An Automatic Tool for Quantification of Nerve Fibers in Corneal Confocal Microscopy Images

• Published in: IEEE transactions on biomedical engineering Vol. 64; no. 4; pp. 786 - 794
• Main Authors: Chen, Xin, Graham, Jim, Dabbah, Mohammad A., Petropoulos, Ioannis N., Tavakoli, Mitra, Malik, Rayaz A.
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.04.2017; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Automation; Biomarkers; Biomedical measurement; Clinical trials; Computer aided diagnosis; Confocal microscopy; Cornea; Cornea - diagnostic imaging; Cornea - innervation; Cornea - pathology; corneal confocal microscopy (CCM); Correlation analysis; Diabetes; Diabetes mellitus; Diabetes mellitus (insulin dependent); Diabetic Neuropathies - diagnostic imaging; Diabetic Neuropathies - pathology; diabetic sensorimotor polyneuropathy (DSPN); Discrete wavelet transforms; Error detection; Feature extraction; Humans; image analysis; Image detection; Image Interpretation, Computer-Assisted - methods; Machine Learning; Medical imaging; Medical research; Microscopy; Microscopy, Confocal - methods; Morphology; Nerve Fibers - pathology; nerve-fiber quantification; Nerves; Patients; Pattern Recognition, Automated - methods; Peripheral neuropathy; Polyneuropathy; Reproducibility of Results; Sensitivity; Sensitivity and Specificity; Sensorimotor system; Software development tools; Training

We describe and evaluate an automated software tool for nerve-fiber detection and quantification in corneal confocal microscopy (CCM) images, combining sensitive nerve-fiber detection with morphological descriptors. Method: We have evaluated the tool for quantification of Diabetic Sensorimotor Polyn...