Correlation Clustering of Organoid Images: Data
Contributing person | Technology Development Studio of Max Planck Institute of Molecular Cell Biology and Genetics | |
Contributing person | Anne Grapin-Botton (Max Planck Institute of Molecular Cell Biology and Genetics) | |
Documentation of the data | Images of organoids and masks are in 16 bit TIFF format. Images in Train-100 and Test-100 are named as "single_organoid_<organoid_class><image_number>.tif" while masks are named as "single_organoid_<organoid_class><image_number>_mask.tif". The first one to two digits define the organoid class, 1 through 10 (organoid_class). The last two digits enumerate the images within one organoid class, 00 through 09 (image_number). Images in Test-30 are named as "single_organoid_<organoid_class><image_number>.tif", while masks are named as "single_organoid_<organoid_class><image_number>_mask.tif". The first two digits define the organoid class, 11 through 13 (organoid_class). The last two digits enumerate the images within one organoid class, 00 through 09 (image_number). Images in Test-Unlabeled are named as "single_organoid_<image_number>.tif" while masks are named as "single_organoid_<image_number>_mask.tif". The image number is consecutive, i.e., from 1 through 999. | |
References to related material | J. Presberger, R. Keshara, D. Stein, Y. H. Kim, A. Grapin-Botton and B. Andres. Correlation Clustering of Organoid Images. In: GCPR 2024. | |
Description of the data | This collection contains the following four datasets. Train-100 contains 100 images and masks of individual organoids. It contains images of ten different organoid classes, and ten distinct images for each organoid class. Test-100 contains 100 images and masks of individual organoids. It contains images of ten different organoid classes, and ten distinct images for each organoid class. The organoid classes in this dataset are the same as in Train-100. Test-30 contains 30 images and masks of individual organoids. It contains images of three different organoid classes, and ten distinct images for each organoid class. The organoid classes are distinct from those in Train-100 and Test-100. Test-Unlabeled contains 1000 images and masks of individual organoids. | |
Type of the data | Collection | |
Type of the data | Image | |
Total size of the dataset | 433156379 | |
Author | Presberger, Jannik | |
Author | Keshara, Rashmiparvathi | |
Author | Stein, David | |
Author | Kim, Yung Hae | |
Author | Grapin-Botton, Anne | |
Author | Andres, Bjoern | |
Upload date | 2024-08-23T12:11:32Z | |
Publication date | 2024-08-23T12:11:32Z | |
Data of data creation | 2023 | |
Publication date | 2024-08-23 | |
Abstract of the dataset | The data considered in: J. Presberger, R. Keshara, D. Stein, Y. H. Kim, A. Grapin-Botton and B. Andres. Correlation Clustering of Organoid Images. In: GCPR 2024. | |
Public reference to this page | https://opara.zih.tu-dresden.de/handle/123456789/869 | |
Public reference to this page | https://doi.org/10.25532/OPARA-598 | |
Publisher | Technische Universität Dresden | |
Licence | Attribution 4.0 International | en |
URI of the licence text | http://creativecommons.org/licenses/by/4.0/ | |
Specification of the discipline(s) | 4::44::409::409-05 | |
Title of the dataset | Correlation Clustering of Organoid Images: Data | |
Research instruments | Yokogawa CV7000 | |
Project abstract | In biological and medical research, scientists now routinely acquire microscopy images of hundreds of morphologically heterogeneous organoids and are then faced with the task of finding patterns in the image collection, i.e., subsets of organoids that appear similar and potentially represent the same morphological class. We implement models and algorithms for correlating organoid images, i.e., for quantifying the similarity in appearance and geometry of the organoids they depict, and for clustering organoid images by consolidating conflicting correlations. For correlating organoid images, we implement and compare two alternatives, a partial quadratic assignment problem and a twin network. For clustering organoid images, we employ the correlation clustering problem. Empirically, we learn the parameters of these models, infer a clustering of organoid images, and quantify the accuracy of the inferred clusters, with respect to a training set and a test set we contribute of state-of-the-art light microscopy images of organoids clustered manually by biologists. | |
Public project website(s) | https://github.com/JannikPresberger/Correlation_Clustering_of_Organoid_Images | |
Project title | Correlation Clustering of Organoid Images |
Files
Original bundle
License bundle
- Name:
- license.txt
- Size:
- 4.66 KB
- Format:
- Item-specific license agreed to upon submission
- Description:
Collections
