Exploring Separable Attention for Multi-Contrast MR Image Super-Resolution.

Super-resolving the magnetic resonance (MR) image of a target contrast under the guidance of the corresponding auxiliary contrast, which provides additional anatomical information, is a new and effective solution for fast MR imaging. However, current multi-contrast super-resolution (SR) methods tend to concatenate different contrasts directly, ignoring their relationships in different clues, e.g., in the high-and low-intensity regions. In this study, we propose a separable attention network (comprising high-intensity priority (HP) attention and low-intensity separation (LS) attention), named SANet. Our SANet could explore the areas of high-and low-intensity regions in the "forward" and "reverse" directions with the help of the auxiliary contrast while learning clearer anatomical structure and edge information for the SR of a target-contrast MR image. SANet provides three appealing benefits: First, it is the first model to explore a separable attention mechanism that uses the auxiliary contrast to predict the high-and low-intensity regions, diverting more attention to refining any uncertain details between these regions and correcting the fine areas in the reconstructed results. Second, a multistage integration module is proposed to learn the response of multi-contrast fusion at multiple stages, get the dependency between the fused representations, and boost their representation ability. Third, extensive experiments with various state-of-the-art multi-contrast SR methods on fastMRI and clinical in vivo datasets demonstrate the superiority of our model. The code is released at https://github.com/chunmeifeng/SANet.

Multi-Contrast Complementary Learning for Accelerated MR Imaging.

Thanks to its powerful ability to depict high-resolution anatomical information, magnetic resonance imaging (MRI) has become an essential non-invasive scanning technique in clinical practice. However, excessive acquisition time often leads to the degradation of image quality and psychological discomfort among subjects, hindering its further popularization. Besides reconstructing images from the undersampled protocol itself, multi-contrast MRI protocols bring promising solutions by leveraging additional morphological priors for the target modality. Nevertheless, previous multi-contrast techniques mainly adopt a simple fusion mechanism that inevitably ignores valuable knowledge. In this work, we propose a novel multi-contrast complementary information aggregation network named MCCA, aiming to exploit available complementary representations fully to reconstruct the undersampled modality. Specifically, a multi-scale feature fusion mechanism has been introduced to incorporate complementary-transferable knowledge into the target modality. Moreover, a hybrid convolution transformer block was developed to extract global-local context dependencies simultaneously, which combines the advantages of CNNs while maintaining the merits of Transformers. Compared to existing MRI reconstruction methods, the proposed method has demonstrated its superiority through extensive experiments on different datasets under different acceleration factors and undersampling patterns.

Zero-Shot Camouflaged Object Detection.

The goal of Camouflaged object detection (COD) is to detect objects that are visually embedded in their surroundings. Existing COD methods only focus on detecting camouflaged objects from seen classes, while they suffer from performance degradation to detect unseen classes. However, in a real-world scenario, collecting sufficient data for seen classes is extremely difficult and labeling them requires high professional skills, thereby making these COD methods not applicable. In this paper, we propose a new zero-shot COD framework (termed as ZSCOD), which can effectively detect the never unseen classes. Specifically, our framework includes a Dynamic Graph Searching Network (DGSNet) and a Camouflaged Visual Reasoning Generator (CVRG). In details, DGSNet is proposed to adaptively capture more edge details for boosting the COD performance. CVRG is utilized to produce pseudo-features that are closer to the real features of the seen camouflaged objects, which can transfer knowledge from seen classes to unseen classes to help detect unseen objects. Besides, our graph reasoning is built on a dynamic searching strategy, which can pay more attention to the boundaries of objects for reducing the influences of background. More importantly, we construct the first zero-shot COD benchmark based on the COD10K dataset. Experimental results on public datasets show that our ZSCOD not only detects the camouflaged object of unseen classes but also achieves state-of-the-art performance in detecting seen classes.

The association between serum complement C3a and severity in patients with community-acquired pneumonia.

