Software to accompany the manuscript "Deep Learning Generates Xenohistologic Representations of Cancer for Explainability and Education". This software provides tools for generating synthetic, xenohistologic images to assist with deep learning model explainability and education. Visualizations are generated with a conditional generative adversarial network (cGAN) based on the StyleGAN2 architecture, and an interactive interface is provided for navigating the cGAN latent space and performing both class and layer blending
Many modern histopathology laboratories are in the process of digitising their workflows. Once image...
Conditional visual synthesis is the process of artificially generating images or videos that satisf...
Background: One of the common limitations in the treatment of cancer is in the early detection of th...
These are generated (synthetic) histology images of colorectal cancer. These images were generated b...
Computational technologies can contribute to the modeling and simulation of the biological environme...
Lack of explainability in artificial intelligence, specifically deep neural networks, remains ...
Computational histopathology algorithms can interpret very large volumes of data, which can navigate...
An unsupervised deep learning algorithm based on cycle-consistent generative adversarial networks (C...
Deep Convolutional Neuronal Networks (DCNNs) are showing remarkable performance on many computer vis...
Deep learning allows computers to learn from observations, or else training data. Successful applica...
Histopathological images contain information about how a tumor interacts with its micro-environment....
We ask what it means to understand a concept in a visual format by integrating knowledge bases into ...
This thesis deals with the use of generative adversarial networks for the synthesis of medical image...
For deep learning, the size of the dataset greatly affects the final training effect. However, in th...
Obtaining healthcare data such as magnetic resonance imaging data for medical diagnosis is expensive...
Many modern histopathology laboratories are in the process of digitising their workflows. Once image...
Conditional visual synthesis is the process of artificially generating images or videos that satisf...
Background: One of the common limitations in the treatment of cancer is in the early detection of th...
These are generated (synthetic) histology images of colorectal cancer. These images were generated b...
Computational technologies can contribute to the modeling and simulation of the biological environme...
Lack of explainability in artificial intelligence, specifically deep neural networks, remains ...
Computational histopathology algorithms can interpret very large volumes of data, which can navigate...
An unsupervised deep learning algorithm based on cycle-consistent generative adversarial networks (C...
Deep Convolutional Neuronal Networks (DCNNs) are showing remarkable performance on many computer vis...
Deep learning allows computers to learn from observations, or else training data. Successful applica...
Histopathological images contain information about how a tumor interacts with its micro-environment....
We ask what it means to understand a concept in a visual format by integrating knowledge bases into ...
This thesis deals with the use of generative adversarial networks for the synthesis of medical image...
For deep learning, the size of the dataset greatly affects the final training effect. However, in th...
Obtaining healthcare data such as magnetic resonance imaging data for medical diagnosis is expensive...
Many modern histopathology laboratories are in the process of digitising their workflows. Once image...
Conditional visual synthesis is the process of artificially generating images or videos that satisf...
Background: One of the common limitations in the treatment of cancer is in the early detection of th...