Computer-Aided Diagnosis of Diagnostically Challenging Lesions in Breast MRI: A Comparison between a Radiomics and a Feature-Selective Approach

S. Hoffmann; M. Lobbes; I. Houben; K. Pinker-Domenig; G. Wengert; B. Burgeth; U. Meyer-Base; G. Lemaitre; A. Meyer-Baese

doi:10.1117/12.2228994

Computer-Aided Diagnosis of Diagnostically Challenging Lesions in Breast MRI: A Comparison between a Radiomics and a Feature-Selective Approach

S. Hoffmann^*, M. Lobbes, I. Houben, K. Pinker-Domenig, G. Wengert, B. Burgeth, U. Meyer-Base, G. Lemaitre, A. Meyer-Baese

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceeding › Academic › peer-review

Abstract

Diagnostically challenging lesions pose a challenge both for the radiological reading and also for current CAD systems. They are not well-defined in both morphology (geometric shape) and kinetics (temporal enhancement) and pose a problem to lesion detection and classification. Their strong phenotypic differences can be visualized by MRI. Radiomics represents a novel approach to achieve a detailed quantification of the tumour phenotypes by analyzing a large number of image descriptors. In this paper, we apply a quantitative radiomics approach based on shape, texture and kinetics tumor features and evaluate it in comparison to a reduced-order feature approach in a computer-aided diagnosis system applied to diagnostically challenging lesions.

Original language	English
Title of host publication	SENSING AND ANALYSIS TECHNOLOGIES FOR BIOMEDICAL AND COGNITIVE APPLICATIONS 2016
Editors	Liyi Dai, Yufeng Zheng, Henry Chu, Anke D. Meyer-Bäse
Publisher	SPIE-INT SOC OPTICAL ENGINEERING
Number of pages	7
Volume	9871
ISBN (Print)	9781510601123
DOIs	https://doi.org/10.1117/12.2228994
Publication status	Published - 2016
Event	Conference on Sensing and Analysis Technologies for Biomedical and Cognitive Applications - Baltimore, United States Duration: 17 Apr 2016 → 18 Apr 2016

Publication series

Series	Proceedings of SPIE
Number	98710H
Volume	9871
ISSN	0277-786X

Conference

Conference	Conference on Sensing and Analysis Technologies for Biomedical and Cognitive Applications
Country/Territory	United States
City	Baltimore
Period	17/04/16 → 18/04/16

Keywords

Diagnostically challenging lesions
morphological and kinetic features
classification
computer-aided diagnosis
radiomics
breast magnetic resonance imaging
ENHANCEMENT
TOOL

Access to Document

10.1117/12.2228994

Cite this

Hoffmann, S., Lobbes, M., Houben, I., Pinker-Domenig, K., Wengert, G., Burgeth, B., Meyer-Base, U., Lemaitre, G., & Meyer-Baese, A. (2016). Computer-Aided Diagnosis of Diagnostically Challenging Lesions in Breast MRI: A Comparison between a Radiomics and a Feature-Selective Approach. In L. Dai, Y. Zheng, H. Chu, & A. D. Meyer-Bäse (Eds.), SENSING AND ANALYSIS TECHNOLOGIES FOR BIOMEDICAL AND COGNITIVE APPLICATIONS 2016 (Vol. 9871). SPIE-INT SOC OPTICAL ENGINEERING. https://doi.org/10.1117/12.2228994

Hoffmann, S. ; Lobbes, M. ; Houben, I. et al. / Computer-Aided Diagnosis of Diagnostically Challenging Lesions in Breast MRI: A Comparison between a Radiomics and a Feature-Selective Approach. SENSING AND ANALYSIS TECHNOLOGIES FOR BIOMEDICAL AND COGNITIVE APPLICATIONS 2016. editor / Liyi Dai ; Yufeng Zheng ; Henry Chu ; Anke D. Meyer-Bäse. Vol. 9871 SPIE-INT SOC OPTICAL ENGINEERING, 2016. (Proceedings of SPIE; No. 98710H, Vol. 9871).

@inproceedings{d21be629d8304bda8d1442ee3741432b,

title = "Computer-Aided Diagnosis of Diagnostically Challenging Lesions in Breast MRI: A Comparison between a Radiomics and a Feature-Selective Approach",

abstract = "Diagnostically challenging lesions pose a challenge both for the radiological reading and also for current CAD systems. They are not well-defined in both morphology (geometric shape) and kinetics (temporal enhancement) and pose a problem to lesion detection and classification. Their strong phenotypic differences can be visualized by MRI. Radiomics represents a novel approach to achieve a detailed quantification of the tumour phenotypes by analyzing a large number of image descriptors. In this paper, we apply a quantitative radiomics approach based on shape, texture and kinetics tumor features and evaluate it in comparison to a reduced-order feature approach in a computer-aided diagnosis system applied to diagnostically challenging lesions.",

keywords = "Diagnostically challenging lesions, morphological and kinetic features, classification, computer-aided diagnosis, radiomics, breast magnetic resonance imaging, ENHANCEMENT, TOOL",

author = "S. Hoffmann and M. Lobbes and I. Houben and K. Pinker-Domenig and G. Wengert and B. Burgeth and U. Meyer-Base and G. Lemaitre and A. Meyer-Baese",

year = "2016",

doi = "10.1117/12.2228994",

language = "English",

isbn = "9781510601123",

volume = "9871",

series = "Proceedings of SPIE",

publisher = "SPIE-INT SOC OPTICAL ENGINEERING",

number = "98710H",

editor = "Liyi Dai and Yufeng Zheng and Henry Chu and Meyer-B{\"a}se, {Anke D.}",

booktitle = "SENSING AND ANALYSIS TECHNOLOGIES FOR BIOMEDICAL AND COGNITIVE APPLICATIONS 2016",

note = "Conference on Sensing and Analysis Technologies for Biomedical and Cognitive Applications ; Conference date: 17-04-2016 Through 18-04-2016",

}

Hoffmann, S, Lobbes, M, Houben, I, Pinker-Domenig, K, Wengert, G, Burgeth, B, Meyer-Base, U, Lemaitre, G & Meyer-Baese, A 2016, Computer-Aided Diagnosis of Diagnostically Challenging Lesions in Breast MRI: A Comparison between a Radiomics and a Feature-Selective Approach. in L Dai, Y Zheng, H Chu & AD Meyer-Bäse (eds), SENSING AND ANALYSIS TECHNOLOGIES FOR BIOMEDICAL AND COGNITIVE APPLICATIONS 2016. vol. 9871, SPIE-INT SOC OPTICAL ENGINEERING, Proceedings of SPIE, no. 98710H, vol. 9871, Conference on Sensing and Analysis Technologies for Biomedical and Cognitive Applications, Baltimore, Maryland, United States, 17/04/16. https://doi.org/10.1117/12.2228994

Computer-Aided Diagnosis of Diagnostically Challenging Lesions in Breast MRI: A Comparison between a Radiomics and a Feature-Selective Approach. / Hoffmann, S.; Lobbes, M.; Houben, I. et al.
SENSING AND ANALYSIS TECHNOLOGIES FOR BIOMEDICAL AND COGNITIVE APPLICATIONS 2016. ed. / Liyi Dai; Yufeng Zheng; Henry Chu; Anke D. Meyer-Bäse. Vol. 9871 SPIE-INT SOC OPTICAL ENGINEERING, 2016. (Proceedings of SPIE; No. 98710H, Vol. 9871).

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceeding › Academic › peer-review

TY - GEN

T1 - Computer-Aided Diagnosis of Diagnostically Challenging Lesions in Breast MRI: A Comparison between a Radiomics and a Feature-Selective Approach

AU - Hoffmann, S.

AU - Lobbes, M.

AU - Houben, I.

AU - Pinker-Domenig, K.

AU - Wengert, G.

AU - Burgeth, B.

AU - Meyer-Base, U.

AU - Lemaitre, G.

AU - Meyer-Baese, A.

PY - 2016

Y1 - 2016

N2 - Diagnostically challenging lesions pose a challenge both for the radiological reading and also for current CAD systems. They are not well-defined in both morphology (geometric shape) and kinetics (temporal enhancement) and pose a problem to lesion detection and classification. Their strong phenotypic differences can be visualized by MRI. Radiomics represents a novel approach to achieve a detailed quantification of the tumour phenotypes by analyzing a large number of image descriptors. In this paper, we apply a quantitative radiomics approach based on shape, texture and kinetics tumor features and evaluate it in comparison to a reduced-order feature approach in a computer-aided diagnosis system applied to diagnostically challenging lesions.

AB - Diagnostically challenging lesions pose a challenge both for the radiological reading and also for current CAD systems. They are not well-defined in both morphology (geometric shape) and kinetics (temporal enhancement) and pose a problem to lesion detection and classification. Their strong phenotypic differences can be visualized by MRI. Radiomics represents a novel approach to achieve a detailed quantification of the tumour phenotypes by analyzing a large number of image descriptors. In this paper, we apply a quantitative radiomics approach based on shape, texture and kinetics tumor features and evaluate it in comparison to a reduced-order feature approach in a computer-aided diagnosis system applied to diagnostically challenging lesions.

KW - Diagnostically challenging lesions

KW - morphological and kinetic features

KW - classification

KW - computer-aided diagnosis

KW - radiomics

KW - breast magnetic resonance imaging

KW - ENHANCEMENT

KW - TOOL

U2 - 10.1117/12.2228994

DO - 10.1117/12.2228994

M3 - Conference article in proceeding

SN - 9781510601123

VL - 9871

T3 - Proceedings of SPIE

BT - SENSING AND ANALYSIS TECHNOLOGIES FOR BIOMEDICAL AND COGNITIVE APPLICATIONS 2016

A2 - Dai, Liyi

A2 - Zheng, Yufeng

A2 - Chu, Henry

A2 - Meyer-Bäse, Anke D.

PB - SPIE-INT SOC OPTICAL ENGINEERING

T2 - Conference on Sensing and Analysis Technologies for Biomedical and Cognitive Applications

Y2 - 17 April 2016 through 18 April 2016

ER -

Hoffmann S, Lobbes M, Houben I, Pinker-Domenig K, Wengert G, Burgeth B et al. Computer-Aided Diagnosis of Diagnostically Challenging Lesions in Breast MRI: A Comparison between a Radiomics and a Feature-Selective Approach. In Dai L, Zheng Y, Chu H, Meyer-Bäse AD, editors, SENSING AND ANALYSIS TECHNOLOGIES FOR BIOMEDICAL AND COGNITIVE APPLICATIONS 2016. Vol. 9871. SPIE-INT SOC OPTICAL ENGINEERING. 2016. (Proceedings of SPIE; No. 98710H, Vol. 9871). doi: 10.1117/12.2228994

Computer-Aided Diagnosis of Diagnostically Challenging Lesions in Breast MRI: A Comparison between a Radiomics and a Feature-Selective Approach

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this