Computational cancer detection of pathological images based on an optimization method for color-index local auto-correlation feature extraction
Jia Qu, Hirokazu Nosato, Hidenori Sakanashi, Eiichi Takahashi, Kensuke Terai, Nobuyuki Hiruta · 2014
Aiming to lessen the burdens of the pathologist with efficient diagnosis assistance, this paper proposes a cancer detection method for pathological images utilizing color features based on color-index local auto-correlations (CILAC), applied to color-indexed images to utilize co-occurrence information about indexed pixels. Moreover, a method for the automatic optimization of feature extraction is also proposed. Based on a database including both benign and cancerous pathological images, experimental results show enhanced performance compared to prior research, which demonstrate the effectiveness of the proposed cancer detection method.