Background: A few studies found that the complement system may be involved in the onset and progression of community-acquired pneumonia (CAP). However, the role of the complement system in CAP was obscure. The goal of this study was to analyze the association of serum complement C3a with CAP severity scores based on a cross-sectional study. Methods: All 190 CAP patients and 95 control subjects were enrolled. Demographic information and clinical data were extracted. Peripheral blood samples were collected on admission. Results: Serum complement C3a on admission was elevated in CAP patients compared with healthy subjects. The level of complement C3a was gradually elevated in parallel with CAP severity scores (CURB-65, CRB-65, PSI, SMART-COP, and CURXO). Complement C3a was positively correlated with blood routine parameters, renal function markers, and inflammatory cytokines in CAP patients. Furthermore, multivariate linear and logistic regression models found that serum complement C3a on admission was positively associated with CAP severity scores. Mechanistic research suggested that complement system inhibition alleviated Streptococcus pneumoniae-induced upregulation of IL-1ß, TNF-α, IL-6, and CRP in MLE-12 cells. Conclusions: Serum complement C3a on admission is positively associated with the severity of CAP patients. Inhibiting complement system attenuates S. pneumoniae-elevated secretion of inflammatory cytokines in pulmonary epithelial cells, indicating that complement C3a is involved in the pathophysiology of CAP. Serum complement C3a may serve as an earlier diagnostic biomarker for CAP.

Multimodal Transformer for Accelerated MR Imaging.

Accelerated multi-modal magnetic resonance (MR) imaging is a new and effective solution for fast MR imaging, providing superior performance in restoring the target modality from its undersampled counterpart with guidance from an auxiliary modality. However, existing works simply combine the auxiliary modality as prior information, lacking in-depth investigations on the potential mechanisms for fusing different modalities. Further, they usually rely on the convolutional neural networks (CNNs), which is limited by the intrinsic locality in capturing the long-distance dependency. To this end, we propose a multi-modal transformer (MTrans), which is capable of transferring multi-scale features from the target modality to the auxiliary modality, for accelerated MR imaging. To capture deep multi-modal information, our MTrans utilizes an improved multi-head attention mechanism, named cross attention module, which absorbs features from the auxiliary modality that contribute to the target modality. Our framework provides three appealing benefits: (i) Our MTrans use an improved transformers for multi-modal MR imaging, affording more global information compared with existing CNN-based methods. (ii) A new cross attention module is proposed to exploit the useful information in each modality at different scales. The small patch in the target modality aims to keep more fine details, the large patch in the auxiliary modality aims to obtain high-level context features from the larger region and supplement the target modality effectively. (iii) We evaluate MTrans with various accelerated multi-modal MR imaging tasks, e.g., MR image reconstruction and super-resolution, where MTrans outperforms state-of-the-art methods on fastMRI and real-world clinical datasets.

Specificity-Preserving Federated Learning for MR Image Reconstruction.

Federated learning (FL) can be used to improve data privacy and efficiency in magnetic resonance (MR) image reconstruction by enabling multiple institutions to collaborate without needing to aggregate local data. However, the domain shift caused by different MR imaging protocols can substantially degrade the performance of FL models. Recent FL techniques tend to solve this by enhancing the generalization of the global model, but they ignore the domain-specific features, which may contain important information about the device properties and be useful for local reconstruction. In this paper, we propose a specificity-preserving FL algorithm for MR image reconstruction (FedMRI). The core idea is to divide the MR reconstruction model into two parts: a globally shared encoder to obtain a generalized representation at the global level, and a client-specific decoder to preserve the domain-specific properties of each client, which is important for collaborative reconstruction when the clients have unique distribution. Such scheme is then executed in the frequency space and the image space respectively, allowing exploration of generalized representation and client-specific properties simultaneously in different spaces. Moreover, to further boost the convergence of the globally shared encoder when a domain shift is present, a weighted contrastive regularization is introduced to directly correct any deviation between the client and server during optimization. Extensive experiments demonstrate that our FedMRI's reconstructed results are the closest to the ground-truth for multi-institutional data, and that it outperforms state-of-the-art FL methods.

