OBJECTIVE: Medical electrical impedance tomography is a non-ionizing imaging modality in which low-amplitude, low-frequency currents are applied on electrodes on the body, the resulting voltages are measured, and an inverse problem is solved to determine the conductivity distribution in the region of interest. Due the ill-posedness of the inverse problem, the boundaries of internal organs are typically blurred in the reconstructed image. METHODS: A deep learning approach is introduced in the D-bar method for reconstructing a 2-D slice of the thorax to recover the boundaries of organs. This is accomplished by training a deep neural network on labeled pairs of scattering transforms and the boundaries of the organs in the data from which the transforms were computed. This allows the network to "learn" the nonlinear mapping between them by minimizing the error between the output of the network and known actual boundaries. Further, a "sparse" reconstruction is computed by fusing the results of the standard D-bar reconstruction with reconstructed organ boundaries from the neural network. RESULTS: Results are shown on simulated and experimental data collected on a saline-filled tank with agar targets simulating the conductivity of the heart and lungs. CONCLUSIONS AND SIGNIFICANCE: The results demonstrate that deep neural networks can successfully learn the mapping between scattering transforms and the internal boundaries of structures.
OBJECTIVE: Medical electrical impedance tomography is a non-ionizing imaging modality in which low-amplitude, low-frequency currents are applied on electrodes on the body, the resulting voltages are measured, and an inverse problem is solved to determine the conductivity distribution in the region of interest. Due the ill-posedness of the inverse problem, the boundaries of internal organs are typically blurred in the reconstructed image. METHODS: A deep learning approach is introduced in the D-bar method for reconstructing a 2-D slice of the thorax to recover the boundaries of organs. This is accomplished by training a deep neural network on labeled pairs of scattering transforms and the boundaries of the organs in the data from which the transforms were computed. This allows the network to "learn" the nonlinear mapping between them by minimizing the error between the output of the network and known actual boundaries. Further, a "sparse" reconstruction is computed by fusing the results of the standard D-bar reconstruction with reconstructed organ boundaries from the neural network. RESULTS: Results are shown on simulated and experimental data collected on a saline-filled tank with agar targets simulating the conductivity of the heart and lungs. CONCLUSIONS AND SIGNIFICANCE: The results demonstrate that deep neural networks can successfully learn the mapping between scattering transforms and the internal boundaries of structures.
Authors: Josué A Victorino; João B Borges; Valdelis N Okamoto; Gustavo F J Matos; Mauro R Tucci; Maria P R Caramez; Harki Tanaka; Fernando Suarez Sipmann; Durval C B Santos; Carmen S V Barbas; Carlos R R Carvalho; Marcelo B P Amato Journal: Am J Respir Crit Care Med Date: 2003-12-23 Impact factor: 21.405
Authors: Eduardo L V Costa; Caroline N Chaves; Susimeire Gomes; Marcelo A Beraldo; Márcia S Volpe; Mauro R Tucci; Ivany A L Schettino; Stephan H Bohm; Carlos R R Carvalho; Harki Tanaka; Raul G Lima; Marcelo B P Amato Journal: Crit Care Med Date: 2008-04 Impact factor: 7.598
Authors: Jennifer L Mueller; Peter Muller; Michelle Mellenthin; Rashmi Murthy; Michael Capps; Melody Alsaker; Robin Deterding; Scott D Sagel; Emily DeBoer Journal: Physiol Meas Date: 2018-05-31 Impact factor: 2.833