Dual adversarial models with cross-coordination consistency constraint for domain adaption in brain tumor segmentation.

The brain tumor segmentation task with different domains remains a major challenge because tumors of different grades and severities may show different distributions, limiting the ability of a single segmentation model to label such tumors. Semi-supervised models (e.g., mean teacher) are strong unsupervised domain-adaptation learners. However, one of the main drawbacks of using a mean teacher is that given a large number of iterations, the teacher model weights converge to those of the student model, and any biased and unstable predictions are carried over to the student. In this article, we proposed a novel unsupervised domain-adaptation framework for the brain tumor segmentation task, which uses dual student and adversarial training techniques to effectively tackle domain shift with MR images. In this study, the adversarial strategy and consistency constraint for each student can align the feature representation on the source and target domains. Furthermore, we introduced the cross-coordination constraint for the target domain data to constrain the models to produce more confident predictions. We validated our framework on the cross-subtype and cross-modality tasks in brain tumor segmentation and achieved better performance than the current unsupervised domain-adaptation and semi-supervised frameworks.

Dynamically aggregating MLPs and CNNs for skin lesion segmentation with geometry regularization.

BACKGROUND AND OBJECTIVE: Melanoma is a highly malignant skin tumor. Accurate segmentation of skin lesions from dermoscopy images is pivotal for computer-aided diagnosis of melanoma. However, blurred lesion boundaries, variable lesion shapes, and other interference factors pose a challenge in this regard. METHODS: This work proposes a novel framework called CFF-Net (Cross Feature Fusion Network) for supervised skin lesion segmentation. The encoder of the network includes dual branches, where the CNNs branch aims to extract rich local features while MLPs branch is used to establish both the global-spatial-dependencies and global-channel-dependencies for precise delineation of skin lesions. Besides, a feature-interaction module between two branches is designed for strengthening the feature representation by allowing dynamic exchange of spatial and channel information, so as to retain more spatial details and inhibit irrelevant noise. Moreover, an auxiliary prediction task is introduced to learn the global geometric information, highlighting the boundary of the skin lesion. RESULTS: Comprehensive experiments using four publicly available skin lesion datasets (i.e., ISIC 2018, ISIC 2017, ISIC 2016, and PH2) indicated that CFF-Net outperformed the state-of-the-art models. In particular, CFF-Net greatly increased the average Jaccard Index score from 79.71% to 81.86% in ISIC 2018, from 78.03% to 80.21% in ISIC 2017, from 82.58% to 85.38% in ISIC 2016, and from 84.18% to 89.71% in PH2 compared with U-Net. Ablation studies demonstrated the effectiveness of each proposed component. Cross-validation experiments in ISIC 2018 and PH2 datasets verified the generalizability of CFF-Net under different skin lesion data distributions. Finally, comparison experiments using three public datasets demonstrated the superior performance of our model. CONCLUSION: The proposed CFF-Net performed well in four public skin lesion datasets, especially for challenging cases with blurred edges of skin lesions and low contrast between skin lesions and background. CFF-Net can be employed for other segmentation tasks with better prediction and more accurate delineation of boundaries.

MAD-Net: Multi-attention dense network for functional bone marrow segmentation.

Radiotherapy is the main treatment modality for various pelvic malignancies. However, high intensity radiation can damage the functional bone marrow (FBM), resulting in hematological toxicity (HT). Accurate identification and protection of the FBM during radiotherapy planning can reduce pelvic HT. The traditional manual method for contouring the FBM is time-consuming and laborious. Therefore, development of an efficient and accurate automatic segmentation mode can provide a distinct leverage in clinical settings. In this paper, we propose the first network for performing the FBM segmentation task, which is referred to as the multi-attention dense network (named MAD-Net). Primarily, we introduce the dense convolution block to promote the gradient flow in the network as well as incite feature reuse. Next, a novel slide-window attention module is proposed to emphasize long-range dependencies and exploit interdependencies between features. Finally, we design a residual-dual attention module as the bottleneck layer, which further aggregates useful spatial details and explores intra-class responsiveness of high-level features. In this work, we conduct extensive experiments on our dataset of 3838 two-dimensional pelvic slices. Experimental results demonstrate that the proposed MAD-Net transcends previous state-of-the-art models in various metrics. In addition, the contributions of the proposed components are verified by ablation analysis, and we conduct experiments on three other datasets to manifest the generalizability of MAD-Net.

