Population genetic structure of Pomacea canaliculata in China based on the COI and ITS1 genes.

Comprehending the phylogeography of invasive organisms enhances our insight into their distribution dynamics, which is instrumental for the development of effective prevention and management strategies. In China, Pomacea canaliculata and Pomacea maculata are the two most widespread and damaging species of the non-native Pomacea spp.. Given this species' rapid spread throughout country, it is urgent to investigate the genetic diversity and structure of its different geographic populations, a task undertaken in the current study using the COI and ITS1 mitochondrial and ribosomal DNA genes, respectively. The result of this study, based on a nationwide systematic survey, a collection of Pomacea spp., and the identification of cryptic species, showed that there is a degree of genetic diversity and differentiation in P. canaliculata, and that all of its variations are mainly due to differences between individuals within different geographical populations. Indeed, this species contains multiple haplotypes, but none of them form a systematic geographical population structure. Furthermore, the COI gene exhibits higher genetic diversity than the ITS1 gene. Our study further clarifies the invasive pathways and dispersal patterns of P. canaliculata in China to provide a theoretical basis.

Functional Plasticity, Redundancy, and Specificity of Lanosterol 14α-Demethylase in Regulating the Sensitivity to DMIs in Calonectria ilicicola.

Cytochrome P450 sterol 14α-demethylase (CYP51) is a key enzyme involved in the sterol biosynthesis pathway and serves as a target for sterol demethylation inhibitors (DMIs). In this study, the 3D structures of three CPY51 paralogues from Calonectria ilicicola (C. ilicicola) were first modeled by AlphaFold2, and molecular docking results showed that CiCYP51A, CiCYP51B, or CiCYP51C proteins individually possessed two active pockets that interacted with DMIs. Our results showed that the three paralogues play important roles in development, pathogenicity, and sensitivity to DMI fungicides. Specifically, CiCYP51A primarily contributed to cell wall integrity maintenance and tolerance to abiotic stresses, and CiCYP51B was implicated in sexual reproduction and virulence, while CiCYP51C exerted negative regulatory effects on sterol 14α-demethylase activity within the ergosterol biosynthetic pathway, revealing its genus-specific function in C. ilicicola. These findings provide valuable insights into developing rational strategies for controlling soybean red crown rot caused by C. ilicicola.

LGDNet: local feature coupling global representations network for pulmonary nodules detection.

Detection of suspicious pulmonary nodules from lung CT scans is a crucial task in computer-aided diagnosis (CAD) systems. In recent years, various deep learning-based approaches have been proposed and demonstrated significant potential for addressing this task. However, existing deep convolutional neural networks exhibit limited long-range dependency capabilities and neglect crucial contextual information, resulting in reduced performance on detecting small-size nodules in CT scans. In this work, we propose a novel end-to-end framework called LGDNet for the detection of suspicious pulmonary nodules in lung CT scans by fusing local features and global representations. To overcome the limited long-range dependency capabilities inherent in convolutional operations, a dual-branch module is designed to integrate the convolutional neural network (CNN) branch that extracts local features with the transformer branch that captures global representations. To further address the issue of misalignment between local features and global representations, an attention gate module is proposed in the up-sampling stage to selectively combine misaligned semantic data from both branches, resulting in more accurate detection of small-size nodules. Our experiments on the large-scale LIDC dataset demonstrate that the proposed LGDNet with the dual-branch module and attention gate module could significantly improve the nodule detection sensitivity by achieving a final competition performance metric (CPM) score of 89.49%, outperforming the state-of-the-art nodule detection methods, indicating its potential for clinical applications in the early diagnosis of lung diseases.

Lightweight semantic segmentation network with configurable context and small object attention.

The current semantic segmentation algorithms suffer from encoding feature distortion and small object feature loss. Context information exchange can effectively address the feature distortion problem, but it has the issue of fixed spatial range. Maintaining the input feature resolution can reduce the loss of small object information but would slow down the network's operation speed. To tackle these problems, we propose a lightweight semantic segmentation network with configurable context and small object attention (CCSONet). CCSONet includes a long-short distance configurable context feature enhancement module (LSCFEM) and a small object attention decoding module (SOADM). The LSCFEM differs from the regular context exchange module by configuring long and short-range relevant features for the current feature, providing a broader and more flexible spatial range. The SOADM enhances the features of small objects by establishing correlations among objects of the same category, avoiding the introduction of redundancy issues caused by high-resolution features. On the Cityscapes and Camvid datasets, our network achieves the accuracy of 76.9 mIoU and 73.1 mIoU, respectively, while maintaining speeds of 87 FPS and 138 FPS. It outperforms other lightweight semantic segmentation algorithms in terms of accuracy.

