Fluorescence Microscopy Data for Cellular Detection using Object Detection Networks.
Creators
- 1. Wolfson Imaging Centre Oxford and MRC WIMM Centre for Computational Biology, Weatherall Institute of Molecular Medicine, Oxford University, Oxford, OX3 9DS, UK
- 2. MRC Molecular Haematology Unit, Weatherall Institute of Molecular Medicine, Oxford University, Oxford, OX3 9DS, UK
- 3. MRC Human Immunology Unit, Weatherall Institute of Molecular Medicine, Oxford University, Oxford, OX3 9DS, UK
- 4. Nuffield Division of Clinical Laboratory Sciences, Radcliffe Department of Medicine, John Radcliffe Hospital, University of Oxford, Headley Way, Oxford, OX3 9DU
- 5. Wolfson Imaging Centre Oxford and MRC Human Immunology Unit, Weatherall Institute of Molecular Medicine, University of Oxford, OX3 9DS, Oxford, United Kingdom. Institute of Applied Optics Friedrich-Schiller-University Jena, Max-Wien Platz 4, 07743 Jena, Germany. Leibniz Institute of Photonic Technology e.V., Albert-Einstein-Straße 9, 07745 Jena, Germany
Description
This data accompanies work from the paper entitled:
Object Detection Networks and Augmented Reality for Cellular Detection in Fluorescence Microscopy Acquisition and Analysis.
Further details of these datasets can be found in the methods section of the above paper.
Erythroblast DAPI (+GlyphorinA): Erythroblast cells were stained with DAPI and for glycophorin A protein. Cells were stained with CD235a antibody (JC159 clone from Dako) and with Alexa Fluor 488 secondary antibody from Invitrogen. DAPI staining was performed through using VectorShield Hard Set mounting solution with DAPI (Vector Lab). Num of images used for training: 80 and testing: 80. Average number of cells per image: 4.5.
Neuroblastoma phalloidin (+DAPI): Images of Neuroblastoma cells (N1E115) stained with phalloidin and DAPI were acquired from the Cell Image Library [25]. The images were stained for FITC-phalloidin and DAPI. Images were acquired on a Zeiss Aviovert 200 microscope with filters for DAPI and FITC. Num of images used for training: 180, testing: 180. Average number of cells per image: 11.7.
Fibroblast Nucleopore: Fibroblast (GM5756T) cells were stained for Nucleopore protein. Staining was performed using Anti-Nup153 mouse antibody (Abcam) and counterstained using Alex Fluor 488 (anti-mouse). Num of images for training: 26 and testing: 20. Average number of cells per image: 4.8.
Eukaryote DAPI: Eukaryote cells were stained with DAPI and fixed and mounted in Vectashield. Num of images for training: 40 and testing: 40. Average number of cells per image: 8.9.
C127 DAPI: C127 cells were stained with DAPI and fixed and mounted in Vectashield. Num of images for training: 30 and testing: 30. Average number of cells per image: 7.1.
Hela peroxisome: Hela cells expressing peroxisome localised SCP2-GFP protein. Cells were transfected with GFP-SCP2 protein, which contains the PTS-1 localisation signal, which redirects the fluorescently tagged protein to the actively importing peroxisomes. Cells were fixed and mounted. Num of images for training: 55 and testing: 55. Average number of cells per image: 7.9.
Dataset Annotation
Datasets were annotated by a skilled user. Bounding boxes were drawn to encapsulate the various staining of the cells. The dataset labels were then converted into a format compatible both with Faster-RCNN (Pascal) and with YOLOv2. T
Files
micro_vision_data.zip
Files
(94.6 MB)
| Name | Size | Download all |
|---|---|---|
|
md5:0e202fcbe180315cd465930be829f6b6
|
94.6 MB | Preview Download |