4.2 to compute the segmentations.

Finally, for stacks with floating-point voxel precision, such as the tubularity volumes, the conversion to 8-bits (after the MIP step) is performed using the Fiji (http://fiji.sc) software [27]. The 3D renderings under the Videos links below are created using the publicly available Vaa3D visualization and analysis software [28].

• Additional Performance Curves
• Retina
• Ground Truth
• Stack 1
• Stack 2
• Videos*
• Brainbow
• Ground Truth
• Sample Stack 1
• Sample Stack 2
• Videos*
• Brightfield
• Ground Truth
• Sample Stack 1
• Sample Stack 2
• Videos*
• VC6
• Ground Truth
• Sample Stack 1
• Sample Stack 2
• Videos*


[26] M. Everingham, L. Van Gool, C.K.I. Williams, J Winn and A. Zisserman, The PASCAL Visual Object Classes (VOC) Challenge, International Journal of Computer Vision , 88(2), 303-338, 2010.
[27] J. Schindelin and I. Arganda-Carreras and E. Frise and V. Kaynig and M. Longair and T. Pietzsch and S. Preibisch and C. Rueden and S. Saalfeld and B. Schmid, Fiji: an open-source platform for biological-image analysis, Nature Methods , 9, 676-682, 2012.
[28] H. Peng, Z. Ruan, F. Long, J. H. Simpson, and E. W. Myers, V3D enables real-time 3D visualization and quantitative analysis of large-scale biological image data sets, Nature Biotechnology , 28(4), 348-353, 2010.

* The videos are encoded in H264 format using the ffmpeg software (http://www.ffmpeg.org). Please see the VLC website (http://www.videolan.org/vlc/) for a compatible player.

NOTE: All images and videos are copyright protected and may not be used in publications without permission and appropriate citations.