Optic disc detection based on fully convolutional network and weighted matrix recovery model.

Eye diseases often affect human health. Accurate detection of the optic disc contour is one of the important steps in diagnosing and treating eye diseases. However, the structure of fundus images is complex, and the optic disc region is often disturbed by blood vessels. Considering that the optic disc is usually a saliency region in fundus images, we propose a weakly-supervised optic disc detection method based on the fully convolution neural network (FCN) combined with the weighted low-rank matrix recovery model (WLRR). Firstly, we extract the low-level features of the fundus image and cluster the pixels using the Simple Linear Iterative Clustering (SLIC) algorithm to generate the feature matrix. Secondly, the top-down semantic prior information provided by FCN and bottom-up background prior information of the optic disc region are used to jointly construct the prior information weighting matrix, which more accurately guides the decomposition of the feature matrix into a sparse matrix representing the optic disc and a low-rank matrix representing the background. Experimental results on the DRISHTI-GS dataset and IDRiD dataset show that our method can segment the optic disc region accurately, and its performance is better than existing weakly-supervised optic disc segmentation methods. Graphical abstract of optic disc segmentation.

Research on Small Sample Multi-Target Grasping Technology Based on Transfer Learning.

This article proposes a CBAM-ASPP-SqueezeNet model based on the attention mechanism and atrous spatial pyramid pooling (CBAM-ASPP) to solve the problem of robot multi-target grasping detection. Firstly, the paper establishes and expends a multi-target grasping dataset, as well as introduces and uses transfer learning to conduct network pre-training on the single-target dataset and slightly modify the model parameters using the multi-target dataset. Secondly, the SqueezeNet model is optimized and improved using the attention mechanism and atrous spatial pyramid pooling module. The paper introduces the attention mechanism network to weight the transmitted feature map in the channel and spatial dimensions. It uses a variety of parallel operations of atrous convolution with different atrous rates to increase the size of the receptive field and preserve features from different ranges. Finally, the CBAM-ASPP-SqueezeNet algorithm is verified using the self-constructed, multi-target capture dataset. When the paper introduces transfer learning, the various indicators converge after training 20 epochs. In the physical grabbing experiment conducted by Kinova and SIASUN Arm, a network grabbing success rate of 93% was achieved.

Degradation Adaption Local-to-Global Transformer for Low-Dose CT Image Denoising.

Computer tomography (CT) has played an essential role in the field of medical diagnosis. Considering the potential risk of exposing patients to X-ray radiations, low-dose CT (LDCT) images have been widely applied in the medical imaging field. Since reducing the radiation dose may result in increased noise and artifacts, methods that can eliminate the noise and artifacts in the LDCT image have drawn increasing attentions and produced impressive results over the past decades. However, recent proposed methods mostly suffer from noise remaining, over-smoothing structures, or false lesions derived from noise. To tackle these issues, we propose a novel degradation adaption local-to-global transformer (DALG-Transformer) for restoring the LDCT image. Specifically, the DALG-Transformer is built on self-attention modules which excel at modeling long-range information between image patch sequences. Meanwhile, an unsupervised degradation representation learning scheme is first developed in medical image processing to learn abstract degradation representations of the LDCT images, which can distinguish various degradations in the representation space rather than the pixel space. Then, we introduce a degradation-aware modulated convolution and gated mechanism into the building modules (i.e., multi-head attention and feed-forward network) of each Transformer block, which can bring in the complementary strength of convolution operation to emphasize on the spatially local context. The experimental results show that the DALG-Transformer can provide superior performance in noise removal, structure preservation, and false lesions elimination compared with five existing representative deep networks. The proposed networks may be readily applied to other image processing tasks including image reconstruction, image deblurring, and image super-resolution.

PILN: A posterior information learning network for blind reconstruction of lung CT images.