[Research on three-dimensional skull repair by combining residual and informer attention].

Cranial defects may result from clinical brain tumor surgery or accidental trauma. The defect skulls require hand-designed skull implants to repair. The edge of the skull implant needs to be accurately matched to the boundary of the skull wound with various defects. For the manual design of cranial implants, it is time-consuming and technically demanding, and the accuracy is low. Therefore, an informer residual attention U-Net (IRA-Unet) for the automatic design of three-dimensional (3D) skull implants was proposed in this paper. Informer was applied from the field of natural language processing to the field of computer vision for attention extraction. Informer attention can extract attention and make the model focus more on the location of the skull defect. Informer attention can also reduce the computation and parameter count from N 2 to log( N). Furthermore,the informer residual attention is constructed. The informer attention and the residual are combined and placed in the position of the model close to the output layer. Thus, the model can select and synthesize the global receptive field and local information to improve the model accuracy and speed up the model convergence. In this paper, the open data set of the AutoImplant 2020 was used for training and testing, and the effects of direct and indirect acquisition of skull implants on the results were compared and analyzed in the experimental part. The experimental results show that the performance of the model is robust on the test set of 110 cases fromAutoImplant 2020. The Dice coefficient and Hausdorff distance are 0.940 4 and 3.686 6, respectively. The proposed model reduces the resources required to run the model while maintaining the accuracy of the cranial implant shape, and effectively assists the surgeon in automating the design of efficient cranial repair, thereby improving the quality of the patient's postoperative recovery.

Joint Dense Residual and Recurrent Attention Network for DCE-MRI Breast Tumor Segmentation.

Breast cancer detection largely relies on imaging characteristics and the ability of clinicians to easily and quickly identify potential lesions. Magnetic resonance imaging (MRI) of breast tumors has recently shown great promise for enabling the automatic identification of breast tumors. Nevertheless, state-of-the-art MRI-based algorithms utilizing deep learning techniques are still limited in their ability to accurately separate tumor and healthy tissue. Therefore, in the current work, we propose an automatic and accurate two-stage U-Net-based segmentation framework for breast tumor detection using dynamic contrast-enhanced MRI (DCE-MRI). This framework was evaluated using T2-weighted MRI data from 160 breast tumor cases, and its performance was compared with that of the standard U-Net model. In the first stage of the proposed framework, a refined U-Net model was utilized to automatically delineate a breast region of interest (ROI) from the surrounding healthy tissue. Importantly, this automatic segmentation step reduced the impact of the background chest tissue on breast tumors' identification. For the second stage, we employed an improved U-Net model that combined a dense residual module based on dilated convolution with a recurrent attention module. This model was used to accurately and automatically segment the tumor tissue from healthy tissue in the breast ROI derived in the previous step. Overall, compared to the U-Net model, the proposed technique exhibited increases in the Dice similarity coefficient, Jaccard similarity, positive predictive value, sensitivity, and Hausdorff distance of 3%, 3%, 3%, 2%, and 16.2, respectively. The proposed model may in the future aid in the clinical diagnosis of breast cancer lesions and help guide individualized patient treatment.

Improved U-Net3+ with stage residual for brain tumor segmentation.

