Case report: Isolated eyelid metastasis of ccRCC 5 years after receiving radical nephrectomy.

Introduction: The most common sites of clear cell renal cell carcinoma(ccRCC) metastasis are the lung, bones, liver and brain; eyelid metastasis is a rare occurrence. Case presentation: We report a case of ccRCC metastasis to the left eyelid after radical nephrectomy, and remission after sunitinib treatment. Conclusions: Although the probability of eyelid metastasis rate is very low, tumor metastasis to the eyelid skin is possible after radical nephrectomy. Therefore, any rash like changes on the skin during the review procedure cannot be ignored by the physician.

DiffGAN: An adversarial diffusion model with local transformer for MRI reconstruction.

Magnetic resonance imaging (MRI) is non-invasive and crucial for clinical diagnosis, but it has long acquisition time and aliasing artifacts. Accelerated imaging techniques can effectively reduce the scanning time of MRI, thereby decreasing the anxiety and discomfort of patients. Vision Transformer (ViT) based methods have greatly improved MRI image reconstruction, but their computational complexity and memory requirements for the self-attention mechanism grow quadratically with image resolution, which limits their use for high resolution images. In addition, the current generative adversarial networks in MRI reconstruction are difficult to train stably. To address these problems, we propose a Local Vision Transformer (LVT) based adversarial Diffusion model (Diff-GAN) for accelerating MRI reconstruction. We employ a generative adversarial network (GAN) as the reverse diffusion model to enable large diffusion steps. In the forward diffusion module, we use a diffusion process to generate Gaussian mixture distribution noise, which mitigates the gradient vanishing issue in GAN training. This network leverages the LVT module with the local self-attention, which can capture high-quality local features and detailed information. We evaluate our method on four datasets: IXI, MICCAI 2013, MRNet and FastMRI, and demonstrate that Diff-GAN can outperform several state-of-the-art GAN-based methods for MRI reconstruction.

IWNeXt: an image-wavelet domain ConvNeXt-based network for self-supervised multi-contrast MRI reconstruction.

Objective.Multi-contrast magnetic resonance imaging (MC MRI) can obtain more comprehensive anatomical information of the same scanning object but requires a longer acquisition time than single-contrast MRI. To accelerate MC MRI speed, recent studies only collect partial k-space data of one modality (target contrast) to reconstruct the remaining non-sampled measurements using a deep learning-based model with the assistance of another fully sampled modality (reference contrast). However, MC MRI reconstruction mainly performs the image domain reconstruction with conventional CNN-based structures by full supervision. It ignores the prior information from reference contrast images in other sparse domains and requires fully sampled target contrast data. In addition, because of the limited receptive field, conventional CNN-based networks are difficult to build a high-quality non-local dependency.Approach.In the paper, we propose an Image-Wavelet domain ConvNeXt-based network (IWNeXt) for self-supervised MC MRI reconstruction. Firstly, INeXt and WNeXt based on ConvNeXt reconstruct undersampled target contrast data in the image domain and refine the initial reconstructed result in the wavelet domain respectively. To generate more tissue details in the refinement stage, reference contrast wavelet sub-bands are used as additional supplementary information for wavelet domain reconstruction. Then we design a novel attention ConvNeXt block for feature extraction, which can capture the non-local information of the MC image. Finally, the cross-domain consistency loss is designed for self-supervised learning. Especially, the frequency domain consistency loss deduces the non-sampled data, while the image and wavelet domain consistency loss retain more high-frequency information in the final reconstruction.Main results.Numerous experiments are conducted on the HCP dataset and the M4Raw dataset with different sampling trajectories. Compared with DuDoRNet, our model improves by 1.651 dB in the peak signal-to-noise ratio.Significance.IWNeXt is a potential cross-domain method that can enhance the accuracy of MC MRI reconstruction and reduce reliance on fully sampled target contrast images.

Clinical study of renal artery cold perfusion combined with laparoscopic nephron retention in the treatment of complex renal angiomyolipoma.

