Vertically Integrated Monolithic Neuromorphic Nanowire Device for Physiological Information Processing.

This study demonstrates the conceptual design and fabrication of a vertically integrated monolithic (VIM) neuromorphic device. The device comprises an n-type SnO2 nanowire bottom channel connected by a shared gate to a p-type P3HT nanowire top channel. This architecture establishes two distinct neural pathways with different response behaviors. The device generates excitatory and inhibitory postsynaptic currents, mimicking the corelease mechanism of bilingual synapses. To enhance the signal processing efficiency, we employed a bipolar spike encoding strategy to convert fluctuating sensory signals to spike trains containing positive and negative pulses. Utilizing the neuromorphic platform for synaptic processing, physiological signals featuring bidirectional fluctuations, including electrocardiogram and breathing signals, can be classified with an accuracy of over 90%. The VIM device holds considerable promise as a solution for developing highly integrated neuromorphic hardware for healthcare and edge intelligence applications.

Vasculogenic mimicry triggers early recidivation and resistance to adjuvant therapy in esophageal cancer.

OBJECTIVE: To investigate the impact of vasculogenic mimicry (VM) and postoperative adjuvant therapy on the prognosis and survival of patients with esophageal squamous cell carcinoma (ESCC), as well as to assess whether VM affects the clinical benefit of postoperative adjuvant therapy. METHODS: This single-center retrospective analysis included patients who underwent radical surgery for ESCC, which was documented in the medical record system. The presence or absence of VM in surgical specimens was determined using double staining with PAS/CD31. Stratification was applied based on adjuvant therapy and VM status. Survival curves and COX modeling were used to analyze the impact of the presence or absence of VM on the benefit of adjuvant therapy and the survival prognosis of patients. RESULTS: VM-positive patients were more prone to postoperative recurrence and metastasis. VM was identified as an independent risk factor for progression-free survival (PFS) (p < 0.001, 95% CI:1.809-3.852) and overall survival (OS) (p < 0.001, 95% CI:1.603-2.786) in postoperative ESCC. Postoperative adjuvant therapy significantly prolonged PFS (p = 0.008) and OS time (p < 0.001) in patients with stage II and III ESCC, with concurrent chemoradiotherapy being the most effective. However, the presence of VM significantly reduced the benefits of postoperative adjuvant therapy (p < 0.001). CONCLUSION: VM negatively impacts the prognosis of postoperative ESCC patients and reduces the efficacy of postoperative adjuvant therapy.

Atmospheric Light Estimation Using Polarization Degree Gradient for Image Dehazing.

A number of image dehazing techniques depend on the estimation of atmospheric light intensity. The majority of dehazing algorithms do not incorporate a physical model to estimate atmospheric light, leading to reduced accuracy and significantly impacting the effectiveness of dehazing. This article presents a novel approach for estimating atmospheric light using the polarization state and polarization degree gradient of the sky. We utilize this approach to enhance the outcomes of image dehazing by applying it to pre-existing dehazing algorithms. Our study and development of a real-time dehazing system has shown that the approach we propose has a clear advantage over previous methods for estimating ambient light. After incorporating the proposed approach into existing defogging methods, a significant improvement in the effectiveness of defogging was noted through the assessment of various criteria such as contrast, PSNR, and SSIM.

TransConv: Transformer Meets Contextual Convolution for Unsupervised Domain Adaptation.

Unsupervised domain adaptation (UDA) aims to reapply the classifier to be ever-trained on a labeled source domain to a related unlabeled target domain. Recent progress in this line has evolved with the advance of network architectures from convolutional neural networks (CNNs) to transformers or both hybrids. However, this advance has to pay the cost of high computational overheads or complex training processes. In this paper, we propose an efficient alternative hybrid architecture by marrying transformer to contextual convolution (TransConv) to solve UDA tasks. Different from previous transformer based UDA architectures, TransConv has two special aspects: (1) reviving the multilayer perception (MLP) of transformer encoders with Gaussian channel attention fusion for robustness, and (2) mixing contextual features to highly efficient dynamic convolutions for cross-domain interaction. As a result, TransConv enables to calibrate interdomain feature semantics from the global features and the local ones. Experimental results on five benchmarks show that TransConv attains remarkable results with high efficiency as compared to the existing UDA methods.