BACKGROUND AND OBJECTIVE: Computer tomography (CT) imaging technology has played significant roles in the diagnosis and treatment of various lung diseases, but the degradations in CT images usually cause the loss of detailed structural information and interrupt the judgement from clinicians. Therefore, reconstructing noise-free, high-resolution CT images with sharp details from degraded ones is of great importance for the computer-assisted diagnosis (CAD) system. However, current image reconstruction methods suffer from unknown parameters of multiple degradations in actual clinical images. METHODS: To solve these problems, we propose a unified framework, so called Posterior Information Learning Network (PILN), for blind reconstruction of lung CT images. The framework consists of two stages: Firstly, a noise level learning (NLL) network is proposed to quantify the Gaussian and artifact noise degradations into different levels. Inception-residual modules are designed to extract multi-scale deep features from the noisy image, and residual self-attention structures are proposed to refine deep features to essential representations of noise. Secondly, by taking the estimated noise levels as prior information, a cyclic collaborative super-resolution (CyCoSR) network is proposed to iteratively reconstruct the high-resolution CT image and estimate the blur kernel. Two convolutional modules are designed based on cross-attention transformer structure, named as Reconstructor and Parser. The high-resolution image is restored from the degraded image by the Reconstructor under the guidance of the predicted blur kernel, while the blur kernel is estimated by the Parser according to the reconstructed image and the degraded one. The NLL and CyCoSR networks are formulated as an end-to-end framework to handle multiple degradations simultaneously. RESULTS: The proposed PILN is applied to the Cancer Imaging Archive (TCIA) dataset and the Lung Nodule Analysis 2016 Challenge (LUNA16) dataset to evaluate its ability in reconstructing lung CT images. Compared with the state-of-the-art image reconstruction algorithms, it can provide high-resolution images with less noise and sharper details with respect to quantitative benchmarks. CONCLUSIONS: Extensive experimental results demonstrate that our proposed PILN can achieve better performance on blind reconstruction of lung CT images, providing noise-free, detail-sharp and high-resolution images without knowing the parameters of multiple degradation sources.

5'-tiRNA-Gln inhibits hepatocellular carcinoma progression by repressing translation through the interaction with eukaryotic initiation factor 4A-I.

tRNA-derived small RNAs (tsRNAs) are novel non-coding RNAs that are involved in the occurrence and progression of diverse diseases. However, their exact presence and function in hepatocellular carcinoma (HCC) remain unclear. Here, differentially expressed tsRNAs in HCC were profiled. A novel tsRNA, tRNAGln-TTG derived 5'-tiRNA-Gln, is significantly downregulated, and its expression level is correlated with progression in patients. In HCC cells, 5'-tiRNA-Gln overexpression impaired the proliferation, migration, and invasion in vitro and in vivo, while 5'-tiRNA-Gln knockdown yielded opposite results. 5'-tiRNA-Gln exerted its function by binding eukaryotic initiation factor 4A-I (EIF4A1), which unwinds complex RNA secondary structures during translation initiation, causing the partial inhibition of translation. The suppressed downregulated proteins include ARAF, MEK1/2 and STAT3, causing the impaired signaling pathway related to HCC progression. Furthermore, based on the construction of a mutant 5'-tiRNA-Gln, the sequence of forming intramolecular G-quadruplex structure is crucial for 5'-tiRNA-Gln to strongly bind EIF4A1 and repress translation. Clinically, 5'-tiRNA-Gln expression level is negatively correlated with ARAF, MEK1/2, and STAT3 in HCC tissues. Collectively, these findings reveal that 5'-tiRJNA-Gln interacts with EIF4A1 to reduce related mRNA binding through the intramolecular G-quadruplex structure, and this process partially inhibits translation and HCC progression.

Association between parental autoimmune disease and childhood atopic dermatitis varied by sex: a nationwide case-control study.

Atopic dermatitis (AD) is a common inflammatory skin disorder induced by dysfunction of immune suppression sharing similar pathogenesis to autoimmune diseases. To explore the association between autoimmune diseases and AD in children, we linked the birth data from National Birth Registry with National Health Insurance Research Database. There were 1,174,941 children obtained from 2006 to 2012 birth cohort. A total of 312,329 children diagnosed with AD before 5 years old were compared to 862,612 children without AD in the control group. Conditional logistic regression was utilized to calculate adjusted odds ratio (OR) and Bonferroni-corrected confidence interval (CI) for overall significance level of 0.05. In 2006-2012 birth cohort, the prevalence rate of AD was 26.6% (95% CI 26.5, 26.7) before 5 years of age. Having parental autoimmune disease (including rheumatoid arthritis, systemic lupus erythematosus, Sjogren's syndrome, ankylosing spondylitis, and psoriasis) was associated with a significant higher risk of children AD development. The other associated factors were maternal obstetric complications (including gestational diabetes mellitus and cervical incompetence), parental systemic diseases (including anemia, hypertension, diabetes mellitus, chronic obstructive pulmonary disease, hyperthyroidism, and obstructive sleep apnea), and parental allergic disease (including asthma and AD). The subgroup analysis showed similar results between children's sexes. Moreover, maternal autoimmune disease had higher impact on the risk of developing AD in the child compared with paternal autoimmune disease. In conclusion, parental autoimmune diseases were found to be related to their children's AD before 5 years old.