Objective: The aim of this study is to summarize the surgical experience of renal artery cold perfusion combined with laparoscopic nephron preserving surgery for the treatment of complex renal angiomyolipoma and to evaluate the safety and feasibility of this surgical protocol. Materials and methods: Clinical data of nine patients who received renal artery cold perfusion combined with laparoscopic nephron preserving surgery for complex renal angiomyolipoma in our hospital from February 2017 to August 2020 were retrospectively analyzed. The study parameters included imaging findings, total renal function before and after surgery, glomerular filtration rate (GFR) of affected kidney before and after surgery, and related complications. Results: Eight of the nine patients successfully completed the operation, one patient was intolerant to renal artery balloon implantation, and the success rate of the operation was 88.89%. The mean maximum tumor diameter was 6.8 cm, and RENAL score was 7 points. Postoperative total renal function and GFR of the affected kidney had no significant changes compared with that before surgery, and imaging examination showed no tumor residue or recurrence. Conclusion: This surgical procedure is safe and feasible for complex renal angiomyolipoma and can be used as a surgical option for renal hamartoma. The long-term effect needs to be confirmed by further studies.

DC-SiamNet: Deep contrastive Siamese network for self-supervised MRI reconstruction.

Reconstruction methods based on deep learning have greatly shortened the data acquisition time of magnetic resonance imaging (MRI). However, these methods typically utilize massive fully sampled data for supervised training, restricting their application in certain clinical scenarios and posing challenges to the reconstruction effect when high-quality MR images are unavailable. Recently, self-supervised methods have been developed that only undersampled MRI images participate in the network training. Nevertheless, due to the lack of complete referable MR image data, self-supervised reconstruction is prone to produce incorrect structure contents, such as unnatural texture details and over-smoothed tissue sites. To solve this problem, we propose a self-supervised Deep Contrastive Siamese Network (DC-SiamNet) for fast MR imaging. First, DC-SiamNet performs the reconstruction with a Siamese unrolled structure and obtains visual representations in different iterative phases. Particularly, an attention-weighted average pooling module is employed at the bottleneck layer of the U-shape regularization unit, which can effectively aggregate valuable local information of the underlying feature map in the generated representation vector. Then, a novel hybrid loss function is designed to drive the self-supervised reconstruction and contrastive learning simultaneously by forcing the output consistency across different branches in the frequency domain, the image domain, and the latent space. The proposed method is extensively evaluated with different sampling patterns on the IXI brain dataset and the MRINet knee dataset. Experimental results show that DC-SiamNet can achieve 0.93 in structural similarity and 33.984 dB in peak signal-to-noise ratio on the IXI brain dataset under 8x acceleration. It has better reconstruction accuracy than other methods, and the performance is close to the corresponding model trained with full supervision, especially when the sampling rate is low. In addition, generalization experiments verify that our method has a strong cross-domain reconstruction ability for different contrast brain images.

OM-NAS: pigmented skin lesion image classification based on a neural architecture search.

Because pigmented skin lesion image classification based on manually designed convolutional neural networks (CNNs) requires abundant experience in neural network design and considerable parameter tuning, we proposed the macro operation mutation-based neural architecture search (OM-NAS) approach in order to automatically build a CNN for image classification of pigmented skin lesions. We first used an improved search space that was oriented toward cells and contained micro and macro operations. The macro operations include InceptionV1, Fire and other well-designed neural network modules. During the search process, an evolutionary algorithm based on macro operation mutation was employed to iteratively change the operation type and connection mode of parent cells so that the macro operation was inserted into the child cell similar to the injection of virus into host DNA. Ultimately, the searched best cells were stacked to build a CNN for the image classification of pigmented skin lesions, which was then assessed on the HAM10000 and ISIC2017 datasets. The test results showed that the CNN built with this approach was more accurate than or almost as accurate as state-of-the-art (SOTA) approaches such as AmoebaNet, InceptionV3 + Attention and ARL-CNN in terms of image classification. The average sensitivity of this method on the HAM10000 and ISIC2017 datasets was 72.4% and 58.5%, respectively.

SwinGAN: A dual-domain Swin Transformer-based generative adversarial network for MRI reconstruction.

