Review on Deep Learning-Based CAD Systems for Breast Cancer Diagnosis

Abstract

Breast Cancer (BC) is a major health issue in women of the age group above 45. Identification of BC at an earlier stage is important to reduce the mortality rate. Image-based noninvasive methods are used for early detection and for providing appropriate treatment. Computer-Aided Diagnosis (CAD) schemes can support radiologists in making correct decisions. Computational intelligence paradigms such as Machine Learning (ML) and Deep Learning (DL) have been used in the recent past in CAD systems to accelerate diagnosis. ML techniques are feature driven and require a high amount of domain expertise. However, DL approaches make decisions directly from the image. The current advancement in DL approaches for early diagnosis of BC is the motivation behind this review. This article throws light on various types of CAD approaches used in BC detection and diagnosis. A survey on DL, Transfer Learning, and DL-based CAD approaches for the diagnosis of BC is presented in detail. A comparative study on techniques, datasets, and performance metrics used in state-of-the-art literature in BC diagnosis is also summarized. The proposed work provides a review of recent advancements in DL techniques for enhancing BC diagnosis.

Breast cancer screening in women taking hormone replacement therapy needs updating

“…An RCT is not suited for rare events, and breast cancer trials require huge numbers taking time to perform with the risk of being outdated before being finished. This explains the lack of data on newer techniques in ultrasound, digital imaging, deep learning ( Arun Kumar and Sasikala, 2023 ) and artificial intelligence ( Gao et al, 2023 ). The translation of predictive values or Bayesian probabilities, into guidelines, results from estimating truth or clinical importance, decided by consensus or voting by a group of experts ( Kubota et al, 2023 ), thus introducing subjectivity based on previous experiences.…”

The application of traditional machine learning and deep learning techniques in mammography: a review

“…The primary function of the convolutional layer is to perform feature extraction and calculate the convolution results of data feature mapping using trainable convolutional filters and bias parameters ( 17 ). The pooling layer filters and consolidates the features, which are then fed into the fully connected layer for non-linear combination and output ( 18 ). The fully connected layer is a structure where every neuron in two adjacent layers is interconnected.…”

“…( 21 ) for breast cancer detection with mammography, Gastounioti et al. ( 22 ) for breast cancer risk prediction with mammography, Computer-aided breast cancer detection and classification in mammography ( 23 ), DL for breast cancer diagnosis ( 18 ), DL for Classification of Breast Microcalcifications ( 24 ), and etc. This review paper has a distinctive focus compared to previous articles for the following reasons.…”