721 citations · 859 across the 6 of their papers we have counts for
3 papers · 1 filter
Atlas H&E-TME: Scalable AI-Based Tissue Profiling at Expert Pathologist-Level Accuracy
Kai Standvoss, Miriam Hägele, Rosemarie Krupar +25
Hematoxylin and eosin (H&E) staining is the cornerstone of histopathology, yet scalable, quantitative analysis of H&E whole-slide images (WSIs) remains a central challenge in compu…
Streaming convolutional neural networks for end-to-end learning with multi-megapixel images
Hans Pinckaers, Bram van Ginneken, Geert Litjens
Due to memory constraints on current hardware, most convolution neural networks (CNN) are trained on sub-megapixel images. For example, most popular datasets in computer vision con…
Training convolutional neural networks with megapixel images
Hans Pinckaers, Geert Litjens
To train deep convolutional neural networks, the input data and the intermediate activations need to be kept in memory to calculate the gradient descent step. Given the limited mem…