Neoadjuvant Savolitinib targeted therapy stage IIIA-N2 primary lung adenocarcinoma harboring MET Exon 14 skipping mutation: A case report.

MET exon 14 skipping mutation (METex14m) is rare and occurs in approximately 1-4% of all non-small cell lung cancer (NSCLC) patients and approximately 2.8% of resected stage I-III NSCLC patients. Savolitinib is an oral, potent and highly selective type Ib MET inhibitor, which has been shown to be promising activity and acceptable safety profile in patients with advanced NSCLC harboring METex14m. Most recently, many studies have been probing into the feasibility and efficacy of target therapy for perioperative application in NSCLC. Interestingly, there are very few recorded cases of such treatments. Here, we presented that systemic treatment with the MET inhibitor savolitinib before surgery could provide the potential to prolong overall survival (OS) of patients with locally advanced potentially resectable NSCLC. A 49-year-old woman was diagnosed with stage IIIA (T2bN2M0) primary lung adenocarcinoma exhibiting a METex14m by real-time quantitative polymerase chain reaction (RT-qPCR). Given that the tumor load and the size of lymph nodes experienced a significant downstaging after the neoadjuvant treatment of savolitinib with 600mg once a day for 5 weeks, left lower lobectomy and systemic lymphadenectomy were successfully performed. The pathological response was 50% and the final postoperative pathological staging was pT1cN0M0, IA3 (AJCC, 8th edition). The case provides empirical basis for the neoadjuvant treatment with savolitinib in METex14m-positive locally advanced primary lung adenocarcinoma, which will offer some innovative insights and clinical evidence for more effective clinical treatment of neoadjuvant targeted therapy for METex14m-positive NSCLC.

Acute Respiratory Distress Syndrome Caused by Occupational Exposure to Waterproofing Spray: A Case Report and Literature Review.

Background: Acute respiratory distress syndrome (ARDS) is a serious respiratory disease, caused by severe infection, trauma, shock, inhalation of harmful gases and poisons and presented with acute-onset and high mortality. Timely and accurate identification will be helpful to the treatment and prognosis of ARDS cases. Herein, we report a case of ARDS caused by occupational exposure to waterproofing spray. To our knowledge, inhalation of waterproofing spray is an uncommon cause of ARDS, and what makes our case special is that we ruled out concurrent infections with some pathogens by using metagenomic next-generation sequencing (mNGS) as an auxiliary diagnosis, which presents the most comprehensive etiological examination of similar reports. Case Presentation: A previously healthy 25 years old delivery man developed hyperpyrexia, chest tightness, cough and expectoration. The symptoms occurred and gradually exacerbated after exposure to a waterproofing spray. The chest computed tomography (CT) finding showed diffuse ground glass and infiltrative shadows in both lungs. The diagnosis of ARDS related to waterproofing spray was established on the basis of comprehensive differential diagnosis and etiological examination. The patient achieved good curative effect after proper systemic glucocorticoid therapy. Conclusions: The diagnosis and differential diagnosis of acute respiratory failure for outdoor workers, such as delivery drivers or hikers, should be considered whether toxic aerosol exposure exists from daily contacts. The case can educate the public that more attention should be paid to avoid exposure to these chemicals by aerosols/ingestion mode and some preventive strategies should be taken in occupational environment. The treatment effect of glucocorticoids is significant in ARDS patients with general chemical damage caused by inhaling toxic gases and substances.

Serum IL-27 predicts the severity and prognosis in patients with community-acquired pneumonia: a prospective cohort study.

