IRCM-Caps: An X-ray image detection method for COVID-19.

OBJECTIVE: COVID-19 is ravaging the world, but traditional reverse transcription-polymerase reaction (RT-PCR) tests are time-consuming and have a high false-negative rate and lack of medical equipment. Therefore, lung imaging screening methods are proposed to diagnose COVID-19 due to its fast test speed. Currently, the commonly used convolutional neural network (CNN) model requires a large number of datasets, and the accuracy of the basic capsule network for multiple classification is limital. For this reason, this paper proposes a novel model based on CNN and CapsNet. METHODS: The proposed model integrates CNN and CapsNet. And attention mechanism module and multi-branch lightweight module are applied to enhance performance. Use the contrast adaptive histogram equalization (CLAHE) algorithm to preprocess the image to enhance image contrast. The preprocessed images are input into the network for training, and ReLU was used as the activation function to adjust the parameters to achieve the optimal. RESULT: The test dataset includes 1200 X-ray images (400 COVID-19, 400 viral pneumonia, and 400 normal), and we replace CNN of VGG16, InceptionV3, Xception, Inception-Resnet-v2, ResNet50, DenseNet121, and MoblieNetV2 and integrate with CapsNet. Compared with CapsNet, this network improves 6.96%, 7.83%, 9.37%, 10.47%, and 10.38% in accuracy, area under the curve (AUC), recall, and F1 scores, respectively. In the binary classification experiment, compared with CapsNet, the accuracy, AUC, accuracy, recall rate, and F1 score were increased by 5.33%, 5.34%, 2.88%, 8.00%, and 5.56%, respectively. CONCLUSION: The proposed embedded the advantages of traditional convolutional neural network and capsule network and has a good classification effect on small COVID-19 X-ray image dataset.

Retinal OCTA Image Segmentation Based on Global Contrastive Learning.

The automatic segmentation of retinal vessels is of great significance for the analysis and diagnosis of retinal related diseases. However, the imbalanced data in retinal vascular images remain a great challenge. Current image segmentation methods based on deep learning almost always focus on local information in a single image while ignoring the global information of the entire dataset. To solve the problem of data imbalance in optical coherence tomography angiography (OCTA) datasets, this paper proposes a medical image segmentation method (contrastive OCTA segmentation net, COSNet) based on global contrastive learning. First, the feature extraction module extracts the features of OCTA image input and maps them to the segment head and the multilayer perceptron (MLP) head, respectively. Second, a contrastive learning module saves the pixel queue and pixel embedding of each category in the feature map into the memory bank, generates sample pairs through a mixed sampling strategy to construct a new contrastive loss function, and forces the network to learn local information and global information simultaneously. Finally, the segmented image is fine tuned to restore positional information of deep vessels. The experimental results show the proposed method can improve the accuracy (ACC), the area under the curve (AUC), and other evaluation indexes of image segmentation compared with the existing methods. This method could accomplish segmentation tasks in imbalanced data and extend to other segmentation tasks.

A Liver Segmentation Method Based on the Fusion of VNet and WGAN.

Accurate segmentation of liver images is an essential step in liver disease diagnosis, treatment planning, and prognosis. In recent years, although liver segmentation methods based on 2D convolutional neural networks have achieved good results, there is still a lack of interlayer information that causes severe loss of segmentation accuracy to a certain extent. Meanwhile, making the best of high-level and low-level features more effectively in a 2D segmentation network is a challenging problem. Therefore, we designed and implemented a 2.5-dimensional convolutional neural network, VNet_WGAN, to improve the accuracy of liver segmentation. First, we chose three adjacent layers of a liver model as the input of our network and adopted two convolution kernels in series connection, which can integrate cross-sectional spatial information and interlayer information of liver models. Second, a chain residual pooling module is added to fuse multilevel feature information to optimize the skip connection. Finally, the boundary loss function in the generator is employed to compensate for the lack of marginal pixel accuracy in the Dice loss function. The effectiveness of the proposed method is verified on two datasets, LiTS and CHAOS. The Dice coefficients are 92% and 90%, respectively, which are better than those of the compared segmentation networks. In addition, the experimental results also show that the proposed method can reduce computational consumption while retaining higher segmentation accuracy, which is significant for liver segmentation in practice and provides a favorable reference for clinicians in liver segmentation.

Verteporfin suppresses osteosarcoma progression by targeting the Hippo signaling pathway.