Observer studies of image quality of denoising reduced-count cardiac single photon emission computed tomography myocardial perfusion imaging by three-dimensional Gaussian post-reconstruction filtering and deep learning.

BACKGROUND: The aim of this research was to asses perfusion-defect detection-accuracy by human observers as a function of reduced-counts for 3D Gaussian post-reconstruction filtering vs deep learning (DL) denoising to determine if there was improved performance with DL. METHODS: SPECT projection data of 156 normally interpreted patients were used for these studies. Half were altered to include hybrid perfusion defects with defect presence and location known. Ordered-subset expectation-maximization (OSEM) reconstruction was employed with the optional correction of attenuation (AC) and scatter (SC) in addition to distance-dependent resolution (RC). Count levels varied from full-counts (100%) to 6.25% of full-counts. The denoising strategies were previously optimized for defect detection using total perfusion deficit (TPD). Four medical physicist (PhD) and six physician (MD) observers rated the slices using a graphical user interface. Observer ratings were analyzed using the LABMRMC multi-reader, multi-case receiver-operating-characteristic (ROC) software to calculate and compare statistically the area-under-the-ROC-curves (AUCs). RESULTS: For the same count-level no statistically significant increase in AUCs for DL over Gaussian denoising was determined when counts were reduced to either the 25% or 12.5% of full-counts. The average AUC for full-count OSEM with solely RC and Gaussian filtering was lower than for the strategies with AC and SC, except for a reduction to 6.25% of full-counts, thus verifying the utility of employing AC and SC with RC. CONCLUSION: We did not find any indication that at the dose levels investigated and with the DL network employed, that DL denoising was superior in AUC to optimized 3D post-reconstruction Gaussian filtering.

Restoration of Spatially Variant Blurred Images with Wide-Field Telescope Based on Deep Learning.

The wide-field telescope is a research hotspot in the field of aerospace. Increasing the field of view of the telescope can expand the observation range and enhance the observation ability. However, a wide field will cause some spatially variant optical aberrations, which makes it difficult to obtain stellar information accurately from astronomical images. Therefore, we propose a network for restoring wide-field astronomical images by correcting optical aberrations, called ASANet. Based on the encoder-decoder structure, ASANet improves the original feature extraction module, adds skip connection, and adds a self-attention module. With these methods, we enhanced the capability to focus on the image globally and retain the shallow features in the original image to the maximum extent. At the same time, we created a new dataset of astronomical aberration images as the input of ASANet. Finally, we carried out some experiments to prove that the structure of ASANet is meaningful from two aspects of the image restoration effect and quality evaluation index. According to the experimental results, compared with other deblur networks, the PSNR and SSIM of ASANet are improved by about 0.5 and 0.02 db, respectively.

Nonuniform Correction of Ground-Based Optical Telescope Image Based on Conditional Generative Adversarial Network.

Ground-based telescopes are often affected by vignetting, stray light and detector nonuniformity when acquiring space images. This paper presents a space image nonuniform correction method using the conditional generative adversarial network (CGAN). Firstly, we create a dataset for training by introducing the physical vignetting model and by designing the simulation polynomial to realize the nonuniform background. Secondly, we develop a robust conditional generative adversarial network (CGAN) for learning the nonuniform background, in which we improve the network structure of the generator. The experimental results include a simulated dataset and authentic space images. The proposed method can effectively remove the nonuniform background of space images, achieve the Mean Square Error (MSE) of 4.56 in the simulation dataset, and improve the target's signal-to-noise ratio (SNR) by 43.87% in the real image correction.

Improving detection accuracy of perfusion defect in standard dose SPECT-myocardial perfusion imaging by deep-learning denoising.