Background: The previous studies have revealed that IL-27 was involved in the pathophysiology of pulmonary inflammatory diseases. However, the role of IL-27 in community-acquired pneumonia (CAP) was unclear. The goal of this research was to explore the associations of serum IL-27 with the severity and prognosis among CAP patients through a prospective cohort study. Methods: The whole of 239 healthy population and 239 CAP patients were enrolled. Fasting blood samples were collected. Inflammatory cytokines were detected using enzyme linked immunosorbent assay (ELISA). Demographic characteristics and clinical information were analyzed. Results: Serum IL-27 on admission was significantly risen in CAP patients compared with control subjects. Besides, serum IL-27 was gradually increased in line with CAP severity scores. Correlative analysis suggested that serum IL-27 was associated with blood routine indices, renal function, liver function, myocardial function and inflammatory cytokines. Linear and logistic regression analyses revealed that serum IL-27 was positively correlated with CAP severity scores. Logistic regression analysis demonstrated that serum higher IL-27 on admission elevated the risks of vasoactive agent usage and longer hospital stay during hospitalization among CAP patients. Conclusions: Serum IL-27 is markedly and positively associated with the severity and poor prognosis among CAP patients, indicating that IL-27 may involve in the pathophysiological process of CAP. Serum IL-27 may be used as a biomarker for diagnosis and prognosis in CAP patients.

Group-Wise Learning for Weakly Supervised Semantic Segmentation.

Acquiring sufficient ground-truth supervision to train deep visual models has been a bottleneck over the years due to the data-hungry nature of deep learning. This is exacerbated in some structured prediction tasks, such as semantic segmentation, which require pixel-level annotations. This work addresses weakly supervised semantic segmentation (WSSS), with the goal of bridging the gap between image-level annotations and pixel-level segmentation. To achieve this, we propose, for the first time, a novel group-wise learning framework for WSSS. The framework explicitly encodes semantic dependencies in a group of images to discover rich semantic context for estimating more reliable pseudo ground-truths, which are subsequently employed to train more effective segmentation models. In particular, we solve the group-wise learning within a graph neural network (GNN), wherein input images are represented as graph nodes, and the underlying relations between a pair of images are characterized by graph edges. We then formulate semantic mining as an iterative reasoning process which propagates the common semantics shared by a group of images to enrich node representations. Moreover, in order to prevent the model from paying excessive attention to common semantics, we further propose a graph dropout layer to encourage the graph model to capture more accurate and complete object responses. With the above efforts, our model lays the foundation for more sophisticated and flexible group-wise semantic mining. We conduct comprehensive experiments on the popular PASCAL VOC 2012 and COCO benchmarks, and our model yields state-of-the-art performance. In addition, our model shows promising performance in weakly supervised object localization (WSOL) on the CUB-200-2011 dataset, demonstrating strong generalizability. Our code is available at: https://github.com/Lixy1997/Group-WSSS.

Serum 8-Hydroxydeoxyguanosine Is a Potential Indicator for the Severity and Prognosis in Patients with Community-Acquired Pneumonia: A Prospective Cohort Study.

Previous studies have demonstrated that 8-hydroxydeoxyguanosine (8-OHdG) exerted key roles in various pulmonary diseases, but the evidence for its role in community-acquired pneumonia (CAP) was lacking. The goal of this research was to evaluate the correlations of serum 8-OHdG with the severity and prognosis among patients with CAP through a prospective cohort study. A total of 239 patients with CAP and 239 healthy participants were enrolled. Fasting blood samples were collected. 8-OHdG and inflammatory cytokines were measured by ELISA. On admission, serum 8-OHdG was significantly increased in patients with CAP compared with control subjects. Besides, serum 8-OHdG was incrementally increased in line with CAP severity scores. Pearson correlative analysis found that serum 8-OHdG was correlated with clinical characteristics and inflammatory cytokines in patients with CAP. Linear and logistic regression analysis showed that serum 8-OHdG was positively associated with CAP severity scores. Furthermore, the prognostic outcomes were tracked. Higher serum 8-OHdG on admission increased the risks for intensive care unit admission, mechanical ventilation, vasoactive agent usage, death, and longer hospital stay among patients with CAP. Serum 8-OHdG combination with confusion, respiratory rate, blood pressure, and age ≥65 y or pneumonia severity index had stronger predictive powers for death than single 8-OHdG, CAP severity scores, or several inflammatory cytokines in patients with CAP. These results indicated that serum 8-OHdG is positively associated with the severity and poor prognosis in patients with CAP, demonstrating that 8-OHdG may be involved in the pathophysiology process of CAP.

