Development and Validation of a 3D Resnet Model for Prediction of Lymph Node Metastasis in Head and Neck Cancer Patients.

The accurate diagnosis and staging of lymph node metastasis (LNM) are crucial for determining the optimal treatment strategy for head and neck cancer patients. We aimed to develop a 3D Resnet model and investigate its prediction value in detecting LNM. This study enrolled 156 head and neck cancer patients and analyzed 342 lymph nodes segmented from surgical pathologic reports. The patients' clinical and pathological data related to the primary tumor site and clinical and pathology T and N stages were collected. To predict LNM, we developed a dual-pathway 3D Resnet model incorporating two Resnet models with different depths to extract features from the input data. To assess the model's performance, we compared its predictions with those of radiologists in a test dataset comprising 38 patients. The study found that the dimensions and volume of LNM + were significantly larger than those of LNM-. Specifically, the Y and Z dimensions showed the highest sensitivity of 84.6% and specificity of 72.2%, respectively, in predicting LNM + . The analysis of various variations of the proposed 3D Resnet model demonstrated that Dual-3D-Resnet models with a depth of 34 achieved the highest AUC values of 0.9294. In the validation test of 38 patients and 86 lymph nodes dataset, the 3D Resnet model outperformed both physical examination and radiologists in terms of sensitivity (80.8% compared to 50.0% and 91.7%, respectively), specificity(90.0% compared to 88.5% and 65.4%, respectively), and positive predictive value (77.8% compared to 66.7% and 55.0%, respectively) in detecting individual LNM + . These results suggest that the 3D Resnet model can be valuable for accurately identifying LNM + in head and neck cancer patients. A prospective trial is needed to evaluate further the role of the 3D Resnet model in determining LNM + in head and neck cancer patients and its impact on treatment strategies and patient outcomes.

Cross-Scale Fusion Transformer for Histopathological Image Classification.

Histopathological images provide the medical evidences to help the disease diagnosis. However, pathologists are not always available or are overloaded by work. Moreover, the variations of pathological images with respect to different organs, cell sizes and magnification factors lead to the difficulty of developing a general method to solve the histopathological image classification problems. To address these issues, we propose a novel cross-scale fusion (CSF) transformer which consists of the multiple field-of-view patch embedding module, the transformer encoders and the cross-fusion modules. Based on the proposed modules, the CSF transformer can effectively integrate patch embeddings of different field-of-views to learn cross-scale contextual correlations, which represent tissues and cells of different sizes and magnification factors, with less memory usage and computation compared with the state-of-the-art transformers. To verify the generalization ability of the CSF transformer, experiments are performed on four public datasets of different organs and magnification factors. The CSF transformer outperforms the state-of-the-art task specific methods, convolutional neural network-based methods and transformer-based methods. The source code will be available in our GitHub https://github.com/nchucvml/CSFT.

Multiple Field-of-View Based Attention Driven Network for Weakly Supervised Common Bile Duct Stone Detection.

OBJECTIVE: Common bile duct (CBD) stones caused diseases are life-threatening. Because CBD stones locate in the distal part of the CBD and have relatively small sizes, detecting CBD stones from CT scans is a challenging issue in the medical domain. METHODS AND PROCEDURES: We propose a deep learning based weakly-supervised method called multiple field-of-view based attention driven network (MFADNet) to detect CBD stones from CT scans based on image-level labels. Three dominant modules including a multiple field-of-view encoder, an attention driven decoder and a classification network are collaborated in the network. The encoder learns the feature of multi-scale contextual information while the decoder with the classification network is applied to locate the CBD stones based on spatial-channel attentions. To drive the learning of the whole network in a weakly-supervised and end-to-end trainable manner, four losses including the foreground loss, background loss, consistency loss and classification loss are proposed. RESULTS: Compared with state-of-the-art weakly-supervised methods in the experiments, the proposed method can accurately classify and locate CBD stones based on the quantitative and qualitative results. CONCLUSION: We propose a novel multiple field-of-view based attention driven network for a new medical application of CBD stone detection from CT scans while only image-levels are required to reduce the burdens of labeling and help physicians automatically diagnose CBD stones. The source code is available at https://github.com/nchucvml/MFADNet after acceptance. CLINICAL IMPACT: Our deep learning method can help physicians localize relatively small CBD stones for effectively diagnosing CBD stone caused diseases.

