A dynamic lesion model for differentiation of malignant and benign pathologies

• Published in: Scientific reports Vol. 11; no. 1; pp. 3485 - 11
• Main Authors: Cao, Weiguo, Liang, Zhengrong, Gao, Yongfeng, Pomeroy, Marc J., Han, Fangfang, Abbasi, Almas, Pickhardt, Perry J.
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 10.02.2021; Nature Publishing Group; Nature Portfolio
• Subjects: 631/67/2322; 639/166/985; 692/308/2778; Algorithms; Colon; Colonic Polyps - diagnosis; Colonic Polyps - pathology; Diagnosis, Computer-Assisted; Eigenvalues; Humanities and Social Sciences; Humans; Lesions; Lung nodules; Mathematical Concepts; Models, Biological; multidisciplinary; Neoplasm Invasiveness; Neoplasms - diagnosis; Neoplasms - pathology; Polyps; Science; Science (multidisciplinary); Solitary Pulmonary Nodule - diagnosis; Solitary Pulmonary Nodule - pathology

Malignant lesions have a high tendency to invade their surrounding environment compared to benign ones. This paper proposes a dynamic lesion model and explores the 2nd order derivatives at each image voxel, which reflect the rate of change of image intensity, as a quantitative measure of the tendenc...