Serum interleukin-17 predicts severity and prognosis in patients with community acquired pneumonia: a prospective cohort study.

BACKGROUND: Some studies previously demonstrated that interleukin-17 (IL-17) involves in pulmonary diseases progression. Nevertheless, the role of IL-17 in community-acquired pneumonia (CAP) remains unknown. This study aims to examine the correlations between serum IL-17 with the severity and prognosis in CAP patients through a prospective cohort study. METHODS: All 239 CAP patients were recruited. Serum IL-17 was detected by enzyme-linked immunosorbent assay (ELISA). The CAP severity was evaluated through CAP severity scores, including CURB-65, CRB-65, PSI, SMART-COP, CURXO and APACHE II. RESULTS: Serum IL-17 was gradually increased consistent with the severity of CAP. Correlative analysis suggested that serum IL-17 was associated with clinical physiologic indicators among CAP patients. Logistic regression indicated that serum IL-17 was positively related to CAP severity scores. Additionally, the prognostic outcomes were tracked among CAP patients. The levels of IL-17 on admission were significantly increased in CAP patients with ICU admission, mechanical ventilation, vasoactive agent, death and longer hospitalization days. Logistic regression analyses revealed serum higher IL-17 on admission elevated the risks of vasoactive agent usage and longer hospital stays in CAP patients. The cut-off concentrations of serum IL-17 for death, ICU admission, mechanical ventilation and ≥ 14 hospital stays were 86.80 ng/mL, 84.92 ng/mL, 84.92 ng/mL and 60.29 ng/mL respectively. CONCLUSIONS: Serum IL-17 on admission is positively associated with the severity and poor prognosis among CAP patients, revealing that IL-17 may implicate in the pathological process of CAP. Therefore, serum IL-17 may become an effective biomarker for diagnosis, prognosis and therapy for CAP patients.

Associations of Serum Resistin With the Severity and Prognosis in Patients With Community-Acquired Pneumonia.

Background: Resistin is an endogenous ligand of Toll-like receptor 4 that activates several inflammatory signals. But the physiological function of resistin in community-acquired pneumonia (CAP) remains unknown. The goal of this research was to explore the associations between serum resistin and the severity and prognosis in CAP patients through a retrospective cohort study. Methods: All 212 CAP patients and 106 healthy cases were enrolled. Demographic characteristics were extracted. Serum resistin was determined via enzyme-linked immunosorbent assay. The prognosis was tracked in CAP patients. Results: Serum resistin on admission was raised in CAP patients compared with control cases. The level of resistin was gradually increased in parallel with CAP severity scores in CAP patients. Pearson and Spearman analyses revealed that serum resistin was positively correlated with CAP severity scores, white blood cells, urea nitrogen, creatinine, and inflammatory cytokines among CAP patients. There were negative relationships between resistin and hematocrit and albumin in CAP patients. Besides, linear and logistic regression analyses further indicated that serum resistin on admission was positively associated with CAP severity scores among CAP patients. Follow-up research revealed that serum resistin elevation on admission prolonged hospital stay in CAP patients. Conclusion: Serum resistin on admission is positively correlated with the severity and hospital stay in CAP patients, indicating that resistin may be involved in the physiological process of CAP. Serum resistin may be a potential biomarker in the diagnosis and prognosis for CAP.

Associations of Serum S100A12 With Severity and Prognosis in Patients With Community-Acquired Pneumonia: A Prospective Cohort Study.