Magnetic resonance imaging (MRI) is one of the most important modalities for clinical diagnosis. However, the main disadvantages of MRI are the long scanning time and the moving artifact caused by patient movement during prolonged imaging. It can also lead to patient anxiety and discomfort, so accelerated imaging is indispensable for MRI. Convolutional neural network (CNN) based methods have become the fact standard for medical image reconstruction, and generative adversarial network (GAN) have also been widely used. Nevertheless, due to the limited ability of CNN to capture long-distance information, it may lead to defects in the structure of the reconstructed images such as blurry contour. In this paper, we propose a novel Swin Transformer-based dual-domain generative adversarial network (SwinGAN) for accelerated MRI reconstruction. The SwinGAN consists of two generators: a frequency-domain generator and an image-domain generator. Both the generators utilize Swin Transformer as backbone for effectively capturing the long-distance dependencies. A contextual image relative position encoder (ciRPE) is designed to enhance the ability to capture local information. We extensively evaluate the method on the IXI brain dataset, MICCAI 2013 dataset and MRNet knee dataset. Compared with KIGAN, the peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) are improved by 6.1% and 1.49% to 37.64 dB and 0.98 on IXI dataset respectively, which demonstrates that our model can sufficiently utilize the local and global information of image. The model shows promising performance and robustness under different undersampling masks, different acceleration rates and different datasets. But it needs high hardware requirements with the increasing of the network parameters. The code is available at: https://github.com/learnerzx/SwinGAN.

NVTrans-UNet: Neighborhood vision transformer based U-Net for multi-modal cardiac MR image segmentation.

With the rapid development of artificial intelligence and image processing technology, medical imaging technology has turned into a critical tool for clinical diagnosis and disease treatment. The extraction and segmentation of the regions of interest in cardiac images are crucial to the diagnosis of cardiovascular diseases. Due to the erratically diastolic and systolic cardiac, the boundaries of Magnetic Resonance (MR) images are quite fuzzy. Moreover, it is hard to provide complete information using a single modality due to the complex structure of the cardiac image. Furthermore, conventional CNN-based segmentation methods are weak in feature extraction. To overcome these challenges, we propose a multi-modal method for cardiac image segmentation, called NVTrans-UNet. Firstly, we employ the Neighborhood Vision Transformer (NVT) module, which takes advantage of Neighborhood Attention (NA) and inductive biases. It can better extract the local information of the cardiac image as well as reduce the computational cost. Secondly, we introduce a Multi-modal Gated Fusion (MGF) network, which can automatically adjust the contributions of different modal feature maps and make full use of multi-modal information. Thirdly, the bottleneck layer with Atrous Spatial Pyramid Pooling (ASPP) is proposed to expand the feature receptive field. Finally, the mixed loss is added to the cardiac image to focus the fuzzy boundary and realize accurate segmentation. We evaluated our model on MyoPS 2020 dataset. The Dice score of myocardial infarction (MI) was 0.642 ± 0.171, and the Dice score of myocardial infarction + edema (MI + ME) was 0.574 ± 0.110. Compared with the baseline, the MI increases by 11.2%, and the MI + ME increases by 12.5%. The results show the effectiveness of the proposed NVTrans-UNet in the segmentation of MI and ME.

Platelet-derived growth factor AA-modified electrospun fibers promote tendon healing.

Platelet-derived growth factor AA (PDGF-AA) is an important promoter of tissue injury repair and might be a candidate for improving the mechanical properties of repaired tendons. Here, we designed a PDGF-AA-modified poly(lactide-co-glycolide) acid (PLGA) electrospun fibers to promote tendon rehabilitation after injury. In the present study, we grafted PDGF-AA on the surface of PLGA. In structural experiments, we found that the hydrophilicity of PLGA containing PDGF-AA (PLGA-PDGF-AA) increased, but the strength of the material did not change significantly. Moreover, no significant changes in tendon cell proliferation and viability were observed in the PLGA-PDGF-AA treatment compared with the control group. The mouse tendon injury model (n = 9) experiment illustrated that PLGA-PDGF-AA effectively promoted tendon healing, and we confirmed that PLGA-PDGF-AA promoted collagen synthesis and deposition by immunohistochemistry and RT-PCR. Moreover, the mechanical strength of PLGA-PDGF-AA-treated mouse (n = 9) tendon tissue was also higher than that of the PLGA-treated group alone. In conclusion, PLGA-PDGF-AA promoted regeneration after tendon injury and serves as a potential adjuvant material for surgical tendon injury repair.

Risk stratification of 2- to 5-cm gastric stromal tumors based on clinical and computed tomography manifestations.

