Diagnosing renal disease requires time consuming manual inspection of needle biopsies. Automated quantification of the same characteristics of biopsies by a digital method greatly decreases the burden on pathologists and improves the reproducibility of the biopsy process. The current barrier to the automated quantification of renal injury in proteinuria is the digital identification of the glomerulus. We have developed an integrated method, based on Gabor filter bank based textural segmentation, statistical F-testing, and distance transform, for segmenting glomerular boundaries from renal biopsies. Our method outperforms sole Gabor filter bank based method, and is able to operate on multiple histological stains.
B. Ginley, J. E. Tomaszewski, R. Yacoub, F. Chen, and P. Sarder, “Unsupervised labeling of glomerular boundaries using Gabor filters and statistical testing in renal histology,” Journal of Medical Imaging – SPIE, vol. 4, no. 2, pp. 021102:1–13, Feb. 2017.