Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Recurso digital |
| Language: | |
| Published: |
Zenodo
2026
|
| Subjects: | |
| Online Access: | https://doi.org/10.5281/zenodo.19222986 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866902230919020544 |
|---|---|
| author | Duchrow, Lukas Voß, Imke Franke, Raphael |
| author_facet | Duchrow, Lukas Voß, Imke Franke, Raphael |
| contents | <p><strong>Overview</strong><br>The FOCI dataset contains 446 fluorescence microscopy images of irradiated human lymphocyte nuclei stained for γ-H2AX, a biomarker of DNA double-strand breaks (DSBs). The dataset is designed for object counting and density estimation tasks in biomedical image analysis. Image acquisition and annotation were performed by the <em>Bundesamt für Strahlenschutz</em>, while preprocessing was carried out by the <em>Umweltbundesamt</em>.</p> <p><strong>Data Acquisition</strong><br>Lymphocytes were isolated from whole blood samples of healthy donors, irradiated, and stained with γ-H2AX antibodies following the protocol described in Bucher et al. (2021). Images are provided in TIFF format with a resolution of 288×288 pixels, center-cropped to 220×220 pixels to remove preprocessing artifacts.</p> <p><strong>Biological Context</strong><br>γ-H2AX foci represent sites of radiation-induced DNA double-strand breaks. These appear as red fluorescent spots within blue-stained nuclei. Foci typically exhibit oval shapes with diffuse boundaries, with increasing overlap and signal diffusion at higher radiation doses.</p> <p><strong>Annotations</strong></p> <ul> <li>Bounding boxes for each detected focus</li> <li>Dot annotations derived from bounding box centers</li> <li>Only large, bright foci were annotated; small or dim signals were excluded</li> </ul> <p><strong>Label Format</strong></p> <ul> <li><strong>xywh: </strong>YOLO format: <code><class_id> <x_center> <y_center> <width> <height></code> (normalized coordinates, single class “foci”)</li> <li><strong>dots</strong>: JSON dot annotations with absolute pixel coordinates for each object center (<code>center</code>), plus a <code>count</code> field, suitable for single-class density map generation.</li> </ul> <p><strong>Annotation Uncertainty</strong><br>Annotation is subject to variability due to:</p> <ul> <li>ambiguous focus definition (intensity/size thresholds)</li> <li>overlapping foci</li> <li>non-symmetric shapes</li> <li>manual placement variability</li> </ul> <p>These uncertainties should be considered when training and evaluating models.</p> <p><strong>Intended Use</strong></p> <ul> <li>Object counting (cellular foci)</li> <li>Density map estimation</li> </ul> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_19222986 |
| institution | Zenodo |
| language | |
| publishDate | 2026 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | Irradiated-Cell-Foci Duchrow, Lukas Voß, Imke Franke, Raphael fluorescence microscopy foci lymphocytes radiation biology object counting computer vision <p><strong>Overview</strong><br>The FOCI dataset contains 446 fluorescence microscopy images of irradiated human lymphocyte nuclei stained for γ-H2AX, a biomarker of DNA double-strand breaks (DSBs). The dataset is designed for object counting and density estimation tasks in biomedical image analysis. Image acquisition and annotation were performed by the <em>Bundesamt für Strahlenschutz</em>, while preprocessing was carried out by the <em>Umweltbundesamt</em>.</p> <p><strong>Data Acquisition</strong><br>Lymphocytes were isolated from whole blood samples of healthy donors, irradiated, and stained with γ-H2AX antibodies following the protocol described in Bucher et al. (2021). Images are provided in TIFF format with a resolution of 288×288 pixels, center-cropped to 220×220 pixels to remove preprocessing artifacts.</p> <p><strong>Biological Context</strong><br>γ-H2AX foci represent sites of radiation-induced DNA double-strand breaks. These appear as red fluorescent spots within blue-stained nuclei. Foci typically exhibit oval shapes with diffuse boundaries, with increasing overlap and signal diffusion at higher radiation doses.</p> <p><strong>Annotations</strong></p> <ul> <li>Bounding boxes for each detected focus</li> <li>Dot annotations derived from bounding box centers</li> <li>Only large, bright foci were annotated; small or dim signals were excluded</li> </ul> <p><strong>Label Format</strong></p> <ul> <li><strong>xywh: </strong>YOLO format: <code><class_id> <x_center> <y_center> <width> <height></code> (normalized coordinates, single class “foci”)</li> <li><strong>dots</strong>: JSON dot annotations with absolute pixel coordinates for each object center (<code>center</code>), plus a <code>count</code> field, suitable for single-class density map generation.</li> </ul> <p><strong>Annotation Uncertainty</strong><br>Annotation is subject to variability due to:</p> <ul> <li>ambiguous focus definition (intensity/size thresholds)</li> <li>overlapping foci</li> <li>non-symmetric shapes</li> <li>manual placement variability</li> </ul> <p>These uncertainties should be considered when training and evaluating models.</p> <p><strong>Intended Use</strong></p> <ul> <li>Object counting (cellular foci)</li> <li>Density map estimation</li> </ul> |
| title | Irradiated-Cell-Foci |
| topic | fluorescence microscopy foci lymphocytes radiation biology object counting computer vision |
| url | https://doi.org/10.5281/zenodo.19222986 |