BACKGROUND: We previously developed a deep-learning (DL) network for image denoising in SPECT-myocardial perfusion imaging (MPI). Here we investigate whether this DL network can be utilized for improving detection of perfusion defects in standard-dose clinical acquisitions. METHODS: To quantify perfusion-defect detection accuracy, we conducted a receiver-operating characteristic (ROC) analysis on reconstructed images with and without processing by the DL network using a set of clinical SPECT-MPI data from 190 subjects. For perfusion-defect detection hybrid studies were used as ground truth, which were created from clinically normal studies with simulated realistic lesions inserted. We considered ordered-subset expectation-maximization (OSEM) reconstruction with corrections for attenuation, resolution, and scatter and with 3D Gaussian post-filtering. Total perfusion deficit (TPD) scores, computed by Quantitative Perfusion SPECT (QPS) software, were used to evaluate the reconstructed images. RESULTS: Compared to reconstruction with optimal Gaussian post-filtering (sigma = 1.2 voxels), further DL denoising increased the area under the ROC curve (AUC) from 0.80 to 0.88 (P-value < 10-4). For reconstruction with less Gaussian post-filtering (sigma = 0.8 voxels), thus better spatial resolution, DL denoising increased the AUC value from 0.78 to 0.86 (P-value < 10-4) and achieved better spatial resolution in reconstruction. CONCLUSIONS: DL denoising can effectively improve the detection of abnormal defects in standard-dose SPECT-MPI images over conventional reconstruction.

[Machine learning-based method for interpreting the guidelines of the diagnosis and treatment of COVID-19].

The outbreak of pneumonia caused by novel coronavirus (COVID-19) at the end of 2019 was a major public health emergency in human history. In a short period of time, Chinese medical workers have experienced the gradual understanding, evidence accumulation and clinical practice of the unknown virus. So far, National Health Commission of the People's Republic of China has issued seven trial versions of the "Guidelines for the Diagnosis and Treatment of COVID-19". However, it is difficult for clinicians and laymen to quickly and accurately distinguish the similarities and differences among the different versions and locate the key points of the new version. This paper reports a computer-aided intelligent analysis method based on machine learning, which can automatically analyze the similarities and differences of different treatment plans, present the focus of the new version to doctors, reduce the difficulty in interpreting the "diagnosis and treatment plan" for the professional, and help the general public better understand the professional knowledge of medicine. Experimental results show that this method can achieve the topic prediction and matching of the new version of the program text through unsupervised learning of the previous versions of the program topic with an accuracy of 100%. It enables the computer interpretation of "diagnosis and treatment plan" automatically and intelligently.

Two-dimensional plumbum-doped tin diselenide monolayer transistor with high on/off ratio.

Doping can effectively regulate the electrical and optical properties of two-dimensional semiconductors. Here, we present high-quality Pb-doped SnSe2 monolayer exfoliated using a micromechanical cleavage method. X-ray photoelectron spectroscopy measurement demonstrates that Pb content of the doped sample is ∼3.6% and doping induces the downward shift of the Fermi level with respect to the pure SnSe2. Transmission electron microscopy characterization exhibits that Pb0.036Sn0.964Se2 nanosheets have a high-quality hexagonal symmetry structure and Pb element is uniformly distributed in the nanosheets. The current of the SnSe2 field effect transistors (FETs) was found to be very difficult to turn off due to the high electron density. The FETs based on the Pb0.036Sn0.964Se2 monolayer show n-type behavior with a high on/off ratio of 106 which is higher than any values of SnSe2 FETs reported at the moment. The estimated carrier concentration of Pb0.036Sn0.964Se2 is approximately six times lower than that of SnSe2. The results suggest that the method of reducing carrier concentration by doping to achieve high on/off ratio is effective, and Pb-doped SnSe2 monolayer has significant potential in future nanoelectronic and optoelectronic applications.

Cultivation and morphology of jujube (Ziziphus Jujuba Mill.) in the Qi River Basin of Northern China during the Neolithic Period.

