Deep feature selection using local search embedded social ski-driver optimization algorithm for breast cancer detection in mammograms

Abstract

Breast cancer has become a common malignancy in women. However, early detection and identification of this disease can save many lives. As computer-aided detection helps radiologists in detecting abnormalities efficiently, researchers across the world are striving to develop reliable models to deal with. One of the common approaches to identifying breast cancer is through breast mammograms. However, the identification of malignant breasts from mass lesions is a challenging research problem. In the current work, we propose a method for the classification of breast mass using mammograms which consists of two main stages. At first, we extract deep features from the input mammograms using the well-known VGG16 model while incorporating an attention mechanism into this model. Next, we apply a meta-heuristic called Social Ski-Driver (SSD) algorithm embedded with Adaptive Beta Hill Climbing based local search to obtain an optimal features subset. The optimal features subset is fed to the K-nearest neighbors (KNN) classifier for the classification. The proposed model is demonstrated to be very useful for identifying and differentiating malignant and healthy breasts successfully. For experimentation, we evaluate our model on the digital database for screening mammography (DDSM) database and achieve 96.07% accuracy using only 25% of features extracted by the attention-aided VGG16 model. The Python code of our research work is publicly available at: https://github.com/Ppayel/BreastLocalSearchSSD.

A Systematic Literature Review on Mammography: Deep Learning in Redefining Breast Cancer Diagnosis for the Asian Perspective

“…GoogleNet (Inception) developed the concept of inception modules, which use parallel convolutional operations utilizing various kernel sizes for capturing multi-scale features efficiently. TL -Inception (Mahmood et al, 2021) Malathi and Latha, 2023;Sakthivel et al, 2022b;Samee et al, 2022b,a;Singh et al, 2023;Ahmad et al, 2023;Arora et al, 2020;Hekal et al, 2021) TL -VGG Net (Mahmood et al, 2021), (Jones et al, 2023;Pramanik et al, 2023;Sajid et al, 2023;Salama et al, 2020;Samee et al, 2022b,a;Yu et al, 2023a;Arora et al, 2020;Boudouh and Bouakkaz, 2023c;Chakravarthy et al, 2023b;Nemade et al, 2023a;Rani et al, 2023) TL -DenseNet (Mahmood et al, 2021), (Kumbhare et al, 2023;Zhang et al, 2020;Boudouh and Bouakkaz, 2023c;Chakravarthy et al, 2023b;Saber et al, 2023;Malibari et al, 2022) The Inception architecture has gone through several iterations. Inception-v2, also known as BN-Inception, added batch normalization to accelerate training.…”

“…K-nearest Neighbor (KNN) (Gnanasekaran et al, 2020), (Khanna et al, 2022;Pramanik et al, 2023;Jabeen et al, 2023;Malathi and Latha, 2023;Mokni and Haoues, 2022;Qu et al, 2022;Razali et al, 2023b,a;Sajid et al, 2023;Samee et al, 2022b,a;Sannasi Chakravarthy and Rajaguru, 2021;Zahoor et al, 2022) KNN classifies a data point according to the majority group of its k-nearest neighbors.…”

DAU-Net: Dual attention-aided U-Net for segmenting tumor in breast ultrasound images

“…affected women [17][18][19][20]. Among these efforts, deep learning-based CAD systems have shown great promise to address this challenge.…”

Breast Cancer-Risk Factors and Prediction Using Machine-Learning Algorithms and Data Source: A Review of Literature

“…The research found a number of ideal features and had an accuracy rate of 83.74%. Pramanik et al [111] explored the use of deep features extracted from breast mammograms to predict breast mass. The study identified 25% of the predictive features and achieved an accuracy of 96.07%.…”