Verteporfin (VP) is a specific inhibitor of yes-associated protein 1 (YAP1) that suppresses tumor progression by inhibiting YAP1 expression. The present study aimed to determine the inhibitory effect of VP on osteosarcoma and the underlying mechanism of its anticancer effects. Cell viability, cell cycle and apoptosis and cell migration and invasion were analyzed using the MTT assay, flow cytometry, wound healing assay and Transwell assay, respectively. Expressions of YAP1 and TEA domain transcription factor 1 (TEAD1) were measured using reverse transcription-quantitative PCR and western blotting, while their interaction was identified by the co-immunoprecipitation assay. In vivo mouse xenograft experiments were performed to evaluate the effect of VP on osteosarcoma growth. The results demonstrated that YAP1 and TEAD1 were highly expressed in osteosarcoma cells and tissues, whereas VP significantly downregulated the expression levels of YAP1 and TEAD1 in the osteosarcoma cell line Saos-2 compared with those in untreated control cells. In addition, compared with those in the control group, VP suppressed the viability, migration and invasion, induced cell cycle arrest in the G1 phase and promoted apoptosis in Saos-2 cells. In addition, VP inhibited mouse xenograft tumor growth in vivo compared with that observed in the control group. Notably, VP downregulated the levels of CYR61 expression in Saos-2 cells, whereas CYR61 overexpression mitigated the inhibitory effects of VP on osteosarcoma cells, as indicated by the increased viability and reduced apoptotic rates in Saos-2 cells overexpressing CYR61 compared with those in the control group. In summary, VP suppressed osteosarcoma by downregulating the expression of YAP1 and TEAD1. Additionally, CYR61 may mediate the effects of VP on osteosarcoma progression.

MTQA: Text-Based Multitype Question and Answer Reading Comprehension Model.

Text-based multitype question answering is one of the research hotspots in the field of reading comprehension models. Multitype reading comprehension models have the characteristics of shorter time to propose, complex components of relevant corpus, and greater difficulty in model construction. There are relatively few research works in this field. Therefore, it is urgent to improve the model performance. In this paper, a text-based multitype question and answer reading comprehension model (MTQA) is proposed. The model is based on a multilayer transformer encoding and decoding structure. In the decoding structure, the headers of the answer type prediction decoding, fragment decoding, arithmetic decoding, counting decoding, and negation are added for the characteristics of multiple types of corpora. Meanwhile, high-performance ELECTRA checkpoints are employed, and secondary pretraining based on these checkpoints and an absolute loss function are designed to improve the model performance. The experimental results show that the performance of the proposed model on the DROP and QUOREF corpora is better than the best results of the current existing models, which proves that the proposed MTQA model has high feature extraction and relatively strong generalization capabilities.

Biosynthesis of gold nanoparticles, characterization and their loading with zonisamide as a novel drug delivery system for the treatment of acute spinal cord injury.

In the present work, a facile biosynthetic approach for the synthesis of AuNPs using bark extract of Juglans regia (J. regia) is reported. Ultra-violet visible (UV-vis) absorption spectroscopic studies exhibited and narrow SPR absorption band at 540 nm, represented the isotropy in particle size. The transmission electron microscopy (TEM) and X-ray diffraction (XRD) analysis, confirmed the fabrication of spherical and crystalline nanoparticles of average size of about 14 nm. Also, typical characteristic selected area electron diffraction (SAED) pattern showed the crystalline nature of AuNPs. The prepared AuNPs were loaded with zonisamide which can be used for future spinal cord injury repair applications. The fourier transform infrared spectroscopy (FTIR) analysis represented the zonisamide loading onto AuNPs. The biological preparation of AuNPs using the bark extract of J. regia is prominent approach because of its eco friendly nature without using any toxic chemicals. The controlled-release of zonisamide-AuNPs was about 43.0 ±â€¯2.2 nm with high stability and solubility under room temperature conditions. Further, the cytotoxicity results showed the comparatively higher toxicity of zonisamide-AuNPs towards CTX TNA2 cells than free zonisamide. Hence, zonisamide-AuNPs may act as very good clinical drug for future therapeutic treatment of spinal cord injury.

[Reconstruction of medial patellofemoral ligament with Tightrope button fixation on the femoral side for the treatment of traumatic patellar dislocation].

