Segmentation Guided Crossing Dual Decoding Generative Adversarial Network for Synthesizing Contrast-Enhanced Computed Tomography Images.

Although contrast-enhanced computed tomography (CE-CT) images significantly improve the accuracy of diagnosing focal liver lesions (FLLs), the administration of contrast agents imposes a considerable physical burden on patients. The utilization of generative models to synthesize CE-CT images from non-contrasted CT images offers a promising solution. However, existing image synthesis models tend to overlook the importance of critical regions, inevitably reducing their effectiveness in downstream tasks. To overcome this challenge, we propose an innovative CE-CT image synthesis model called Segmentation Guided Crossing Dual Decoding Generative Adversarial Network (SGCDD-GAN). Specifically, the SGCDD-GAN involves a crossing dual decoding generator including an attention decoder and an improved transformation decoder. The attention decoder is designed to highlight some critical regions within the abdominal cavity, while the improved transformation decoder is responsible for synthesizing CE-CT images. These two decoders are interconnected using a crossing technique to enhance each other's capabilities. Furthermore, we employ a multi-task learning strategy to guide the generator to focus more on the lesion area. To evaluate the performance of proposed SGCDD-GAN, we test it on an in-house CE-CT dataset. In both CE-CT image synthesis tasks-namely, synthesizing ART images and synthesizing PV images-the proposed SGCDD-GAN demonstrates superior performance metrics across the entire image and liver region, including SSIM, PSNR, MSE, and PCC scores. Furthermore, CE-CT images synthetized from our SGCDD-GAN achieve remarkable accuracy rates of 82.68%, 94.11%, and 94.11% in a deep learning-based FLLs classification task, along with a pilot assessment conducted by two radiologists.

Multitask deep learning for prediction of microvascular invasion and recurrence-free survival in hepatocellular carcinoma based on MRI images.

BACKGROUND AND AIMS: Accurate preoperative prediction of microvascular invasion (MVI) and recurrence-free survival (RFS) is vital for personalised hepatocellular carcinoma (HCC) management. We developed a multitask deep learning model to predict MVI and RFS using preoperative MRI scans. METHODS: Utilising a retrospective dataset of 725 HCC patients from seven institutions, we developed and validated a multitask deep learning model focused on predicting MVI and RFS. The model employs a transformer architecture to extract critical features from preoperative MRI scans. It was trained on a set of 234 patients and internally validated on a set of 58 patients. External validation was performed using three independent sets (n = 212, 111, 110). RESULTS: The multitask deep learning model yielded high MVI prediction accuracy, with AUC values of 0.918 for the training set and 0.800 for the internal test set. In external test sets, AUC values were 0.837, 0.815 and 0.800. Radiologists' sensitivity and inter-rater agreement for MVI prediction improved significantly when integrated with the model. For RFS, the model achieved C-index values of 0.763 in the training set and ranged between 0.628 and 0.728 in external test sets. Notably, PA-TACE improved RFS only in patients predicted to have high MVI risk and low survival scores (p < .001). CONCLUSIONS: Our deep learning model allows accurate MVI and survival prediction in HCC patients. Prospective studies are warranted to assess the clinical utility of this model in guiding personalised treatment in conjunction with clinical criteria.

OA-GAN: organ-aware generative adversarial network for synthesizing contrast-enhanced medical images.

Contrast-enhanced computed tomography (CE-CT) images are vital for clinical diagnosis of focal liver lesions (FLLs). However, the use of CE-CT images imposes a significant burden on patients due to the injection of contrast agents and extended shooting. Deep learning-based image synthesis models offer a promising solution that synthesizes CE-CT images from non-contrasted CT (NC-CT) images. Unlike natural images, medical image synthesis requires a specific focus on certain organs or localized regions to ensure accurate diagnosis. Determining how to effectively emphasize target organs poses a challenging issue in medical image synthesis. To solve this challenge, we present a novel CE-CT image synthesis model called, Organ-Aware Generative Adversarial Network (OA-GAN). The OA-GAN comprises an organ-aware (OA) network and a dual decoder-based generator. First, the OA network learns the most discriminative spatial features about the target organ (i.e. liver) by utilizing the ground truth organ mask as localization cues. Subsequently, NC-CT image and captured feature are fed into the dual decoder-based generator, which employs a local and global decoder network to simultaneously synthesize the organ and entire CECT image. Moreover, the semantic information extracted from the local decoder is transferred to the global decoder to facilitate better reconstruction of the organ in entire CE-CT image. The qualitative and quantitative evaluation on a CE-CT dataset demonstrates that the OA-GAN outperforms state-of-the-art approaches for synthesizing two types of CE-CT images such as arterial phase and portal venous phase. Additionally, subjective evaluations by expert radiologists and a deep learning-based FLLs classification also affirm that CE-CT images synthesized from the OA-GAN exhibit a remarkable resemblance to real CE-CT images.