Rethinking 1D convolution for lightweight semantic segmentation.

Lightweight semantic segmentation promotes the application of semantic segmentation in tiny devices. The existing lightweight semantic segmentation network (LSNet) has the problems of low precision and a large number of parameters. In response to the above problems, we designed a full 1D convolutional LSNet. The tremendous success of this network is attributed to the following three modules: 1D multi-layer space module (1D-MS), 1D multi-layer channel module (1D-MC), and flow alignment module (FA). The 1D-MS and the 1D-MC add global feature extraction operations based on the multi-layer perceptron (MLP) idea. This module uses 1D convolutional coding, which is more flexible than MLP. It increases the global information operation, improving features' coding ability. The FA module fuses high-level and low-level semantic information, which solves the problem of precision loss caused by the misalignment of features. We designed a 1D-mixer encoder based on the transformer structure. It performed fusion encoding of the feature space information extracted by the 1D-MS module and the channel information extracted by the 1D-MC module. 1D-mixer obtains high-quality encoded features with very few parameters, which is the key to the network's success. The attention pyramid with FA (AP-FA) uses an AP to decode features and adds a FA module to solve the problem of feature misalignment. Our network requires no pre-training and only needs a 1080Ti GPU for training. It achieved 72.6 mIoU and 95.6 FPS on the Cityscapes dataset and 70.5 mIoU and 122 FPS on the CamVid dataset. We ported the network trained on the ADE2K dataset to mobile devices, and the latency of 224 ms proves the application value of the network on mobile devices. The results on the three datasets prove that the network generalization ability we designed is powerful. Compared to state-of-the-art lightweight semantic segmentation algorithms, our designed network achieves the best balance between segmentation accuracy and parameters. The parameters of LSNet are only 0.62 M, which is currently the network with the highest segmentation accuracy within 1 M parameters.

Inhibition of integrated stress response protects against lipid-induced senescence in hypothalamic neural stem cells in adamantinomatous craniopharyngioma.

BACKGROUND: Adamantinomatous craniopharyngioma (ACP) is a benign tumor with malignant clinical manifestations. ACP adjacent to the hypothalamus often presents with more severe symptoms and higher incidence of hypothalamic dysfunction. However, the mechanism underlying hypothalamic dysfunction remains unclear. METHODS: Immunostaining was performed to determine the nerve damage to the floor of the third ventricle (3VF) adjacent to ACP and to examine the recruitment and senescence of hypothalamic neural stem cells (htNSCs). The accumulation of lipid droplets (LDs) in htNSCs was evaluated via BODIPY staining, oil red O staining, and transmission electron microscopy. In vitro and in vivo assays were used to evaluate the effect of cystic fluid or oxidized low-density lipoprotein and that of oxytocin (OXT) on htNSC senescence and the hypothalamic function. The protein expression levels were analyzed using western blotting. RESULTS: htNSCs with massive LD accumulation were recruited to the damaged 3VF adjacent to ACP. The LDs in htNSCs induced senescence and reduced neuronal differentiation; however, htNSC senescence was effectively prevented by inhibiting either CD36 or integrated stress response (ISR) signaling. Furthermore, OXT pretreatment reduced lipotoxicity via the inhibition of ISR signaling and the repair of the blood-brain barrier. CONCLUSIONS: Reduced LD aggregation or ISR signaling inhibition prevented senescence in htNSCs and identified molecular pathways and potential therapeutic targets that may improve hypothalamic dysfunction in ACP patients.

Mechanistic effects of microwave radiation on pupal emergence in the leafminer fly, Liriomyza trifolii.

