An assessment of the usefulness of image pre-processing for the classification of first trimester fetal heart ultrasound using convolutional neural networks.
Catalin StoeanRuxandra StoeanMircea HotoleanuDominic IliescuCiprian PatruRodica NagyPublished in: ICSTCC (2021)
Keyphrases
- preprocessing
- image classification
- ultrasound images
- echocardiographic images
- input image
- image features
- image data
- post processing
- multiscale
- image analysis
- convolutional neural networks
- image retrieval
- image content
- image representation
- edge detection
- preprocessing stage
- pattern recognition
- feature extraction
- image segmentation
- classification accuracy
- high resolution
- feature space
- support vector
- extracted features
- single image
- feature values
- decision trees
- image regions
- segmentation algorithm
- text classification
- energy function
- gray level
- image quality assessment
- textural features
- pre processed
- similarity measure
- feature selection
- thematic mapper
- convolutional network