MSPA-DLA++: A Multi-Scale Phase Attention Deep Layer Aggregation for Lesion Detection in Multi-Phase CT Images.

Object detection using convolutional neural networks (CNNs) has achieved high performance and achieved state-of-the-art results with natural images. Compared to natural images, medical images present several challenges for lesion detection. First, the sizes of lesions vary tremendously, from several millimeters to several centimeters. Scale variations significantly affect lesion detection accuracy, especially for the detection of small lesions. Moreover, the effective extraction of temporal and spatial features from multi-phase CT images is also an important issue. In this paper, we propose a group-based deep layer aggregation method with multiphase attention for liver lesion detection in multi-phase CT images. The method, which is called MSPA-DLA++, is a backbone feature extraction network for anchor-free liver lesion detection in multi-phase CT images that addresses scale variations and extracts hidden features from such images. The effectiveness of the proposed method is demonstrated on public datasets (LiTS2017) and our private multiphase dataset. The results of the experiments show that MSPA-DLA++ can improve upon the performance of state-of-the-art networks by approximately 3.7%.

Unsupervised Domain Adaptation Using Fourier Phase Enhanced Training Images for Liver Tumors Detection in Multi-phase CT Images.

Computer-aided diagnostic methods, such as automatic and precise liver tumor detection, have a significant impact on healthcare. In recent years, deep learning-based liver tumor detection methods in multi-phase computed tomography (CT) images have achieved noticeable performance. Deep learning frameworks require a substantial amount of annotated training data but obtaining enough training data with high quality annotations is a major issue in medical imaging. Additionally, deep learning frameworks experience domain shift problems when they are trained using one dataset (source domain) and applied to new test data (target domain). To address the lack of training data and domain shift issues in multiphase CT images, here, we present an adversarial learning-based strategy to mitigate the domain gap across different phases of multiphase CT scans. We introduce to use Fourier phase component of CT images in order to improve the semantic information and more reliably identify the tumor tissues. Our approach eliminates the requirement for distinct annotations for each phase of CT scans. The experiment results show that our proposed method performs noticeably better than conventional training and other methods.

Multi-task Model for Glioma Segmentation and Isocitrate Dehydrogenase Status Prediction Using Global and Local Features.

According to the 2021 World Health Organization IDH status prediction scheme for gliomas, isocitrate dehydrogenase (IDH) is a particularly important basis for glioma diagnosis. In general, 3D multimodal brain MRI is an effective diagnostic tool. However, only using brain MRI data is difficult for experienced doctors to predict the IDH status. Surgery is necessary to be performed for confirming the IDH. Previous studies have shown that brain MRI images of glioma areas contain a lot of useful information for diagnosis. These studies usually need to mark the glioma area in advance to complete the prediction of IDH status, which takes a long time and has high computational cost. The tumor segmentation task model can automatically segment and locate the tumor region, which is exactly the information needed for the IDH prediction task. In this study, we proposed a multi-task deep learning model using 3D multimodal brain MRI images to achieve glioma segmentation and IDH status prediction simultaneously, which improved the accuracy of both tasks effectively. Firstly, we used a segmentation model to segment the tumor region. Also, the whole MRI image and the segmented glioma region features as the global and local features were used to predict IDH status. The effectiveness of the proposed method was validated via a public glioma dataset from the BraTS2020. Our experimental results show that our proposed method outperformed state-of-the-art methods with a prediction accuracy of 88.5% and average dice of 79.8%. The improvements in prediction and segmentation are 3% and 1% compared with the state-of-the-art method, respectively.

