A novel wavelet decomposition and transformation convolutional neural network with data augmentation for breast cancer detection using digital mammogram

Abstract

Research in deep learning (DL) has continued to provide significant solutions to the challenges of detecting breast cancer in digital images. Image preprocessing methods and architecture enhancement techniques have been proposed to improve the performance of DL models such as convolutional neural networks (CNNs). For instance, the wavelet decomposition function has been used for image feature extraction in CNNs due to its strong compactness. Additionally, CNN architectures have been optimized to improve the process of feature detection to support the classification process. However, these approaches still lack completeness, as no mechanism exists to discriminate features to be enhanced and features to be eliminated for feature enhancement. More so, no studies have approached the use of wavelet transform to restructure CNN architectures to improve the detection of discriminant features in digital mammography for increased classification accuracy. Therefore, this study addresses these problems through wavelet-CNN-wavelet architecture. The approach presented in this paper combines seam carving and wavelet decomposition algorithms for image preprocessing to find discriminative features. These features are passed as input to a CNN-wavelet structure that uses the new wavelet transformation function proposed in this paper. The CNN-wavelet architecture applied layers of wavelet transform and reduced feature maps to obtain features suggestive of abnormalities that support the classification process. Meanwhile, we synthesized image samples with architectural distortion using a generative adversarial network (GAN) model to argue for their training datasets' insufficiency. Experimentation of the proposed method was carried out using DDSM + CBIS and MIAS datasets. The results obtained showed that the new method improved the classification accuracy and lowered the loss function values. The study's findings demonstrate the usefulness of the wavelet transform function in restructuring CNN architectures for performance enhancement in detecting abnormalities leading to breast cancer in digital mammography.

Immunity-based Ebola optimization search algorithm for minimization of feature extraction with reduction in digital mammography using CNN models

“…The SVM result showed that the method yielded 89.24% and 97.19% for recall and precision, respectively. In our recent study 86 , we demonstrated the use of the wavelet function to optimize the selection process of suggestive features leading to classification accuracy. A hybrid algorithm involving seam carving and wavelet decomposition was experimented with for image preprocessing to find discriminative features.…”

A Diagnostic Model of Breast Cancer Based on Digital Mammogram Images Using Machine Learning Techniques

“…ere are numerous approaches that have been anticipated for mammogram diagnosing. In general, they are can be grouped into statistical-based methods [13,14], waveletsbased methods [15][16][17], Markovian-based models [18], machine-learning-based methods [19], etc. Numerous investigations have been issued on computer breast cancer diagnosis.…”

Data Augmentation-aided Convolutional Neural Network for Detection of Abnormalities in Digital Mammography

“…The study investigated different transformational operations in achieving image synthesis on-the-fly to augment real images during training. In a recent study, (Olaide & Ezugwu, 2022) proposed the application of GAN-based data-augmentation approach to experiment on the performance of a CNN architecture with a novel wavelet function. Using the combination of MIAS and DDSM+CBIS datasets, the study showed that the classification of the network model yielded better classification and recall rate as compared with using the model without the augmentation method.…”

“…These methods have reported improved accuracy and recall with some values of 78% and 7.7% have been reported for both accuracy and recall rate respectively in some CAD-based systems (Freer & Ulissey, 2001). However, recent studies have shown that deep learning methods present more computational power to detecting the disease in medical images and identifying even very subtle abnormalities (Olaide & Ezugwu, 2022). Furthermore, the outstanding performance of deep learning method has motivated the use of CNN architectures to addressing the problem of classification of digital images for reduced false positive rate.…”