Experimental investigation of neural network estimator and transfer learning techniques for K-edge spectral CT imaging.

PURPOSE: Spectral computed tomography (CT) material decomposition algorithms require accurate physics-based models or empirically derived models. This study investigates a machine learning algorithm and transfer learning techniques for Spectral CT imaging of K-edge contrast agents using simulated and experimental measurements. METHODS: A feed forward multilayer perceptron was implemented and trained on data acquired using a step wedge phantom containing acrylic, aluminum, and gadolinium materials. The neural network estimator was evaluated by scanning a rod phantom with varying dilutions of gadolinium oxide nanoparticles and by scanning a rat leg specimen with injected nanoparticles on a bench-top photon-counting computed tomography system. The algorithm decomposed each spectral projection measurement into path lengths of acrylic and aluminum and mass lengths of gadolinium. Each basis material sinogram was reconstructed into basis material images using filtered backprojection. Machine learning techniques of data standardization, transfer learning from aggregated pixel data, and transfer learning from simulations were investigated to improve image quality. The algorithm was compared to a previously published empirical method based on a linear approximation and calibration error look-up tables. RESULTS: The combined transfer learning techniques did not improve quantification in the rod phantom and provided only a small qualitative improvement in ring artifacts. Transfer learning from aggregated pixel data and from simulations improved the qualitative image quality of the rat specimen, for which the calibration data were limited. Transfer learning from aggregated pixel data and simulations estimated 3.26, 6.26, and 12.45 mg/mL Gd concentrations compared to true 2.72, 5.44, and 10.88 mg/mL concentrations in the rod phantom. Additionally, the neural networks were able to separate the soft tissue, bone, and gadolinium nanoparticles of the ex vivo rat leg specimen into the different basis images. CONCLUSIONS: The results demonstrate that empirical K-edge imaging from calibration measurements using machine learning and transfer learning is possible without explicit models of material attenuations, incident spectra, or the detector response.

Vascular Interventional Radiology-Guided Photothermal Therapy of Colorectal Cancer Liver Metastasis with Theranostic Gold Nanorods.

We report sub-100 nm optical/magnetic resonance (MR)/X-ray contrast-bearing theranostic nanoparticles (TNPs) for interventional image-guided photothermal therapy (PTT) of solid tumors. TNPs were composed of Au@Gd2O3:Ln (Ln = Yb/Er) with X-ray contrast (∼486 HU; 1014 NPs/mL, 0.167 nM) and MR contrast (∼1.1 × 108 mM-1 S-1 at 9.4 T field strength). Although TNPs are deposited in tumors following systemic administration via enhanced permeation and retention effect, the delivered dose to tumors is typically low; this can adversely impact the efficacy of PTT. To overcome this limitation, we investigated the feasibility of site-selective hepatic image-guided delivery of TNPs in rats bearing colorectal liver metastasis (CRLM). The mesenteric vein of tumor-bearing rats was catheterized, and TNPs were infused into the liver by accessing the portal vein for site-selective delivery. The uptake of TNPs with hepatic delivery was compared with systemic administration. MR imaging confirmed that delivery via the hepatic portal vein can double the CRLM tumor-to-liver contrast compared with systemic administration. Photothermal ablation was performed by inserting a 100 µm fiber-optic carrying 808 nm light via a JB1, 3-French catheter for 3 min under DynaCT image guidance. Histological analysis revealed that the thermal damage was largely confined to the tumor region with minimal damage to the adjacent liver tissue. Transmission electron microscopy imaging validated the stability of core-shell structure of TNPs in vivo pre- and post-PTT. TNPs comprising Gd-shell-coated Au nanorods can be effectively employed for the site-directed PTT of CRLM by leveraging interventional radiology methods.

Preparation and structure refinement of Eu3+ doped CaMoO4 nanoparticles.

The nanoparticles of CaMoO(4) : Eu(3+) (Eu(3+) = 0, 1, 3, 5, 7, 10 at. %) are prepared at low temperature (150 °C for 3 h) using urea hydrolysis in ethylene glycol. These are characterized by X-ray diffraction (XRD), infrared spectroscopy (IR) and transmission electron microscopy (TEM). From XRD study, it was found that the solubility limit of Eu(3+) ions at the Ca(2+) sites is up to 3 at. % and above this, phase segregation occurs. In combination with Rietveld analysis, its crystal structure was found to be tetragonal phase (space group I4(1)/a (88) and Z = 4 (number of CaMoO(4) formula units per unit cell). Unit cell parameters and bond distances are calculated. The average crystallite sizes of as-prepared, 500 and 900 °C heated samples are found to be 20, 35 and 70 nm, respectively. The lattice strain is found to be 0.003-0.005. From IR study, the bands at 820 and 441 cm(-1) are assigned to asymmetric stretching and bending vibrations of the MoO(4)(2-) tetrahedron, respectively. From TEM study, the shape of particle was found to be spherical. The high resolution TEM suggests a change in orientation of the crystal on annealing up to 900 °C.

Luminescence properties of Eu3+ doped CaMoO4 nanoparticles.

When Eu(3+) ions occupy Ca(2+) sites of CaMoO(4), which has a body centered tetragonal structure with inversion symmetry, only the magnetic dipole transition ((5)D(0)→(7)F(1)) should be allowed according to Judd-Ofelt theory. Even if there are a few distortions in the Eu(3+) environment, its intensity should be more than that of the electric dipole transition ((5)D(0)→(7)F(2)). We report here the opposite effect experimentally and ascribe this to the polarizability effect of the MoO(4) tetrahedron, which is neighboring to EuO(8) (symmetric environment). The contribution of the energy transfer process from the Mo-O charge transfer band to Eu(3+) and the role of Eu(3+) over the surface of the particle could be distinguished when luminescence decay processes were measured at two different excitations (250 and 398 nm). Further, the luminescence intensities and lifetimes increase significantly with increasing heat-treatment temperature of the doped samples. This is attributed to the reduction of H(2)O from the surface of the particles and a non-radiative process after heat treatment.