Adaptive Graph Convolutional Networks for Medical Image Segmentation.

Medical image segmentation is very essential for computer-aided diagnosis in the field of medical imaging. In the last decade, Deep Learning-based frameworks (e.g., UNet) have been widely used in medical applications such as image segmentation tasks. Recently, numerous Transformer-based frameworks are presented for the image segmentation tasks as their design can utilize long-range dependencies. Transformer's design has a weak inductive bias since it does not take advantage of local relationships between pixels and lacks scale invariance. Consequently, Transformers require large datasets for convergence whereas the availability of massive medical datasets is challenging. In this paper, we present a graph-based approach replacing Transformer design to capture long-range dependencies and reduce computational cost. Our proposed framework achieves competitive performance using publicly available dataset Synapse.

Spatial Attention-Guided Generative Adversarial Network for Synthesizing Contrast-enhanced Computed Tomography Images.

Compared to non-contrast computed tomography (NC-CT) scans, contrast-enhanced (CE) CT scans provide more abundant information about focal liver lesions (FLLs), which play a crucial role in the FLLs diagnosis. However, CE-CT scans require patient to inject contrast agent into the body, which increase the physical and economic burden of the patient. In this paper, we propose a spatial attention-guided generative adversarial network (SAG-GAN), which can directly obtain corresponding CE-CT images from the patient's NC-CT images. In the SAG-GAN, we devise a spatial attention-guided generator, which utilize a lightweight spatial attention module to highlight synthesis task-related areas in NC-CT image and neglect unrelated areas. To assess the performance of our approach, we test it on two tasks: synthesizing CE-CT images in arterial phase and portal venous phase. Both qualitative and quantitative results demonstrate that SAG-GAN is superior to existing GANs-based image synthesis methods.

Intestinal Microbiota Community and Blood Fatty Acid Profiles of Albas Cashmere Goats Fed with Flaxseed Oil and Whole Flaxseed.

The present study investigated the effects of flaxseed oil or flaxseed grain on the intestinal microbiota and blood fatty acid profiles of Albas cashmere goats. Sixty kid goats were allocated to three treatments and fed for 90 days with a control treatment, comprising a basal diet (CON, total-mixed ration with flaxseed meal), or experimental treatments, comprising a basal diet with added flaxseed oil (LNO) and a basal diet with added heated flaxseed grain (HLS). On day 90, two goats were randomly selected from each pen (eight goats per treatment) for euthanizing; then, five of the eight goats were randomly selected, and we collected their intestinal (duodenum, jejunum, ileum, cecum, and colon) digesta for analysis of the bacteria community. The results indicated that Firmicutes are the most predominant phylum in different segments of the intestinal digesta. Compared with the CON group, the relative abundance of duodenal Firmicutes, jejunal Saccharibacteria, and Verrucomicrobia significantly decreased in the LNO and HLS groups (p < 0.05), but there was no significant difference between the LNO and HLS groups. Compared with the CON and HLS groups, the RA of duodenal and jejunal Proteobacteria remarkably increased in the LNO group (p < 0.05), and there was no significant difference between the CON and HLS groups. Compared with the CON and LNO groups, the RA of Actinobacteria remarkably increased in the small intestine of the HLS group (p < 0.05), but there was no significant difference between the CON and LNO groups in the duodenum and ileum. The results of linear discriminant analysis (LDA) effect size (LEfSe) analysis showed that the HLS group was characterized by a higher RA of the [Eubacterium]_coprostanoligenes_group in the small intestine and the LNO group was represented by a higher RA of the Lachnospiraceae_NK3A20_group in the cecum and colon, while the CON group was represented by a higher RA of Solobacterium, Pseudoramibacter, and Acetitomaculum in the small intestine and a higher RA of norank_o__Bradymonadales, the Prevotellaceae_Ga6A1_group, and Ruminiclostridium_1 in the cecum and colon. In conclusion, the addition of flaxseed oil and grain rich in c18:3n3 to the diet could reduce the microbial diversity of the small intestinal segments and the microbial diversity and richness of the cecum and colon in Albas cashmere goats. And flaxseed grain is more efficient than flaxseed oil in protecting intestinal health and promoting the absorption of c18:3n3.

