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

Fuente: Zenodo
Saved in:
Bibliographic Details
Main Authors: Mangili, Andrea, Arrigoni, Alberto, Sangalli, Fabio, Caroli, Anna
Format: Recurso digital
Language:English
Published: Zenodo 2026
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866901746361565184
author Mangili, Andrea
Arrigoni, Alberto
Sangalli, Fabio
Caroli, Anna
author_facet Mangili, Andrea
Arrigoni, Alberto
Sangalli, Fabio
Caroli, Anna
contents <p>The dataset contains two files:</p> <p>1) 1_Segmentation_pipeline.zip, which contains:</p> <ul> <li>Dataset 1 <ul> <li>Training Set <ul> <li>Images: resampled µCT scans used to train the models</li> <li>Ground Truth: semi-automatic annotations of training samples</li> </ul> </li> <li>Test Set <ul> <li>Images: resampled µCT scans used to test the models</li> <li>Ground Truth: semi-automatic annotations of test samples</li> <li>Inferences <ul> <li>n5 Model: predicted mask of D1 test sample by the model trained using 5 samples + summary.json</li> <li>n5 one-channel Model: predicted mask of D1 test sample by the one-channel model trained using 5 samples + summary.json</li> <li>n10 Model: predicted mask of D1 test sample by the model trained using 10 samples + summary.json</li> <li>n15 Model: predicted mask of D1 test sample by the model trained using 15 samples + summary.json</li> <li>n20 Model: predicted mask of D1 test sample by the model trained using 20 samples + summary.json</li> </ul> </li> </ul> </li> </ul> </li> <li>Dataset 2 <ul> <li>Images: resampled µCT scans used to test the models</li> <li>Ground Truth: semi-automatic annotations of test samples</li> <li>Inferences <ul> <li>n5 Model: predicted mask of D1 test sample by the model trained using 5 samples + summary.json</li> <li>n5 one-channel Model: predicted mask of D1 test sample by the one-channel model trained using 5 samples + summary.json</li> <li>n10 Model: predicted mask of D1 test sample by the model trained using 10 samples + summary.json</li> <li>n15 Model: predicted mask of D1 test sample by the model trained using 15 samples + summary.json</li> <li>n20 Model: predicted mask of D1 test sample by the model trained using 20 samples + summary.json</li> </ul> </li> </ul> </li> </ul> <p>2) 2_Cyst_counting_pipeline.zip, which contains:</p> <ul> <li>Optimization set <ul> <li>Cyst masks: input masks (0 background, 1 kidney, 2 cysts) used in the optimization set</li> <li>O1_count.xlsx: Operator 1 manual counts on the Optimization set samples</li> </ul> </li> <li>Evaluation set <ul> <li>Cyst masks: input masks (0 background, 1 kidney, 2 cysts) used in the evaluation set</li> <li>O1_O2_counts.xlsx: Operator 1 and Operator 2 manual counts on the Evaluation set samples</li> </ul> </li> </ul>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_19049543
institution Zenodo
language eng
publishDate 2026
publisher Zenodo
record_format zenodo
spellingShingle Dataset related to article "A comprehensive pipeline for automatic cyst segmentation and counting on µCT scans from PKD animal models"
Mangili, Andrea
Arrigoni, Alberto
Sangalli, Fabio
Caroli, Anna
<p>The dataset contains two files:</p> <p>1) 1_Segmentation_pipeline.zip, which contains:</p> <ul> <li>Dataset 1 <ul> <li>Training Set <ul> <li>Images: resampled µCT scans used to train the models</li> <li>Ground Truth: semi-automatic annotations of training samples</li> </ul> </li> <li>Test Set <ul> <li>Images: resampled µCT scans used to test the models</li> <li>Ground Truth: semi-automatic annotations of test samples</li> <li>Inferences <ul> <li>n5 Model: predicted mask of D1 test sample by the model trained using 5 samples + summary.json</li> <li>n5 one-channel Model: predicted mask of D1 test sample by the one-channel model trained using 5 samples + summary.json</li> <li>n10 Model: predicted mask of D1 test sample by the model trained using 10 samples + summary.json</li> <li>n15 Model: predicted mask of D1 test sample by the model trained using 15 samples + summary.json</li> <li>n20 Model: predicted mask of D1 test sample by the model trained using 20 samples + summary.json</li> </ul> </li> </ul> </li> </ul> </li> <li>Dataset 2 <ul> <li>Images: resampled µCT scans used to test the models</li> <li>Ground Truth: semi-automatic annotations of test samples</li> <li>Inferences <ul> <li>n5 Model: predicted mask of D1 test sample by the model trained using 5 samples + summary.json</li> <li>n5 one-channel Model: predicted mask of D1 test sample by the one-channel model trained using 5 samples + summary.json</li> <li>n10 Model: predicted mask of D1 test sample by the model trained using 10 samples + summary.json</li> <li>n15 Model: predicted mask of D1 test sample by the model trained using 15 samples + summary.json</li> <li>n20 Model: predicted mask of D1 test sample by the model trained using 20 samples + summary.json</li> </ul> </li> </ul> </li> </ul> <p>2) 2_Cyst_counting_pipeline.zip, which contains:</p> <ul> <li>Optimization set <ul> <li>Cyst masks: input masks (0 background, 1 kidney, 2 cysts) used in the optimization set</li> <li>O1_count.xlsx: Operator 1 manual counts on the Optimization set samples</li> </ul> </li> <li>Evaluation set <ul> <li>Cyst masks: input masks (0 background, 1 kidney, 2 cysts) used in the evaluation set</li> <li>O1_O2_counts.xlsx: Operator 1 and Operator 2 manual counts on the Evaluation set samples</li> </ul> </li> </ul>
title Dataset related to article "A comprehensive pipeline for automatic cyst segmentation and counting on µCT scans from PKD animal models"
url https://doi.org/10.5281/zenodo.19049543