OBJECTIVE: To evaluate the risk stratification of 2- to 5-cm gastric stromal tumors (GSTs) by analyzing their clinical and computed tomography (CT) manifestations with the goal of providing imaging evidence for rational selection of surgical methods. METHODS: This study involved 223 patients with pathologically diagnosed GSTs of 2 to 5 cm in diameter. According to the pathological results and malignant risk category, the patients were divided into a low-risk biological behavior group (very low and low risk) and high-risk biological behavior group (intermediate and high risk). The clinical and CT manifestations were compared between the groups. The chi-square test was used to analyze categorical variables, and the independent-samples t test was used to analyze continuous variables. Multivariate logistic regression and receiver operating characteristic curve analysis were performed for statistically significant variables. RESULTS: The tumor contour, necrosis, surface ulceration, and long diameter were significantly different between the low-risk group and the high-risk group (P < 0.05). Multivariate logistic regression analysis showed that the tumor contour and long diameter were independent risk factors. The area under the curve was 0.82, and the accuracy, sensitivity, and specificity were 0.78, 77.4 %, and 79.7 %, respectively. CONCLUSIONS: The risk associated with 2- to 5-cm GSTs can be preoperatively predicted in an indirect manner through analysis of clinical and CT manifestations, and this model has high diagnostic value.

The Effectiveness and Safety of Mesenchymal Stem Cells in the Treatment of Osteoarthritis: A Systematic Review and Meta-analysis of 28 Randomized Controlled Trials.

Objective: To evaluate the effectiveness and safety of mesenchymal stem cells (MSCs) in the treatment of osteoarthritis (OA). Methods: Chinese databases (such as CNKI and SinoMed) and English databases (such as PubMed and Embase) were searched to collect randomized controlled trials (RCTs) of MSCs in the treatment of OA. The retrieval time is from inception to October 10, 2021. The literature was strictly selected according to the inclusion and exclusion criteria, data was extracted, and the quality was evaluated. RevMan 5.3 software was used for meta-analysis. STATA was used to evaluate publication bias. The registration number of this systematic review and meta-analysis is CRD42021277145. Results: A total of 28 RCTs involving 1494 participants were included. The primary outcomes showed that MSCs may reduce WOMAC pain and VAS at the 3rd-month follow-up [WOMAC pain: -3.81 (-6.95, -0.68), P = 0.02. VAS: -1.11 (-1.53, -0.68), P < 0.00001], and the effect lasts for at least 12 months [WOMAC pain: -4.29 (-7.12, -1.47), P = 0.003. VAS: -1.77 (-2.43, -1.12), P < 0.00001]. MSCs may also reduce WOMAC stiffness and physical function at the 6th-month follow-up [WOMAC stiffness: -1.12 (-2.09, -0.14), P = 0.03. WOMAC physical function: -4.40 (-6.84, -1.96), P = 0.0004], and the effect lasts for at least 12 months [WOMAC stiffness: -0.99 (-1.95, -0.03), P = 0.04. WOMAC physical function: -3.26 (-5.91, -0.61), P = 0.02]. The improvement of WOMAC pain, VAS, WOMAC stiffness, and WOMAC physical function may be clinically significant. Meanwhile, after the MSC injection, Lequesne had been reduced compared with the control group [-4.49 (-8.21, -0.77), P = 0.002]. For adverse events, there is no significant difference in the safety of MSC injection and the control group [1.20 (0.97, 1.48), P = 0.09]. The quality of WOMAC physical function and adverse events were moderate. Conclusion: Based on current evidence, MSCs may be a safety therapy that have a good curative effect in the treatment of OA, the onset time is no later than 3 months, and the time to maintain the curative effect is no less than 12 months. However, these results should be generalized with caution due to the generally low quality of evidence and RCTs.

Research on the Mechanism of Liuwei Dihuang Decoction for Osteoporosis Based on Systematic Biological Strategies.

