Layer-Wise Mutual Information Meta-Learning Network for Few-Shot Segmentation.

The goal of few-shot segmentation (FSS) is to segment unlabeled images belonging to previously unseen classes using only a limited number of labeled images. The main objective is to transfer label information effectively from support images to query images. In this study, we introduce a novel meta-learning framework called layer-wise mutual information (LayerMI), which enhances the propagation of label information by maximizing the mutual information (MI) between support and query features at each layer. Our approach involves the utilization of a LayerMI Block based on information-theoretic co-clustering. This block performs online co-clustering on the joint probability distribution obtained from each layer, generating a target-specific attention map. The LayerMI Block can be seamlessly integrated into the meta-learning framework and applied to all convolutional neural network (CNN) layers without altering the training objectives. Notably, the LayerMI Block not only maximizes MI between support and query features but also facilitates internal clustering within the image. Extensive experiments demonstrate that LayerMI significantly enhances the performance of baseline and achieves competitive performance compared to state-of-the-art methods on three challenging benchmarks: PASCAL-5 i , COCO-20 i , and FSS-1000.

Single-cell RNA-seq reveals heterogeneity in metastatic renal cell carcinoma and effect of anti-angiogenesis therapy in the pancreas metastatic lesion.

Metastatic clear cell renal cell carcinoma has heterogenous tumor microenvironment (TME). Among the metastatic lesions, pancreas metastasis is rare and controversy in treatment approaches. Here, extensive primary and metastatic lesion samples were included by single-cell RNA-seq to decipher the distinct metastasis TME. The hypoxic and inflammatory TME of pancreas metastasis was decoded in this study, and the activation of PAX8-myc signaling, and metabolic reprogramming were observed. The active components including endothelial cells, fibroblasts and T cells were profiled. Meanwhile, we also evaluated the effect of anti-angiogenesis treatment in the pancreas metastasis patient. The potential mechanisms of pancreatic tropism, instability of genome, and the response of immunotherapy were also discussed in this work. Taken together, our findings suggest a clue to the heterogeneity in metastasis TME and provide evidence for the treatment of pancreas metastasis in renal cell carcinoma patients.

Unbiasedly decoding the tumor microenvironment with single-cell multiomics analysis in pancreatic cancer.

Pancreatic ductal adenocarcinoma (PDAC) is a highly aggressive malignancy with a poor prognosis and limited therapeutic options. Research on the tumor microenvironment (TME) of PDAC has propelled the development of immunotherapeutic and targeted therapeutic strategies with a promising future. The emergence of single-cell sequencing and mass spectrometry technologies, coupled with spatial omics, has collectively revealed the heterogeneity of the TME from a multiomics perspective, outlined the development trajectories of cell lineages, and revealed important functions of previously underrated myeloid cells and tumor stroma cells. Concurrently, these findings necessitated more refined annotations of biological functions at the cell cluster or single-cell level. Precise identification of all cell clusters is urgently needed to determine whether they have been investigated adequately and to identify target cell clusters with antitumor potential, design compatible treatment strategies, and determine treatment resistance. Here, we summarize recent research on the PDAC TME at the single-cell multiomics level, with an unbiased focus on the functions and potential classification bases of every cellular component within the TME, and look forward to the prospects of integrating single-cell multiomics data and retrospectively reusing bulk sequencing data, hoping to provide new insights into the PDAC TME.

Learning curve of robotic pancreatoduodenectomy by a single surgeon with extensive laparoscopic pancreatoduodenectomy experience.

With the development of robotic systems, robotic pancreatoduodenectomies (RPDs) have been increasingly performed. However, the number of cases required by surgeons with extensive laparoscopic pancreatoduodenectomy (LPD) experience to overcome the learning curve of RPD remains unclear. Therefore, we aimed to analyze and explore the impact of different phases of the learning curve of RPD on perioperative outcomes. Clinical data were prospectively collected and retrospectively analyzed for 100 consecutive patients who underwent RPD performed by a single surgeon. This surgeon had previous experience with LPD, having performed 127 LPDs with low morbidity. The learning curve for RPD was analyzed using the cumulative sum (CUSUM) method based on operation time, and perioperative outcomes were compared between the learning and proficiency phases. Between April 2020 and November 2022, one hundred patients (56 men, 44 women) were included in this study. Based on the CUSUM curve of operation time, the learning curve for RPD was divided into two phases: phase I was the learning phase (cases 1-33) and phase II was the proficiency phase (cases 34-100). The operation time during the proficiency phase was significantly shorter than that during the learning phase. In the learning phase of RPD, no significant increases were observed in estimated blood loss, conversion to laparotomy, severe complications, postoperative pancreatic hemorrhage, clinical pancreatic fistula, or other perioperative complications compared to the proficiency phases of either RPD or LPD. A surgeon with extensive prior experience in LPD can safely surmount the RPD learning curve without increasing morbidity in the learning phase. The proficiency was significantly improved after accumulating experience of 33 RPD cases.

MAPK/ERK-PK(Ser11) pathway regulates divergent thermal metabolism of two congeneric oyster species.

Pyruvate kinase (PK), as a key rate-limiting enzyme in glycolysis, has been widely used to assess the stress tolerance and sensitivity of organisms. However, its phosphorylation regulatory mechanisms mainly focused on human cancer research, with no reports in marine organisms. In this study, we firstly reported a conserved PK Ser11 phosphorylation site in mollusks, which enhanced enzyme activity by promoting substrate binding, thereby regulating divergent thermal metabolism of two allopatric congeneric oyster species with differential habitat temperature. It was phosphorylated by ERK kinase, and regulated by the classical MAPK pathway. The MAPK/ERK-PK signaling cascade responded to increased environmental temperature and exhibited stronger activation pattern in the relatively thermotolerant species (Crassostrea angulata), indicating its involvement in shaping temperature adaptation. These findings highlight the presence of complex and unique phosphorylation-mediated signaling transduction mechanisms in marine organisms, and provide new insights into the evolution and function of the crosstalk between classical pathways.

