Dataset related to article "A comprehensive pipeline for automatic cyst segmentation and counting on µCT scans from PKD animal models"

The dataset contains two files: 1) 1_Segmentation_pipeline.zip, which contains: Dataset 1 Training Set Images: resampled µCT scans used to train the models Ground Truth: semi-automatic annotations of training samples Test Set Images: resampled µCT scans used to test the models Ground Truth: semi-automatic annotations of test samples Inferences n5 Model: predicted mask of D1 test sample by the model trained using 5 samples + summary.json n5 one-channel Model: predicted mask of D1 test sample by the one-channel model trained using 5 samples + summary.json n10 Model: predicted mask of D1 test sample by the model trained using 10 samples + summary.json n15 Model: predicted mask of D1 test sample by the model trained using 15 samples + summary.json n20 Model: predicted mask of D1 test sample by the model trained using 20 samples + summary.json Dataset 2 Images: resampled µCT scans used to test the models Ground Truth: semi-automatic annotations of test samples Inferences n5 Model: predicted mask of D1 test sample by the model trained using 5 samples + summary.json n5 one-channel Model: predicted mask of D1 test sample by the one-channel model trained using 5 samples + summary.json n10 Model: predicted mask of D1 test sample by the model trained using 10 samples + summary.json n15 Model: predicted mask of D1 test sample by the model trained using 15 samples + summary.json n20 Model: predicted mask of D1 test sample by the model trained using 20 samples + summary.json 2) 2_Cyst_counting_pipeline.zip, which contains: Optimization set Cyst masks: input masks (0 background, 1 kidney, 2 cysts) used in the optimization set O1_count.xlsx: Operator 1 manual counts on the Optimization set samples Evaluation set Cyst masks: input masks (0 background, 1 kidney, 2 cysts) used in the evaluation set O1_O2_counts.xlsx: Operator 1 and Operator 2 manual counts on the Evaluation set samples