Background: Osteoporosis is an important health problem worldwide. Liuwei Dihuang Decoction (LDD) and its main ingredients may have a good clinical effect on osteoporosis. Meanwhile, its mechanism for treating osteoporosis needs to be further revealed in order to provide a basis for future drug development. Methods: A systematic biological methodology was utilized to construct and analyze the LDD-osteoporosis network. After that, the human transcription data of LDD intervention in patients with osteoporosis and protein arrays data of LDD intervention in osteoporosis rats were collected. The human transcription data analysis, protein arrays data analysis, and molecular docking were performed to validate the findings of the prediction network (LDD-osteoporosis PPI network). Finally, animal experiments were conducted to verify the prediction results of systematic pharmacology. Results: (1) LDD-osteoporosis PPI network shows the potential compounds, potential targets (such as ALB, IGF1, SRC, and ESR1), clusters, biological processes (such as positive regulation of calmodulin 1-monooxygenase activity, estrogen metabolism, and endothelial cell proliferation), and signaling and Reactome pathways (such as JAK-STAT signaling pathway, osteoclast differentiation, and degradation of the extracellular matrix) of LDD intervention in osteoporosis. (2) Human transcriptomics data and protein arrays data validated the findings of the LDD-osteoporosis PPI network. (3) The animal experiments showed that LDD can improve bone mineral density (BMD), increase serum estradiol (E2) and alkaline phosphatase (ALP) levels, and upregulate Wnt3a and ß-catenin mRNA expression (P < 0.05). (4) Molecular docking results showed that alisol A, dioscin, loganin, oleanolic acid, pachymic acid, and ursolic acid may stably bind to JAK2, ESR1, and CTNNB1. Conclusion: LDD may have a therapeutic effect on osteoporosis through regulating the targets (such as ALB, IGF1, SRC, and ESR1), biological processes (such as positive regulation of calmodulin 1-monooxygenase activity, estrogen metabolism, and endothelial cell proliferation), and pathways (such as JAK-STAT signaling pathway, osteoclast differentiation, and degradation of the extracellular matrix) found in this research.

Curcumin and Curcuma longa Extract in the Treatment of 10 Types of Autoimmune Diseases: A Systematic Review and Meta-Analysis of 31 Randomized Controlled Trials.

Objective: To evaluate the randomized controlled trials (RCTs) of Curcumin and Curcuma longa Extract in the treatment of autoimmune diseases. Methods: Databases such as Embase, Web of Science, PubMed and The Cochrane Library were searched from the database establishment to February 2022 to collect RCTs of Curcumin and Curcuma longa Extract in the treatment of autoimmune diseases. Then the literature was screened and the data were extracted. Meta-analysis was performed using RevMan 5.3 software. Results: A total of 34 records were included, involving 31 RCTs and 10 types of autoimmune disease. Among them, ankylosing spondylitis (AS) involves one RCT, Behcet 's disease (BD) involves one RCT, Crohn 's disease involves two RCTs, multiple sclerosis (MS) involves two RCTs, oral lichen planus involves six RCTs, psoriasis involves two RCTs, rheumatoid arthritis (RA) involves five RCTs, systemic lupus erythematosus (SLE) involves two RCTs, arteritis involves one RCT, ulcerative colitis (UC) involves nine RCTs. Among them, most of the RCTs of ulcerative colitis (UC), oral lichen planus, RA showed that curcumin and curcumin extracts improved clinical or laboratory results. Crohn ' s disease, MS, SLE, psoriasis included two RCTs; they all showed improvements (at least one RCT reported improvements in clinical outcomes). AS, BD and arteritis included only one RCT, and the clinical results showed improvement. However, due to the small number of RCTs and the small number of patients involved in each disease, there is still a need for more high-quality RCTs. Conclusion: Curcumin and Curcuma longa Extract had good clinical efficacy in the treatment of Psoriasis, UC and RA, so Curcumin and Curcuma longa Extract could be used in the treatment of the above diseases in the future. The results of Meta-analysis showed that Curcumin and Curcuma longa Extract did not show efficacy in the treatment of oral lichen planus, while Takayasu arteritis, SLE, MS, AS, BD and CD did not report sufficient clinical data for meta-analysis. Therefore, large-sample, multi-center clinical trials are still needed for revision or validation.

Efficacy and Safety of Curcumin and Curcuma longa Extract in the Treatment of Arthritis: A Systematic Review and Meta-Analysis of Randomized Controlled Trial.

