Vector textures derived from higher order derivative domains for classification of colorectal polyps

• Published in: Visual computing for industry, biomedicine and art biomedicine and art, 2022-06, Vol.5 (1), p.16-16, Article 16
• Main Authors: Cao, Weiguo, Pomeroy, Marc J., Liang, Zhengrong, Abbasi, Almas F., Pickhardt, Perry J., Lu, Hongbing
• Format: Article
• Language: English
• Subjects: AI based precision diagnosis; CAE) and Design; Classification; Computed tomography; Computer Graphics; Computer Imaging; Computer Science; Computer-Aided Engineering (CAD; Differential equations; Gradient; Haralick feature; Hessian matrices; Hessian matrix; Image contrast; Image Processing and Computer Vision; Image texture; Lesions; Machine learning; Mathematical analysis; Media Design; Operators (mathematics); Original; Original Article; Pattern Recognition and Graphics; Performance evaluation; Polyps; Random forest; Texture; Vision
• ISSN: 2524-4442; 2096-496X; 2524-4442
• DOI: 10.1186/s42492-022-00108-1

Textures have become widely adopted as an essential tool for lesion detection and classification through analysis of the lesion heterogeneities. In this study, higher order derivative images are being employed to combat the challenge of the poor contrast across similar tissue types among certain imaging modalities. To make good use of the derivative information, a novel concept of vector texture is firstly introduced to construct and extract several types of polyp descriptors. Two widely used differential operators, i.e., the gradient operator and Hessian operator, are utilized to generate the first and second order derivative images. These derivative volumetric images are used to produce two angle-based and two vector-based (including both angle and magnitude) textures. Next, a vector-based co-occurrence matrix is proposed to extract texture features which are fed to a random forest classifier to perform polyp classifications. To evaluate the performance of our method, experiments are implemented over a private colorectal polyp dataset obtained from computed tomographic colonography. We compare our method with four existing state-of-the-art methods and find that our method can outperform those competing methods over 4%-13% evaluated by the area under the receiver operating characteristics curves.