A Deep Learning Computer-Aided Diagnosis Approach for Breast Cancer

Abstract

Breast cancer is a gigantic burden on humanity, causing the loss of enormous numbers of lives and amounts of money. It is the world’s leading type of cancer among women and a leading cause of mortality and morbidity. The histopathological examination of breast tissue biopsies is the gold standard for diagnosis. In this paper, a computer-aided diagnosis (CAD) system based on deep learning is developed to ease the pathologist’s mission. For this target, five pre-trained convolutional neural network (CNN) models are analyzed and tested—Xception, DenseNet201, InceptionResNetV2, VGG19, and ResNet152—with the help of data augmentation techniques, and a new approach is introduced for transfer learning. These models are trained and tested with histopathological images obtained from the BreakHis dataset. Multiple experiments are performed to analyze the performance of these models through carrying out magnification-dependent and magnification-independent binary and eight-class classifications. The Xception model has shown promising performance through achieving the highest classification accuracies for all the experiments. It has achieved a range of classification accuracies from 93.32% to 98.99% for magnification-independent experiments and from 90.22% to 100% for magnification-dependent experiments.

Integrated analysis of diverse cancer types reveals a breast cancer-specific serum miRNA biomarker through relative expression orderings analysis

“…Many BrC patients are diagnosed with metastases or at an advanced stage [ 44 ]. Although imaging and histopathological examinations are commonly used for diagnosis, they have limitations [ 3 – 5 ]. Therefore, developing accurate biomarkers to support clinical diagnosis for BrC remains an important issue.…”

“…However, the positive detection rate of breast X-ray is low [ 3 ], while magnetic resonance imaging with higher accuracy is expensive [ 4 ]. Histopathological examination is the gold standard for diagnosing BrC [ 5 ]. However, as an invasive examination, it is unsuitable for daily screening and comes with a risk of infection.…”

Analyzing Histological Images Using Hybrid Techniques for Early Detection of Multi-Class Breast Cancer Based on Fusion Features of CNN and Handcrafted

“…Some common transformations include: This technology artificially increases the images of the data set through many operations such as rotation, shifting, flipping, rotating the image in several angles, and others. Thus, the problem of overfitting was solved by generating many images in the training phase [46]. When increasing the data set images, the unbalanced data set was considered, and the images were increased unevenly to make the data set balanced.…”

Enhancing Breast Cancer Histopathological Image Classification using Attention-Based High Order Covariance Pooling

“…There are a number of studies in the literature which have been applied to these datasets. For instance, many researchers have utilised BreakHis dataset to test their networks [11,12,19,20,[26][27][28][45][46][47][48][49][50][51][52]. Zhou et al [45] proposed a novel resolution adaptive network (RAN) to classify different forms of breast cancer.…”