Abstract The use of deep learning in the computer-aided diagnosis (CAD) of breast cancer is an area of active research, and it has shown promising results in recent years. Deep learning algorithms, such as convolutional neural networks (CNNs), have demonstrated superior performance in image analysis tasks, including medical image analysis. With the help of deep learning algorithms, the proposed CAD framework can extract and learn complex features from mammograms, which can be challenging for traditional image analysis techniques. This can lead to more accurate and reliable detection of suspicious lesions in mammograms, which can aid radiologists in making a more informed diagnosis. Using pre-trained deep CNNs such as AlexNet, GoogleNet, ResNet50, and Dense-Net121 is a common approach in deep learning-based image classification tasks, including breast cancer diagnosis. These pre-trained models are trained on large datasets such as ImageNet and can extract relevant features from images effectively. In the proposed experimentation, using pre-trained deep CNNs is likely to yield high accuracy in breast cancer diagnosis. The pre-trained models can be fine-tuned on a smaller dataset of mammogram images, and the learned features can be used for classification. This approach can potentially save time and computational resources compared to training a deep CNN from scratch. This work has produced a number of intriguing discoveries that will help scholars and researchers in evaluating and planning their future directions.
Alan : Mühendislik
Dergi Türü : Uluslararası
Benzer Makaleler | Yazar | # |
---|
Makale | Yazar | # |
---|