Abstract
In longitudinal medical studies, multicomponent images of the tissues, acquired at a given stage of a disease, are used to provide information on the fate of the tissues. We propose a quantification of the predictive value of multicomponent images using information theory. To this end, we revisit the predictive information introduced for monodimensional time series and extend it to multicomponent images. The interest of this theoretical approach is illustrated on multicomponent magnetic resonance images acquired on stroke patients at acute and late stages, for which we propose an original and realistic model of noise together with a spatial encoding for the images. We address therefrom very practical questions such as the impact of noise on the predictability, the optimal choice of an observation scale and the predictability gain brought by the addition of imaging components.
Highlights
In the medical context, one often needs to predict the future health of tissues based on information contained in one or more imaging components from one or more acquisition time points
We demonstrate the interest of such a modeling approach to address generic practical questions such as (i) the quantification of the gain in predictability obtained by the addition of new image components in prediction studies; (ii) the selection of a relevant spatial observation scale to optimally predict tissue fate; and (iii) the quantification of the impact of imaging noise on the predictability
In order to quantify the gain in predictability when integrating perfusion-weighted imaging (PWI) imaging components to prediction models, we propose using the predictive power defined in Equation (1) to select the best combination of n components in terms of tissue fate prediction and evaluating the relative gain in predictability from an n- to an (n + 1)-component combination
Summary
One often needs to predict the future health of tissues based on information contained in one or more imaging components from one or more acquisition time points. An important problem in this type of multicomponent and longitudinal imaging studies is to process jointly several components, and to a priori quantify the benefits (if any) of multi-component and multi-time point integration. This problem is challenging when faced, as is always the case in medical imaging studies, with biological variability and noise in the imaging system. In such a context, the informational content of physical signals can be defined and quantified in a powerful way by means of statistical information theory, as pioneered by Shannon [1,2]. The modeling of imaging problems in the framework of information theory is an active research topic and was recently applied for instance to spectral reduction [5,6], observation scale optimization [7], image visualization [8,9]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