BACKGROUND: For the encoding part of U-Net3+,the ability of brain tumor feature extraction is insufficient, as a result, the features can not be fused well during up-sampling, and the accuracy of segmentation will reduce. METHODS: In this study, we put forward an improved U-Net3+ segmentation network based on stage residual. In the encoder part, the encoder based on the stage residual structure is used to solve the vanishing gradient problem caused by the increasing in network depth, and enhances the feature extraction ability of the encoder which is instrumental in full feature fusion when up-sampling in the network. What's more, we replaced batch normalization (BN) layer with filter response normalization (FRN) layer to eliminate batch size impact on the network. Based on the improved U-Net3+ two-dimensional (2D) model with stage residual, IResUnet3+ three-dimensional (3D) model is constructed. We propose appropriate methods to deal with 3D data, which achieve accurate segmentation of the 3D network. RESULTS: The experimental results showed that: the sensitivity of WT, TC, and ET increased by 1.34%, 4.6%, and 8.44%, respectively. And the Dice coefficients of ET and WT were further increased by 3.43% and 1.03%, respectively. To facilitate further research, source code can be found at: https://github.com/YuOnlyLookOne/IResUnet3Plus . CONCLUSION: The improved network has a significant improvement in the segmentation task of the brain tumor BraTS2018 dataset, compared with the classical networks u-net, v-net, resunet and u-net3+, the proposed network has smaller parameters and significantly improved accuracy.

BeautyNet: Joint Multiscale CNN and Transfer Learning Method for Unconstrained Facial Beauty Prediction.

Because of the lack of discriminative face representations and scarcity of labeled training data, facial beauty prediction (FBP), which aims at assessing facial attractiveness automatically, has become a challenging pattern recognition problem. Inspired by recent promising work on fine-grained image classification using the multiscale architecture to extend the diversity of deep features, BeautyNet for unconstrained facial beauty prediction is proposed in this paper. Firstly, a multiscale network is adopted to improve the discriminative of face features. Secondly, to alleviate the computational burden of the multiscale architecture, MFM (max-feature-map) is utilized as an activation function which can not only lighten the network and speed network convergence but also benefit the performance. Finally, transfer learning strategy is introduced here to mitigate the overfitting phenomenon which is caused by the scarcity of labeled facial beauty samples and improves the proposed BeautyNet's performance. Extensive experiments performed on LSFBD demonstrate that the proposed scheme outperforms the state-of-the-art methods, which can achieve 67.48% classification accuracy.

Robust SAR Automatic Target Recognition Based on Transferred MS-CNN with L2-Regularization.

Though Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR) via Convolutional Neural Networks (CNNs) has made huge progress toward deep learning, some key issues still remain unsolved due to the lack of sufficient samples and robust model. In this paper, we proposed an efficient transferred Max-Slice CNN (MS-CNN) with L2-Regularization for SAR ATR, which could enrich the features and recognize the targets with superior performance. Firstly, the data amplification method is presented to reduce the computational time and enrich the raw features of SAR targets. Secondly, the proposed MS-CNN framework with L2-Regularization is trained to extract robust features, in which the L2-Regularization is incorporated to avoid the overfitting phenomenon and further optimizing our proposed model. Thirdly, transfer learning is introduced to enhance the feature representation and discrimination, which could boost the performance and robustness of the proposed model on small samples. Finally, various activation functions and dropout strategies are evaluated for further improving recognition performance. Extensive experiments demonstrated that our proposed method could not only outperform other state-of-the-art methods on the public and extended MSTAR dataset but also obtain good performance on the random small datasets.

Deep Convolutional Neural Network Used in Single Sample per Person Face Recognition.

Face recognition (FR) with single sample per person (SSPP) is a challenge in computer vision. Since there is only one sample to be trained, it makes facial variation such as pose, illumination, and disguise difficult to be predicted. To overcome this problem, this paper proposes a scheme combined traditional and deep learning (TDL) method to process the task. First, it proposes an expanding sample method based on traditional approach. Compared with other expanding sample methods, the method can be used easily and conveniently. Besides, it can generate samples such as disguise, expression, and mixed variation. Second, it uses transfer learning and introduces a well-trained deep convolutional neural network (DCNN) model and then selects some expanding samples to fine-tune the DCNN model. Third, the fine-tuned model is used to implement experiment. Experimental results on AR face database, Extend Yale B face database, FERET face database, and LFW database demonstrate that TDL achieves the state-of-the-art performance in SSPP FR.

Antihyperglycemic and antioxidant effect of the total flavones of Potentilla kleiniana Wight et Arn. in streptozotocin induced diabetic rats.

