Synthetic Nodules for Evaluation of 3D Deep Learning Segmentation Attribution

Both the algorithm used to generate this dataset as well as the comprehensive evaluation metric for visual explanations are detailed in the paper "Attribution of 3D Deep Learning Segmentation in Medical Imaging".

This is a synthetic dataset developed to enable the comprehensive evaluation of visual explanation methods applied to deep learning segmentation predictions. The data provided here include 100 training and 100 testing volumes, binary segmentation labels for model training, and explanation segmentation labels for explanation evaluation.

The intended workflow for this dataset is: 1) Train a deep learning segmentation model using the 100 training volumes and binary segmentation labels. 2) Use a method of visual explanation to explain the trained model's segmentation decisions on the 100 testing volumes. 3) Use the explanation labels to evaluate the generated explanations.

The folders imagesTr and imagesTs contain the training and testing image volumes, respectively. A dataset.json file has also been generated for the images to enable training using the nnUNet pipeline.

The folders labelsTr and labelsTs contain the training and testing binary segmentation labels. In both cases, 1 indicates foreground voxels (spiculated nodule) and 0 indicates background voxels.

The folders labelsTr_full and labelsTs_full contain the training and testing explanation labels. In both cases, 1 indicates non-spiculated nodule, 2 indicates spiculation structure (discriminating background), 3 indicates spiculated nodule body (segmentation foreground), and 0 indicates background.