Download PDF

Scale AI > Case Studies > Accelerating Neuroscience Research at Harvard Medical School's Datta Lab with Scale Rapid

Accelerating Neuroscience Research at Harvard Medical School's Datta Lab with Scale Rapid

Technology Category

Analytics & Modeling - Machine Learning
Wearables - Implants

Applicable Industries

Education
Transportation

Applicable Functions

Product Research & Development
Quality Assurance

Use Cases

Public Transportation Management
Time Sensitive Networking

Services

Testing & Certification
Training

The Challenge

The Datta Lab at Harvard Medical School is engaged in studying the neural mechanisms associated with behavior in rodents. Their research involves recording the behavior of mice using cameras and measuring their neural activity using neural implants. The challenge lies in the analysis of this data, particularly in interpreting the behavioral data. This requires the researchers to label the poses of the mouse over time. While machine learning models can automate this process, a significant amount of video footage needs to be manually annotated first. This annotation process is time-consuming and detracts from the time that researchers could be spending on other aspects of research that require their expertise. The lab was in need of a solution to speed up their data annotation process.

About The Customer

The Datta Lab at Harvard Medical School is a research lab focused on studying the neural mechanisms associated with behavior in rodents. Their research involves placing mice in an experimental rig, recording each mouse’s behavior using cameras, and measuring each mouse’s neural activity using neural implants. The lab then analyzes this data to examine the link between neural activity and behavior, as well as to advance their understanding of specific brain areas of mice. The lab was previously spending a significant amount of time manually annotating video footage to interpret the behavioral data, which was detracting from the time that could be spent on other aspects of research.

The Solution

The Datta Lab partnered with Scale Rapid to expedite their data annotation process. Instead of annotating their data in-house, they now send their raw videos of mice to Scale Rapid and receive quality annotations in return. These annotations provide the lab with the information they need to train their machine learning models for automated pose tracking. This partnership with Scale Rapid saves the lab weeks of labeling time, allowing researchers to spend their time more effectively. It also enables the lab to acquire a higher volume of annotations than they could ever accomplish in-house. This large volume of high-quality annotations makes it easier for the lab to train high-performing machine learning models, while also freeing up researcher time.

Operational Impact

The partnership with Scale Rapid has significantly improved the research outcomes at the Datta Lab. The easy access to data annotations has lowered the barrier to training new models, enabling the lab to try out new ideas and iterate more rapidly. If a researcher needs to collect new training data after updating an experiment, or if they need to track a different part of the mouse in existing data, they can easily send their footage to Scale Rapid for new annotations. This has opened up possibilities that were not feasible before. Additionally, the ease with which the lab can obtain high volumes of data annotations has made it easier to produce high-performing machine learning models. This has reduced the need for model fine-tuning, as the majority of edge cases are naturally handled by the model, freeing up more time for researchers to advance their research in neuroscience.

Quantitative Benefit

The lab saves weeks of labeling time by using Scale Rapid for data annotation.
The lab can acquire a higher volume of annotations than they could ever accomplish in-house.
The lab can receive quality annotations as quickly as overnight.