Breast Density Analysis on Mammograms: Application of Machine Learning with Textural Features

Breast cancer (BC) is the world’s most prevalent cancer in female population, with 2.3 million new cases diagnosed worldwide in 2020. The great efforts made to set screening campaigns, early detection programs, and increasingly targeted treatments led to a significant improvement in patients’ survival. Full-Field Digital Mammograph (FFDM) is considered the gold standard method for the early diagnosis of BC. From several previous studies it has emerged that breast density (BD) is a risk factor in the development of BC, affecting the periodicity of screening plans present today at an international level. In this study, the focus is the development of mammographic image processing techniques that allows the extraction of indicators derived from textural patterns of the mammary parenchyma indicative of BD risk factor. Different Machine Learning (ML) techniques have been employed to classify breasts based on the values of the tissue density. Textural features were extracted only from breast parenchyma with which to train classifiers thanks to aid of ML algorithms. The preliminary results are in line with those obtained in the literature, reaching an accuracy of 93.55% for a binary classification between dense and no-dense tissues.

[1]  M. Romano,et al.  Multiparametric Investigation of Dynamics in Fetal Heart Rate Signals , 2021, Bioengineering.

[2]  Carlo Ricciardi,et al.  A Combined Radiomics and Machine Learning Approach to Distinguish Clinically Significant Prostate Lesions on a Publicly Available MRI Dataset , 2021, J. Imaging.

[3]  Maria Romano,et al.  Optimization of an artificial neural network to study accelerations of foetal heart rhythm , 2021, 2021 IEEE 6th International Forum on Research and Technology for Society and Industry (RTSI).

[4]  Maria Romano,et al.  A Comprehensive Review of Techniques for Processing and Analyzing Fetal Heart Rate Signals , 2021, Sensors.

[5]  E. Emiliani,et al.  A Machine Learning Predictive Model for Post-Ureteroscopy Urosepsis Needing Intensive Care Unit Admission: A Case–Control YAU Endourology Study from Nine European Centres , 2021, Journal of clinical medicine.

[6]  V. Provitera,et al.  Positive impact of short-term gait rehabilitation in Parkinson patients: a combined approach based on statistics and machine learning. , 2021, Mathematical biosciences and engineering : MBE.

[7]  Alfonso Maria Ponsiglione,et al.  Application of DMAIC Cycle and Modeling as Tools for Health Technology Assessment in a University Hospital , 2021, Journal of healthcare engineering.

[8]  Alfonso Maria Ponsiglione,et al.  Comparison of machine learning algorithms to predict length of hospital stay in patients undergoing heart bypass surgery , 2021, BECB.

[9]  Alfonso Maria Ponsiglione,et al.  A comparison of different regression and classification methods for predicting the length of hospital stay after cesarean sections , 2021, ICMHI.

[10]  M. Cesarelli,et al.  Machine learning to predict mortality after rehabilitation among patients with severe stroke , 2020, Scientific Reports.

[11]  S. Kwon,et al.  Reliability and Clinical Utility of Machine Learning to Predict Stroke Prognosis: Comparison with Logistic Regression , 2020, Journal of stroke.

[12]  H. Alkadhi,et al.  Radiomics in medical imaging—“how-to” guide and critical reflection , 2020, Insights into Imaging.

[13]  P. Gargiulo,et al.  Machine learning predictive system based upon radiodensitometric distributions from mid-thigh CT images , 2020, European journal of translational myology.

[14]  R. Steenbakkers,et al.  The Image Biomarker Standardization Initiative: Standardized Quantitative Radiomics for High-Throughput Image-based Phenotyping. , 2020, Radiology.

[15]  M. Cesarelli,et al.  Linear discriminant analysis and principal component analysis to predict coronary artery disease , 2020, Health Informatics J..

[16]  Reinhilde Jacobs,et al.  Radiomics and Machine Learning in Oral Healthcare , 2020, Proteomics. Clinical applications.

[17]  Yuntian Chen,et al.  Study Progress of Radiomics With Machine Learning for Precision Medicine in Bladder Cancer Management , 2019, Front. Oncol..

[18]  Improta Giovanni,et al.  Distinguishing Functional from Non-functional Pituitary Macroadenomas with a Machine Learning Analysis , 2019, IFMBE Proceedings.

[19]  Antonella Petrillo,et al.  Mammographic density: Comparison of visual assessment with fully automatic calculation on a multivendor dataset , 2018, European Radiology.

[20]  Stefan Leger,et al.  Image biomarker standardisation initiative version 1 . 4 , 2016, 1612.07003.

[21]  Aimilia Gastounioti,et al.  Breast parenchymal patterns in processed versus raw digital mammograms: A large population study toward assessing differences in quantitative measures across image representations. , 2016, Medical physics.

[22]  E. Conant,et al.  Beyond breast density: a review on the advancing role of parenchymal texture analysis in breast cancer risk assessment , 2016, Breast Cancer Research.

[23]  Yuanjie Zheng,et al.  Parenchymal texture analysis in digital mammography: A fully automated pipeline for breast cancer risk assessment. , 2015, Medical physics.

[24]  D. Easton,et al.  Breast cancer screening: time to target women at risk , 2013, British Journal of Cancer.

[25]  I. Buchan,et al.  Prevention of breast cancer in the context of a national breast screening programme , 2012, Journal of internal medicine.

[26]  N. Boyd,et al.  Mammographic density and breast cancer risk: current understanding and future prospects , 2011, Breast Cancer Research.

[27]  Max Kuhn,et al.  Building Predictive Models in R Using the caret Package , 2008 .

[28]  Karla Kerlikowske,et al.  The mammogram that cried Wolfe. , 2007, The New England journal of medicine.

[29]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[30]  V. McCormack,et al.  Breast Density and Parenchymal Patterns as Markers of Breast Cancer Risk: A Meta-analysis , 2006, Cancer Epidemiology Biomarkers & Prevention.

[31]  D. Miglioretti,et al.  Individual and Combined Effects of Age, Breast Density, and Hormone Replacement Therapy Use on the Accuracy of Screening Mammography , 2003, Annals of Internal Medicine.

[32]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[33]  M. Cesarelli,et al.  Resolution Resampling of Ultrasound Images in Placenta Previa Patients: Influence on Radiomics Data Reliability and Usefulness for Machine Learning , 2020 .

[34]  Riaz Ahmed Ahmed Khan,et al.  ROCit- An R Package for Performance Assessment of Binary Classifier with Visualization , 2019 .

[35]  Max Kuhn,et al.  The caret Package , 2007 .