To investigate the antihyperglycemic and antioxidant activity of the total flavones of Potentilla kleiniana Wight et Arn. (TFP) in streptozotocin (STZ) induced diabetic rats. STZ-induced diabetic rats were treated with TFP weekly for 4 weeks at three doses (100 mg/kg, 200 mg/kg and 400 mg/kg). Blood glucose levels (BGL), body weight, insulin, total cholesterol (TC), triglyceride (TG), high density lipoprotein (HDL), very low density lipoprotein (VLDL), low density lipoprotein (LDL), malondialdehyde (MDA), glutathione (GSH), super oxide dismutase (SOD) and catalase (CAT) levels of liver and pancreas were measured weekly for 4 weeks. STZ administration resulted in oxidative damage of pancreas, then hyperglycemia proved by higher MDA, lower insulin and higher BGL in comparison to normal rats. TC, TG, LDL and VLDL cholesterol levels were also significantly elevated with decreased GSH, SOD, and CAT levels. A steady decrease in BGL and increase in insulin level were observed 4 weeks after TFP treatment in a dose dependent manner, as well as remarkable improvement in body weight and biochemical parameters. TFP have the effect of inhibiting hyperglycemia and oxidative stress, and the administration may be helpful in the prevention of diabetic complications associated with oxidative stress.

[Study on impact of ethanol extracts from Sedum sarmentosum in inhibiting STAT-3 signaling and inducing apoptosis of human hepatocellular carcinoma cell line HepG2].

OBJECTIVE: To investigate the impact of ethanol extracts from Sedum sarmentosum (ESB) on STAT-3 signaling and its probable molecular mechanism in inducing apoptosis. METHOD: MTT assay was used to detect the impact of ESB on HepG2 cell proliferation. FITC-Annexin V-FITC /PI double-labeling were used to investigate the impact on hepatoma carcinoma cell apoptosis. Western blot analysis was used to test the expression levels of cell apoptosis-related proteins Caspase-3, Caspase-9, PARP, P-STAT-3 (Tyr705) , STAT-3, Bcl-2, Mcl-1. RESULT: ESB could notably inhibit proliferation of HepG2 cells, and induce HepG2 cell apoptosis, with the dose-dependent inhibitory effect. In addition, ESB could inhibit STAT-3 signaling, down-regulate Mcl-1 and Bcl-2 expressions, and induce degradation/activation of apoptosis-related proteins Caspase-3 and Caspase-9 and PARP degradation in a dose-dependent manner. CONCLUSION: ESB inhibits HepG2 cell proliferation and induces apoptosis by inhibiting STAT-3 signaling and Mcl-1 and Bcl-2 expressions.

Synergistic activities of MET/RON inhibitor BMS-777607 and mTOR inhibitor AZD8055 to polyploid cells derived from pancreatic cancer and cancer stem cells.

Tyrosine kinase inhibitor BMS-777067 is an inhibitor of RON/MET receptor tyrosine kinases currently under clinical trials. Here, we report the synergistic activity of BMS-777607 in combination with mTOR inhibitor AZD8055 in killing chemoresistant pancreatic cancer and cancer stem cells. Treatment of pancreatic cancer L3.6pl cells with BMS-777607 alone inhibited clonogenic growth and moderately induced apoptotic death. However, BMS-777607 caused extensive polyploidy in L3.6pl cells through inhibition of aurora kinase B activity, independent of RON expression. In contrast, L3.6pl-derived cancer stem cells were highly resistant to BMS-777607-induced growth inhibition and apoptosis. The effect of BMS-777607 on induction of cancer stem cell polyploidy was also weak. BMS-777607-induced polyploidy features a predominant cell population with 8N chromosome content in both L3.6pl and cancer stem cells. These cells also showed decreased sensitivity toward chemotherapeutics by increased survival of IC(50) values in response to doxorubicin, cisplatin, methotrexate, 5-fluorouracial, and gemcitabine. Among a panel of chemical inhibitors that target different signaling proteins, we found that BMS-777607 in combination with mTOR inhibitor AZD8055 exerted synergistic effects on L3.6pl and cancer stem cells. More than 70% of L3.6pl and cancer stem cells lost their viability when both inhibitors were used. Specifically, BMS-777607 in combination with inhibition of mTORC2, but not mTORC1, was responsible for the observed synergism. Our findings demonstrate that BMS-777607 at therapeutic doses exerts inhibitory activities on pancreatic cancer cells but also induces polyploidy insensitive to chemotherapeutics. Combination of BMS-777607 with AZD8055 achieves the maximal cytotoxic effect on pancreatic cancer and cancer stem cells.

