Academic Journal

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

التفاصيل البيبلوغرافية
العنوان: Vector textures derived from higher order derivative domains for classification of colorectal polyps
المؤلفون: Weiguo Cao, Marc J. Pomeroy, Zhengrong Liang, Almas F. Abbasi, Perry J. Pickhardt, Hongbing Lu
المصدر: Visual Computing for Industry, Biomedicine, and Art, Vol 5, Iss 1, Pp 1-14 (2022)
بيانات النشر: SpringerOpen, 2022.
سنة النشر: 2022
المجموعة: LCC:Drawing. Design. Illustration
LCC:Computer applications to medicine. Medical informatics
LCC:Computer software
مصطلحات موضوعية: Machine learning, Gradient, Hessian matrix, Haralick feature, Random forest, Image texture, Drawing. Design. Illustration, NC1-1940, Computer applications to medicine. Medical informatics, R858-859.7, Computer software, QA76.75-76.765
الوصف: Abstract 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.
نوع الوثيقة: article
وصف الملف: electronic resource
اللغة: English
تدمد: 2524-4442
Relation: https://doaj.org/toc/2524-4442
DOI: 10.1186/s42492-022-00108-1
URL الوصول: https://doaj.org/article/a78d2f730e00491e8f101826466f49ca
رقم الانضمام: edsdoj.78d2f730e00491e8f101826466f49ca
قاعدة البيانات: Directory of Open Access Journals
الوصف
تدمد:25244442
DOI:10.1186/s42492-022-00108-1