A dynamic lesion model for differentiation of malignant and benign pathologies

Abstract 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 th...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Weiguo Cao, Zhengrong Liang, Yongfeng Gao, Marc J. Pomeroy, Fangfang Han, Almas Abbasi, Perry J. Pickhardt
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/6eeeb9f0e11e4bf18f7064c086038263
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:6eeeb9f0e11e4bf18f7064c086038263
record_format	dspace
spelling	oai:doaj.org-article:6eeeb9f0e11e4bf18f7064c0860382632021-12-02T13:30:22ZA dynamic lesion model for differentiation of malignant and benign pathologies10.1038/s41598-021-83095-22045-2322https://doaj.org/article/6eeeb9f0e11e4bf18f7064c0860382632021-02-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-83095-2https://doaj.org/toc/2045-2322Abstract 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 tendency. The 2nd order derivatives at each image voxel are usually represented by the Hessian matrix, but it is difficult to quantify a matrix field (or image) through the lesion space as a measure of the tendency. We conjecture that the three eigenvalues contain important information of the Hessian matrix and are chosen as the surrogate representation of the Hessian matrix. By treating the three eigenvalues as a vector, called Hessian vector, which is defined in a local coordinate formed by three orthogonal Hessian eigenvectors and further adapting the gray level occurrence computing method to extract the vector texture descriptors (or measures) from the Hessian vector, a quantitative presentation for the dynamic lesion model is completed. The vector texture descriptors were applied to differentiate malignant from benign lesions from two pathologically proven datasets: colon polyps and lung nodules. The classification results not only outperform four state-of-the-art methods but also three radiologist experts.Weiguo CaoZhengrong LiangYongfeng GaoMarc J. PomeroyFangfang HanAlmas AbbasiPerry J. PickhardtNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-11 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Weiguo Cao Zhengrong Liang Yongfeng Gao Marc J. Pomeroy Fangfang Han Almas Abbasi Perry J. Pickhardt A dynamic lesion model for differentiation of malignant and benign pathologies
description	Abstract 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 tendency. The 2nd order derivatives at each image voxel are usually represented by the Hessian matrix, but it is difficult to quantify a matrix field (or image) through the lesion space as a measure of the tendency. We conjecture that the three eigenvalues contain important information of the Hessian matrix and are chosen as the surrogate representation of the Hessian matrix. By treating the three eigenvalues as a vector, called Hessian vector, which is defined in a local coordinate formed by three orthogonal Hessian eigenvectors and further adapting the gray level occurrence computing method to extract the vector texture descriptors (or measures) from the Hessian vector, a quantitative presentation for the dynamic lesion model is completed. The vector texture descriptors were applied to differentiate malignant from benign lesions from two pathologically proven datasets: colon polyps and lung nodules. The classification results not only outperform four state-of-the-art methods but also three radiologist experts.
format	article
author	Weiguo Cao Zhengrong Liang Yongfeng Gao Marc J. Pomeroy Fangfang Han Almas Abbasi Perry J. Pickhardt
author_facet	Weiguo Cao Zhengrong Liang Yongfeng Gao Marc J. Pomeroy Fangfang Han Almas Abbasi Perry J. Pickhardt
author_sort	Weiguo Cao
title	A dynamic lesion model for differentiation of malignant and benign pathologies
title_short	A dynamic lesion model for differentiation of malignant and benign pathologies
title_full	A dynamic lesion model for differentiation of malignant and benign pathologies
title_fullStr	A dynamic lesion model for differentiation of malignant and benign pathologies
title_full_unstemmed	A dynamic lesion model for differentiation of malignant and benign pathologies
title_sort	dynamic lesion model for differentiation of malignant and benign pathologies
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/6eeeb9f0e11e4bf18f7064c086038263
work_keys_str_mv	AT weiguocao adynamiclesionmodelfordifferentiationofmalignantandbenignpathologies AT zhengrongliang adynamiclesionmodelfordifferentiationofmalignantandbenignpathologies AT yongfenggao adynamiclesionmodelfordifferentiationofmalignantandbenignpathologies AT marcjpomeroy adynamiclesionmodelfordifferentiationofmalignantandbenignpathologies AT fangfanghan adynamiclesionmodelfordifferentiationofmalignantandbenignpathologies AT almasabbasi adynamiclesionmodelfordifferentiationofmalignantandbenignpathologies AT perryjpickhardt adynamiclesionmodelfordifferentiationofmalignantandbenignpathologies AT weiguocao dynamiclesionmodelfordifferentiationofmalignantandbenignpathologies AT zhengrongliang dynamiclesionmodelfordifferentiationofmalignantandbenignpathologies AT yongfenggao dynamiclesionmodelfordifferentiationofmalignantandbenignpathologies AT marcjpomeroy dynamiclesionmodelfordifferentiationofmalignantandbenignpathologies AT fangfanghan dynamiclesionmodelfordifferentiationofmalignantandbenignpathologies AT almasabbasi dynamiclesionmodelfordifferentiationofmalignantandbenignpathologies AT perryjpickhardt dynamiclesionmodelfordifferentiationofmalignantandbenignpathologies
_version_	1718392921459261440

A dynamic lesion model for differentiation of malignant and benign pathologies

Ejemplares similares