Background: Previous studies indicated the calcium-binding protein S100A12 to be involved in the pathophysiology of pulmonary inflammatory diseases. However, the role of S100A12 has remained elusive in patients with community-acquired pneumonia (CAP). Therefore, the purpose of this prospective cohort study was to evaluate the association between serum S100A12 with severity and prognosis in CAP patients. Methods: Two groups with either 239 CAP patients or 239 healthy controls were enrolled in our study. Fasting blood and clinical characteristics were collected. On admission, serum S100A12 was measured using enzyme-linked immunosorbent assay (ELISA). Results: Serum S100A12 was increased in CAP patients compared to control subjects. Furthermore, serum S100A12 was elevated according to the severity of CAP. Correlative analysis suggested that the level of serum S100A12 was associated with blood routine indices, renal function markers, inflammatory cytokines and other clinical parameters among CAP patients. Additionally, linear and logistical regression analyses indicated that serum S100A12 was positively associated with CAP severity scores in CAP patients. In addition, the association of high serum S100A12 and prognosis was accessed using a follow-up research. Elevated serum S100A12 on admission increased the risk of death and hospital stay in CAP patients during hospitalization. Conclusions: Elevated serum S100A12 on admission is positively associated with the severity and adverse prognosis in CAP patients, suggesting that S100A12 may involve in the pathophysiological process of CAP. The titre of serum S100A12 may be used as a biomarker for diagnosis and prognosis among CAP patients.

DONet: Dual-Octave Network for Fast MR Image Reconstruction.

Magnetic resonance (MR) image acquisition is an inherently prolonged process, whose acceleration has long been the subject of research. This is commonly achieved by obtaining multiple undersampled images, simultaneously, through parallel imaging. In this article, we propose the dual-octave network (DONet), which is capable of learning multiscale spatial-frequency features from both the real and imaginary components of MR data, for parallel fast MR image reconstruction. More specifically, our DONet consists of a series of dual-octave convolutions (Dual-OctConvs), which are connected in a dense manner for better reuse of features. In each Dual-OctConv, the input feature maps and convolutional kernels are first split into two components (i.e., real and imaginary) and then divided into four groups according to their spatial frequencies. Then, our Dual-OctConv conducts intragroup information updating and intergroup information exchange to aggregate the contextual information across different groups. Our framework provides three appealing benefits: 1) it encourages information interaction and fusion between the real and imaginary components at various spatial frequencies to achieve richer representational capacity; 2) the dense connections between the real and imaginary groups in each Dual-OctConv make the propagation of features more efficient by feature reuse; and 3) DONet enlarges the receptive field by learning multiple spatial-frequency features of both the real and imaginary components. Extensive experiments on two popular datasets (i.e., clinical knee and fastMRI), under different undersampling patterns and acceleration factors, demonstrate the superiority of our model in accelerated parallel MR image reconstruction.

Serum 8-iso-PGF2α Predicts the Severity and Prognosis in Patients With Community-Acquired Pneumonia: A Retrospective Cohort Study.

Background: Many studies have identified the important role of 8-isoprostane (8-iso-PGF2α) in pulmonary diseases. However, the role of 8-iso-PGF2α in community-acquired pneumonia (CAP) remains unclear. Therefore, the main goal was to investigate the correlations of serum 8-iso-PGF2α with the severity and prognosis in CAP patients through a hospital-based retrospective cohort study. Methods: All 220 patients with CAP were enrolled. Demographic information and clinical data were collected. Levels of 8-iso-PGF2α and inflammatory cytokines were detected in serum using ELISA. Results: The levels of 8-iso-PGF2α were gradually increased in parallel with the CAP severity scores. Univariate and multivariate logistic regression analyses revealed a positive association between serum 8-iso-PGF2α and the CAP severity scores. Additionally, serum 8-iso-PGF2α levels were positively correlated with circulating inflammatory cytokines (CRP and TNFα). Serum 8-iso-PGF2α levels were increased in the patients with a longer hospital stay than those with a shorter hospital stay. Additionally, 20 patients died after hospitalization. Dead patients presented a higher serum 8-iso-PGF2α than surviving patients. A subsequent survival analysis revealed that higher serum 8-iso-PGF2α levels positively correlated with the risk of death in patients with CAP. Conclusions: Serum 8-iso-PGF2α levels on admission are positively associated with the severity of CAP patients. Elevated serum 8-iso-PGF2α on admission prolongs hospital stay and increases the risk of death in patients with CAP, indicating that 8-iso-PGF2α may be involved in the progression of CAP and serve as an early serum prognostic biomarker for CAP.