Video Summarization With Spatiotemporal Vision Transformer.

Video summarization aims to generate a compact summary of the original video for efficient video browsing. To provide video summaries which are consistent with the human perception and contain important content, supervised learning-based video summarization methods are proposed. These methods aim to learn important content based on continuous frame information of human-created summaries. However, simultaneously considering both of inter-frame correlations among non-adjacent frames and intra-frame attention which attracts the humans for frame importance representations are rarely discussed in recent methods. To address these issues, we propose a novel transformer-based method named spatiotemporal vision transformer (STVT) for video summarization. The STVT is composed of three dominant components including the embedded sequence module, temporal inter-frame attention (TIA) encoder, and spatial intra-frame attention (SIA) encoder. The embedded sequence module generates the embedded sequence by fusing the frame embedding, index embedding and segment class embedding to represent the frames. The temporal inter-frame correlations among non-adjacent frames are learned by the TIA encoder with the multi-head self-attention scheme. Then, the spatial intra-frame attention of each frame is learned by the SIA encoder. Finally, a multi-frame loss is computed to drive the learning of the network in an end-to-end trainable manner. By simultaneously using both inter-frame and intra-frame information, our method outperforms state-of-the-art methods in both of the SumMe and TVSum datasets. The source code of the spatiotemporal vision transformer will be available at https://github.com/nchucvml/STVT.

ADMM-SRNet: Alternating Direction Method of Multipliers Based Sparse Representation Network for One-Class Classification.

One-class classification aims to learn one-class models from only in-class training samples. Because of lacking out-of-class samples during training, most conventional deep learning based methods suffer from the feature collapse problem. In contrast, contrastive learning based methods can learn features from only in-class samples but are hard to be end-to-end trained with one-class models. To address the aforementioned problems, we propose alternating direction method of multipliers based sparse representation network (ADMM-SRNet). ADMM-SRNet contains the heterogeneous contrastive feature (HCF) network and the sparse dictionary (SD) network. The HCF network learns in-class heterogeneous contrastive features by using contrastive learning with heterogeneous augmentations. Then, the SD network models the distributions of the in-class training samples by using dictionaries computed based on ADMM. By coupling the HCF network, SD network and the proposed loss functions, our method can effectively learn discriminative features and one-class models of the in-class training samples in an end-to-end trainable manner. Experimental results show that the proposed method outperforms state-of-the-art methods on CIFAR-10, CIFAR-100 and ImageNet-30 datasets under one-class classification settings. Code is available at https://github.com/nchucvml/ADMM-SRNet.

Semantic Context-Aware Image Style Transfer.

To provide semantic image style transfer results which are consistent with human perception, transferring styles of semantic regions of the style image to their corresponding semantic regions of the content image is necessary. However, when the object categories between the content and style images are not the same, it is difficult to match semantic regions between two images for semantic image style transfer. To solve the semantic matching problem and guide the semantic image style transfer based on matched regions, we propose a novel semantic context-aware image style transfer method by performing semantic context matching followed by a hierarchical local-to-global network architecture. The semantic context matching aims to obtain the corresponding regions between the content and style images by using context correlations of different object categories. Based on the matching results, we retrieve semantic context pairs where each pair is composed of two semantically matched regions from the content and style images. To achieve semantic context-aware style transfer, a hierarchical local-to-global network architecture, which contains two sub-networks including the local context network and the global context network, is proposed. The former focuses on style transfer for each semantic context pair from the style image to the content image, and generates a local style transfer image storing the detailed style feature representations for corresponding semantic regions. The latter aims to derive the stylized image by considering the content, the style, and the intermediate local style transfer images, so that inconsistency between different corresponding semantic regions can be addressed and solved. The experimental results show that the stylized results using our method are more consistent with human perception compared with the state-of-the-art methods.

Deep Ensemble Feature Network for Gastric Section Classification.

