TY - GEN
T1 - Bayesian classifiers of solid lesions with dynamic CT
T2 - 15th IEEE International Symposium on Biomedical Imaging, ISBI 2018
AU - Chen, Nan
AU - Ng, Chaan
AU - Hobbs, Brian Paul
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/5/23
Y1 - 2018/5/23
N2 - Solid lesions emerge within diverse host tissue environments, making their diagnosis a challenge on the basis of non-invasive techniques alone. Various techniques have been developed to transform images into quantifiable feature sets producing summary statistics that describe enhancement distributions of solid masses. Relying on empirical distributional summaries, conventional approaches to cancer radiomics analysis are limited by the application of regression or machine learning algorithms to correlated feature sets. Moreover, often relying on summary statistics that derive from a single scan, current analytical approaches ignore temporal patterns that describe washout across multiple scans with contrast. Motivated by the diagnosis of adrenal masses on the basis of dynamic contrast enhanced computed tomography, this article presents novel statistical methodology for formulating similarity networks that integrate the entire enhancement and washout distributions of a delineated region of interest (ROI) with the duration of the delay scan interval. Applying consensus clustering to the network, we demonstrate unsupervised learning, revealing five discrete patterns of the combination of non-contrast enhancement distribution and contrast washout. Additionally, we demonstrate how the resultant network may be used to train a supervised Bayesian classifier based on the concept of partial exchangeability. When applied to predict the true pathology-verified malignancy status of adrenal lesions in our study, classification using Bayesian predictive probabilities deriving from the similarity network yielded an area under the ROC curve of 0.908 outperforming prediction with conventional regression analysis based on summary statistics of the enhancement densities, which yielded only 0.828.
AB - Solid lesions emerge within diverse host tissue environments, making their diagnosis a challenge on the basis of non-invasive techniques alone. Various techniques have been developed to transform images into quantifiable feature sets producing summary statistics that describe enhancement distributions of solid masses. Relying on empirical distributional summaries, conventional approaches to cancer radiomics analysis are limited by the application of regression or machine learning algorithms to correlated feature sets. Moreover, often relying on summary statistics that derive from a single scan, current analytical approaches ignore temporal patterns that describe washout across multiple scans with contrast. Motivated by the diagnosis of adrenal masses on the basis of dynamic contrast enhanced computed tomography, this article presents novel statistical methodology for formulating similarity networks that integrate the entire enhancement and washout distributions of a delineated region of interest (ROI) with the duration of the delay scan interval. Applying consensus clustering to the network, we demonstrate unsupervised learning, revealing five discrete patterns of the combination of non-contrast enhancement distribution and contrast washout. Additionally, we demonstrate how the resultant network may be used to train a supervised Bayesian classifier based on the concept of partial exchangeability. When applied to predict the true pathology-verified malignancy status of adrenal lesions in our study, classification using Bayesian predictive probabilities deriving from the similarity network yielded an area under the ROC curve of 0.908 outperforming prediction with conventional regression analysis based on summary statistics of the enhancement densities, which yielded only 0.828.
KW - Adrenal Cancer
KW - Bayesian Predictive Probability
KW - Cancer Radiomics
KW - Diagnostic Radiology
KW - Kullback-Leibler Divergence
UR - http://www.scopus.com/inward/record.url?scp=85048120778&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85048120778&partnerID=8YFLogxK
U2 - 10.1109/ISBI.2018.8363563
DO - 10.1109/ISBI.2018.8363563
M3 - Conference contribution
AN - SCOPUS:85048120778
T3 - Proceedings - International Symposium on Biomedical Imaging
SP - 236
EP - 239
BT - 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018
PB - IEEE Computer Society
Y2 - 4 April 2018 through 7 April 2018
ER -