Feature Of The Week 2/3/13: Automated Segmentation Algorithm for Medical Image Processing using Optical Coherence Tomography
Optical coherence tomography (OCT) is a noninvasive optical imaging technique for in vivo and in situ imaging of microstructure in biological tissues. Improvements in identification, imaging, and visualization of biological microstructures are necessary before OCT clinical use.
Using the proposed algorithm, OCT images of the prostate and cervicovaginal epithelium were segmented to differentiate the cavernous nerves from the prostate gland and to detect minute changes in the epithelial layer, respectively. To detect these nerves and epithelial layer changes, three image features were employed: Gabor filter, Daubechies wavelet, and Laws filter. The Gabor feature was applied with different standard deviations in the x and y directions. In the Daubechies wavelet feature, an 8-tap Daubechies orthonormal wavelet was implemented, and the low-pass sub-band was chosen as the filtered image. Last, Laws feature extraction was applied to the images. The features were segmented using a nearest-neighbor classifier. N-ary morphological postprocessing was used to remove small voids.
The cavernous nerves were differentiated from the prostate gland with a segmentation error rate of 5.8% ± 1.9%. The overall error rate for segmentation of cervicovaginal epithelium was 8.7% ± 2.2%. These results show the robustness of the proposed technique. This algorithm may be useful for implementation in clinical endoscopic OCT systems for various segmentation applications.
For more information see recent Article. Courtesy Shahab Chitchian from Intel Corporation.