DeepBacs E. Coli - Dataset Ninja

Introduction #

Released 2021-10-05 ·Christoph Spahn, Romain F. Laine, Pedro Matos Pereiraet al.

The authors of the DeepBacs: Bacterial Image Analysis Using Open-source Deep Learning Approaches biomedical project highlight the rapid transformation of microscopy through Deep Learning, which has enabled efficient analysis of complex data and often surpassed the performance of classical algorithms. As a result, there has been a significant effort to develop user-friendly tools that allow biomedical researchers, with limited computer science backgrounds, to leverage DL effectively. While such approaches have primarily focused on analyzing microscopy images from eukaryotic samples, they have been underutilized in microbiology.

To support researchers in their training process, the authors provide a specifically designed database of training and testing data, allowing bacteriologists to quickly explore how to analyze their data using DL techniques. The ultimate goal is to foster the efficient application of DL in microbiology, leading to the creation of novel tools for bacterial cell biology and antibiotic research.

The presented dataset contains training and test images of E. coli cells treated with different antibiotics for antibiotic phenotyping:

Characteristic	Value
Data type	Paired microscopy images (confocal fluorescence) and manual annotations
Microscopy data type	Confocal fluorescence images of fixed E. coli cells stained for membrane (Nile Red) and DNA (DAPI) paired with annotations in PASCAL VOC format
Microscope	Zeiss LSM710 confocal microscope with a Plan-Apo 63x oil objective (1.4 NA)
Cell type	Chemically fixed E. coli NO34 cells (MreB-sfGFPsw, kindly provided by Zemer Gitai) (untreated or drug-treated);
Image size	400 x 400 px² (Pixel size: 84 nm)

Expand

Homepage

Research Paper

GitHub

Summary #

DeepBacs: Escherichia Coli Antibiotic Phenotyping Object Detection Dataset and YOLOv2 Model is a dataset for an object detection task. It is used in the biomedical research.

The dataset consists of 235 images with 3564 labeled objects belonging to 8 different classes including Oblique, Vesicle, Nalidixate, and other: Rifampicin, CAM, Control, Mecillinam, and MP265.

Images in the DeepBacs E. Coli dataset have bounding box annotations. All images are labeled (i.e. with annotations). There are 3 splits in the dataset: train (153 images), test_individual_treatment (50 images), and test_stitched_images (32 images). The dataset was released in 2021 by the Institute of Physical and Theoretical Chemistry, Goethe-University Frankfurt, Germany.

Here is the visualized example grid with annotations:

Explore #

DeepBacs E. Coli dataset has 235 images. Click on one of the examples below or open "Explore" tool anytime you need to view dataset images with annotations. This tool has extended visualization capabilities like zoom, translation, objects table, custom filters and more. Hover the mouse over the images to hide or show annotations.

Sample annotation mask from DeepBacs E. Coli

👀

Have a look at 235 images

View images along with annotations and tags, search and filter by various parameters

Class balance #

There are 8 annotation classes in the dataset. Find the general statistics and balances for every class in the table below. Click any row to preview images that have labels of the selected class. Sort by column to find the most rare or prevalent classes.

Rows 1-8 of 8

Class ㅤ	Images ㅤ	Objects ㅤ	Count on image average	Area on image average
Oblique➔ rectangle	201	789	3.93	2.98%
Vesicle➔ rectangle	100	393	3.93	0.45%
Nalidixate➔ rectangle	64	209	3.27	4.64%
Rifampicin➔ rectangle	56	597	10.66	8.82%
CAM➔ rectangle	52	374	7.19	5.82%
Control➔ rectangle	48	308	6.42	7.88%
Mecillinam➔ rectangle	47	484	10.3	6.73%
MP265➔ rectangle	37	410	11.08	6.5%

Co-occurrence matrix #

Co-occurrence matrix is an extremely valuable tool that shows you the images for every pair of classes: how many images have objects of both classes at the same time. If you click any cell, you will see those images. We added the tooltip with an explanation for every cell for your convenience, just hover the mouse over a cell to preview the description.

Images #

Explore every single image in the dataset with respect to the number of annotations of each class it has. Click a row to preview selected image. Sort by any column to find anomalies and edge cases. Use horizontal scroll if the table has many columns for a large number of classes in the dataset.

Object distribution #

Interactive heatmap chart for every class with object distribution shows how many images are in the dataset with a certain number of objects of a specific class. Users can click cell and see the list of all corresponding images.

Class sizes #

The table below gives various size properties of objects for every class. Click a row to see the image with annotations of the selected class. Sort columns to find classes with the smallest or largest objects or understand the size differences between classes.

