A new CNN architecture for efficient classification of ultrasound breast tumor images with activation map clustering based prediction validation.
Revathy SivanandanJ. JayakumariPublished in: Medical Biol. Eng. Comput. (2021)
Keyphrases
- image classification
- image data
- image database
- ground truth
- input image
- prediction accuracy
- image features
- test images
- pigmented skin lesions
- preprocessing stage
- image analysis
- three dimensional
- maximum a posteriori probability
- feature vectors
- decision trees
- object recognition
- segmentation algorithm
- cellular neural networks
- segmentation method
- feature points
- pattern recognition
- edge detection
- image registration
- image retrieval
- text classification
- classification accuracy
- support vector
- feature space
- image set
- ultrasound images
- hyperspectral images
- support vector machine
- convolutional neural network
- feature selection