In this paper, we propose a novel deep ensemble feature (DEF) network to classify gastric sections from endoscopic images. Different from recent deep ensemble learning methods, which need to train deep features and classifiers individually to obtain fused classification results, the proposed method can simultaneously learn the deep ensemble feature from arbitrary number of convolutional neural networks (CNNs) and the decision classifier in an end-to-end trainable manner. It comprises two sub networks, the ensemble feature network and the decision network. The former sub network learns the deep ensemble feature from multiple CNNs to represent endoscopic images. The latter sub network learns to obtain the classification labels by using the deep ensemble feature. Both sub networks are optimized based on the proposed ensemble feature loss and the decision loss which guide the learning of deep features and decisions. As shown in the experimental results, the proposed method outperforms the state-of-the-art deep learning, ensemble learning, and deep ensemble learning methods.

USEAQ: Ultra-fast Superpixel Extraction via Adaptive Sampling from Quantized Regions.

We present a novel and highly efficient superpixel extraction method called USEAQ to generate regular and compact superpixels in an image. To reduce the computational cost of iterative optimization procedures adopted in most recent approaches, the proposed USEAQ for superpixel generation works in a one-pass fashion. It firstly performs joint spatial and color quantizations and groups pixels into regions. It then takes into account the variations between regions, and adaptively samples one or a few superpixel candidates for each region. It finally employs maximum a posteriori (MAP) estimation to assign pixels to the most spatially consistent and perceptually similar superpixels. It turns out that the proposed USEAQ is quite efficient, and the extracted superpixels can precisely adhere to boundaries of objects. Experimental results show that USEAQ achieves better or equivalent performance compared to the stateof- the-art superpixel extraction approaches in terms of boundary recall, undersegmentation error, achievable segmentation accuracy, the average miss rate, average undersegmentation error, and average unexplained variation, and it is significantly faster than these approaches.

Gastroesophageal Reflux Disease Diagnosis Using Hierarchical Heterogeneous Descriptor Fusion Support Vector Machine.

A new computer-aided diagnosis method is proposed to diagnose the gastroesophageal reflux disease (GERD) from endoscopic images of the esophageal-gastric junction. To avoid the interferences of different endoscope devices and automatic camera white balance adjustment, heterogeneous descriptors computed from heterogeneous color models are used to represent endoscopic images. Instead of concatenating these descriptors to a super vector, a hierarchical heterogeneous descriptor fusion support vector machine (HHDF-SVM) framework is proposed to simultaneously apply heterogeneous descriptors for GERD diagnosis and overcome the curse of dimensionality problem. During validation, heterogeneous descriptors are extracted from test endoscopic images at first. The classification result is obtained by using HHDF-SVM with heterogeneous descriptors. As shown in the experiments, our method can automatically diagnose GERD without any manual selection of region of interest and achieve better accuracy compared to states-of-the-art methods.

Harmine Hydrochloride Triggers G2 Phase Arrest and Apoptosis in MGC-803 Cells and SMMC-7721 Cells by Upregulating p21, Activating Caspase-8/Bid, and Downregulating ERK/Bad Pathway.

This study aimed to investigate the effects of harmine hydrochloride (HMH) on digestive tumor cells in vitro and its molecular mechanism. MTT assays showed that HMH inhibited the proliferation of some human cancer cell lines and had no obvious inhibitory effects on human LO2 cells. Flow cytometry assays showed that HMH trigged G2 phase arrest in MGC-803 cells and SMMC-7721 cells, while the expression of cyclin A, cyclin B, p21, Myt1, and p-cdc2 (Tyr15) was upregulated. Flow cytometry assays also showed that the percentages of apoptotic cells were increased, the mitochondrial transmembrane potential (ΔΨm) decreased, and the cleavage of caspase-9, caspase-3, and poly (Adenosine diphosphate ribose) polymerase (PARP) were observed, the expression of Bad increased, phospho-Bad (S112) decreased, pro-caspase-8 was cleaved, and Bid (22 kDa) was cleaved. The expression of p-ERK decreased in both cells. In conclusion, these results demonstrated that HMH upregulates the expression of p21, activates Myt1 and inhibits cdc2 by phospho-cdc2 (Y15), and triggers G2 phase arrest in both MGC-803 cells and SMMC-7721 cells. It can also activate the mitochondria-related cell apoptosis pathway through the caspase-8/Bid pathway, inhibiting the ERK/Bad pathway and promoting apoptosis in both of these two cell types.

The inducible effect of LBP on maturation of dendritic cells and the related immune signaling pathways in hepatocellular carcinoma (HCC).