Background: Modern pharmacological research found that the chemical components of Curcuma longa L. are mainly curcumin and turmeric volatile oil. Several recent randomized controlled trials (RCT) have shown that curcumin improves symptoms and inflammation in patients with arthritis. Methods: Pubmed, Cochran Library, CNKI, and other databases were searched to collect the randomized controlled trials (RCTs). Then, the risk of bias of RCTs were assessed and data of RCTs were extracted. Finally, RevMan 5.3 was utilized for meta-analysis. Results: Twenty-nine (29) RCTs involving 2396 participants and 5 types of arthritis were included. The arthritis included Ankylosing Spondylitis (AS), Rheumatoid Arthritis (RA), Osteoarthritis (OA), Juvenile idiopathic arthritis (JIA) and gout/hyperuricemia. Curcumin and Curcuma longa Extract were administered in doses ranging from 120 mg to 1500 mg for a duration of 4-36 weeks. In general, Curcumin and Curcuma longa Extract showed safety in all studies and improved the severity of inflammation and pain levels in these arthritis patients. However, more RCTs are needed in the future to elucidate the effect of Curcumin and Curcuma longa Extract supplementation in patients with arthritis, including RA, OA, AS and JIA. Conclusion: Curcumin and Curcuma longa Extract may improve symptoms and inflammation levels in people with arthritis. However, due to the low quality and small quantity of RCTs, the conclusions need to be interpreted carefully.

GraformerDIR: Graph convolution transformer for deformable image registration.

PURPOSE: Deformable image registration (DIR) plays an important role in assisting disease diagnosis. The emergence of the Transformer enables the DIR framework to extract long-range dependencies, which relieves the limitations of intrinsic locality caused by convolution operation. However, suffering from the interference of missing or spurious connections, it is a challenging task for Transformer-based methods to capture the high-quality long-range dependencies. METHODS: In this paper, by staking the graph convolution Transformer (Graformer) layer at the bottom of the feature extraction network, we propose a Graformer-based DIR framework, named GraformerDIR. The Graformer layer is consist of the Graformer module and the Cheby-shev graph convolution module. Among them, the Graformer module is designed to capture high-quality long-range dependencies. Cheby-shev graph convolution module is employed to further enlarge the receptive field. RESULTS: The performance and generalizability of GraformerDIR have been evaluated on publicly available brain datasets including the OASIS, LPBA40, and MGH10 datasets. Compared with VoxelMorph, the GraformerDIR has obtained performance improvements of 4.6% in Dice similarity coefficient (DSC) and 0.055 mm in the average symmetric surface distance (ASD) while reducing the non-positive rate of Jacobin determinant (Npr.Jac) index about 60 times on publicly available OASIS dataset. On unseen dataset MGH10, the GraformerDIR has obtained the performance improvements of 4.1% in DSC and 0.084 mm in ASD compared with VoxelMorph, which demonstrates the GraformerDIR with better generalizability. The promising performance on the clinical cardiac dataset ACDC indicates the GraformerDIR is practicable. CONCLUSION: With the advantage of Transformer and graph convolution, the GraformerDIR has obtained comparable performance with the state-of-the-art method VoxelMorph.

A laparoscopic radical inguinal lymphadenectomy approach partly preserving great saphenous vein branches can benefit for patients with penile carcinoma.

BACKGROUND: Inguinal lymphadenectomy (iLAD) is effective for penile carcinoma treatment, but usually results in many complications. This study aims to clinically evaluate the feasibility and clinical significance of a laparoscopic radical iLAD approach partly preserving great saphenous vein branches for penile carcinoma patients. METHODS: A total of 48 patients with penile cancer who underwent laparoscopic radical iLAD with retention of the great saphenous vein in Henan Cancer Hospital from 2012 Jan to 2020 Dec were included in this study. Sixteen penile carcinoma patients who underwent laparoscopic radical iLAD preserving parts of superficial branches of the great saphenous vein were identified as the sparing group, and the matched 32 patients who incised those branches were identified as control group. This new procedure was performed by laparoscopy, preserving parts of superficial branches of the great saphenous vein, superficial lateral and medial femoral veins. Clinicopathological features and perioperative variables were recorded. Postoperative complications, including skin flap necrosis, lymphorrhagia, and lower extremity edema were analyzed retrospectively. RESULTS: We found that the operative time of the sparing group is significantly longer than the control group (p = 0.011). There was no statistical difference in intraoperative blood loss, the lymph node number per side, average time to remove the drainage tube and postoperative hospital stay between the two groups. Compared to the control group, the sparing group showed a significantly decreased incidence of lower extremity edema (p = 0.018). The preservation of parts of superficial branches of the great saphenous vein was mainly decreased the incidence of edema below ankle (p = 0.034). CONCLUSIONS: This study demonstrated that the iLAD with preserving parts of superficial branches of the great saphenous vein, with a decreased incidence of postoperative complications, is a safe and feasible approach for penile cancer.