This transition from gathering to cultivation is a significant aspect of studying early agricultural practices. Fruit trees are an essential component of food resources and have played a vital role in both ancient and modern agricultural production systems. The jujube (Ziziphus jujuba Mill.), with its long history of cultivation in northern China, holds great importance in uncovering the diet of prehistoric humans and understanding the origins of Chinese agricultural civilization. This paper focuses on the domestication of jujube by analyzing the morphology of jujube stones found in three Neolithic sites in northern China's Qi River basin, Zhujia, Wangzhuang, and Dalaidian. The measurements of these jujube kernels are compared with those found in other areas of northern China, as well as modern jujube kernels that were collected. The measurements revealed that the length-to-diameter (L/D) ratio of sour jujube kernels ranged from 1.36 to 1.78, whereas the L/D ratio of cultivated jujube stones varied between 1.96 and 4.23. Furthermore, jujube stones obtained from Zhujia and Wangzhuang sites exhibit pointed ends and possess an elongated oval or narrow oval shape overall, which is indicative of clearly artificial domestication traits. Therefore, this study suggests that jujube was selected and cultivated as an important food supplement in the Qi River basin no later than around 6200 BP.

COE targets EphA2 to inhibit vasculogenic mimicry formation induced by hypoxia in hepatocellular carcinoma.

Background: Vasculogenic Mimicry (VM) can reduce the efficacy of anti-angiogenesis and promote distant metastasis in hepatocellular carcinoma (HCC). Our previous studies have found that Celastrus orbiculatus extract (COE) can inhibit the VM formation in HCC by reducing EphA2 expression. However the underlying mechanism related to EphA2 in VM formation is unclear. Purpose: This study aimed to confirm that EphA2 is one of the potential targets of COE, and to explore the effect of EphA2 in VM formation in hypoxia context in HCC. Methods: TCM Systems Pharmacology database and proteomics analysis were used to explore the key targets of COE in HCC treatment. CD31-PAS double staining and VE-CAD staining were used to indicate vasculogenic mimicry. The localization of EphA2 and VE-CAD was examined through fluorescent microscopy. CCK8 assay, cell invasion assay, and tube formation assay were used to indicate the formation of VM under hypoxic conditions. The regulatory relationship of EphA2 upstream and downstream molecules were evaluated through COIP and Western Blot. The nude mouse xenograft tumor models were used to observe the VM formation after knocking down or overexpressing EphA2. Results: EphA2 is identified to the target of COE, and the driving gene of HCC. In HCC surgical specimens, EphA2 expression is closely associated with the VM formation of HCC. COE-regulated EphA2 is involved in hypoxia-induced VM formation in HCC cells in vitro. EphA2 is regulated by HIF directly or indirectly by C-MYC. Overexpression of EphA2 can promote the VM formation of HCC in nude mice, while knocking down EphA2 can inhibit the VM formation. Conclusion: EphA2, as a target of COE, plays a crucial regulatory role in the formation of vasculogenic mimicry in HCC, involving upstream HIF/MYC transcriptional promotion and downstream PI3K/FAK/VE-CAD expression regulation.

AI-Powered Microfluidics: Shaping the Future of Phenotypic Drug Discovery.

Phenotypic drug discovery (PDD), which involves harnessing biological systems directly to uncover effective drugs, has undergone a resurgence in recent years. The rapid advancement of artificial intelligence (AI) over the past few years presents numerous opportunities for augmenting phenotypic drug screening on microfluidic platforms, leveraging its predictive capabilities, data analysis, efficient data processing, etc. Microfluidics coupled with AI is poised to revolutionize the landscape of phenotypic drug discovery. By integrating advanced microfluidic platforms with AI algorithms, researchers can rapidly screen large libraries of compounds, identify novel drug candidates, and elucidate complex biological pathways with unprecedented speed and efficiency. This review provides an overview of recent advances and challenges in AI-based microfluidics and their applications in drug discovery. We discuss the synergistic combination of microfluidic systems for high-throughput screening and AI-driven analysis for phenotype characterization, drug-target interactions, and predictive modeling. In addition, we highlight the potential of AI-powered microfluidics to achieve an automated drug screening system. Overall, AI-powered microfluidics represents a promising approach to shaping the future of phenotypic drug discovery by enabling rapid, cost-effective, and accurate identification of therapeutically relevant compounds.

