Parameter optimization of parenchymal texture analysis for prediction of false-positive recalls from screening mammography

Shonket Ray; Brad M. Keller; Jinbo Chen; Emily F. Conant; Despina Kontos

doi:10.1117/12.2216856

Translator Disclaimer

24 March 2016 Parameter optimization of parenchymal texture analysis for prediction of false-positive recalls from screening mammography

Shonket Ray, Brad M. Keller, Jinbo Chen, Emily F. Conant, Despina Kontos

Author Affiliations +

Proceedings Volume 9785, Medical Imaging 2016: Computer-Aided Diagnosis; 97851Y (2016) https://doi.org/10.1117/12.2216856
Event: SPIE Medical Imaging, 2016, San Diego, California, United States

Abstract

This work details a methodology to obtain optimal parameter values for a locally-adaptive texture analysis algorithm that extracts mammographic texture features representative of breast parenchymal complexity for predicting falsepositive (FP) recalls from breast cancer screening with digital mammography. The algorithm has two components: (1) adaptive selection of localized regions of interest (ROIs) and (2) Haralick texture feature extraction via Gray- Level Co-Occurrence Matrices (GLCM). The following parameters were systematically varied: mammographic views used, upper limit of the ROI window size used for adaptive ROI selection, GLCM distance offsets, and gray levels (binning) used for feature extraction. Each iteration per parameter set had logistic regression with stepwise feature selection performed on a clinical screening cohort of 474 non-recalled women and 68 FP recalled women; FP recall prediction was evaluated using area under the curve (AUC) of the receiver operating characteristic (ROC) and associations between the extracted features and FP recall were assessed via odds ratios (OR). A default instance of mediolateral (MLO) view, upper ROI size limit of 143.36 mm (2048 pixels²), GLCM distance offset combination range of 0.07 to 0.84 mm (1 to 12 pixels) and 16 GLCM gray levels was set. The highest ROC performance value of AUC=0.77 [95% confidence intervals: 0.71-0.83] was obtained at three specific instances: the default instance, upper ROI window equal to 17.92 mm (256 pixels²), and gray levels set to 128. The texture feature of sum average was chosen as a statistically significant (p<0.05) predictor and associated with higher odds of FP recall for 12 out of 14 total instances.

Citation Download Citation

Shonket Ray, Brad M. Keller, Jinbo Chen, Emily F. Conant, and Despina Kontos "Parameter optimization of parenchymal texture analysis for prediction of false-positive recalls from screening mammography", Proc. SPIE 9785, Medical Imaging 2016: Computer-Aided Diagnosis, 97851Y (24 March 2016); https://doi.org/10.1117/12.2216856

ACCESS THE FULL ARTICLE