ProstateZones – Segmentations of the prostatic zones and urethra for the PROSTATEx dataset
(2024) In Scientific Data 11(1).- Abstract
Manual segmentations are considered the gold standard for ground truth in machine learning applications. Such tasks are tedious and time-consuming, albeit necessary to train reliable models. In this work, we present a dataset with expert segmentations of the prostatic zones and urethra for 200 randomly selected patients from the PROSTATEx dataset. Notably, independent duplicate segmentations were performed for 40 patients, providing inter-reader variability data. This results in a total of 240 segmentations. This dataset can be used to train machine learning models or serve as an external test set for evaluating models trained on private data, thereby addressing a current gap in the field. The delineated structures and terminology... (More)
Manual segmentations are considered the gold standard for ground truth in machine learning applications. Such tasks are tedious and time-consuming, albeit necessary to train reliable models. In this work, we present a dataset with expert segmentations of the prostatic zones and urethra for 200 randomly selected patients from the PROSTATEx dataset. Notably, independent duplicate segmentations were performed for 40 patients, providing inter-reader variability data. This results in a total of 240 segmentations. This dataset can be used to train machine learning models or serve as an external test set for evaluating models trained on private data, thereby addressing a current gap in the field. The delineated structures and terminology adhere to the latest Prostate Imaging Reporting and Data Systems v2.1 guidelines, ensuring consistency.
(Less)
- author
- publishing date
- 2024-12
- type
- Contribution to journal
- publication status
- published
- subject
- in
- Scientific Data
- volume
- 11
- issue
- 1
- article number
- 1097
- publisher
- Nature Publishing Group
- external identifiers
-
- scopus:85205955286
- pmid:39379407
- ISSN
- 2052-4463
- DOI
- 10.1038/s41597-024-03945-2
- language
- English
- LU publication?
- no
- additional info
- Publisher Copyright: © The Author(s) 2024.
- id
- e757b2e7-4b73-41de-9131-c6927831280b
- date added to LUP
- 2024-11-26 13:00:28
- date last changed
- 2025-07-09 07:42:24
@article{e757b2e7-4b73-41de-9131-c6927831280b, abstract = {{<p>Manual segmentations are considered the gold standard for ground truth in machine learning applications. Such tasks are tedious and time-consuming, albeit necessary to train reliable models. In this work, we present a dataset with expert segmentations of the prostatic zones and urethra for 200 randomly selected patients from the PROSTATEx dataset. Notably, independent duplicate segmentations were performed for 40 patients, providing inter-reader variability data. This results in a total of 240 segmentations. This dataset can be used to train machine learning models or serve as an external test set for evaluating models trained on private data, thereby addressing a current gap in the field. The delineated structures and terminology adhere to the latest Prostate Imaging Reporting and Data Systems v2.1 guidelines, ensuring consistency.</p>}}, author = {{Holmlund, William and Simkó, Attila and Söderkvist, Karin and Palásti, Péter and Tótin, Szilvia and Kalmár, Kamilla and Domoki, Zsófia and Fejes, Zsuzsanna and Kincses, Zsigmond Tamás and Brynolfsson, Patrik and Nyholm, Tufve}}, issn = {{2052-4463}}, language = {{eng}}, number = {{1}}, publisher = {{Nature Publishing Group}}, series = {{Scientific Data}}, title = {{ProstateZones – Segmentations of the prostatic zones and urethra for the PROSTATEx dataset}}, url = {{http://dx.doi.org/10.1038/s41597-024-03945-2}}, doi = {{10.1038/s41597-024-03945-2}}, volume = {{11}}, year = {{2024}}, }