Deep Learning in Medical Post-Processing

Challenge

A well-known manufacturer of medical image post-processing applications and long-time Method Park customer in the sector of medical technology asked Method Park engineers to support its evaluation of new technology trends in the algorithmic image processing domain. The customer aimed at increasing the quality of its products, while maintaining the same level of product suitability for daily use.

Main goal was the evaluation of opportunities in machine learning – particularly Deep Learning – and, if applicable, their integration into existing medical devices. Method Park supported this customer on his journey from the prototype, to the integration of robust Deep Learning-based algorithms.

Duration of the project

about 1.5 years

2 .net developers 

Solution

First, an established Open Source Deep Learning library was introduced into the international multi-team project setup. The library was adapted to meet the project’s technological requirements and license rights, under consideration of the customer’s existing processes and relevant norms and standards in the regulated medical environment.

Principles of Software Craftsmanship were considered and implemented compliant to industry standards. Additionally, all tasks were bound to numerous requirements of the medical and regulatory environment, including creation and maintenance of comprehensive technical documentation.

Method Park ensured compliance to requirements in terms of code efficiency, execution times and consumption of software resources on customer-specific hardware configurations. In the course of development, Method Park worked closely together with clinical experts. Method Park engineers were contact persons for all questions by the customer’s technical experts who used the new implemented functionalities. Additionally, Method Park was in constant dialogue with medical algorithmic image processing scientists.

Method Park engineers integrated the new machine learning technology into the existing comprehensive code base of the customer project. Method Park’s work included preventive measures against unwanted side effects on algorithmic results due to changes in central components.

Solution

Introduction of an Open Source Deep Learning library

Consideration of Software Craftsmanship rules

Integration of latest clinical and scientific expert knowledge

More Information

Software Engineering

Benefit

With the support of Method Park, the customer successfully implemented the new technological trend Deep Learning with the benefit of increased software quality in medical imaging. That way the customer strengthened his position as a technological leader.

Benefit

Early application of the technological trend Deep Learning

Standard-compliant integration of new technologies

Increased software Quality