Image-based motion artifact reduction on liver dynamic contrast enhanced MRI.

Liver MRI images often suffer from degraded quality due to ghosting or blurring artifacts caused by patient respiratory or bulk motion. In this study, we developed a two-stage deep learning model to reduce motion artifact on dynamic contrast enhanced (DCE) liver MRIs. The stage-I network utilized a deep residual network with a densely connected multi-resolution block (DRN-DCMB) network to remove most motion artifacts. The stage-II network applied the generative adversarial network (GAN) and perceptual loss compensation to preserve image structural features. The stage-I network served as the generator of GAN and its pretrained parameters in stage-I were further updated via backpropagation during stage-II training. The stage-I network was trained using small image patches with simulated motion artifacts including image-space rotational and translational motion, and K-space based centric and interleaved linear motion, sinusoidal, and rotational motion to mimic liver motion patterns. The stage-II network training used full-size images with the same types of simulated motion. The liver DCE-MRI image volumes without obvious motion artifacts in 10 patients were used for the training process, of which 1020 images of 8 patients were used for training and 240 images of 2 patients for validation. Finally, the whole two-stage deep learning model was tested with simulated motion images (312 clean images from 5 test patients) and patient images with real motion artifacts (28 motion images from 12 patients). The resulted images after two-stage processing demonstrated reduced motion artifacts while preserved anatomic details without image blurriness, with SSIM of 0.935 ± 0.092, MSE of 60.7 ± 9.0 × 10-3, and PSNR of 32.054 ± 2.219.

Genome-wide association study (GWAS) analysis of black color trait in the leopard coral grouper (Plectropomus leopardus) using whole genome resequencing.

The leopard coral grouper (Plectropomus leopardus) is a coral reef fish species that exhibits rapid and diverse color variation. However, the presence of melanoma and the high proportion of individuals displaying black color in artificial breeding have led to reduced economic and ornamental value. To pinpoint single nucleotide polymorphisms (SNPs) and potential genes linked to the black pigmentation characteristic in this particular species, This study gathered a cohort of 360 specimens from diverse origins and conducted a comprehensive genome-wide association analysis (GWAS) employing whole-genome resequencing. As a result, 57 SNPs related to the black skin trait were identified, and a grand total of 158 genes were annotated within 50 kb of these SNPs. Subsequently, GWAS was applied to three populations (LED, QHH, and QHL), and the corresponding results were compared with the analysis results of the total population. The results of the four GWAS models showed significant enrichment in Rap1 signaling pathway, melanin biosynthesis, metabolic pathways, tyrosine metabolism, cAMP signaling pathway, AMPK signaling pathway, PI3K-Akt signaling pathway, EGFR tyrosine kinase inhibitor resistance, HIF-1 signaling pathway, Ras signaling pathway, MAPK signaling pathway, etc. (p < 0.05), which were mainly associated with eleven genes (POL4, MET, E2F2, COMT, ZBED1, TYRP2, FOXP2, THIKA, LORF2, MYH16 and SOX2). Significant differences (p < 0.05) were observed in the expression of all 11 genes in the dorsal skin tissue, in 10 genes except COMT in the ventral skin tissue, and in all 11 genes in the caudal fin tissue. These findings imply that the control of body color in the P. leopardus is the result of the joint action of multiple genes and signaling pathways. These findings will contribute to a more profound comprehension of the genetic attributes that underlie the development of black skin in the vibrant P. leopardus, thus furnishing a theoretical foundation for genetic enhancement.

An artificially-intelligent cornea with tactile sensation enables sensory expansion and interaction.