Effects of Noni (Morinda citrifolia L.) Fruit Extract Supplemented in Cashmere Goats with a High-Concentrate Diet on Growth Performance, Ruminal and Colonic Fermentation and SARA.

This experiment was conducted to investigate the effects of noni fruit extract (NFE) on growth performance, ruminal and colonic fermentation, nutrient digestion, and subacute rumen acidosis (SARA) of cashmere goats with the high-concentrate diet. Twenty-four cashmere kids (17.9 ± 1.45 kg of BW ± SD) were randomly assigned to three treatments: low-concentrate diet, high-concentrate (HC) diet, or HC diet supplemented with NFE at 1 g per kg DM (0.1%). The results showed that although the HC diet improved the average daily gain (ADG) and feed conversion rate (FCR), it was accompanied by SARA with a decreased pH and an increased lactic acid of both rumen and colon, and decreased digestibility of neutral detergent fiber (NDF)and acid detergent fiber (ADF). The supplementation of 0.10% NFE in the HC diet could not only effectively alleviate SARA symptoms and colon fermentation disorders, such as reversing the decrease of pH and alleviating the increase of lactic acid in rumen and colon, but also mitigate the decline of fiber digestibility caused by long-term feeding in the HC diet, and increase the digestibility of crude protein(CP) and dry matter (DM), which improved the ADG and FCR of cashmere kids. Thus, NFE provides new strategies for alleviating SARA and promoting cashmere goat growth.

A Boundary-Enhanced Liver Segmentation Network for Multi-Phase CT Images with Unsupervised Domain Adaptation.

Multi-phase computed tomography (CT) images have gained significant popularity in the diagnosis of hepatic disease. There are several challenges in the liver segmentation of multi-phase CT images. (1) Annotation: due to the distinct contrast enhancements observed in different phases (i.e., each phase is considered a different domain), annotating all phase images in multi-phase CT images for liver or tumor segmentation is a task that consumes substantial time and labor resources. (2) Poor contrast: some phase images may have poor contrast, making it difficult to distinguish the liver boundary. In this paper, we propose a boundary-enhanced liver segmentation network for multi-phase CT images with unsupervised domain adaptation. The first contribution is that we propose DD-UDA, a dual discriminator-based unsupervised domain adaptation, for liver segmentation on multi-phase images without multi-phase annotations, effectively tackling the annotation problem. To improve accuracy by reducing distribution differences between the source and target domains, we perform domain adaptation at two levels by employing two discriminators, one at the feature level and the other at the output level. The second contribution is that we introduce an additional boundary-enhanced decoder to the encoder-decoder backbone segmentation network to effectively recognize the boundary region, thereby addressing the problem of poor contrast. In our study, we employ the public LiTS dataset as the source domain and our private MPCT-FLLs dataset as the target domain. The experimental findings validate the efficacy of our proposed methods, producing substantially improved results when tested on each phase of the multi-phase CT image even without the multi-phase annotations. As evaluated on the MPCT-FLLs dataset, the existing baseline (UDA) method achieved IoU scores of 0.785, 0.796, and 0.772 for the PV, ART, and NC phases, respectively, while our proposed approach exhibited superior performance, surpassing both the baseline and other state-of-the-art methods. Notably, our method achieved remarkable IoU scores of 0.823, 0.811, and 0.800 for the PV, ART, and NC phases, respectively, emphasizing its effectiveness in achieving accurate image segmentation.

Effectively facilitating the degradation of chloramphenicol by the synergism of Shewanella oneidensis MR-1 and the metal-organic framework.

