Name
Abstract | ||
|---|---|---|
Breast cancer is a major cause of transience amongst women. In this paper, two novel techniques, ResNet50 and VGG-16, are utilised and re-trained to recognise two classes rather than 1000 classes with high accuracy and low computational requirements. In addition, transfer learning and data augmentation are performed to solve the problem of lack of tagged data. To get a better accuracy, the support vector machine (SVM) classifier is utilised instead of the last fully connected layer. Our models performance are verified utilising k-fold cross-validation. Our proposed techniques are trained and evaluated on three mammographic datasets: mammographic image analysis society, digital database for screening mammography (DDSM) and the curated breast imaging subset of DDSM. This paper explains end-to-end fully convolutional neural networks without any prepossessing or post-processing. The proposed technique of employing ResNet50 hybridised with SVM achieves the best performance, specifically with the DDSM dataset, producing 97.98% accuracy, 98.46% area under the curve, 97.63% sensitivity, 96.51% precision, 95.97% F1 score and computational time 1.8934 s. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1049/iet-ipr.2020.0122 | IET IMAGE PROCESSING |
Keywords | DocType | Volume |
support vector machines, pattern classification, mammography, medical image processing, feature extraction, image classification, cancer, learning (artificial intelligence), convolutional neural nets, screening mammography, curated breast imaging subset, end-to-end fully convolutional neural networks, ResNet50, SVM, DDSM dataset, computational time, breast cancer classification framework, deep learning, low computational requirements, digital database, mammographic image analysis society, mammographic datasets, cross-validation, models performance, fully connected layer, support vector machine classifier, tagged data, data augmentation, transfer learning | Journal | 14 |
Issue | ISSN | Citations |
13 | 1751-9659 | 0 |
PageRank | References | Authors |
0.34 | 0 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Wessam M. Salama | 1 | 0 | 1.01 |
| Azza M. Elbagoury | 2 | 0 | 0.34 |
| Moustafa H. Aly | 3 | 7 | 7.10 |