Case report: Gemcitabine intravesical hyperthermic infusion combined with tislelizumab in muscle invasive bladder urothelium carcinoma.

Background: Muscle invasive bladder urothelium carcinoma is a common urinary tract tumor. With the deepening of research, more and more treatment methods are applied in clinical practice, extending the life of patients. Among them, the clinical application of chemotherapeutic intravesical hyperthermia and tumor immunotherapy provides new ideas for our treatment. Case report: An 81-year-old female patient was diagnosed with stage T2N0M0 bladder cancer in our hospital. Because the patient and her family were keen to preserve her bladder, they declined surgery and opted for combined chemotherapy. After informed consent from the patient and her family, she received cisplatin combined with gemcitabine intravesical hyperthermic infusion. But the side effects of cisplatin made her intolerable to chemotherapy. With their informed consent we changed her to intravenous tislelizumab in combination with gemcitabine intravesical hyperthermic infusion to continue her treatment. During the subsequent follow-up visits, we found a surprising effect of the treatment. Conclusion: Gemcitabine intravesical hyperthermia therapy combined with intravenous tislelizumab in the treatment of muscle invasive bladder urothelium carcinoma may provide a new possible therapeutic strategy of some patients who are inoperable or refuse surgery.

TransDIR: Deformable imaging registration network based on transformer to improve the feature extraction ability.

PURPOSE: Imaging registration has a significant contribution to guide and support physicians in the process of decision-making for diagnosis, prognosis, and treatment. However, existing registration methods based on the convolutional neural network cannot extract global features effectively, which significantly influences registration performance. Moreover, the smoothness of the displacement vector field (DVF) fails to be ensured due to the miss folding penalty. METHODS: In order to capture abundant global information as well as local information, we have proposed a novel 3D deformable image registration network based on Transformer (TransDIR). In the encoding phase, the transformer with the atrous reduction attention block is designed to capture the long-distance dependencies that are crucial for extracting global information. A zero-padding position encoder is embedded into the transformer to capture the local information. In the decoding phase, an up-sampling module based on an attention mechanism is designed to increase the significance of ROIs. Because of adding folding penalty term into loss function, the smoothness of DVF is improved. RESULTS: Finally, we carried out experiments on OASIS, LPBA40, MGH10, and MM-WHS open datasets to validate the effectiveness of TransDIR. Compared with LapIRN, the DSC score is improved by 1.1% and 0.9% on OASIS and LPBA40, separately. In addition, compared with VoxelMorph, the DSC score is improved by 2.8% on the basis of the folding index decreased by hundreds of times on MM-WHS. CONCLUSIONS: The results show that the TransDIR achieves robust registration and promising generalizability compared with LapIRN and VoxelMorph.

RA-SIFA: Unsupervised domain adaptation multi-modality cardiac segmentation network combining parallel attention module and residual attention unit.

BACKGROUND: Convolutional neural network has achieved a profound effect on cardiac image segmentation. The diversity of medical imaging equipment brings the challenge of domain shift for cardiac image segmentation. OBJECTIVE: In order to solve the domain shift existed in multi-modality cardiac image segmentation, this study aims to investigate and test an unsupervised domain adaptation network RA-SIFA, which combines a parallel attention module (PAM) and residual attention unit (RAU). METHODS: First, the PAM is introduced in the generator of RA-SIFA to fuse global information, which can reduce the domain shift from the respect of image alignment. Second, the shared encoder adopts the RAU, which has residual block based on the spatial attention module to alleviate the problem that the convolution layer is insensitive to spatial position. Therefore, RAU enables to further reduce the domain shift from the respect of feature alignment. RA-SIFA model can realize the unsupervised domain adaption (UDA) through combining the image and feature alignment, and then solve the domain shift of cardiac image segmentation in a complementary manner. RESULTS: The model is evaluated using MM-WHS2017 datasets. Compared with SIFA, the Dice of our new RA-SIFA network is improved by 8.4%and 3.2%in CT and MR images, respectively, while, the average symmetric surface distance (ASD) is reduced by 3.4 and 0.8mm in CT and MR images, respectively. CONCLUSION: The study results demonstrate that our new RA-SIFA network can effectively improve the accuracy of whole-heart segmentation from CT and MR images.