We demonstrate an artificially-intelligent cornea that can assume the functions of the native human cornea such as protection, tactile perception, and light refraction, and possesses sensory expansion and interactive functions. These functions are realized by an artificial corneal reflex arc that is constructed to implement mechanical and light information coding, information processing, and the regulation of transmitted light. Digitally-aligned, long and continuous zinc tin oxide (ZTO) semiconductor fabric patterns were fabricated as the active channels of the artificial synapse, which are non-toxic, heavy-metal-free, low-cost, and ensure superior comprehensive optical properties (transmittance >99.89%, haze <0.36%). Precisely-tuned crystal-phase structures of the ZTO fibers enabled reconfigurable synaptic plasticity, which is applicable to encrypted communication and associative learning. This work suggests new strategies for the tuning of synaptic plasticity and the design of visual neuroprosthetics, and has important implications for the development of neuromorphic electronics and for visual restoration.

Contribution of nitrogen sources to streams in mixed-use watershed varies seasonally in a temperate region.

The Beiyun river flows through a hot spot region of Beijing-Tianjin-Hebei in China that serves a majority of occupants. However, the region experiences severe nitrate pollution, posing a threat to human health due to inadequate self-purification capacity. In that context, there is an urgent need to assess nitrate levels in this region. Herein, we used δ15N-NO3, δ18O-NO3 isotopes analysis, and stable isotope analysis model to evaluate the nitrate source apportionment in the Beiyun river. A meta-analysis was then used to compare the potential similarity of nitrate sources among the Beiyun riverine watershed and other watersheds. Results of nitrate source apportionment revealed that nitrate originated from the manure and sewage (contribution rate: 89.6%), soil nitrogen (5.9%), and nitrogen fertilizer (3.9%) in the wet season. While in the dry season, nitrate mainly originated from manure and sewage (91.6%). Furthermore, different land-use types exhibited distinct nitrate compositions. Nitrate in urban and suburban areas mostly was traced from manure and sewage (90.5% and 78.8%, respectively). Notably, the different nitrate contribution in the rural-urban fringe and plant-covered areas were manure and sewage (44.3% and 32.8%), soil nitrogen (26.9% and 35.7%), nitrogen fertilizer (23.5% and 29.4%), and atmospheric deposition (5.3% and 2.0%). Through a meta-analysis, we found nitrogen fertilizer, soil nitrogen, and manure and sewage as the main nitrate sources in the Beiyun riverine watershed or the other similar complexed watersheds in the temperate regions. Thus, this study provides a scientific basis for nitrate source apportionment and nitrate pollution preventive management in watersheds with complexed land-use types in temperate regions.

Deep learning with noise-to-noise training for denoising in SPECT myocardial perfusion imaging.

PURPOSE: Post-reconstruction filtering is often applied for noise suppression due to limited data counts in myocardial perfusion imaging (MPI) with single-photon emission computed tomography (SPECT). We study a deep learning (DL) approach for denoising in conventional SPECT-MPI acquisitions, and investigate whether it can be more effective for improving the detectability of perfusion defects compared to traditional postfiltering. METHODS: Owing to the lack of ground truth in clinical studies, we adopt a noise-to-noise (N2N) training approach for denoising in SPECT-MPI images. We consider a coupled U-Net (CU-Net) structure which is designed to improve learning efficiency through feature map reuse. For network training we employ a bootstrap procedure to generate multiple noise realizations from list-mode clinical acquisitions. In the experiments we demonstrated the proposed approach on a set of 895 clinical studies, where the iterative OSEM algorithm with three-dimensional (3D) Gaussian postfiltering was used to reconstruct the images. We investigated the detection performance of perfusion defects in the reconstructed images using the non-prewhitening matched filter (NPWMF), evaluated the uniformity of left ventricular (LV) wall in terms of image intensity, and quantified the effect of smoothing on the spatial resolution of the reconstructed LV wall by using its full-width at half-maximum (FWHM). RESULTS: Compared to OSEM with Gaussian postfiltering, the DL denoised images with CU-Net significantly improved the detection performance of perfusion defects at all contrast levels (65%, 50%, 35%, and 20%). The signal-to-noise ratio (SNRD ) in the NPWMF output was increased on average by 8% over optimal Gaussian smoothing (P < 10-4 , paired t-test), while the inter-subject variability was greatly reduced. The CU-Net also outperformed a 3D nonlocal means (NLM) filter and a convolutional autoencoder (CAE) denoising network in terms of SNRD . In addition, the FWHM of the LV wall in the reconstructed images was varied by less than 1%. Furthermore, CU-Net also improved the detection performance when the images were processed with less post-reconstruction smoothing (a trade-off of increased noise for better LV resolution), with SNRD improved on average by 23%. CONCLUSIONS: The proposed DL with N2N training approach can yield additional noise suppression in SPECT-MPI images over conventional postfiltering. For perfusion defect detection, DL with CU-Net could outperform conventional 3D Gaussian filtering with optimal setting as well as NLM and CAE.

