An electronic bomb nose learning to sniff cancer

by Thomas Lindblad (KTH)

Thursday 14 May 2009, 10:00 → 11:00 Europe/Stockholm

Ovarian carcinoma is one of the most deadly diseases, especially in the case of late diagnosis. This seminar describes the result of a pilot study on an early detection method that could be inexpensive and simple based on data processing and machine learning algorithms in an electronic nose system. The nose hardware was originally developed for the bomb group of the Stockholm police, but seems do be doing a fair job with this new task following a minor relearning course. Experimental analysis using real ovarian carcinoma samples is used here. However, even if the apparatus used is the same, it is shown that the use of proper algorithms for analysis of the multi-sensor data from the electronic nose yielded surprisingly good results with more than 77% classification rate. These results are suggestive for further extensive experiments and development of the hardware as well as the software.