Analysis of breast CT lesions using computer-aided diagnosis: An application of neural networks on extracted morphologic and texture features

Shonket Ray, Nicolas D. Prionas, Karen K Lindfors, John M Boone

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Citations (Scopus)

Abstract

Dedicated cone-beam breast CT (bCT) scanners have been developed as a potential alternative imaging modality to conventional X-ray mammography in breast cancer diagnosis. As with other modalities, quantitative imaging (QI) analysis can potentially be utilized as a tool to extract useful numeric information concerning diagnosed lesions from high quality 3D tomographic data sets. In this work, preliminary QI analysis was done by designing and implementing a computer-aided diagnosis (CADx) system consisting of image preprocessing, object(s) of interest (i.e. masses, microcalcifications) segmentation, structural analysis of the segmented object(s), and finally classification into benign or malignant disease. Image sets were acquired from bCT patient scans with diagnosed lesions. Iterative watershed segmentation (IWS), a hybridization of the watershed method using observer-set markers and a gradient vector flow (GVF) approach, was used as the lesion segmentation method in 3D. Eight morphologic parameters and six texture features based on gray level co-occurrence matrix (GLCM) calculations were obtained per segmented lesion and combined into multi-dimensional feature input data vectors. Artificial neural network (ANN) classifiers were used by performing cross validation and network parameter optimization to maximize area under the curve (AUC) values of the resulting receiver-operating characteristic (ROC) curves. Within these ANNs, biopsy-proven diagnoses of malignant and benign lesions were recorded as target data while the feature vectors were saved as raw input data. With the image data separated into post-contrast (n = 55) and pre-contrast sets (n = 39), a maximum AUC of 0.70 ± 0.02 and 0.80 ± 0.02 were achieved, respectively, for each data set after ANN application.

Original languageEnglish (US)
Title of host publicationProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume8315
DOIs
StatePublished - 2012
EventMedical Imaging 2012: Computer-Aided Diagnosis - San Diego, CA, United States
Duration: Feb 7 2012Feb 9 2012

Other

OtherMedical Imaging 2012: Computer-Aided Diagnosis
CountryUnited States
CitySan Diego, CA
Period2/7/122/9/12

Fingerprint

Computer aided diagnosis
breast
lesions
Breast
textures
Textures
Watersheds
Neural networks
Imaging techniques
Area Under Curve
Calcinosis
Mammography
Cone-Beam Computed Tomography
Biopsy
Structural analysis
ROC Curve
curves
Cones
Classifiers
X-Rays

Keywords

  • Artificial neural network
  • Breast CT
  • Computer-aided diagnosis
  • Lesion characterization
  • Quantitative imaging

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics
  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Radiology Nuclear Medicine and imaging

Cite this

Analysis of breast CT lesions using computer-aided diagnosis : An application of neural networks on extracted morphologic and texture features. / Ray, Shonket; Prionas, Nicolas D.; Lindfors, Karen K; Boone, John M.

Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 8315 2012. 83152E.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ray, S, Prionas, ND, Lindfors, KK & Boone, JM 2012, Analysis of breast CT lesions using computer-aided diagnosis: An application of neural networks on extracted morphologic and texture features. in Progress in Biomedical Optics and Imaging - Proceedings of SPIE. vol. 8315, 83152E, Medical Imaging 2012: Computer-Aided Diagnosis, San Diego, CA, United States, 2/7/12. https://doi.org/10.1117/12.910982
Ray, Shonket ; Prionas, Nicolas D. ; Lindfors, Karen K ; Boone, John M. / Analysis of breast CT lesions using computer-aided diagnosis : An application of neural networks on extracted morphologic and texture features. Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 8315 2012.
@inproceedings{fc1611e7f9264c9c89f5258b1a4def1a,
title = "Analysis of breast CT lesions using computer-aided diagnosis: An application of neural networks on extracted morphologic and texture features",
abstract = "Dedicated cone-beam breast CT (bCT) scanners have been developed as a potential alternative imaging modality to conventional X-ray mammography in breast cancer diagnosis. As with other modalities, quantitative imaging (QI) analysis can potentially be utilized as a tool to extract useful numeric information concerning diagnosed lesions from high quality 3D tomographic data sets. In this work, preliminary QI analysis was done by designing and implementing a computer-aided diagnosis (CADx) system consisting of image preprocessing, object(s) of interest (i.e. masses, microcalcifications) segmentation, structural analysis of the segmented object(s), and finally classification into benign or malignant disease. Image sets were acquired from bCT patient scans with diagnosed lesions. Iterative watershed segmentation (IWS), a hybridization of the watershed method using observer-set markers and a gradient vector flow (GVF) approach, was used as the lesion segmentation method in 3D. Eight morphologic parameters and six texture features based on gray level co-occurrence matrix (GLCM) calculations were obtained per segmented lesion and combined into multi-dimensional feature input data vectors. Artificial neural network (ANN) classifiers were used by performing cross validation and network parameter optimization to maximize area under the curve (AUC) values of the resulting receiver-operating characteristic (ROC) curves. Within these ANNs, biopsy-proven diagnoses of malignant and benign lesions were recorded as target data while the feature vectors were saved as raw input data. With the image data separated into post-contrast (n = 55) and pre-contrast sets (n = 39), a maximum AUC of 0.70 ± 0.02 and 0.80 ± 0.02 were achieved, respectively, for each data set after ANN application.",
keywords = "Artificial neural network, Breast CT, Computer-aided diagnosis, Lesion characterization, Quantitative imaging",
author = "Shonket Ray and Prionas, {Nicolas D.} and Lindfors, {Karen K} and Boone, {John M}",
year = "2012",
doi = "10.1117/12.910982",
language = "English (US)",
isbn = "9780819489647",
volume = "8315",
booktitle = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

