article · Neural Computing and Applications
Breast cancer is a widespread cancer affecting women globally, and timely identification improves the chance of successful treatment. Although machine learning and deep learning show promise for screening, particularly where specialist physicians are scarce, sparse medical imaging data often limits deep learning effectiveness. To address this, a classification approach combines pre-trained convolutional neural networks, specifically DenseNet-121 and EfficientNet-B5 as feature extractors, alongside a support vector machine for final classification. The hyperparameters of the pre-trained networks are tuned using a modified meta-heuristic optimiser to boost diagnostic performance. When evaluated on the INbreast dataset, the EfficientNet-B5 model achieved high classification results, demonstrating an overall accuracy of 99.9 percent, sensitivity of 99.9 percent, specificity of 99.8 percent, precision of 99.1 percent, and an area under the curve of 1.0.
Early breast cancer detection dramatically improves patient survival rates, but regions lacking medical specialists face significant screening hurdles. Machine learning approaches can support early diagnosis, yet standard deep learning often underperforms on sparse medical imagery. Enhancing pre-trained models with meta-heuristic optimisation offers high diagnostic accuracy, helping clinical systems deliver dependable automated screening tools.
This work could enable automated diagnostic support software for radiologists and clinical screening centres, particularly in underserved regions lacking specialist physicians. Evaluated strictly on the benchmark INbreast dataset, the technique represents early-stage applied research that would require clinical validation and integration testing before reaching real-world diagnostic use.
AI-generated from the published abstract. Always read the original work before citing.
Abstract One of the most common cancers among women worldwide is breast cancer (BC), and early diagnosis can save lives. Early detection of BC increases the likelihood of a successful outcome by enabling treatment to start sooner. Even in areas without access to a specialist physician, machine learning (ML) aids in early BC detection. The medical imaging community is becoming more interested in using ML, and deep learning (DL) to increase the accuracy of cancer screening. Many disease-related data are sparse. However, for DL models to perform well, a large amount of data is required. Because of this, the DL models that are currently in use on medical images are not as effective as they could be. Convolutional neural network (CNN) models have recently gained popularity in the medical industry, and they perform admirably in terms of high performance and robustness at image classification. The proposed method classifies data using ensemble pre-trained models such as the dense convolutional network (DenseNet)-121 and EfficientNet-B5 feature extractor networks, as well as the support vector machine for classification. Using a modified meta-heuristic optimizer, the selected pre-trained CNN hyperparameters were optimized to improve the performance. The experimental results for the presented model on the INbreast dataset show that the EfficientNet-B5 model is effective for BC classification, with overall accuracy, sensitivity, specificity, precision, and area under the ROC curve (AUC) values of 99.9%, 99.9%, 99.8%, 99.1%, 1.0, respectively.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1007/s00521-024-10719-9
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
