Towards Explainable End-to-End Prostate Cancer Relapse Prediction from H&E Images Combining Self-Attention Multiple Instance Learning with a Recurrent Neural Network.
Esther DietrichPatrick FuhlertAnne ErnstGuido SauterMaximilian LennartzH. Siegfried StiehlMarina ZimmermannStefan BonnPublished in: CoRR (2021)
Keyphrases
- end to end
- multiple instance learning
- image categorization
- prostate cancer
- object based image retrieval
- image annotation
- text localization and recognition
- image database
- multiple instance
- image data
- image classification
- input image
- prostate segmentation
- image retrieval
- computer aided
- object recognition
- multi class
- image understanding
- computer vision
- image registration
- image features
- image set
- mr images
- segmentation method
- supervised learning
- similarity measure
- machine learning