Joint Breast Neoplasm Detection and Subtyping using Multi-Resolution Network Trained on Large-Scale H&E Whole Slide Images with Weak Labels.
Adam CassonSiqi LiuRan A. GodrichHamed AghdamBrandon RothrockKasper MalfroidChristopher KananThomas J. FuchsPublished in: MIDL (2023)
Keyphrases
- multiresolution
- digital mammography
- image database
- image data
- ground truth
- mammogram images
- manually labeled
- image collections
- detection rate
- image analysis
- image registration
- image classification
- three dimensional
- test images
- mammographic images
- coarse to fine strategy
- input image
- image features
- image retrieval
- segmentation algorithm
- object recognition
- neural network
- digital mammograms
- multiscale
- coarse to fine
- training data
- image fusion
- traffic signs
- breast ultrasound
- hierarchical representation
- complex background
- segmented images
- network structure
- breast cancer
- image content
- detection method
- object detection
- training set