TY - JOUR
T1 - Deep learning based Image reconstruction for MRI guided near infra-red spectral tomography
AU - Feng, Jinchao
AU - Zhang, Wanlong
AU - Jia, Kebin
AU - Jiang, Shudong
AU - Dehghani, Hamid
AU - Pogue, Brian
AU - Paulsen, Keith D.
PY - 2022/3
Y1 - 2022/3
N2 - Non-invasive Near infrared spectral tomography (NIRST) can incorporate the structural information provided by simultaneous magnetic resonance imaging (MRI), and this has significantly improved the images obtained of tissue function. However, the process of MRI-guidance in NIRST has been time consuming because of the needs for tissue-type segmentation and forward diffuse modeling of light propagation. To overcome these problems, a novel reconstruction algorithm for MRI guided NIRST based on deep learning has been proposed and validated by simulation and real patient imaging data for breast cancer characterization. In this approach, diffused optical signals and MRI images were both used as the input to the neural network, and simultaneously recovered the concentrations of oxy-hemoglobin, deoxy-hemoglobin, and water via end-to-end training by using 20, 000 sets of computer generated simulation phantoms. The simulation phantom studies showed that the quality of the re-constructed images have been improved, when compared to that obtained by other existing reconstruction methods. Reconstructed patient images show that the well-trained neural network with only simulation data sets can be directly used for differentiating the malignant, from benign breast tumor.
AB - Non-invasive Near infrared spectral tomography (NIRST) can incorporate the structural information provided by simultaneous magnetic resonance imaging (MRI), and this has significantly improved the images obtained of tissue function. However, the process of MRI-guidance in NIRST has been time consuming because of the needs for tissue-type segmentation and forward diffuse modeling of light propagation. To overcome these problems, a novel reconstruction algorithm for MRI guided NIRST based on deep learning has been proposed and validated by simulation and real patient imaging data for breast cancer characterization. In this approach, diffused optical signals and MRI images were both used as the input to the neural network, and simultaneously recovered the concentrations of oxy-hemoglobin, deoxy-hemoglobin, and water via end-to-end training by using 20, 000 sets of computer generated simulation phantoms. The simulation phantom studies showed that the quality of the re-constructed images have been improved, when compared to that obtained by other existing reconstruction methods. Reconstructed patient images show that the well-trained neural network with only simulation data sets can be directly used for differentiating the malignant, from benign breast tumor.
UR - http://www.scopus.com/inward/record.url?scp=85127581272&partnerID=8YFLogxK
U2 - 10.1364/OPTICA.446576
DO - 10.1364/OPTICA.446576
M3 - Article
SN - 2334-2536
VL - 9
SP - 264
EP - 267
JO - Optica
JF - Optica
IS - 3
ER -