Case Studies Sartorius Transforms Cell Imagery into Data with CloudFactory's Annotation Solution

Edit This Case Study Record

	Sartorius Transforms Cell Imagery into Data with CloudFactory's Annotation Solution

Sartorius Transforms Cell Imagery into Data with CloudFactory's Annotation Solution

Technology Category	Analytics & Modeling - Machine Learning Analytics & Modeling - Predictive Analytics Application Infrastructure & Middleware - Data Visualization
Applicable Industries	Healthcare & Hospitals
Applicable Functions	Product Research & Development Quality Assurance
Use Cases	Machine Condition Monitoring Predictive Maintenance Remote Asset Management
Services	Data Science Services System Integration Training
Challenge	The IncucyteⓇ Live-Cell Analysis System automates live-cell imaging, producing a vast number of microscopic images that are beyond human capacity to analyze. Neural networks can handle this task, but they require a large, annotated dataset for training. Sartorius needed to identify and characterize individual cells within these images, which contain hundreds to millions of cells in various shapes and sizes. Although the IncucyteⓇ system has integrated software for automatic cell segmentation, it requires user training and bespoke analysis for different cell types. The neural network method, however, allows for a single analysis across a wide range of cell types without user training. Faced with the diversity and volume of cells needed for the training dataset, Sartorius realized they couldn't manage the annotation process alone. Read More
About Customer	Sartorius is a biotechnology company that supports scientists and engineers in developing and manufacturing medications for incurable diseases. By simplifying workflows, enabling faster research, and reducing human error, Sartorius helps the biopharmaceutical industry bring improved medications to patients quickly and safely. One of their key products is the IncucyteⓇ Live-Cell Analysis System, which quantifies cell behavior and captures cellular changes using high-definition phase and fluorescence images. This system extracts and records image data in real-time, allowing scientists to observe complex biological changes as they happen. It also employs machine learning and artificial intelligence to help customers extract more information from samples in simple, easy ways. Read More
Solution	Rickard Sjögren, a senior scientist at Sartorius, led the initiative to find a solution for the data annotation problem. After comparing several vendors, Sartorius chose to partner with CloudFactory for three main reasons: low turnover and a dedicated team of data analysts, matching values in terms of ethical workforce practices, and the combination of CloudFactory’s managed workforce with the Dataloop platform. CloudFactory’s data analysts use Dataloop to perform individual cell segmentation and identify key cell types among thousands in each image. Nicola Bevan, Manager of Cell Imaging Applications, highlighted that the combination of workforce and platform contributes to project success. CloudFactory’s trained annotators apply precision labeling techniques to complex microscopy images, even when cells are touching, out of focus, or overlapping. They also support cell tracking projects by drawing bounding boxes around cells as they move between frames in time-lapse datasets. Read More Log in to view content
Contents

Technology Category

Analytics & Modeling - Machine Learning

Analytics & Modeling - Predictive Analytics

Application Infrastructure & Middleware - Data Visualization

Applicable Industries

Healthcare & Hospitals

Applicable Functions

Product Research & Development

Quality Assurance

Use Cases

Machine Condition Monitoring

Predictive Maintenance

Remote Asset Management

Services

Data Science Services

System Integration

Training

Challenge

The IncucyteⓇ Live-Cell Analysis System automates live-cell imaging, producing a vast number of microscopic images that are beyond human capacity to analyze. Neural networks can handle this task, but they require a large, annotated dataset for training. Sartorius needed to identify and characterize individual cells within these images, which contain hundreds to millions of cells in various shapes and sizes. Although the IncucyteⓇ system has integrated software for automatic cell segmentation, it requires user training and bespoke analysis for different cell types. The neural network method, however, allows for a single analysis across a wide range of cell types without user training. Faced with the diversity and volume of cells needed for the training dataset, Sartorius realized they couldn't manage the annotation process alone.

About Customer

Sartorius is a biotechnology company that supports scientists and engineers in developing and manufacturing medications for incurable diseases. By simplifying workflows, enabling faster research, and reducing human error, Sartorius helps the biopharmaceutical industry bring improved medications to patients quickly and safely. One of their key products is the IncucyteⓇ Live-Cell Analysis System, which quantifies cell behavior and captures cellular changes using high-definition phase and fluorescence images. This system extracts and records image data in real-time, allowing scientists to observe complex biological changes as they happen. It also employs machine learning and artificial intelligence to help customers extract more information from samples in simple, easy ways.

Solution

Rickard Sjögren, a senior scientist at Sartorius, led the initiative to find a solution for the data annotation problem. After comparing several vendors, Sartorius chose to partner with CloudFactory for three main reasons: low turnover and a dedicated team of data analysts, matching values in terms of ethical workforce practices, and the combination of CloudFactory’s managed workforce with the Dataloop platform. CloudFactory’s data analysts use Dataloop to perform individual cell segmentation and identify key cell types among thousands in each image. Nicola Bevan, Manager of Cell Imaging Applications, highlighted that the combination of workforce and platform contributes to project success. CloudFactory’s trained annotators apply precision labeling techniques to complex microscopy images, even when cells are touching, out of focus, or overlapping. They also support cell tracking projects by drawing bounding boxes around cells as they move between frames in time-lapse datasets.

Impact #1	With CloudFactory’s services, Sartorius has been able to considerably speed up projects.
Impact #2	The company developed an open-source dataset of more than 5,000 images, containing 1.6 million individually annotated cells, which was published in Nature Methods.
Impact #3	CloudFactory’s work helped Sartorius step into the machine learning, artificial intelligence, and image analysis spaces, leading to more informed research and better health outcomes.

Impact #1

With CloudFactory’s services, Sartorius has been able to considerably speed up projects.

Impact #2

The company developed an open-source dataset of more than 5,000 images, containing 1.6 million individually annotated cells, which was published in Nature Methods.

Impact #3

CloudFactory’s work helped Sartorius step into the machine learning, artificial intelligence, and image analysis spaces, leading to more informed research and better health outcomes.

Benefit #1	1.6 million cells annotated
Benefit #2	More than 5,000 images in the open-source dataset
Benefit #3	Many years saved in project timelines

Benefit #1

1.6 million cells annotated

Benefit #2

More than 5,000 images in the open-source dataset

Benefit #3

Many years saved in project timelines

Download PDF Version

Overview

Sartorius Transforms Cell Imagery into Data with CloudFactory's Annotation Solution

Operational Impact

Quantitative Benefit