Mining hidden data to predict patient prognosis: texture feature extraction and machine learning in mammography

J. A. Leighs; M. D. Halling-Brown; M. N. Patel

doi:10.1117/12.2293523

6 March 2018 Mining hidden data to predict patient prognosis: texture feature extraction and machine learning in mammography

J. A. Leighs, M. D. Halling-Brown, M. N. Patel

Author Affiliations +

Proceedings Volume 10579, Medical Imaging 2018: Imaging Informatics for Healthcare, Research, and Applications; 105790W (2018) https://doi.org/10.1117/12.2293523
Event: SPIE Medical Imaging, 2018, Houston, Texas, United States

Abstract

The UK currently has a national breast cancer-screening program and images are routinely collected from a number of screening sites, representing a wealth of invaluable data that is currently under-used. Radiologists evaluate screening images manually and recall suspicious cases for further analysis such as biopsy. Histological testing of biopsy samples confirms the malignancy of the tumour, along with other diagnostic and prognostic characteristics such as disease grade. Machine learning is becoming increasingly popular for clinical image classification problems, as it is capable of discovering patterns in data otherwise invisible. This is particularly true when applied to medical imaging features; however clinical datasets are often relatively small. A texture feature extraction toolkit has been developed to mine a wide range of features from medical images such as mammograms. This study analysed a dataset of 1,366 radiologist-marked, biopsy-proven malignant lesions obtained from the OPTIMAM Medical Image Database (OMI-DB). Exploratory data analysis methods were employed to better understand extracted features. Machine learning techniques including Classification and Regression Trees (CART), ensemble methods (e.g. random forests), and logistic regression were applied to the data to predict the disease grade of the analysed lesions. Prediction scores of up to 83% were achieved; sensitivity and specificity of the models trained have been discussed to put the results into a clinical context. The results show promise in the ability to predict prognostic indicators from the texture features extracted and thus enable prioritisation of care for patients at greatest risk.

Conference Presentation

Citation Download Citation

J. A. Leighs, M. D. Halling-Brown, and M. N. Patel "Mining hidden data to predict patient prognosis: texture feature extraction and machine learning in mammography", Proc. SPIE 10579, Medical Imaging 2018: Imaging Informatics for Healthcare, Research, and Applications, 105790W (6 March 2018); https://doi.org/10.1117/12.2293523

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available