OBJECTIVE: To explore the operating procedures and therapeutic effects of medial patellofemoral ligament reconstruction with Tightrope(Arthrex, FL, USA) button fixation at lateral femoral cortex. METHODS: From May 2014 to July 2016, 9 patients with traumatic patellar dislocation were treated. There were 5 males and 4 females, ranging in age from 16 to 47 years old, with an average of 23.7 years old. All the patients underment arthroscopic lateral retinaculum release and joint debridement first. Then the medial patellofemoral ligament was reconstructed by using a semitendinosus autograft. The ends of semitendinosus were pulled into two patellar tunnels respectively, knotted and fixed at the lateral side of patella. The semitendinosus loops were suspended and fixed through femoral tunnel with Tightrope button. The knee was fixed to about 60 degree and the tension of MPFL was adjusted by pulling Tightrope wire under arthroscopic observation. Two patients received superomedial transfer of tibial tuberosity on account of TT-TG >=20 mm. RESULTS: All the patients were followed up, and the duration ranged from 6 to 23 months, with an average of 13.6 months. Patellar stability was re-obtained in all patients. No dislocation re-currenced during the follow-up period. The Kujala score(scoring of patellofemoral disorders) was improved at the latest follow-up compared with that before operation. All the patients returned to routine life. CONCLUSIONS: Reconstruction of medial patellofemoral ligament with the Tightrope button fixation on the femoral side for the treatment of traumatic patellar dislocation is effective and economic. The method make the MPFL tension adjustable during the reconstuction under arthroscopy. The MPFL tension should be adjusted at 60 degree flexion of knee in order to avoid making tension level too high.

[Outcomes and complications of Tightrope button plate for repairing acromioclavicular dislocation].

OBJECTIVE: To study the clinical outcome and complications of Tightrope button plate for repairing acromioclavicular dislocation of Rockwood type III to V. METHODS: From May 2014 to December 2016, 17 patients with acromioclavicular dislocation of type III-V were treated with Tightrope button plate including 10 males and 7 females with an average age 39.8 years old ranging from 20 to 68 years old. Four patients were treated with arthroscopy and 17 patients were treated with mini-invasive by X-ray assisted. Shoulder function, X-ray and complications after operation were assessed. RESULTS: All patients were followed up for 5 to 23 months with a mean of 10.8 months. All patients got satisfying reduction immediately postoperatively. Among them, 1 case of clavicle end wound foreign body reaction, rupture, effusion, healing after the second suture; 1 case of foreign body granuloma formation at the end of clavicle were resected and removed at 4 months after operation; 3 cases loss reduction(less than 50% of acromioclavicular joint). No coracoid fracture and suture breakage observed. The shoulder mobility was restored in 15 cases at 4 to 6 weeks postoperatively, and the shoulder adhesion in 2 cases was delayed to 5 to 7 months after operation. The Constant scores were improved from 46.9±6.0 preoperatively to 92.7±4.0 at the final follow-up. X-ray evaluation of postoperative coracoclavicular tunnel location, patients' coracoclavicular tunnel with mini-invasive fluoroscopy all closed to the ideal position (across the clavicle vertically through the coracoid base center), while different degree of tunnel position deviation were observed in arthroscopic patients. CONCLUSIONS: Tightrope button plate for the treatment of acromioclavicular joint dislocation had advantages of minimally invasive, effective, good clinical results, the majority of common complications does not affect efficacy. Small incision X-ray method can provide more satisfactory and reliable tunnel location.

A method of protein model classification and retrieval using bag-of-visual-features.

In this paper we propose a novel visual method for protein model classification and retrieval. Different from the conventional methods, the key idea of the proposed method is to extract image features of proteins and measure the visual similarity between proteins. Firstly, the multiview images are captured by vertices and planes of a given octahedron surrounding the protein. Secondly, the local features are extracted from each image of the different views by the SURF algorithm and are vector quantized into visual words using a visual codebook. Finally, KLD is employed to calculate the similarity distance between two feature vectors. Experimental results show that the proposed method has encouraging performances for protein retrieval and categorization as shown in the comparison with other methods.

Nonlinear radon transform using Zernike moment for shape analysis.

We extend the linear Radon transform to a nonlinear space and propose a method by applying the nonlinear Radon transform to Zernike moments to extract shape descriptors. These descriptors are obtained by computing Zernike moment on the radial and angular coordinates of the pattern image's nonlinear Radon matrix. Theoretical and experimental results validate the effectiveness and the robustness of the method. The experimental results show the performance of the proposed method in the case of nonlinear space equals or outperforms that in the case of linear Radon.