A Deep Learning-Based Decision Support Tool for Precision Risk Assessment of Breast Cancer.

PURPOSE The Breast Imaging Reporting and Data System (BI-RADS) lexicon was developed to standardize mammographic reporting to assess cancer risk and facilitate the decision to biopsy. Because of substantial interobserver variability in the application of the BI-RADS lexicon, the decision to biopsy varies greatly and results in overdiagnosis and excessive biopsies. The false-positive rate from mammograms is estimated to be 7% to approximately 10% overall, but within the BI-RADS 4 category, it is greater than 70%. Therefore, we developed the Breast Cancer Risk Calculator (BRISK) to target a well-characterized and specific patient subgroup (BI-RADS 4) rather than a broad heterogeneous group in assessing breast cancer risk. METHODS BRISK provides a novel precise risk assessment model to reduce overdiagnosis and unnecessary biopsies. It was developed by applying natural language processing and deep learning methods on 5,147 patient records archived in the Houston Methodist systemwide data warehouse from 2006 to May 2015, including imaging and pathology reports, mammographic images, and patient demographics. Key characteristics for BI-RADS 4 patients were collected and computed to output an index measure for biopsy recommendation that is clinically relevant and informative and improves upon the traditional BI-RADS 4 scores. RESULTS For the validation set, we assessed data from 1,247 BI-RADS 4 patients, including mammographic images and medical reports. The BRISK model sensitivity to predict malignancy was 100%, whereas the specificity was 74%. The total accuracy of our implemented model in BRISK was 81%. Overall area under the curve was 0.93. CONCLUSION BRISK for abnormal mammogram uses integrative artificial intelligence technology and has demonstrated high sensitivity in the prediction of malignancy. Prospective evaluation is under way and can lead to improvement in patient-physician engagement in making informed decisions with regard to biopsy.

[1]  J. Weigert,et al.  The Connecticut Experiment: The Role of Ultrasound in the Screening of Women With Dense Breasts , 2012, The breast journal.

[2]  Catarina Eloy,et al.  Classification of breast cancer histology images using Convolutional Neural Networks , 2017, PloS one.

[3]  K. Mandl,et al.  National expenditure for false-positive mammograms and breast cancer overdiagnoses estimated at $4 billion a year. , 2015, Health affairs.

[4]  B. Levin,et al.  American Cancer Society Guidelines for the Early Detection of Cancer , 2002, CA: a cancer journal for clinicians.

[5]  K. Chew,et al.  High mammographic breast density is independent predictor of local but not distant recurrence after lumpectomy and radiotherapy for invasive breast cancer. , 2009, International journal of radiation oncology, biology, physics.

[6]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[7]  Yoshua Bengio,et al.  Extracting and composing robust features with denoising autoencoders , 2008, ICML '08.

[8]  Anant Madabhushi,et al.  A Deep Convolutional Neural Network for segmenting and classifying epithelial and stromal regions in histopathological images , 2016, Neurocomputing.

[9]  Ilya Safro,et al.  Multilevel Weighted Support Vector Machine for Classification on Healthcare Data with Missing Values , 2016, PloS one.

[10]  J. Shavlik,et al.  Breast cancer risk estimation with artificial neural networks revisited , 2010, Cancer.

[11]  Mammographic density and survival in interval breast cancers , 2013, Breast Cancer Research.

[12]  C. D. Page,et al.  Probabilistic computer model developed from clinical data in national mammography database format to classify mammographic findings. , 2009, Radiology.

[13]  Stephen T. C. Wong,et al.  Correlating mammographic and pathologic findings in clinical decision support using natural language processing and data mining methods , 2017, Cancer.

[14]  Dan Roth,et al.  Learning Question Classifiers , 2002, COLING.

[15]  M. Tublin,et al.  The American Association of Endocrine Surgeons Guidelines for Definitive Management of Primary Hyperparathyroidism. , 2016, JAMA surgery.

[16]  Eveline A M Heijnsdijk,et al.  Nation-wide data on screening performance during the transition to digital mammography: observations in 6 million screens. , 2013, European journal of cancer.