OBJECTIVE: To investigate the effect of LBP on differentiation and maturation of healthy human peripheral blood-derived dendritic cells cultured in different tumor microenvironment in vitro, and discuss the molecular and immunological mechanisms of LBP in treatment of tumor. METHODS: In this study, we procured the peripheral blood-derived dendritic cells precursor cell by the Density gradient centrifugation method, and used the tumor-cell supernatant to prepare conditioned medium. The GM-CSF and IL-4 induced DCs precursor cell differentiation to DCs, the TNF-α promoted the immature DCs developed to mature DCs. In this way, we detected the influence of LBP on the expressions of surface molecules of DCs cultured in different environments, and especially on the role of related-immunity and NF-κB activity. RESULTS: In LBP-treated group, the molecular phenotype of DCs, its capacity to stimulate allogeneic lymphocyte proliferation, and the levels of IL-12p70 and IFN-γ secretion were higher than the untreated group (p < 0.05), with statistical significance. Meanwhile the expression of NF-κB of the DCs in the medium treated by the LBP was higher than the untreated group (p < 0.05), also with statistical significance. Between the two different tumor microenvironment groups, the cell nucleus protein NF-κB expression is obviously different, the hepG2.2.15 group higher than the hepG2 group. CONCLUSION: LBP could increase the expression of the phenotype of DCs, the secretion of IL-12p70 and IFN-γ in MLR, and enhance the NF-κB expression, especially in the virus-related group, suggesting LBP plays the anti-tumor role stronger in the virus-related environment and this phenomenon correlates with the NF-κB signaling pathway.

Study on the protective effect of shengmai san (see text) on the myocardium in the type 2 diabetic cardiomyopathy model rat.

OBJECTIVE: To study the effect of Shengmai San ((see text) Pulse-activating Powder) in protecting myocardium in the rat of the type 2 diabetic cardiomyopathy (DCM) model. METHODS: The DCM rat model was established by combination of insulin resistance induced by a high-fat diet with intraperitoneal injection of high dose streptozotocin (50 mg/kg). And these rat models were randomly divided into three groups: a normal group (n = 12,one of them died), a model group (n = 15) and a Shengmai San group (treatment group, n = 15).The damage of the myocardium was assessed by electrocardiogram at the twelfth week after modeling, and the blood glucose, cholesterol and triglyceride levels were determined; the content of the left cardiac ventricle myocardial collagen was quantified by Masson staining test; the level of myocardial cell apoptosis was detected with TUNEL apoptosis detection kit; the damage extent of the myocardial sub-cellular structures was observed by electron microscopy; the expression levels of cardiac TSP-1 (Thrombospondin-1), TGF-beta1 (Transforming Growth F factor-beta) and TRB-3 (Tribbles homolog 3) proteins were detected by immunohistochemical method; the expression levels of cardiac TSP-1, A-TGF-beta1 and L-TGF-beta1 proteins were detected by Western blotting; and the expression levels of TSP-1 and TRB-3 mRNAs were detected by real-time quantitative PCR. RESULTS: Compared with the control group, the blood glucose, cholesterol, triglycerides levels in both the model groups and the Shengmai San group were significantly decreased; the myocardial tissue was less damaged and the collagen content was reduced in the Shengmai San group; the myocardial sub-cellular structure was injured to a lesser extent; the expression levels of myocardial TSP-1, TGF-beta1, TRB-3, and TSP-1, A-TGF-beta1, L-TGF-beta1 and chymase were decreased, and the expression levels of TSP-1 mRNA and TRB-3 mRNA were decreased in both the model groups and the Shengmai San group (the latter was better),. CONCLUSION: Shengmai San can inhibit myocardial fibrosis in the rat of diabetic cardiomyopathy, and significantly delay the formation of diabetic cardiomyopathy in hyperglycemia rats through multiple pathways.

Study on the protective effect of the Mixture of Shengmai Powder and Danshen Decoction on the myocardium of diabetic cardiomyopathy in the rat model.