The associations of serum S100A9 with the severity and prognosis in patients with community-acquired pneumonia: a prospective cohort study.

BACKGROUND: Previous studies found that S100A9 may involve in the pathophysiology of community-acquired pneumonia (CAP). However, the role of S100A9 was unclear in the CAP. The goal was to explore the correlations of serum S100A9 with the severity and prognosis of CAP patients based on a prospective cohort study. METHODS: A total of 220 CAP patients and 110 control subjects were recruited. Demographic and clinical data were collected. Serum S100A9 and inflammatory cytokines were measured. RESULTS: Serum S100A9 was elevated in CAP patients on admission. Serum S100A9 was gradually elevated parallelly with CAP severity scores. Additionally, inflammatory cytokines were increased and blood routine parameters were changed in CAP patients compared with control subjects. Correlation analysis found that serum S100A9 was positively associated with CAP severity scores, blood routine parameters (WBC, NLR and MON) and inflammatory cytokines. Further, logistic regression analysis demonstrated that there were positive associations between serum S100A9 and CAP severity scores. Besides, the prognosis of CAP was tracked. Serum higher S100A9 on the early stage elevated the death of risk and hospital stay among CAP patients. CONCLUSION: Serum S100A9 is positively correlated with the severity of CAP. On admission, serum higher S100A9 elevates the risk of death and hospital stay in CAP patients, suggesting that S100A9 may exert a certain role in the pathophysiology of CAP and regard as a serum diagnostic and managing biomarker for CAP.

Corrigendum: Associations of Serum S100A12 With Severity and Prognosis in Patients With Community-Acquired Pneumonia: A Prospective Cohort Study.

[This corrects the article DOI: 10.3389/fimmu.2021.714026.].

TIPE1 Inhibits Breast Cancer Proliferation by Downregulating ERK Phosphorylation and Predicts a Favorable Prognosis.

TIPE1, which acts as a cell death regulator, has emerged as a tumor suppressor in the process of carcinogenesis. However, our recent research demonstrated that it serves as an oncogene in the pathogenesis of cervical cancer, indicating that the role of TIPE1 in carcinogenesis needs to be further evaluated. In this study, we show that TIPE1 is able to inhibit breast cancer cell growth both in vivo and in vitro. Functionally, TIPE1 inhibits cancer cell proliferation preferentially by downregulating ERK phosphorylation. Furthermore, the expression of TIPE1 is decreased in breast cancer tissues compared to matched adjacent tissues, and its expression is positively correlated with patients' lifespan. These data indicate that TIPE1 suppresses breast cancer proliferation by inhibiting the ERK signaling pathway. This study also suggests that TIPE1 could serve as a potential therapeutic target and a diagnostic biomarker for breast cancer.

LJELSR: A Strengthened Version of JELSR for Feature Selection and Clustering.

Feature selection and sample clustering play an important role in bioinformatics. Traditional feature selection methods separate sparse regression and embedding learning. Later, to effectively identify the significant features of the genomic data, Joint Embedding Learning and Sparse Regression (JELSR) is proposed. However, since there are many redundancy and noise values in genomic data, the sparseness of this method is far from enough. In this paper, we propose a strengthened version of JELSR by adding the L1-norm constraint on the regularization term based on a previous model, and call it LJELSR, to further improve the sparseness of the method. Then, we provide a new iterative algorithm to obtain the convergence solution. The experimental results show that our method achieves a state-of-the-art level both in identifying differentially expressed genes and sample clustering on different genomic data compared to previous methods. Additionally, the selected differentially expressed genes may be of great value in medical research.