DIFFnet: Diffusion Parameter Mapping Network Generalized for Input Diffusion Gradient Schemes and b-Value.

In MRI, deep neural networks have been proposed to reconstruct diffusion model parameters. However, the inputs of the networks were designed for a specific diffusion gradient scheme (i.e., diffusion gradient directions and numbers) and a specific b-value that are the same as the training data. In this study, a new deep neural network, referred to as DIFFnet, is developed to function as a generalized reconstruction tool of the diffusion-weighted signals for various gradient schemes and b-values. For generalization, diffusion signals are normalized in a q-space and then projected and quantized, producing a matrix (Qmatrix) as an input for the network. To demonstrate the validity of this approach, DIFFnet is evaluated for diffusion tensor imaging (DIFFnetDTI) and for neurite orientation dispersion and density imaging (DIFFnetNODDI). In each model, two datasets with different gradient schemes and b-values are tested. The results demonstrate accurate reconstruction of the diffusion parameters at substantially reduced processing time (approximately 8.7 times and 2240 times faster processing time than conventional methods in DTI and NODDI, respectively; less than 4% mean normalized root-mean-square errors (NRMSE) in DTI and less than 8% in NODDI). The generalization capability of the networks was further validated using reduced numbers of diffusion signals from the datasets and a public dataset from Human Connection Project. Different from previously proposed deep neural networks, DIFFnet does not require any specific gradient scheme and b-value for its input. As a result, it can be adopted as an online reconstruction tool for various complex diffusion imaging.

DeepResp: Deep learning solution for respiration-induced B0 fluctuation artifacts in multi-slice GRE.

Respiration-induced B0 fluctuation corrupts MRI images by inducing phase errors in k-space. A few approaches such as navigator have been proposed to correct for the artifacts at the expense of sequence modification. In this study, a new deep learning method, which is referred to as DeepResp, is proposed for reducing the respiration-artifacts in multi-slice gradient echo (GRE) images. DeepResp is designed to extract the respiration-induced phase errors from a complex image using deep neural networks. Then, the network-generated phase errors are applied to the k-space data, creating an artifact-corrected image. For network training, the computer-simulated images were generated using artifact-free images and respiration data. When evaluated, both simulated images and in-vivo images of two different breathing conditions (deep breathing and natural breathing) show improvements (simulation: normalized root-mean-square error (NRMSE) from 7.8 ± 5.2% to 1.3 ± 0.6%; structural similarity (SSIM) from 0.88 ± 0.08 to 0.99 ± 0.01; ghost-to-signal-ratio (GSR) from 7.9 ± 7.2% to 0.6 ± 0.6%; deep breathing: NRMSE from 13.9 ± 4.6% to 5.8 ± 1.4%; SSIM from 0.86 ± 0.03 to 0.95 ± 0.01; GSR 20.2 ± 10.2% to 5.7 ± 2.3%; natural breathing: NRMSE from 5.2 ± 3.3% to 4.0 ± 2.5%; SSIM from 0.94 ± 0.04 to 0.97 ± 0.02; GSR 5.7 ± 5.0% to 2.8 ± 1.1%). Our approach does not require any modification of the sequence or additional hardware, and may therefore find useful applications. Furthermore, the deep neural networks extract respiration-induced phase errors, which is more interpretable and reliable than results of end-to-end trained networks.

Genetic susceptibility of eight nonsynonymous polymorphisms in HLA-DRB1 gene to hepatocellular carcinoma in Han Chinese.

Backgrounds and Objective: Mounting evidence suggests that human leukocyte antigen (HLA) plays a central role in anti-virus and tumor defense. To test whether genetic variation in HLA-DRB1 gene, a key component of HLA system, can predict its predisposition to hepatocellular carcinoma (HCC), we thereby conducted an association study by genotyping 8 nonsynonymous polymorphisms in HLA-DRB1 gene among 257 HCC patients and 264 controls. RESULTS: All polymorphisms respected the Hardy-Weinberg equilibrium. The genotypes and alleles of rs17879599 differed significantly between patients and controls after Bonferroni correction (both P < 0.001), and the power to detect this significance was 94.4%. After adjusting for age, gender, smoking, drinking and hepatitis infection, the mutant allele of rs17879702 was significantly associated with an increased risk for HCC under additive (odds ratio [OR] = 2.12, 95% confidence interval [CI]: 1.20-4.02, P = 0.004) and dominant (OR = 2.51, 95% CI: 1.39-2.96, P = 0.004) models. Haplotype analysis indicated that haplotype A-T-C-T-G-C-T-A (alleles ordered by rs199514452, rs201540428, rs201614260, rs17879702, rs17880292, rs17879599, rs17424145 and rs35445101) was overrepresented in patients and enhanced predisposition to HCC (adjusted OR = 2.72, 95% CI: 1.24-5.78, P = 0.004). In cumulative analysis, carriers of 7-9 unfavorable alleles had a 2.41-fold (95% CI: 1.18-4.92, P = 0.016) increased risk for HCC after adjusting for confounding factors relative to those possessing 4 or less unfavorable alleles. MATERIALS AND METHODS: Genotypes were determined by ligase detection reaction. HCC patients were newly diagnosed, histopathologically confirmed or previously untreated and controls were cancer-free. CONCLUSIONS: Our findings suggest an independent leading contribution of rs17879599 in the 2nd exon of HLA-DRB1 gene to HCC risk in Han Chinese.