Abstract

BackgroundThe limitations of traditional computer-aided detection (CAD) systems for mammography, the extreme importance of early detection of breast cancer and the high impact of the false diagnosis of patients drive researchers to investigate deep learning (DL) methods for mammograms (MGs). Recent breakthroughs in DL, in particular, convolutional neural networks (CNNs) have achieved remarkable advances in the medical fields. Specifically, CNNs are used in mammography for lesion localization and detection, risk assessment, image retrieval, and classification tasks. CNNs also help radiologists providing more accurate diagnosis by delivering precise quantitative analysis of suspicious lesions.ResultsIn this survey, we conducted a detailed review of the strengths, limitations, and performance of the most recent CNNs applications in analyzing MG images. It summarizes 83 research studies for applying CNNs on various tasks in mammography. It focuses on finding the best practices used in these research studies to improve the diagnosis accuracy. This survey also provides a deep insight into the architecture of CNNs used for various tasks. Furthermore, it describes the most common publicly available MG repositories and highlights their main features and strengths.ConclusionsThe mammography research community can utilize this survey as a basis for their current and future studies. The given comparison among common publicly available MG repositories guides the community to select the most appropriate database for their application(s). Moreover, this survey lists the best practices that improve the performance of CNNs including the pre-processing of images and the use of multi-view images. In addition, other listed techniques like transfer learning (TL), data augmentation, batch normalization, and dropout are appealing solutions to reduce overfitting and increase the generalization of the CNN models. Finally, this survey identifies the research challenges and directions that require further investigations by the community.

Highlights

  • The limitations of traditional computer-aided detection (CAD) systems for mammography, the extreme importance of early detection of breast cancer and the high impact of the false diagnosis of patients drive researchers to investigate deep learning (DL) methods for mammograms (MGs)

  • convolutional neural networks (CNNs) best practices we explain the practices that contribute to improve the performance of CNNs for MGs

  • It goes beyond the scope of this paper to discuss all the best practices done in CNNs in general, but we are going to highlight and focus on some of them that show significant changes in the classification accuracy when applied to MG images

Read more

Summary

Introduction

The limitations of traditional computer-aided detection (CAD) systems for mammography, the extreme importance of early detection of breast cancer and the high impact of the false diagnosis of patients drive researchers to investigate deep learning (DL) methods for mammograms (MGs). Mammography is one of the most widely used methods for breast cancer screening and has contributed significantly to the reduction of the mortality rate through early detection of cancer [2]. Studies have shown the effectiveness of CAD models; accurate detection of breast cancer has remained challenging [2]. The biggest challenge in using CAD for abnormality detection in MGs is the high false positive rates (FPR). In the USA, millions of women undergo screening mammography each year, as a result, even a small reduction in the FPR result in a widespread benefit [1, 6]. The limitations of current CAD indicate the need for new, more precise detection methods

Methods
Results
Discussion
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call