Liriomyza trifolii is a significant pest of vegetable and ornamental crops across the globe. Microwave radiation has been used for controlling pests in stored products; however, there are few reports on the use of microwaves for eradicating agricultural pests such as L. trifolii, and its effects on pests at the molecular level is unclear. In this study, we show that microwave radiation inhibited the emergence of L. trifolii pupae. Transcriptomic studies of L. trifolii indicated significant enrichment of differentially expressed genes (DEGs) in 'post-translational modification, protein turnover, chaperones', 'sensory perception of pain/transcription repressor complex/zinc ion binding' and 'insulin signaling pathway' when analyzed with the Clusters of Orthologous Groups, Gene Ontology and the Kyoto Encyclopedia of Genes and Genomes databases, respectively. The top DEGs were related to reproduction, immunity and development and were significantly expressed after microwave radiation. Interestingly, there was no significant difference in the expression of genes encoding heat shock proteins or antioxidant enzymes in L. trifolii treated with microwave radiation as compared to the untreated control. The expression of DEGs encoding cuticular protein and protein takeout were silenced by RNA interference, and the results showed that knockdown of these two DEGs reduced the survival of L. trifolii exposed to microwave radiation. The results of this study help elucidate the molecular response of L. trifolii exposed to microwave radiation and provide novel ideas for control.

Object Recognition and Grasping for Collaborative Robots Based on Vision.

This study introduces a parallel YOLO-GG deep learning network for collaborative robot target recognition and grasping to enhance the efficiency and precision of visual classification and grasping for collaborative robots. First, the paper outlines the target classification and detection task, the grasping system of the robotic arm, and the dataset preprocessing method. The real-time recognition and grasping network can identify a diverse spectrum of unidentified objects and determine the target type and appropriate capture box. Secondly, we propose a parallel YOLO-GG deep vision network based on YOLO and GG-CNN. Thirdly, the YOLOv3 network, pre-trained with the COCO dataset, identifies the object category and position, while the GG-CNN network, trained using the Cornell Grasping dataset, predicts the grasping pose and scale. This study presents the processes for generating a target's grasping frame and recognition type using GG-CNN and YOLO networks, respectively. This completes the investigation of parallel networks for target recognition and grasping in collaborative robots. Finally, the experimental results are evaluated on the self-constructed NEU-COCO dataset for target recognition and positional grasping. The speed of detection has improved by 14.1%, with an accuracy of 94%. This accuracy is 4.0% greater than that of YOLOv3. Experimental proof was obtained through a robot grasping actual objects.

Insect hormones affect the toxicity of the insecticidal growth regulator cyromazine in Liriomyza trifolii (Diptera: Agromyzidae).

The leafminer Liriomyza trifolii is an important insect pest of ornamental and vegetable crops worldwide. Cyromazine is an effective, commonly-used insecticide that functions as a growth regulator, but its effect on L. trifolii has not been previously reported. In this study, transcriptome analysis was undertaken in L. trifolii exposed to cyromazine. Clusters of orthologous groups analysis indicated that a large number of differentially expressed genes responding to cyromazine were categorized as "lipid transport and metabolism", "post-translational modification, protein turnover, chaperones", and "cell wall/membrane/envelope biogenesis". Gene ontology analysis indicated that pathways associated with insect hormones, growth and development, and cuticle synthesis were significantly enriched. In general, the transcriptome results showed that the genes related to insect hormones were significantly expressed after treatment with cyromazine. Furthermore, the combined exposure of L. trifolii to cyromazine and the hormone analogues 20-hydroxyecdysone (20E) or juvenile hormone (JH) indicated that hormone analogues can change the expression pattern of hormone-related genes (20EP and JHEH) and pupal length. The combined application of cyromazine with 20E improved the survival rate of L. trifolii, whereas the combination of JH and cyromazine reduced survival. The results of this study help elucidate the mechanistic basis for cyromazine toxicity and provide a foundation for understanding cyromazine resistance.

CT image super-resolution reconstruction based on global hybrid attention.

Computer tomography (CT) has played an essential role in the field of medical diagnosis, but the blurry edges and unclear textures in traditional CT images usually interfere the subsequent judgement from radiologists or clinicians. Deep learning based image super-resolution methods have been applied for CT image restoration recently. However, different levels of information of CT image details are mixed and difficult to be mapped from deep features by traditional convolution operations. Moreover, features representing regions of interest (ROIs) in CT images are treated equally as those for background, resulting in low concentration of meaningful features and high redundancy of computation. To tackle these issues, a CT image super-resolution network is proposed based on hybrid attention mechanism and global feature fusion, which consists of the following three parts: 1) stacked Swin Transformer blocks are used as the backbone to extract initial features from the degraded CT image; 2) a multi-branch hierarchical self-attention module (MHSM) is proposed to adaptively map multi-level features representing different levels of image information from the initial features and establish the relationship between these features through a self-attention mechanism, where three branches apply different strategies of integrating convolution, down-sampling and up-sampling operations according to three different scale factors; 3) a multidimensional local topological feature enhancement module (MLTEM) is proposed and plugged into the end of the backbone to refine features in the channel and spatial dimension simultaneously, so that the features representing ROIs could be enhanced while meaningless ones eliminated. Experimental results demonstrate that our method outperform the state-of-the-art super-resolution methods on restoring CT images with respect to peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) indices.