Electroactive bacteria (EAB) and metal oxides are capable of synergistically removing chloramphenicol (CAP). However, the effects of redox-active metal-organic frameworks (MOFs) on CAP degradation with EAB are not yet known. This study investigated the synergism of iron-based MOFs (Fe-MIL-101) and Shewanella oneidensis MR-1 on CAP degradation. 0.5 g/L Fe-MIL-101 with more possible active sites led to a three-fold higher CAP removal rate in the synergistic system with MR-1 (initial bacterial concentration of 0.2 at OD600), and showed a superior catalytic effect than exogenously added Fe(III)/Fe(II) or magnetite. Mass spectrometry revealed that CAP was transformed into smaller molecular weight and less toxic metabolites in cultures. Transcriptomic analysis showed that Fe-MIL-101 enhanced the expression of genes related to nitro and chlorinated contaminants degradation. Additionally, genes encoding hydrogenases and c-type cytochromes associated with extracellular electron transfer were significantly upregulated, which may contribute to the simultaneous bioreduction of CAP both intracellularly and extracellularly. These results indicated that Fe-MIL-101 can be used as a catalyst to synergize with EAB to effectively facilitate CAP degradation, which might shed new light on the application in the in situ bioremediation of antibiotic-contaminated environments.

In Situ Continuous Measurement of Salinity in Estuarine and Coastal Sediments by All-Solid Potentiometric Sensors.

Salinity is crucial for understanding the environmental and ecological processes in estuarine and coastal sediments. In situ measurements in sediments are scarce due to the low water content and particulate adsorption. Here, a new potentiometric sensor principle is proposed for the real-time in situ measurement of salinity in sediments. The sensor system is based on paper sampling and two all-solid electrodes, a cation-selective electrode (copper hexacyanoferrate, CuHCF) and an anion-selective electrode (Ag/AgCl). The spontaneous aqueous electrolyte extraction and redox reaction can produce a Nernstian response on both electrodes that is directly related to salinity. This potentiometric sensor allows for salinity acquisition in a wide salinity range (1-50 ppt), with high resolution (<1 ppt), and at a low water content (<30%), and it has been applied for the in situ measurement of salinity and the interpretation of cycling processes of metals in estuarine and coastal sediments. Moreover, the sensor coupled to a wireless monitoring system exhibited remote-sensing capability and successfully captured the salinity dynamic processes of the overlying water and pore water during the tidal period. This sensor with its low cost, versatility, and applicability represents a valuable tool to advance the comprehension of salinity and the salinity-driven dissolved-matter variations in estuarine and coastal sediments.

Dietary Polysaccharide-Rich Extract from Noni (Morinda citrifolia L.) Fruit Modified Ruminal Fermentation, Ruminal Bacterial Community and Nutrient Digestion in Cashmere Goats.

In two consecutive studies, we evaluated the effects of polysaccharide-rich noni (Morinda citrifolia L.) fruit extract (NFP) on ruminal fermentation, ruminal microbes and nutrient digestion in cashmere goats. In Exp. 1, the effects of a diet containing NFP of 0, 0.1%, 0.2%, 0.4% and 0.55% on in vitro ruminal fermentation at 3, 6, 9, 12 and 24 h were determined, whereas in Exp. 2, fourteen cashmere goats (46.65 ± 3.36 kg of BW ± SD) were randomly assigned to two treatments: the basal diet with or without (CON) supplementation of NFP at 4 g per kg DM (0.4%). The in vitro results showed that NFP linearly increased concentrations of volatile fatty acids (VFA), quadratically decreased ammonia-N concentration, and changed pH, protozoa number, gas production and the microbial protein (MCP) concentration, and was more effective at 0.4% addition, which yielded similar results in ruminal fermentation in Exp. 2. In addition, NFP increased the apparent digestibility of dry matter and crude protein and the abundance of Firmicutes, and reduced the abundance of Bacteroides and Actinobacteria. Ruminococcus_1 was positively associated with VFA concentration. The Rikenellaceae_RC9_gut_group was positively correlated with protozoa and negatively correlated with MCP concentration. Thus, NFP has potential as a ruminal fermentation enhancer for cashmere goats.

FedMSA: A Model Selection and Adaptation System for Federated Learning.