}

TY - GEN

T1 - Analysis of breast CT lesions using computer-aided diagnosis

T2 - An application of neural networks on extracted morphologic and texture features

AU - Ray, Shonket

AU - Prionas, Nicolas D.

AU - Lindfors, Karen K

AU - Boone, John M

PY - 2012

Y1 - 2012

N2 - Dedicated cone-beam breast CT (bCT) scanners have been developed as a potential alternative imaging modality to conventional X-ray mammography in breast cancer diagnosis. As with other modalities, quantitative imaging (QI) analysis can potentially be utilized as a tool to extract useful numeric information concerning diagnosed lesions from high quality 3D tomographic data sets. In this work, preliminary QI analysis was done by designing and implementing a computer-aided diagnosis (CADx) system consisting of image preprocessing, object(s) of interest (i.e. masses, microcalcifications) segmentation, structural analysis of the segmented object(s), and finally classification into benign or malignant disease. Image sets were acquired from bCT patient scans with diagnosed lesions. Iterative watershed segmentation (IWS), a hybridization of the watershed method using observer-set markers and a gradient vector flow (GVF) approach, was used as the lesion segmentation method in 3D. Eight morphologic parameters and six texture features based on gray level co-occurrence matrix (GLCM) calculations were obtained per segmented lesion and combined into multi-dimensional feature input data vectors. Artificial neural network (ANN) classifiers were used by performing cross validation and network parameter optimization to maximize area under the curve (AUC) values of the resulting receiver-operating characteristic (ROC) curves. Within these ANNs, biopsy-proven diagnoses of malignant and benign lesions were recorded as target data while the feature vectors were saved as raw input data. With the image data separated into post-contrast (n = 55) and pre-contrast sets (n = 39), a maximum AUC of 0.70 ± 0.02 and 0.80 ± 0.02 were achieved, respectively, for each data set after ANN application.

AB - Dedicated cone-beam breast CT (bCT) scanners have been developed as a potential alternative imaging modality to conventional X-ray mammography in breast cancer diagnosis. As with other modalities, quantitative imaging (QI) analysis can potentially be utilized as a tool to extract useful numeric information concerning diagnosed lesions from high quality 3D tomographic data sets. In this work, preliminary QI analysis was done by designing and implementing a computer-aided diagnosis (CADx) system consisting of image preprocessing, object(s) of interest (i.e. masses, microcalcifications) segmentation, structural analysis of the segmented object(s), and finally classification into benign or malignant disease. Image sets were acquired from bCT patient scans with diagnosed lesions. Iterative watershed segmentation (IWS), a hybridization of the watershed method using observer-set markers and a gradient vector flow (GVF) approach, was used as the lesion segmentation method in 3D. Eight morphologic parameters and six texture features based on gray level co-occurrence matrix (GLCM) calculations were obtained per segmented lesion and combined into multi-dimensional feature input data vectors. Artificial neural network (ANN) classifiers were used by performing cross validation and network parameter optimization to maximize area under the curve (AUC) values of the resulting receiver-operating characteristic (ROC) curves. Within these ANNs, biopsy-proven diagnoses of malignant and benign lesions were recorded as target data while the feature vectors were saved as raw input data. With the image data separated into post-contrast (n = 55) and pre-contrast sets (n = 39), a maximum AUC of 0.70 ± 0.02 and 0.80 ± 0.02 were achieved, respectively, for each data set after ANN application.

KW - Artificial neural network

KW - Breast CT

KW - Computer-aided diagnosis

KW - Lesion characterization

KW - Quantitative imaging

UR - http://www.scopus.com/inward/record.url?scp=84874829152&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84874829152&partnerID=8YFLogxK

U2 - 10.1117/12.910982

DO - 10.1117/12.910982

M3 - Conference contribution

AN - SCOPUS:84874829152

SN - 9780819489647

VL - 8315

BT - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

ER -