Energy enhanced tissue texture in spectral computed tomography for lesion classification

Abstract Tissue texture reflects the spatial distribution of contrasts of image voxel gray levels, i.e., the tissue heterogeneity, and has been recognized as important biomarkers in various clinical tasks. Spectral computed tomography (CT) is believed to be able to enrich tissue texture by providing...

Full description

Bibliographic Details
Main Authors: Yongfeng Gao, Yongyi Shi, Weiguo Cao, Shu Zhang, Zhengrong Liang
Format: Article
Language:English
Published: SpringerOpen 2019-11-01
Series:Visual Computing for Industry, Biomedicine, and Art
Subjects:
Online Access:http://link.springer.com/article/10.1186/s42492-019-0028-3
id doaj-621bfda1eb67406f90f8cc91d2a9f958
record_format Article
spelling doaj-621bfda1eb67406f90f8cc91d2a9f9582020-11-25T04:03:47ZengSpringerOpenVisual Computing for Industry, Biomedicine, and Art2524-44422019-11-012111210.1186/s42492-019-0028-3Energy enhanced tissue texture in spectral computed tomography for lesion classificationYongfeng Gao0Yongyi Shi1Weiguo Cao2Shu Zhang3Zhengrong Liang4Department of Radiology, Stony Brook UniversityDepartment of Radiology, Stony Brook UniversityDepartment of Radiology, Stony Brook UniversityDepartment of Radiology, Stony Brook UniversityDepartments of Radiology, Biomedical Engineering, Computer Science, and Electrical Engineering, Stony Brook UniversityAbstract Tissue texture reflects the spatial distribution of contrasts of image voxel gray levels, i.e., the tissue heterogeneity, and has been recognized as important biomarkers in various clinical tasks. Spectral computed tomography (CT) is believed to be able to enrich tissue texture by providing different voxel contrast images using different X-ray energies. Therefore, this paper aims to address two related issues for clinical usage of spectral CT, especially the photon counting CT (PCCT): (1) texture enhancement by spectral CT image reconstruction, and (2) spectral energy enriched tissue texture for improved lesion classification. For issue (1), we recently proposed a tissue-specific texture prior in addition to low rank prior for the individual energy-channel low-count image reconstruction problems in PCCT under the Bayesian theory. Reconstruction results showed the proposed method outperforms existing methods of total variation (TV), low-rank TV and tensor dictionary learning in terms of not only preserving texture features but also suppressing image noise. For issue (2), this paper will investigate three models to incorporate the enriched texture by PCCT in accordance with three types of inputs: one is the spectral images, another is the co-occurrence matrices (CMs) extracted from the spectral images, and the third one is the Haralick features (HF) extracted from the CMs. Studies were performed on simulated photon counting data by introducing attenuation-energy response curve to the traditional CT images from energy integration detectors. Classification results showed the spectral CT enriched texture model can improve the area under the receiver operating characteristic curve (AUC) score by 7.3%, 0.42% and 3.0% for the spectral images, CMs and HFs respectively on the five-energy spectral data over the original single energy data only. The CM- and HF-inputs can achieve the best AUC of 0.934 and 0.927. This texture themed study shows the insight that incorporating clinical important prior information, e.g., tissue texture in this paper, into the medical imaging, such as the upstream image reconstruction, the downstream diagnosis, and so on, can benefit the clinical tasks.http://link.springer.com/article/10.1186/s42492-019-0028-3Tissue textureSpectral computed tomographyLesion classificationMachine learningBayesian reconstruction
collection DOAJ
language English
format Article
sources DOAJ
author Yongfeng Gao
Yongyi Shi
Weiguo Cao
Shu Zhang
Zhengrong Liang
spellingShingle Yongfeng Gao
Yongyi Shi
Weiguo Cao
Shu Zhang
Zhengrong Liang
Energy enhanced tissue texture in spectral computed tomography for lesion classification
Visual Computing for Industry, Biomedicine, and Art
Tissue texture
Spectral computed tomography
Lesion classification
Machine learning
Bayesian reconstruction
author_facet Yongfeng Gao
Yongyi Shi
Weiguo Cao
Shu Zhang
Zhengrong Liang
author_sort Yongfeng Gao
title Energy enhanced tissue texture in spectral computed tomography for lesion classification
title_short Energy enhanced tissue texture in spectral computed tomography for lesion classification
title_full Energy enhanced tissue texture in spectral computed tomography for lesion classification
title_fullStr Energy enhanced tissue texture in spectral computed tomography for lesion classification
title_full_unstemmed Energy enhanced tissue texture in spectral computed tomography for lesion classification
title_sort energy enhanced tissue texture in spectral computed tomography for lesion classification
publisher SpringerOpen
series Visual Computing for Industry, Biomedicine, and Art
issn 2524-4442
publishDate 2019-11-01
description Abstract Tissue texture reflects the spatial distribution of contrasts of image voxel gray levels, i.e., the tissue heterogeneity, and has been recognized as important biomarkers in various clinical tasks. Spectral computed tomography (CT) is believed to be able to enrich tissue texture by providing different voxel contrast images using different X-ray energies. Therefore, this paper aims to address two related issues for clinical usage of spectral CT, especially the photon counting CT (PCCT): (1) texture enhancement by spectral CT image reconstruction, and (2) spectral energy enriched tissue texture for improved lesion classification. For issue (1), we recently proposed a tissue-specific texture prior in addition to low rank prior for the individual energy-channel low-count image reconstruction problems in PCCT under the Bayesian theory. Reconstruction results showed the proposed method outperforms existing methods of total variation (TV), low-rank TV and tensor dictionary learning in terms of not only preserving texture features but also suppressing image noise. For issue (2), this paper will investigate three models to incorporate the enriched texture by PCCT in accordance with three types of inputs: one is the spectral images, another is the co-occurrence matrices (CMs) extracted from the spectral images, and the third one is the Haralick features (HF) extracted from the CMs. Studies were performed on simulated photon counting data by introducing attenuation-energy response curve to the traditional CT images from energy integration detectors. Classification results showed the spectral CT enriched texture model can improve the area under the receiver operating characteristic curve (AUC) score by 7.3%, 0.42% and 3.0% for the spectral images, CMs and HFs respectively on the five-energy spectral data over the original single energy data only. The CM- and HF-inputs can achieve the best AUC of 0.934 and 0.927. This texture themed study shows the insight that incorporating clinical important prior information, e.g., tissue texture in this paper, into the medical imaging, such as the upstream image reconstruction, the downstream diagnosis, and so on, can benefit the clinical tasks.
topic Tissue texture
Spectral computed tomography
Lesion classification
Machine learning
Bayesian reconstruction
url http://link.springer.com/article/10.1186/s42492-019-0028-3
work_keys_str_mv AT yongfenggao energyenhancedtissuetextureinspectralcomputedtomographyforlesionclassification
AT yongyishi energyenhancedtissuetextureinspectralcomputedtomographyforlesionclassification
AT weiguocao energyenhancedtissuetextureinspectralcomputedtomographyforlesionclassification
AT shuzhang energyenhancedtissuetextureinspectralcomputedtomographyforlesionclassification
AT zhengrongliang energyenhancedtissuetextureinspectralcomputedtomographyforlesionclassification
_version_ 1724439300712431616