A novel CapsNet neural network based on MobileNetV2 structure for robot image classification.

Image classification indicates that it classifies the images into a certain category according to the information in the image. Therefore, extracting image feature information is an important research content in image classification. Traditional image classification mainly uses machine learning methods to extract features. With the continuous development of deep learning, various deep learning algorithms are gradually applied to image classification. However, traditional deep learning-based image classification methods have low classification efficiency and long convergence time. The training networks are prone to over-fitting. In this paper, we present a novel CapsNet neural network based on the MobileNetV2 structure for robot image classification. Aiming at the problem that the lightweight network will sacrifice classification accuracy, the MobileNetV2 is taken as the base network architecture. CapsNet is improved by optimizing the dynamic routing algorithm to generate the feature graph. The attention module is introduced to increase the weight of the saliency feature graph learned by the convolutional layer to improve its classification accuracy. The parallel input of spatial information and channel information reduces the computation and complexity of network. Finally, the experiments are carried out in CIFAR-100 dataset. The results show that the proposed model is superior to other robot image classification models in terms of classification accuracy and robustness.

Sterol 14α-Demethylase CaCYP51A and CaCYP51B are Functionally Redundant, but Differentially Regulated in Colletotrichum acutatum: Responsibility for DMI-Fungicide Resistance.

Colletotrichum acutatum, the main pathogen causing anthracnose on chili worldwide, is controlled by tebuconazole [a sterol C14-demethylation inhibitor (DMI) fungicide, abbreviated as Teb] with excellent efficacy. Our previous study exhibited that all C. acutatum isolates were sensitive to Teb while the Colletotrichum gloeosporioides population had developed resistance to Teb on the same fungicide-pressure selection. Therefore, the assessment of Teb-resistance in C. acutatum is impending. Twenty Teb-resistant (TebR) mutants obtained by fungicide domestication and ultraviolet (UV)-mutagenesis displayed similar fitness compared to parental isolates. Data in the current study exhibited that mutations at CaCYP51A and/or overexpression of CaCYP51s were responsible for Teb-resistance. Furthermore, the deletion mutants ΔCaCYP51A and ΔCaCYP51B played different roles in sensitivities to DMIs. Taken together, this study first reported that mutations at CaCYP51A and/or overexpression of CaCYP51s conferred resistance to Teb in C. acutatum, CaCYP51A and CaCYP51B are functionally redundant, but differentially regulated in DMI resistance.

MID-UNet: Multi-input directional UNet for COVID-19 lung infection segmentation from CT images.

Coronavirus Disease 2019 (COVID-19) has spread globally since the first case was reported in December 2019, becoming a world-wide existential health crisis with over 90 million total confirmed cases. Segmentation of lung infection from computed tomography (CT) scans via deep learning method has a great potential in assisting the diagnosis and healthcare for COVID-19. However, current deep learning methods for segmenting infection regions from lung CT images suffer from three problems: (1) Low differentiation of semantic features between the COVID-19 infection regions, other pneumonia regions and normal lung tissues; (2) High variation of visual characteristics between different COVID-19 cases or stages; (3) High difficulty in constraining the irregular boundaries of the COVID-19 infection regions. To solve these problems, a multi-input directional UNet (MID-UNet) is proposed to segment COVID-19 infections in lung CT images. For the input part of the network, we firstly propose an image blurry descriptor to reflect the texture characteristic of the infections. Then the original CT image, the image enhanced by the adaptive histogram equalization, the image filtered by the non-local means filter and the blurry feature map are adopted together as the input of the proposed network. For the structure of the network, we propose the directional convolution block (DCB) which consist of 4 directional convolution kernels. DCBs are applied on the short-cut connections to refine the extracted features before they are transferred to the de-convolution parts. Furthermore, we propose a contour loss based on local curvature histogram then combine it with the binary cross entropy (BCE) loss and the intersection over union (IOU) loss for better segmentation boundary constraint. Experimental results on the COVID-19-CT-Seg dataset demonstrate that our proposed MID-UNet provides superior performance over the state-of-the-art methods on segmenting COVID-19 infections from CT images.