Spatial feature fusion convolutional network for liver and liver tumor segmentation from CT images.

PURPOSE: The accurate segmentation of liver and liver tumors from CT images can assist radiologists in decision-making and treatment planning. The contours of liver and liver tumors are currently obtained by manual labeling, which is time-consuming and subjective. Computer-aided segmentation methods have been widely used in the segmentation of liver and liver tumors. However, due to the diversity of shape, volume, and image intensity, the segmentation is still a difficult task. In this study, we present a Spatial Feature Fusion Convolutional Network (SFF-Net) to automatically segment liver and liver tumors from CT images. METHODS: First, we extract side-outputs at each convolutional block in SFF-Net to make full use of multiscale features. Second, skip-connections are added in the down-sampling phase, therefore, the spatial information can be efficiently transferred to later layers. Third, we present feature fusion blocks (FFBs) to merge spatial features and high-level semantic features from early layers and later layers, respectively. Finally, a fully connected 3D conditional random fields (CRFs) is applied to refine the liver and liver tumor segmentation results. RESULTS: We test our method on the MICCAI 2017 Liver Tumor Segmentation (LiTS) challenge dataset. The Dice Global (DG) score, Dice per case (DC) score, Volume Overlap Error (VOE), Average Symmetric Surface Distance (ASSD), and tumor precision score are calculated to evaluate the liver and liver tumor segmentation accuracies. For the liver segmentation, DG is 0.955; DC is 0.937; VOE is 0.106; and ASSD is 3.678. For the tumor segmentation, DG is 0.746; DC is 0.592; VOE is 0.416; ASSD is 1.585 and the tumor precision score is 0.369. CONCLUSIONS: The SFF-Net learns more spatial information by adding skip-connections and feature fusion blocks. The experiments validate that our method can accurately segment liver and liver tumors from CT images.

Motion artifacts reduction in brain MRI by means of a deep residual network with densely connected multi-resolution blocks (DRN-DCMB).

OBJECTIVE: Magnetic resonance imaging (MRI) acquisition is inherently sensitive to motion, and motion artifact reduction is essential for improving image quality in MRI. METHODS: We developed a deep residual network with densely connected multi-resolution blocks (DRN-DCMB) model to reduce the motion artifacts in T1 weighted (T1W) spin echo images acquired on different imaging planes before and after contrast injection. The DRN-DCMB network consisted of multiple multi-resolution blocks connected with dense connections in a feedforward manner. A single residual unit was used to connect the input and output of the entire network with one shortcut connection to predict a residual image (i.e. artifact image). The model was trained with five motion-free T1W image stacks (pre-contrast axial and sagittal, and post-contrast axial, coronal, and sagittal images) with simulated motion artifacts. RESULTS: In other 86 testing image stacks with simulated artifacts, our DRN-DCMB model outperformed other state-of-the-art deep learning models with significantly higher structural similarity index (SSIM) and improvement in signal-to-noise ratio (ISNR). The DRN-DCMB model was also applied to 121 testing image stacks appeared with various degrees of real motion artifacts. The acquired images and processed images by the DRN-DCMB model were randomly mixed, and image quality was blindly evaluated by a neuroradiologist. The DRN-DCMB model significantly improved the overall image quality, reduced the severity of the motion artifacts, and improved the image sharpness, while kept the image contrast. CONCLUSION: Our DRN-DCMB model provided an effective method for reducing motion artifacts and improving the overall clinical image quality of brain MRI.