...

Guidance on sharing and using datasets related to Machine Learning or Artificial Intelligence studies on TCIA

1. In the case of "radiomics" and other quantitative imaging features it is critical to use standardized image feature definitions such as those outlined in this publication.

...

1.  
2. Radiology: Artificial Intelligence has initiated a collection of articles to address challenges of bias in medical imaging AI systems which we recommend researchers keep in mind when publishing or using datasets on TCIA. 
3. Please

...

1. review our letter to the editors of Radiology: Imaging Cancer to learn more about TCIA's plans and recommendations to address demographic disparities in our datasets.  
2. We encourage researchers to consider the use of https://aime-registry.org/ as a way to provide a detailed reporting record of their AI systems.

List of Deep Learning Parameters

Information about deep Learning parameters are also necessary for researchers to reproduce Deep Learning experiments. Where applicable, we recommend that data submitters include the following key pieces of information in their dataset summaries such that TCIA users can easily reproduce their study and compare their analysis results.

...

1. Deep

...

1. Deep Neural Network (DNN) Name - for example, VGG16, ResNet-101, UNet, etc., or a link to GitHub repository or manuscript for customized DNNs if applicable.
2. Data Augmentation Methods - for example, color augmentation (HSV or RGB color space), transformation, noise, GAN, patch generation, downsizing parameters, etc.
3. Training, Validation, and Testing Set Configuration - for example number of samples per each set, total number of samples, etc.
4. Hyperparameters - for example, learning rate, early stopping, batch size, number of epochs, etc.
5. Training Statistics - for example, wall time spent in training, accuracy metrics such as if average score or best score is reported, etc.
6. Training Environment - for example, GPU type, Deep Learning framework used such as TensorFlow/PyTorch, number of GPUs, number of nodes, etc

We also encourage you to review the following papers:

...

...

American College of Radiology's "Define-AI" Use Case Directory

...