Premium
Corneal nerve tortuosity grading via ordered weighted averaging‐based feature extraction
Author(s) -
Su Pan,
Chen Tianhua,
Xie Jianyang,
Zheng Yalin,
Qi Hong,
Borroni Davide,
Zhao Yitian,
Liu Jiang
Publication year - 2020
Publication title -
medical physics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.473
H-Index - 180
eISSN - 2473-4209
pISSN - 0094-2405
DOI - 10.1002/mp.14431
Subject(s) - tortuosity , artificial intelligence , pattern recognition (psychology) , grading (engineering) , computer science , feature extraction , mathematics , materials science , civil engineering , porosity , engineering , composite material
Purpose Tortuosity of corneal nerve fibers acquired by in vivo Confocal Microscopy (IVCM) are closely correlated to numerous diseases. While tortuosity assessment has conventionally been conducted through labor‐intensive manual evaluation, this warrants an automated and objective tortuosity assessment of curvilinear structures. This paper proposes a method that extracts the image‐level features for corneal nerve tortuosity grading. Methods For an IVCM image, all corneal nerve fibers are first segmented and then, their tortuosity are calculated by morphological measures. The ordered weighted averaging (OWA) approach, and the k ‐Nearest‐Neighbor guided dependent ordered weighted averaging ( k NNDOWA) approach are proposed to aggregate the tortuosity values and form a set of extracted features. This is followed by running the Wrapper method, a supervised feature selection, with an aim to identify the most informative attributes for tortuosity grading. Results Validated on a public and an in‐house benchmark data sets, experimental results demonstrate superiority of the proposed method over the conventional averaging and length‐weighted averaging methods with performance gain in accuracy (15.44% and 14.34%, respectively). Conclusions The simultaneous use of multiple aggregation operators could extract the image‐level features that lead to more stable and robust results compared with that using average and length‐weighted average. The OWA method could facilitate the explanation of derived aggregation behavior through stress functions. The kNNDOWA method could mitigate the effects of outliers in the image‐level feature extraction.