Deep learning performance for detection and classification of microcalcifications on mammography.
Filippo PesapaneChiara TrentinFederica FerrariGiulia SignorelliPriyan TantrigeMarta MontesanoCrispino CicalaRoberto VirgoliSilvia D'AcquistoLuca NicosiaDaniela OriggiEnrico CassanoPublished in: European radiology experimental (2023)
• A novel AI tool was developed and tested to aid radiologists in the interpretation of mammography by accurately detecting and characterizing microcalcifications. • Three neural networks (AlexNet, ResNet18, and ResNet34) were trained, validated, and tested using an annotated dataset of 1,000 patients and 1,986 mammograms. • The AI tool demonstrated high accuracy in detecting/localizing and characterizing microcalcifications on mammography, highlighting the potential of AI-based systems to assist radiologists in the interpretation of mammograms.
Keyphrases
- artificial intelligence
- deep learning
- machine learning
- neural network
- contrast enhanced
- end stage renal disease
- ejection fraction
- image quality
- convolutional neural network
- chronic kidney disease
- newly diagnosed
- prognostic factors
- peritoneal dialysis
- magnetic resonance
- risk assessment
- resistance training
- patient reported
- quantum dots