OBJECTIVE: To study the protective effect of the Mixture of Shengmai Powder and Danshen Decoction (, abbreviated as the Mixture) in the rat model with type 2 diabetic cardiomyopathy in the rat model with type 2 diabetic cardiomyopathy, abbreviated as the Mixture) in the rat model with type 2 diabetic cardiomyopathy (DCM). METHODS: Forty-two SD rats with DCM model, established by the combination of insulin resistance by a high-fat diet with the damage of pancreatic islet ß cells by intraperitoneal injection of high dose streptozotocin (50 mg/kg) once, were evaluated in the damage of the myocardium by electrocardiogram at the end of 12 weeks of grouping and intervention administration; the extent of damage in the myocardial subcellular structure was observed by electron microscopy; the content of myocardial collagen in the left cardiac ventricle was quantified by Masson staining test; the myocardial cell apoptosis was determined by TUNEL; the changes in the mRNA expression levels of thrombospodin-1 (TSP-1) and tribbles homolog 3 (TRB-3) by real-time quantitative PCR, the expression levels of myocardial TSP-1, tumor growth factorß1 (TGF-ß1), TRB-3, and chymase were detected by immunohistochemistry, and the changes in the expression levels of myocardial TSP-1, active-TGF-ß1 (A-TGF-ß1) and latent-TGF-ß1 (L-TGF-ß1) protein were tested by Western blotting. RESULTS: Compared with the control group, the myocardial tissue was less damaged, and the extent of damage in the myocardial subcellular structure was less; the collagen fiber content and the cell apoptosis were reduced; the expression levels of TSP-1mRNA and TRB-3 mRNA, the expression levels of myocardial TSP-1, TGF-ß1, TRB-3, and chymase, as well as the average expression levels of the myocardial TSP-1, A-TGFß1, and L-TGF-ß1 protein were decreased in the Mixture group. CONCLUSION: The Mixture of Shengmai Powder and Danshen Decoction could inhibit the process of myocardial fibrosis in the rat myocardium of DCM through multiple pathways and significantly delay the genesis and progress of DCM in hyperglycemic rats.

Wheelchair detection using cascaded decision tree.

One of the major goals of healthcare systems is to automatically monitor patients of special needs and alarm the caregivers for providing assistant. In this paper, an efficient single-camera multidirectional wheelchair detector based on a cascaded decision tree (CDT) is proposed to detect a wheelchair and its moving direction simultaneously from video frames for a healthcare system. Our approach combines a decision tree structure and boosted-cascade classifiers to construct a new CDT that can perform early confidence decisions in a hierarchical manner to rapidly reject nonwheelchairs and decide the moving directions. We also impose the tracking history to guide detection routes in the CDT to further reduce detection time and increase detection accuracy. The experiments show over 92% detection rate under cluttered scenes.

Helicobacter pylori-related gastric histology classification using support-vector-machine-based feature selection.

This study presents a computer-aided diagnosis system using sequential forward floating selection (SFFS) with support vector machine (SVM) to diagnose gastric histology of Helicobacter pylori (H. pylori) from endoscopic images. To achieve this goal, candidate image features associated with clinical symptoms are extracted from endoscopic images. With these candidate features, the SFFS method is applied to select feature subsets, which perform the best classification results under SVM with respect to different histological features. By using the classifiers obtained from the feature subsets, a new diagnosis system is implemented to provide physicians with H. pylori -related histological results from endoscopic images.

Reconstruction and rendering of microcalcifications from two mammogram views by modified projective grid space (MPGS).

Mammograms taken by two views: cranio-caudal (CC) and medio-lateral oblique (MLO) views provide only 2D projections of the microcalcifications, which lack the depth information. Thus, envisioning the relative lesion location from mammograms is a challenge for radiologists. To assist radiologists in locating and rendering lesion tissues, a modified projective grid space (MPGS) scheme is proposed to reconstruct 3D microcalcifications. The MPGS scheme reconstructs 3D microcalcifications in a unique space defined by corresponding points and the epipoles retrieved from the fundamental matrix of the CC and MLO views. Since only corresponding points of images are required in the proposed MPGS scheme, we can avoid the difficulty associated with most reconstruction approaches that require prior complicated calibration of X-ray machine. Considering the deformation of the breast, a new method based on the concept of bundle adjustment is proposed to rectify the 3D locations of reconstructed microcalcifications by uncompressed breast model reconstructed from the real patient body using MPGS scheme with iterative closest point (ICP). Then, the reconstructed microcalcifications are augmented in the real patient body model to show their relative positions.