Federated Learning (FL) enables multiple clients to train a shared model collaboratively without sharing any personal data. However, selecting a model and adapting it quickly to meet user expectations in a large-scale FL application with heterogeneous devices is challenging. In this paper, we propose a model selection and adaptation system for Federated Learning (FedMSA), which includes a hardware-aware model selection algorithm that trades-off model training efficiency and model performance base on FL developers' expectation. Meanwhile, considering the expected model should be achieved by dynamic model adaptation, FedMSA supports full automation in building and deployment of the FL task to different hardware at scale. Experiments on benchmark and real-world datasets demonstrate the effectiveness of the model selection algorithm of FedMSA in real devices (e.g., Raspberry Pi and Jetson nano).

Residual Multilayer Perceptrons for Genotype-Guided Recurrence Prediction of Non-Small Cell Lung Cancer.

Non-small cell lung cancer (NSCLC) is a malignant tumor with high morbidity and mortality, with a high recurrence rate after surgery, which directly affects the life and health of patients. Recently, many studies are based on Computed Tomography (CT) images. They are cheap but have low accuracy. In contrast, the use of gene expression data to predict the recurrence of NSCLC has high accuracy. However, the acquisition of gene data is expensive and invasive, and cannot meet the recurrence prediction requirement of all patients. In this paper, we proposed a low-cost, high-accuracy residual multilayer perceptrons (ResMLP) recurrence prediction method. First, several proposed ResMLP modules are applied to construct a deep regression estimation model. Then, we build a mapping function of mixed features (handcrafted features and deep features) and gene data via this model. Finally, the recurrence prediction task is realized, by utilizing the gene estimation data obtained from the regression model to learn the information representation related to recurrence. The experimental results show that the proposed method has strong generalization ability and can reach 86.38% prediction accuracy. Clinical Relevance- This study improved the preoperative recurrence of NSCLC prediction accuracy from 78.61% by the conventional method to 86.38% by our proposed method using only the CT image.

The effects of supplementation of noni (Morinda citrifolia L.) fruit polysaccharides-rich extract on antioxidant status and immune function in cashmere goats.

This experiment was designed to examine the effects of a dietary supplementation of polysaccharides-rich noni (Morinda citrifolia L.) fruit extract (NFP) on the anti-oxidant enzyme activities, cytokines level, and expression of corresponding genes in blood of cashmere goats. Twelve castrated, 2-yr-old male cashmere goats (45.44 ± 3.30 kg of BW ± SD) were used in a 2 × 2 crossover design: the basal diet with or without (CON) supplementation of NFP at 4 g per kg DM (0.4%). Each period lasted for 29 d, including 1 wk for diet transition, 20 d for adaptation, and the last 2 d for sampling. The results showed that NFP supplementation increased (P < 0.05) the levels of nitric oxide, interleukin-6 (IL-6) and tumor necrosis factor-alpha (TNF-α), and the activities of catalase (CAT), glutathione peroxidase (GPx), thioredoxin reductase (TrxR), and total superoxide dismutase (T-SOD) in serum. The expressions of CAT, GPx4, TrxR, SOD1, IL-6, and TNF-α genes were upregulated (P < 0.05), whereas the levels of malondialdehyde (P = 0.015) and reactive oxygen species (P = 0.051) in serum were reduced. The body weight gain of goats was increased (P = 0.006) with a nonsignificant increase of feed intake with NFP supplementation. In conclusion, dietary NFP supplementation enhanced the antioxidant status and immune function in blood of cashmere goats.

Due to the limited pasture supply and the seasonal imbalance of nutrients in grazed pastures in China, cashmere goats are commonly raised in a confined yard-feeding system, which may result in oxidative stress from a lack of green pastures. Noni (Morinda citrifolia L.) fruit polysaccharides contain various biological compounds that function as anti-inflammatory, antitumor, and to enhance immune responses, hence likely to relieve oxidative stress in animals. Previous researches in our laboratory have shown that polysaccharides-rich extract from noni fruit (NFP) enhanced rumen fermentation in cashmere goats. This experiment was designed to evaluate the effect of NFP supplementation on serum antioxidant status and immune function in cashmere goats. The results showed that dietary supplementation of 0.40% NFP enhanced the immune signaling molecule levels and antioxidant enzyme activities by upregulating the expression of related genes in blood and reduced the levels of lipid peroxides and free radicals in serum, while mature goats improved body weight. Therefore, NFP could be a viable source of antioxidants for cashmere goats.

