Flywheel Case Studies Automating Workflows in Stanford’s Brain Stimulation Lab

Edit This Case Study Record

	Automating Workflows in Stanford’s Brain Stimulation Lab Flywheel

Automating Workflows in Stanford’s Brain Stimulation Lab

Flywheel

Technology Category	Infrastructure as a Service (IaaS) - Cloud Computing Platform as a Service (PaaS) - Data Management Platforms
Applicable Industries	Healthcare & Hospitals
Applicable Functions	Product Research & Development
Use Cases	Predictive Maintenance
Services	Cloud Planning, Design & Implementation Services Data Science Services
Challenge	Stanford Medicine’s Brain Stimulation Lab is working on solutions for treatment-resistant depression, a condition that affects 5% of adults worldwide. The lab is studying the use of Repetitive Transcranial Magnetic Stimulation (rTMS), a therapy that involves activating or inhibiting the brain directly with electromagnetic fields. The lab's work is growing, and so is their need for smart data management. The lab originally used the Flywheel platform to store raw and reconstructed data and applied its basic tools for reconstruction and quality control. However, when they wanted to perform analysis, researchers were still downloading data to a static lab PC. This process was time-consuming and made it difficult to track data provenance. Read More
About Customer	Stanford Medicine’s Brain Stimulation Lab is a research facility dedicated to finding solutions for treatment-resistant depression. The lab is studying the use of Repetitive Transcranial Magnetic Stimulation (rTMS), a therapy that involves activating or inhibiting the brain directly with electromagnetic fields. The lab is led by Dr. Nolan Williams and includes researchers like Dr. Azeezat Azeez, a postdoctoral scholar with Stanford Psychiatry and Behavioral Sciences. The lab collaborates with the Stanford Center for Cognitive and Neurobiological Imaging (CNI) to obtain its scans. The lab's work has been published in high-impact journals and has attracted mainstream media attention from outlets like CBS and NPR. Read More
Solution	To improve the lab’s workflow, Dr. Azeez began leveraging more of Flywheel’s capabilities. She dedicated time to building custom Flywheel Gears—containerized algorithms that are run and managed within the platform. Flywheel provides an ever-expanding library of ready-to-use Gears, for everything from routine data processing tasks like metadata extraction and classification, to more complicated processes like independent component analysis and structural segmentation. Users also have the ability to develop their own custom Gears. By better utilizing existing Flywheel Gears and developing her own, Dr. Azeez and her collaborators have been able to dramatically streamline their workflows. Flywheel also provides an SDK (software development kit) library, a powerful suite of tools and utilities that allows users to programmatically interface with the platform. Using these tools, Dr. Azeez has daisy-chained Gears together so that once a patient’s baseline scan is received, the platform automatically runs Gears in sequence for reconstruction, quality control, fMRIprep pre-processing, and the lab’s custom targeting algorithm. Read More Log in to view content
Contents

Technology Category

Infrastructure as a Service (IaaS) - Cloud Computing

Platform as a Service (PaaS) - Data Management Platforms

Applicable Industries

Healthcare & Hospitals

Applicable Functions

Product Research & Development

Use Cases

Predictive Maintenance

Services

Cloud Planning, Design & Implementation Services

Data Science Services

Challenge

Stanford Medicine’s Brain Stimulation Lab is working on solutions for treatment-resistant depression, a condition that affects 5% of adults worldwide. The lab is studying the use of Repetitive Transcranial Magnetic Stimulation (rTMS), a therapy that involves activating or inhibiting the brain directly with electromagnetic fields. The lab's work is growing, and so is their need for smart data management. The lab originally used the Flywheel platform to store raw and reconstructed data and applied its basic tools for reconstruction and quality control. However, when they wanted to perform analysis, researchers were still downloading data to a static lab PC. This process was time-consuming and made it difficult to track data provenance.

About Customer

Stanford Medicine’s Brain Stimulation Lab is a research facility dedicated to finding solutions for treatment-resistant depression. The lab is studying the use of Repetitive Transcranial Magnetic Stimulation (rTMS), a therapy that involves activating or inhibiting the brain directly with electromagnetic fields. The lab is led by Dr. Nolan Williams and includes researchers like Dr. Azeezat Azeez, a postdoctoral scholar with Stanford Psychiatry and Behavioral Sciences. The lab collaborates with the Stanford Center for Cognitive and Neurobiological Imaging (CNI) to obtain its scans. The lab's work has been published in high-impact journals and has attracted mainstream media attention from outlets like CBS and NPR.

Solution

To improve the lab’s workflow, Dr. Azeez began leveraging more of Flywheel’s capabilities. She dedicated time to building custom Flywheel Gears—containerized algorithms that are run and managed within the platform. Flywheel provides an ever-expanding library of ready-to-use Gears, for everything from routine data processing tasks like metadata extraction and classification, to more complicated processes like independent component analysis and structural segmentation. Users also have the ability to develop their own custom Gears. By better utilizing existing Flywheel Gears and developing her own, Dr. Azeez and her collaborators have been able to dramatically streamline their workflows. Flywheel also provides an SDK (software development kit) library, a powerful suite of tools and utilities that allows users to programmatically interface with the platform. Using these tools, Dr. Azeez has daisy-chained Gears together so that once a patient’s baseline scan is received, the platform automatically runs Gears in sequence for reconstruction, quality control, fMRIprep pre-processing, and the lab’s custom targeting algorithm.

Impact #1	The new process is enabling the lab to complete its pre-treatment work in under two days, while simultaneously collecting important data to calibrate the stimulation level and position of the TMS coil for each patient.
Impact #2	For inpatient studies that require an expedited process, the lab can accelerate its prep work to under 12 hours.
Impact #3	The lab can run multiple targets simultaneously; they can multitask and have different teams working with the data all at the same time.

Impact #1

The new process is enabling the lab to complete its pre-treatment work in under two days, while simultaneously collecting important data to calibrate the stimulation level and position of the TMS coil for each patient.

Impact #2

For inpatient studies that require an expedited process, the lab can accelerate its prep work to under 12 hours.

Impact #3

The lab can run multiple targets simultaneously; they can multitask and have different teams working with the data all at the same time.

Benefit #1	The lab's remission rate among subjects in the four weeks following treatment is 78.5%.
Benefit #2	The lab's pre-treatment work is completed in under two days, a significant reduction from the previous process.
Benefit #3	For inpatient studies that require an expedited process, the lab can accelerate its prep work to under 12 hours.

Benefit #1

The lab's remission rate among subjects in the four weeks following treatment is 78.5%.

Benefit #2

The lab's pre-treatment work is completed in under two days, a significant reduction from the previous process.

Benefit #3

For inpatient studies that require an expedited process, the lab can accelerate its prep work to under 12 hours.

Download PDF Version

Overview

Automating Workflows in Stanford’s Brain Stimulation Lab

Operational Impact

Quantitative Benefit