— Non invasive liquid level detection

Lab Automation

Do you want to help improve the testing capacity of medical laboratories and hospitals? Do you want to have a direct impact on society’s ability to test for and thereby track diseases faster? Have a look at the data set and convince us of your solution proposal!

Apply until April 18, 2021 / Xplorers Camp on May 4, 2021 

Question to be solved

How do you find the material transitions in a test tube based on two laser absorption signals? Please download the data set available and read the instructions provided. If you have any problems please do not hesitate to reach out to us.

General Background

Roche Diagnostics works on the automation of medical laboratories to achieve high testing capacity and reliability. A Roche installation can support the whole automated lifecycle of analysing human samples for medical testing. These human samples are test tubes filled with blood or urine samples collected at a doctor’s office or hospital. In the case of a doctor’s office these are often sent via courier to a large centralized medical testing laboratory and hospitals might have their own laboratory with Roche equipment in house.

 

We at Roche Diagnostics Automation Solutions (RDA) focus on the initial sorting and preparation of samples to be tested. This is the critical entry point of the samples into the automated testing workflow enabled by Roche devices. One of the most important parameters to quantify at the very beginning of the workflow is the amount of usable liquid is present in a test tube.

Our solution for determining the amount of material in a test tube – called Liquid Level Detection (LLD) – relies on the use of two lasers, each of a different wavelength. The wavelengths we use are selected so that we can detect the liquid levels even if a tube is fully covered by up to three barcode labels. Something not possible with a camera detecting light in the visible range of the electromagnetic spectrum. By analysing the changes in intensity of the transmitted light, our algorithms can detect where and how much liquid is in a test tube.

 

While our liquid level detection system is currently the best on the market, there is always room for improvement. Some examples of how we would like to improve our solution are

  • increasing the accuracy so tubes with very small liquid can still be processed,
  • increase robustness so tubes in many different conditions can still be processed,
  • expand the number and types of tubes that can be processed.

Your mission, should you accept it, is to create a liquid level detection algorithm using modern signal processing and machine learning tools based on a small selection of data.

Data Types & Technologies

  • Time Series
  • Data analysis
  • Python (Pandas)
  • Signal processing
  • Machine learning

Supporting Material or Links

Needed Skills

  • Data science
  • Statistics
  • Programming skills (Python)
  • Machine learning

Mentors

Romain Guerre
Software Engineer, Sample Quality

Dr. Christopher Espy

Form of Cooperation

Preferred scale: 6-12 months full-time (flexible models are also possible) Possible format: from working student to internship to master thesis

How to present your Idea

Free choice of the presentation medium (podcast, video, powerpoint, etc.). Show us how you would approach the problem – we do not expect a bullet-proof solution to the problem. Specific skills we will check during the Xplorers Camp:

  • Communication
  • Problem solving
  • Analytical skills
  • Knowledge of signals processing algorithms

By sending this to us via the submit button you agree to the following:

 

  • you confirm that you are the author of the submission and entitled to dispose of rights of use and exploitation of the contents of your submission, and that you have not yet granted any rights of use and exploitation to third parties that would be infringed by your submission;
  • you grant to Roche Diagnostics GmbH the unrestricted, sublicensable and exclusive right  to use and exploit your submission by all means known today or in the future. This includes without limitation the rights to reproduce, distribute, and exhibit your submission, as well as the right to communicate your submission to the public. You also grant to Roche Diagnostics GmbH the right to edit the submission, to translate it, and to create abbreviations and summaries (abstracts); the aforesaid rights to use and exploit also apply to such edited versions, translations, abbreviations and summaries. 
  • Roche Diagnostics GmbH will designate you as the author of the submission, and will recognize and respect your moral rights in the submission.
  • The relationship you enter into by sending this via the submit button is governed by the laws of the Federal Republic of Germany, and the courts of Germany have international jurisdiction for any disputes arising under or in connection with this relationship..

Submit

Any problems with the submit button? Please send your submission to healthcare.xplorers@roche.com.

 

Further information on our privacy policy can be found here.

Submit

Any problems with the submit button?
Please send your submission to healthcare.xplorers@roche.com.

 

Further information on our privacy policy can be found here.