Oncogenic variant RON160 expression in breast cancer and its potential as a therapeutic target by small molecule tyrosine kinase inhibitor.

Aberrant expression of the RON receptor tyrosine kinase contributes to breast cancer malignancy. Although clinical trials of RON targeting are underway, the intriguing issue is the diversity of RON expression as evident by cancer cells expressing different variants including oncogenic RON160. The current study determines aberrant RON160 expression in breast cancer and its potential as a target for breast cancer therapy. Using mouse monoclonal antibody Zt/h12 in immunohistochemical staining of breast cancer tissue microarray, we observed that RON160 was expressed in high frequency in primary invasive ductal (77.2%, 61/79 cases), lobular (42.5%, 34/80 cases), and lymph node-involved (63.9%, 26/36 cases) breast cancer samples. Moreover, RON160 overexpression was predominantly observed in invasive ductal (26.6%, 21/79 cases) and lymph node-involved (33.3%, 12/36) cases. Among a panel of breast cancer cell lines analyzed, Du4475 cells naturally expressed RON160. Silencing RON160 expression by siRNA reduced Du4475 cell viability. Inhibition of RON160 signaling by tyrosine kinase inhibitor PHA665752 also suppressed Du4475 cell anchorage-independent growth and induced apoptotic cell death. Studies in vivo revealed that PHA665752 inhibited 3T3- RON160 and Du4475 cell-mediated tumor growth in mouse mammary fat pad. A 60% reduction in tumor volume compared to controls was achieved after a 13-day treatment. We conclude from these studies that RON160 is highly expressed in breast cancer and its signaling is integrated into cellular signaling network for tumor cell growth and survival. Experimental treatment by PHA665752 in Du4475 breast cancer xenograft model highlights the significance of RON160 as a drug target in molecular-targeted breast cancer therapy.

Small-molecule inhibitor BMS-777607 induces breast cancer cell polyploidy with increased resistance to cytotoxic chemotherapy agents.

The RON receptor tyrosine kinase is a therapeutic target for cancer treatment. Here, we report therapeutic effect and phenotypic change of breast cancer cells in response to BMS-777607, a RON tyrosine kinase inhibitor. Treatment of breast cancer cells with BMS-777607 at therapeutic doses inhibited cancerous clonogenic growth but had only minimal effect on cell apoptosis. Significantly, BMS-777607 induced extensive polyploidy with multiple sets of chromosomes in cancer cells. This effect is independent of RON expression. Knockdown of RON in T-47D and ZR-75-1 cells by specific siRNA did not prevent polyploid formation. Immunofluorescent analysis of α-tubulin and γ-tubulin expression in polyploid cells revealed that BMS-777607 disrupts bipolar spindle formation and causes multipolar-like microtubule assembly. Also, both metaphase equatorial alignment and chromosomal segregation were absent in polyploid cells. These results suggest that cellular mitosis arrests at prophase/pro-metaphase and fails to undergo cytokinesis. By analyzing kinase-inhibitory profiles, aurora kinase B was identified as the target molecule inhibited by BMS-777607. In BMS-777607-treated cells, aurora kinase B was inhibited followed by protein degradation. Moreover, BMS-777607 inhibited Ser10 phosphorylation of histone H3, a substrate of aurora kinase B. Chemosensitivity analysis indicated the resistance of polyploid cells toward chemotherapeutics. Treatment with doxorubicin, bleomycin, methotrexate, and paclitaxel significantly increased cellular IC50 values. These findings highlight the theory that BMS-777607 acts as a multikinase inhibitor at therapeutic doses and is capable of inducing polyploidy by inhibiting aurora kinase B. Increased resistance of polyploid cells to cytotoxic chemotherapeutics could have a negative impact on targeted cancer therapy using BMS-777607.