Improved characterization of molecular phenotypes in breast lesions using 18F-FDG PET image homogeneity Conference Paper
| Authors: | Cao, K.; Bhagalia, R.; Sood, A.; Brogi, E.; Mellinghoff, I. K.; Larson, S. M. |
| Title: | Improved characterization of molecular phenotypes in breast lesions using 18F-FDG PET image homogeneity |
| Conference Title: | Medical Imaging 2015: Biomedical Applications in Molecular, Structural, and Functional Imaging |
| Abstract: | Positron emission tomography (PET) using uorodeoxyglucose (18F-FDG) is commonly used in the assessment of breast lesions by computing voxel-wise standardized uptake value (SUV) maps. Simple metrics derived from ensemble properties of SUVs within each identified breast lesion are routinely used for disease diagnosis. The maximum SUV within the lesion (SUVmax) is the most popular of these metrics. However these simple metrics are known to be error-prone and are susceptible to image noise. Finding reliable SUV map-based features that correlate to established molecular phenotypes of breast cancer (viz. estrogen receptor (ER), progesterone receptor (PR) and human epidermal growth factor receptor 2 (HER2) expression) will enable non-invasive disease management. This study investigated 36 SUV features based on first and second order statistics, local histograms and texture of segmented lesions to predict ER and PR expression in 51 breast cancer patients. True ER and PR expression was obtained via immunohistochemistry (IHC) of tissue samples from each lesion. A supervised learning, adaptive boosting-support vector machine (AdaBoost-SVM), framework was used to select a subset of features to classify breast lesions into distinct phenotypes. Performance of the trained multi-feature classifier was compared against the baseline single-feature SUVmax classifier using receiver operating characteristic (ROC) curves. Results show that texture features encoding local lesion homogeneity extracted from gray-level co-occurrence matrices are the strongest discriminator of lesion ER expression. In particular, classifiers including these features increased prediction accuracy from 0.75 (baseline) to 0.82 and the area under the ROC curve from 0.64 (baseline) to 0.75. © 2015 SPIE. |
| Keywords: | positron emission tomography; molecular imaging; medical imaging; diagnosis; progesterone receptor; pet; diseases; support vector machines; positron emission tomography (pet); standardized uptake values; medical applications; 18f-fdg; feature extraction; classification (of information); polyethylene terephthalates; receiver operating characteristic curves; human epidermal growth factor receptor 2 (her2); area under the roc curve; adaptive boosting; feature selection; adaboost; gray-level co-occurrence matrix; second order statistics |
| Journal Title | Proceedings of SPIE |
| Volume: | 9417 |
| Conference Dates: | 2015 Feb 22-24 |
| Conference Location: | Orlando, FL |
| ISBN: | 0277-786X |
| Publisher: | SPIE |
| Date Published: | 2015-03-17 |
| Start Page: | 941712 |
| Language: | English |
| DOI: | 10.1117/12.2081940 |
| PROVIDER: | scopus |
| DOI/URL: | |
| Notes: | Source: Scopus |
Altmetric
Citation Impact
BMJ Impact Analytics
MSK Authors
-
269Mellinghoff -
515Brogi -
958Larson
Related MSK Work