Dietary Chitosan Supplementation Improved Egg Production and Antioxidative Function in Laying Breeders.

This study was conducted to explore the dietary effect of chitosan on the production performance, and antioxidative enzyme activities and corresponding gene expression in the liver and duodenum of laying breeders. A total of 450 laying breeders (92.44% ± 0.030% of hen-day egg production) were randomly assigned to five dietary treatments fed 8 weeks: maize-soybean meal as the basal control diet and the basal diet containing 250, 500, 1000 and 2000 mg/kg of chitosan, respectively. Each treatment was randomly divided into 6 equal replicates, with 15 laying breeders in each replicate. The results showed that dietary chitosan could increase hen-day egg production and feed conversion ratio, especially at the level of 250~500 mg/kg; however, chitosan had no prominent effect on feed intake and average egg weight. Dietary chitosan could dose-dependently promote the antioxidant status in serum, liver and duodenum of layer breeders. It has a better promotion effect at the level of 500 mg/kg; however, the effect was weakened at the level of 2000 mg/kg. Chitosan was likely to enhance the gene expression and activities of Nrf2-mediated phase II detoxification enzyme by up-regulating the expression of Nrf2, thereby improving the antioxidant capacity of laying breeder hens.

A deep learning method and device for bone marrow imaging cell detection.

Background: Morphological analysis of bone marrow cells is considered as the gold standard for the diagnosis of leukemia. However, due to the diverse morphology of bone marrow cells, extensive experience and patience are needed for morphological examination. automatic diagnosis system through the comprehensive application of image analysis and pattern recognition technology is urgently needed to reduce work intensity, error probability and improves work efficiency. Methods: In this article, we establish a new morphological diagnosis system for bone marrow cell detection based on the deep learning object detection framework. The model is based on the Faster Region-Convolutional Neural Network (R-CNN), a classical object detection model. The system automatically detects bone marrow cells and determines their types. As specimens have severe long-tail distribution, i.e., the frequency of different types of cells varies dramatically, we proposed a general score ranking loss to solve such a problem. The general score ranking loss considers the ranking relationship between positive and negative samples and optimizes the positive sample with a higher classification probability value. Results: We verified this system with 70 bone marrow specimens of leukemia patients, which proved that it can realize intelligent recognition with high efficiency. The software is finally integrated into the microscope system to build an augmented reality system. Conclusions: Clinical tests show that the response speed of the newly developed diagnostic system is faster than that of trained diagnostic experts.

VolumeNet: A Lightweight Parallel Network for Super-Resolution of MR and CT Volumetric Data.

Deep learning-based super-resolution (SR) techniques have generally achieved excellent performance in the computer vision field. Recently, it has been proven that three-dimensional (3D) SR for medical volumetric data delivers better visual results than conventional two-dimensional (2D) processing. However, deepening and widening 3D networks increases training difficulty significantly due to the large number of parameters and small number of training samples. Thus, we propose a 3D convolutional neural network (CNN) for SR of magnetic resonance (MR) and computer tomography (CT) volumetric data called ParallelNet using parallel connections. We construct a parallel connection structure based on the group convolution and feature aggregation to build a 3D CNN that is as wide as possible with a few parameters. As a result, the model thoroughly learns more feature maps with larger receptive fields. In addition, to further improve accuracy, we present an efficient version of ParallelNet (called VolumeNet), which reduces the number of parameters and deepens ParallelNet using a proposed lightweight building block module called the Queue module. Unlike most lightweight CNNs based on depthwise convolutions, the Queue module is primarily constructed using separable 2D cross-channel convolutions. As a result, the number of network parameters and computational complexity can be reduced significantly while maintaining accuracy due to full channel fusion. Experimental results demonstrate that the proposed VolumeNet significantly reduces the number of model parameters and achieves high precision results compared to state-of-the-art methods in tasks of brain MR image SR, abdomen CT image SR, and reconstruction of super-resolution 7T-like images from their 3T counterparts.