datatorch

/

Sperm Chromatin Dispersion (SCD), partial copy

Public

Updated 21 hours ago

segmentationmicroscopy

Files

About

Sperm Chromatin Dispersion (SCD), partial copy

Bright-field microscopy images from the Sperm Chromatin Dispersion (SCD) assay, a test of sperm DNA fragmentation, with every spermatozoon traced as a polygon and classified as Fragmented or Non-fragmented. Mirrored from the Zenodo record (DOI 10.5281/zenodo.21628868) by Ornelas Nande et al., Centro de Uro Andrología and Universidad de Guadalajara (CUCEI).

This is a partial copy. The record describes 2,000 images, but the published archive contains only 1,102 of them. Slides L01 to L17 and L32 are missing entirely, along with 36 images of L18 and 2 of L19: 898 train images in all. Validation and test are complete. This copy will be completed if the authors re-upload the missing images.

Contents

Images1,098 (the 1,102 in the archive's images_split, minus 4 byte-identical duplicates)
Annotations2,014 sperm-cell polygons: 701 Fragmented, 1,313 Non-fragmented
Classes2 (Fragmented, Non-fragmented; originally Fragmentado, No fragmentado / No Fragmentado)
Datasetsperm-chromatin-dispersion-scd-v1
SplitBy coded slide, kept as folders: images/train/ 710 images (slides L18 to L31; 1,286 polygons), images/val/ 200 (L33 to L36; 364), images/test/ 188 (L37 to L40; 364)
ImagingBright-field microscopy of SCD assay preparations, 1920x1080 RGB PNG, one laboratory workflow and imaging setup

Six images (L22_1083, L22_1092, L22_1105, L23_1143, L23_1149, L24_1189) intentionally have no annotations: the authors found no clearly annotable spermatozoa in them.

Using it

Browse any image to see the per-cell polygons. To download everything (free account required):

  • ZIP: use the Download button on this project.
  • Python SDK: pip install datatorch, then:
datatorch login
datatorch pull datatorch/sperm-chromatin-dispersion-scd

Annotations export in COCO format through the project's export schema. The split is the folder each image sits in.

Conversion notes

  • Source: SCD_Microscopy_YOLOv8seg_Repository.zip (md5 221441f1bd077ce4b84273cde3c8a07d, matching the record). Images come from dataset/images_split/{train,val,test}; polygons from the authors' COCO files annotations/coco_json/Anotaciones01.json and Anotaciones02.json, matched by file name. Only annotations on images present in the archive were imported (2,021 of the record's 3,743).
  • Missing images: images_split/train holds 712 of 1,610 train images. Four of the missing L18/L19 images (L18_0853, L18_0856, L19_0869, L19_0919) exist only in the archive's dataset/images/ folder and were not imported, because this copy follows the published split.
  • Duplicates: 4 images are byte-identical copies of another image in the same split. The first of each pair was kept: train L28_1372 (dropped L28_1379) and L28_1367 (dropped L28_1402); test L37_1818 (dropped L37_1819) and L37_1835 (dropped L37_1836). The copies had been annotated separately, so their 7 polygons were not imported.
  • Class names: normalized to English. The two COCO files spell the second class differently (No fragmentado, No Fragmentado); both map to Non-fragmented.
  • Clipping: 39 polygons ran up to 33 px past the 1920x1080 frame. They were kept and clipped to it (Sutherland-Hodgman), and their bbox and area recomputed. The earlier run's estimate of 70 did not reproduce: 39 on the imported images, 77 across both COCO files.
  • The full list is in errata.txt in this project's storage. The authors' YOLOv8s-seg benchmark model and YOLO label files are not mirrored here.

License and citation

CC BY 4.0 (legal code), as stated on the Zenodo record and in the archive's LICENSE.txt. Credit the authors and indicate changes; this copy is a partial, converted version (see Conversion notes). If you use this data, please cite:

Ornelas Nande, E. J., Adel Domínguez, M. A., Mora Topete, A., Magdaleno Márquez, L. E., Aranguren, I., Valdivia-G, A., & Sanchez, O. D. (2026). Sperm chromatin dispersion microscopy image dataset for instance segmentation [Data set]. Zenodo. https://doi.org/10.5281/zenodo.21628868

The accompanying Data Descriptor is under peer review at Scientific Data; check the record for the article citation once it is published.

Source: zenodo.org/records/21628868.

Related

Description

Sperm Chromatin Dispersion (SCD) assay bright-field microscopy images with polygon instance segmentation of sperm cells, classified as Fragmented or Non-fragmented (DNA fragmentation; original Spanish labels "Fragmentado" and "No fragmentado"/"No Fragmentado"). PARTIAL COPY: the published Zenodo archive contains only 1,102 of the record's 2,000 images; slides L01 to L17 and L32 (plus 36 images of L18 and 2 of L19), 898 train images in all, are missing from it. This copy holds 1,098 images (1,920x1,080 PNG; train 710, val 200, test 188, after removing 4 byte-identical duplicates) with 2,014 polygons (701 Fragmented, 1,313 Non-fragmented), and will be completed if the authors re-upload the missing images. License: CC BY 4.0. Source: https://zenodo.org/records/21628868. Please cite: Ornelas Nande, E. J., Adel Domínguez, M. A., Mora Topete, A., Magdaleno Márquez, L. E., Aranguren, I., Valdivia-G, A., & Sanchez, O. D. (2026). Sperm chromatin dispersion microscopy image dataset for instance segmentation [Data set]. Zenodo. https://doi.org/10.5281/zenodo.21628868

Members

0
View all members →

Progress

99% labeled

1,092 of 1,099 files

Size

1 GB

Datasets

1

Labels

2

Annotations

2,014