Discrimination of Complex Activation Patterns in Near Infrared Optical Tomography with Artificial Neural Networks.

Jiang J; Ahnen L; Lindner S; Di Costanzo Mata A; Kalyanov A; Scholkmann F; Wolf M; Sánchez Majos S

doi:10.1007/978-3-319-91287-5_50

Back

Journal article

Discrimination of Complex Activation Patterns in Near Infrared Optical Tomography with Artificial Neural Networks.

Jiang J Biomedical Optics Research Laboratory (BORL), Department of Neonatology, University Hospital Zurich (USZ), Zurich, Switzerland. jingjing.jiang@usz.ch.
Ahnen L Biomedical Optics Research Laboratory (BORL), Department of Neonatology, University Hospital Zurich (USZ), Zurich, Switzerland.
Lindner S Biomedical Optics Research Laboratory (BORL), Department of Neonatology, University Hospital Zurich (USZ), Zurich, Switzerland.
Di Costanzo Mata A Biomedical Optics Research Laboratory (BORL), Department of Neonatology, University Hospital Zurich (USZ), Zurich, Switzerland.
Kalyanov A Biomedical Optics Research Laboratory (BORL), Department of Neonatology, University Hospital Zurich (USZ), Zurich, Switzerland.
Scholkmann F Biomedical Optics Research Laboratory (BORL), Department of Neonatology, University Hospital Zurich (USZ), Zurich, Switzerland.
Wolf M Biomedical Optics Research Laboratory (BORL), Department of Neonatology, University Hospital Zurich (USZ), Zurich, Switzerland.
Sánchez Majos S Biomedical Optics Research Laboratory (BORL), Department of Neonatology, University Hospital Zurich (USZ), Zurich, Switzerland.

2018-09-05

Published in:

Advances in experimental medicine and biology. - 2018

Image Processing, Computer-Assisted

English Near-infrared optical tomography (NIROT) has great promise for many clinical problems. Here we focus on the study of brain function. During NIROT image reconstruction of brain activity, an inverse problem has to be solved that is sensitive to small superficial perturbations on the head such as e.g. birthmarks on the skin and hair. To consider these perturbations, standard physical modeling is unpractical, since it requires the implementation of detailed information that is generally unavailable. The aim here was to test whether artificial neural networks (ANN) are able to handle such perturbations and thus detect brain activity correctly. For simplicity, we created a virtual test model, where we simulated a pattern of activated and resting brain regions, which was covered by skin features like hair or melanin. We compared the performance of this ANN approach with that of an inverse problem based on a Monte Carlo (MC) model for light propagation. We conclude that ANNs tolerate substantially higher levels of skin perturbations than MC models and consequently are more suitable for detecting brain activity.

Language