Mobius Medical Advanced Image Processing Project

Varian Medical Systems Mobius 3D

Software DevelopmentImage Processing


Innolitics's engineers seamlessly integrate with our existing team. They’ve consistently produced high quality work while helping us solve technical problems in the medical imaging space. In particular, they spearheaded development of a large module that extends our existing product suite. This module has since been cleared be the FDA (K153014) and is live at hospitals around the world. Their work on the module involved software development, researching various image processing algorithms, analysis of these algorithms against real-world data, and writing detailed technical documentation of the system that justified its approach to the FDA.

Nathan Childress, PhD, DABR

Nathan Childress, PhD, DABR

Associated VP at Varian Medical Systems

The Problem

Mobius Medical Systems (since acquired by Varian) produces treatment planning quality-assurance (QA) software. They had a popular solution, but customers were demanding quality checks, and they needed to keep ahead of their competitors. Nathan Childress, then the CEO, needed a team of engineers who could operate in the highly technical and regulated medical device software space. The goal was to help rapidly develop and clear a CBCT check module for their Software as a Medical Device (SaMD) product.

The Outcome

The large CBCT check module that we spearheaded was cleared be the FDA (K153014) and is live at hospitals around the world.

The Solution

We worked closely with Mobius’ existing engineering team to extend their existing Python, C++, and JavaScript application to perform Cone-Beam CT checks.

The CBCT software implements an automatic, quantitative comparison between planning CT images and pre-treatment CBCT images to detect patient positioning errors and anatomical changes. Patients usually have planning CT images taken days or even weeks before starting radiation therapy. The treatment plan is computed and optimized based on the planning CT images. Fast CBCT images are taken minutes before treatment to ensure the alignment of the patient relative to the planning CT images is acceptable. We helped turn the once manual and qualitative process of alignment assessment into an automatic and quantitative one.

Screenshot of Mobius Medical’s landing page

On-Going Work

After the CT/CBCT alignment project, our role grew to encompass the following:

Return production quality software

  • Results follow all existing FDA regulatory procedures
  • Wrote high-quality design documents suitable to include in regulatory documentation
  • Furnished data and results for the FDA
  • Wrote code that was flexible enough to respond to fast-changing market pressures and customer demands
  • Wrote performant log anonymization scripts to ensure HIPPA compliance

DICOM and PACS specific knowledge

  • Interfaced with hospital PACS to automatically retrieve relevant DICOM files for further processing
  • Read and wrote DICOM files; generated radiotherapy DICOM objects from scratch
  • Simulated PACS and network shares for automation tests

Work as an in-house extension

  • Acquired data for marketing materials
  • Helped create a web frontend to an existing product written in MATLAB
  • Automated parts of the quality management system to reduce labor-intensive and error-prone manual preparation
  • Discovered and worked around vendor-specific quirks in input data

Testing and documentation

  • Supported features we wrote; this included writing defect reports, attending support calls with users, gathering additional data from complaints, and pushing updates on live production servers
  • Helped with software maintenance and customer support duties, even for features not originally written by us
  • Came up with improvements to testing infrastructure and developer tools that have increased developer productivity and saved countless developer-hours
  • Created automation tests and harnesses for complex environments such as simulated PACS and network shares
  • Filed issue reports and tracked down solutions to bugs outside of the codebase in third party libraries such as CouchDB and PyDICOM
  • Helped implement and test a 3D/3D image registration algorithm for CBCT/CT images to suggest a table movement to bring the patient into alignment

About Mobius 3D

Mobius 3D software is capable of double-checking the planned dose calculated by a treatment planning system, ensuring the planned dose is within safe limits for critical radiosensitive structures (e.g. spinal cord, optic nerve, etc), and ensuring the dose actually delivered during treatment matches what was intended.

About Nathan Childress

Nathan Childress, Ph.D., DABR
Founder, CEO of Macorva, Inc.

Dr. Nathan Childress, Ph.D., DABR, is an accomplished and versatile professional, currently serving as the Founder, Chairman, and CEO of Macorva, Inc., a position he has held for five years. His academic journey saw him secure degrees in Chemical Engineering and Nuclear Engineering from the University of Missouri-Columbia, culminating in a Ph.D. in Medical Physics from the esteemed MD Anderson Cancer Center. His extensive expertise, amplified by his varied educational background, facilitated his success as the Founder and CEO of Mobius Medical Systems, where he worked for nearly eight years. This role was followed by a year as the Associate Vice President of Strategic Initiatives at Varian Medical Systems. Currently, he contributes his wide-ranging knowledge as a board member of Aspekt Solutions and an advisory board member for Hubly Surgical. His passion for mentorship is displayed through his volunteering work with MassChallenge, Alchemist Accelerator, and Capital Factory. Dr. Childress's commitment to scientific advancement, healthcare innovation, and leadership in the business community firmly establishes him as a prominent figure in the field.

Thought on Innolitics

We were impressed by the quality of software architecture design and implementation, especially related to system stability. Innolitics maintained an extremely high success rate in first-time code deployment, ensuring high-quality output.

There were some concerns about handling of Open Source or Third Party Materials in our systems, but Innolitics strictly adhered to legal and contractual conditions, and thus eliminated the concern with zero incidents of non-compliance noted, throughout the project duration.

We couldn’t entirely predict the continuous software maintenance and upgrade needs, but Innolitics’s well-planned maintenance services significantly reduced the system downtime, ensuring the smooth running of our software systems.