Rows 1-8 of 8

Class	Object count	Avg area	Max area	Min area	Min height	Min height	Max height	Max height	Avg height	Avg height	Min width	Min width	Max width	Max width
Oblique rectangle	789	0.76%	4.84%	0.05%	10px	2.5%	106px	26.5%	35px	8.66%	8px	2%	97px	24.25%
Rifampicin rectangle	597	0.85%	2.21%	0.32%	18px	4.5%	71px	17.75%	36px	9.07%	16px	4%	83px	20.75%
Mecillinam rectangle	484	0.66%	1.86%	0.26%	19px	4.75%	66px	16.5%	33px	8.2%	18px	4.5%	65px	16.25%
MP265 rectangle	410	0.59%	1.55%	0.28%	18px	4.5%	58px	14.5%	31px	7.7%	17px	4.25%	64px	16%
Vesicle rectangle	393	0.12%	0.26%	0.05%	8px	2%	22px	5.5%	14px	3.42%	9px	2.25%	21px	5.25%
CAM rectangle	374	0.81%	2.36%	0.07%	10px	2.5%	86px	21.5%	37px	9.17%	10px	2.5%	83px	20.75%
Control rectangle	308	1.24%	3.26%	0.42%	19px	4.75%	101px	25.25%	48px	11.93%	18px	4.5%	96px	24%
Nalidixate rectangle	209	1.43%	3.49%	0.46%	21px	5.25%	89px	22.25%	50px	12.59%	16px	4%	122px	30.5%

Spatial Heatmap #

The heatmaps below give the spatial distributions of all objects for every class. These visualizations provide insights into the most probable and rare object locations on the image. It helps analyze objects' placements in a dataset.

Objects #

Table contains all 3564 objects. Click a row to preview an image with annotations, and use search or pagination to navigate. Sort columns to find outliers in the dataset.

Rows 1-10 of 3564

Object ID ㅤ	Class ㅤ	Image name click row to open	Image size height x width	Height ㅤ	Height ㅤ	Width ㅤ	Width ㅤ	Area ㅤ
1➔	Oblique rectangle	#6_translated_control_1.png	400 x 400	21px	5.25%	37px	9.25%	0.49%
2➔	Oblique rectangle	#6_translated_control_1.png	400 x 400	33px	8.25%	46px	11.5%	0.95%
3➔	Oblique rectangle	#6_translated_control_1.png	400 x 400	35px	8.75%	38px	9.5%	0.83%
4➔	Oblique rectangle	#6_translated_control_1.png	400 x 400	21px	5.25%	63px	15.75%	0.83%
5➔	Oblique rectangle	#6_translated_control_1.png	400 x 400	42px	10.5%	38px	9.5%	1%
6➔	Oblique rectangle	#6_translated_control_1.png	400 x 400	41px	10.25%	29px	7.25%	0.74%
7➔	Oblique rectangle	#6_translated_control_1.png	400 x 400	39px	9.75%	46px	11.5%	1.12%
8➔	Oblique rectangle	#6_translated_control_1.png	400 x 400	26px	6.5%	34px	8.5%	0.55%
9➔	Oblique rectangle	#6_translated_control_1.png	400 x 400	44px	11%	37px	9.25%	1.02%
10➔	Oblique rectangle	#6_translated_control_1.png	400 x 400	46px	11.5%	22px	5.5%	0.63%

License #

DeepBacs: Escherichia coli antibiotic phenotyping object detection dataset and YOLOv2 model is under CC BY 4.0 license.

Source

Citation #

If you make use of the DeepBacs data, please cite the following reference:

@dataset{spahn_christoph_2021_5551057,
  author       = {Spahn, Christoph and
                  Heilemann, Mike},
  title        = {{DeepBacs – Escherichia coli antibiotic phenotyping 
                   object detection dataset and YOLOv2 model}},
  month        = oct,
  year         = 2021,
  publisher    = {Zenodo},
  doi          = {10.5281/zenodo.5551057},
  url          = {https://doi.org/10.5281/zenodo.5551057}
}

Source

If you are happy with Dataset Ninja and use provided visualizations and tools in your work, please cite us:

@misc{ visualization-tools-for-deepbacs-dataset,
  title = { Visualization Tools for DeepBacs E. Coli Dataset },
  type = { Computer Vision Tools },
  author = { Dataset Ninja },
  howpublished = { \url{ https://datasetninja.com/deepbacs } },
  url = { https://datasetninja.com/deepbacs },
  journal = { Dataset Ninja },
  publisher = { Dataset Ninja },
  year = { 2024 },
  month = { nov },
  note = { visited on 2024-11-21 },
}

Download #

Dataset DeepBacs E. Coli can be downloaded in Supervisely format:

As an alternative, it can be downloaded with dataset-tools package:

pip install --upgrade dataset-tools

… using following python code:

import dataset_tools as dtools

dtools.download(dataset='DeepBacs E. Coli', dst_dir='~/dataset-ninja/')

Make sure not to overlook the python code example available on the Supervisely Developer Portal. It will give you a clear idea of how to effortlessly work with the downloaded dataset.

The data in original format can be downloaded here:

. . .

Disclaimer #

Our gal from the legal dep told us we need to post this:

Dataset Ninja provides visualizations and statistics for some datasets that can be found online and can be downloaded by general audience. Dataset Ninja is not a dataset hosting platform and can only be used for informational purposes. The platform does not claim any rights for the original content, including images, videos, annotations and descriptions. Joint publishing is prohibited.

You take full responsibility when you use datasets presented at Dataset Ninja, as well as other information, including visualizations and statistics we provide. You are in charge of compliance with any dataset license and all other permissions. You are required to navigate datasets homepage and make sure that you can use it. In case of any questions, get in touch with us at hello@datasetninja.com.