Spatiotemporal Reconstruction of the Breathing Function D. Duong 1 , D. Shastri 2 , P. Tsiamyrtzis 3 , and I. Pavlidis 1 1 Department of Computer Science, University of Houston, Houston, TX 77024, USA 2 Department of Computer and Mathematical Sciences, University of Houston-Downtown, Houston, TX 77002, USA 3 Department of Statistics, Athens University of Economics and Business, Athens 10434, Greece dcduong@cs.uh.edu, shastrid@uhd.edu, pt@aueb.gr, ipavlidis@uh.edu Abstract. Breathing waveform extracted via nasal thermistor is the most common method to study respiratory function in sleep studies. In essence, this is a temporal waveform of mean temperatures in the nostril region that at every time step collapses two-dimensional data into a single point. Hence, spatial heat distribution in the nostrils is lost along with valuable functional and anatomical cues. This article presents the construction and experimental validation of a spatiotemporal profile for the breathing function via thermal imaging of the nostrils. The method models nasal airflow advection by using a front-propagating level set algorithm with optimal parameter selection. It is the first time that the full two-dimensional advantage of thermal imaging is brought to the fore in breathing computation. This new multi-dimensional measure is likely to bring diagnostic value in sleep studies and beyond. Keywords: Breathing, data visualization, sleep studies, thermal imag- ing. 1 Introduction Sleep studies require overnight monitoring of the patient’s breathing function which is typically accomplished via contact-sensors. A widely used sensor is the nasal thermistor which extracts the temporal breathing waveform by sensing the average temperatures in the nostril region at every point in time. The sensor is placed inside the nostril, a non-comfortable arrangement for patients who have problems with breathing and sleep in the first place. As an alternative to this clinical practice, a thermal imaging method has been proposed recently [1][2]. The method could be characterized as a ‘virtual thermistor’, because it produces a temporal breathing waveform by averaging emission values in the nostrils at every time step. The comparative advantage lies only in its non- contact nature. Although thermal imaging carries inherently spatial information, this is never recovered and used. Evolution of spatial heat distribution in the nostrils can reveal subtle breathing abnormalities that may hint at anatomical N. Ayache et al. (Eds.): MICCAI 2012, Part I, LNCS 7510, pp. 149–156, 2012. c  Springer-Verlag Berlin Heidelberg 2012