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
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.
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
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.
Software Engineer, Sample Quality
Dr. Christopher Espy
Preferred scale: 6-12 months full-time (flexible models are also possible) Possible format: from working student to internship to master thesis
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:
By sending this to us via the submit button you agree to the following: