Ovarian Cancer Detection by an Electronic Nose
Ovarian Cancer Detection by an Electronic Nose
| |
| Coordinator: | AndreaBonarini (andrea.bonarini@polimi.it), MatteoMatteucci (matteo.matteucci@polimi.it) |
| Tutor: | RossellaBlatt (blatt@elet.polimi.it) |
| Collaborator: | |
| Students: | AlessandroMariaMauri (), NiccoloMoretti () |
| Research Topic: | Early cancer detection |
| Start: | 2009/10/01 |
| Status: | Closed |
| Level: | Ms |
| Type: | Course |
Contents
Short description
The project aims at evaluating the possibility of diagnosing ovarian cancer using an electronic nose, already used with success in the lung cancer detection ( Lung Cancer Detection by an Electronic Nose ).
Laboratory work and risk analysis
Laboratory work for this project will be mainly performed at the Istituto Nazionale dei Tumori di Milano, where the acquisistion of subjects' breath, both sick and healthy will be done. For this kind of work, there are not potential risks.
Project description
The electronic nose is an instrument able to detect and recognize odors, that is the volatile substances in the atmosphere or emitted by the analyzed substance. This device can react to a gas substance by providing signals that can be analyzed to classify the input. It is composed of a sensor array (MOS sensors, in our case) and a pattern classification process based on machine learning techniques. Each sensor reacts in a different way to the analyzed substance, providing multidimensional data that can be considered as a unique olfactory blueprint of the analyzed substance. In our work, we used an array composed of six Metal Oxide Semiconductor (MOS) sensors. In this project, we have been using an electronic nose based on an array of six MOS sensors, to recognize the presence of ovarian cancer in breaths' subjects, diagnosing the disease with a non invasive and low cost method.
Progress
Acquisition phase
In 23 days 29 samples were acquired, 16 sick and 13 sane. Only one type(either sane or sick) was acquired per day (due to problems related to the "rarity" of ovarian cancer) and this could bring some problems in the next phase, even if the only features used will be the one called EOS, that should be independent to time. Moreover the acquisition of samples coming from sane subjects was done mainly at the beginning of the project (2009) while samples coming from sick subjects have been taken for the biggest part after spring 2010. Analysing the response of the 6 MOS sensors for every acquisition no anomaly were discovered, so it is possibile to use all the samples. No blinds were acquired.
Data analysis phase
In progress.. At the moment good results have been achieved, but they will not published yet because we're probably victim of overfitting.
