A rened analytical model for reconstruction problems in diuse reectance spectroscopy

A rened analytical model of spatially resolved diffuse reectance with small source-detector separations(SDSs)for the in vivo skin studies is proposed.Compared to the conventional model developed by Farrell et al.,it accounts for the limited acceptance angle of the detectorber.The rened model is validated in the wide range of optical parameters by Monte Carlo simulations of skin diffuse reectance at SDSs of units of mm.Cases of uniform dermis and two-layered epidermis-dermis structures are studied.Higher accuracy of the rened model compared to the conventional one is demonstrated in the separate,constraint-free reconstruction of absorption and reduced scattering spectra of uniform dermis from the Monte Carlo simulated data.In the case of epidermis-dermis geometry,the recovered values of reduced scattering in dermis are overestimated and the recovered values of absorption are underestimated for both analytical models.Presumably,in the presence of a thin mismatched topical layer,only the effective attenuation coe±cient of the bottom layer can be accurately recovered using a diffusion theorybased analytical model while separate reconstruction of absorption and reduced scattering fails due to the inapplicability of the method of images.These-ndings require implementation of more sophisticated models of light transfer in inhomogeneous media in the recovery algorithms.

Toward Improved Accuracy in Quasi-Static Elastography Using Deep Learning

Elastography is a non-invasive medical imaging technique to map the spatial variation of elastic properties of soft tissues.The quality of reconstruction results in elastography is highly sensitive to the noise induced by imaging measurements and processing.To address this issue,we propose a deep learning(DL)model based on conditional Generative Adversarial Networks(cGANs)to improve the quality of nonhomogeneous shear modulus reconstruction.To train this model,we generated a synthetic displacement field with finite element simulation under known nonhomogeneous shear modulus distribution.Both the simulated and experimental displacement fields are used to validate the proposed method.The reconstructed results demonstrate that the DL model with synthetic training data is able to improve the quality of the reconstruction compared with the well-established optimization method.Moreover,we emphasize that our DL model is only trained on synthetic data.This might provide a way to alleviate the challenge of obtaining clinical or experimental data in elastography.Overall,this work addresses several fatal issues in applying the DL technique into elastography,and the proposed method has shown great potential in improving the accuracy of the disease diagnosis in clinical medicine.

Region stepwise reconstruction method based on two source–detector-separation groups for reconstructing background optical properties of two-layered slab sample

The accuracy of the background optical properties has a considerable effect on the quality of reconstructed images in near-infrared functional brain imaging based on continuous wave diffuse optical tomography（CW-DOT）. We propose a region stepwise reconstruction method in CW-DOT scheme for reconstructing the background absorption and reduced scattering coefficients of the two-layered slab sample with the known geometric information. According to the relation between the thickness of the top layer and source– detector separation, the conventional measurement data are divided into two groups and are employed to reconstruct the top and bottom background optical properties, respectively. The numerical simulation results demonstrate that the proposed method can reconstruct the background optical properties of two-layered slab sample effectively. The region-of-interest reconstruction results are better than those of the conventional simultaneous reconstruction method.