Diffuse Optical Tomography (DOT) Diffuse Optical Tomography (DOT) is a non-invasive imaging technique using near-infrared electromagnetic waves to measure the optical properties of biological tissue from boundary measurement.
Problem Image reconstruction in this method is an inverse, ill-posed, and nonlinear problem. Traditional optimization methods can't overcome explicitly of this problem. Recently, deep neural networks have been used in image reconstruction, and they have achieved significant improvement over existing methods in the quality of the reconstructed image.
Enhacing DOT image reconstruction by Deep learning In this research, we used neural network algorithms to reconstruct absorption coefficients distribution of series 3-dimensionalnal phantoms. We propose several neural networks with various architectures and compare their performances with the conjugate gradient descent method. We demonstrate that deep learning has a good performance in reconstructing DOT images compared to the model-based method.