Lymphocyte-to-Monocyte Ratio Predicts Survival for Intraductal Papillary Mucinous Neoplasm with Associated Invasive Carcinoma of the Pancreas: Results from a High-Volume Center.

INTRODUCTION: Intraductal papillary mucinous neoplasm (IPMN) is an important precursor lesion of pancreatic cancer. Systemic inflammatory parameters are widely used in the prognosis prediction of cancer; however, their prognostic implications in IPMN with associated invasive carcinoma (IPMN-INV) are unclear. This study aims to explore the prognostic value of systemic inflammatory parameters in patients with IPMN-INV. METHODS: From 2015 to 2021, patients with pathologically confirmed IPMN who underwent surgical resection at Peking Union Medical College Hospital were enrolled. The clinical, radiological, and pathological data of the enrolled patients were collected and analyzed. Preoperative systemic inflammatory parameters were calculated as previously reported. RESULTS: Eighty-six patients with IPMN-INV met the inclusion criteria. The lymphocyte-to-monocyte ratio (LMR) was the only systemic inflammatory parameter independently associated with the cancer-specific survival (CSS). An LMR higher than 3.5 was significantly associated with a favorable CSS in univariate (hazard ratio [HR] 0.305, p = 0.003) and multivariate analyses (HR 0.221, p = 0.001). Other independently prognostic factors included the presence of clinical symptoms, cyst size, N stage, and tumor differentiation. Additionally, a model including LMR was established for the prognosis prediction of IPMN-INV and had a C-index of 0.809. CONCLUSIONS: Preoperative LMR could serve as a feasible prognostic biomarker for IPMN-INV. A decreased LMR (cutoff value of 3.5) was an independent predictor of poor survival for IPMN-INV.

Human Equilibrative Nucleoside Transporter 1: Novel Biomarker and Prognostic Indicator for Patients with Gemcitabine-Treated Pancreatic Cancer.

Aim: This article aimed to find appropriate pancreatic cancer (PC) patients to treat with Gemcitabine with better survival outcomes by detecting hENT1 levels. Methods: We collected surgical pathological tissues from PC patients who received radical surgery in our hospital from September 2004 to December 2014. A total of 375 PC tissues and paired adjacent nontumor tissues were employed for the construction of 4 tissue microarrays (TMAs). The quality of the 4 TMAs was examined by HE staining. We performed immunohistochemistry analysis to evaluate hENT1 expression in the TMAs. Moreover, we detected hENT1 expression level and proved the role of hENT1 in cell proliferation, drug resistance, migration and invasion in vivo and vitro. Results: The results indicated that low hENT1 expression indicated a significantly poor outcome in PC patients, including shortened DFS (21.6±2.8 months versus 36.9±4.0 months, p<0.001) and OS (33.6±3.9 versus 39.6±3.9, p=0.004). Meanwhile, patients in stage I/II of TNM stage had a longer OS (40.2±3.4 versus 15.4±1.7, p=0.002) and DFS (31.0±3.1 versus 12.4±1.9, p=0.016) than patients in stage III/IV. Patients in M0 stage had a longer OS (39.7±3.4 versus 16.2±1.9, p=0.026) and DFS(30.7±3.0 versus 11.8±2.2, p=0.031) than patients in M1 stage, and patients with tumors not invading the capsule had a better DFS than those with tumor invasion into the capsule (30.8±3.0 versus 12.6±2.3, p=0.053). Patients with preoperative CA19-9 values ≤467 U/mL have longer DFS than that of patients who had preoperative CA19-9 values >467 U/mL (37.9±4.1 versus 22.9±4.0, p=0.04). In the subgroup analysis, a high hENT1 expression level was related to a longer OS(39.4±4.0 versus 31.5±3.9, p=0.001) and DFS(35.7±4.0 versus 20.6±2.7; p<0.0001) in the Gemcitabine subgroup. Conclusion: PC patients with high hENT1 expression have a better survival outcomes when receiving Gemcitabine. hENT1 expression can be a great prognostic indicator for PC patients to receive Gemcitabine treatment.

Impact of Combined Chemotherapy and Targeted Therapy on Pancreatic Neuroendocrine Carcinoma with Liver Metastasis: A Single-Center Modified Nomogram Analysis.

Objective: To establish a modified nomogram model for pancreatic neuroendocrine carcinoma (pNEC) patients with liver metastasis via single-center clinical data, and to provide guidelines for improving the diagnosis and treatment of patients. Methods: A retrospective analysis of clinical data from pNEC patients with liver metastasis at Peking Union Medical College Hospital (January 2000 to November 2023) was conducted. Univariate and multivariate Cox regression analyses were employed to identify prognostic factors for overall survival (OS). Kaplan-Meier curves were generated, and a modified nomogram predictive model was developed to illustrate the prognosis of pNEC patients with liver metastasis. Calibration plots and C-index were used to validate the model's feasibility, accuracy, and reliability. Results: Forty-five participants with the rare cancer type pNEC and liver metastasis were included in the study. Kaplan-Meier curves revealed that primary tumor resection (PTR), chemotherapy or targeted therapy, and tumor size equal to or less than 5cm significantly improved OS compared to those without PTR, chemotherapy or targeted therapy, and tumor size larger than 5cm. Multivariate Cox regression analysis identified PTR, a combination of chemotherapy and targeted therapy, and tumor size as independent prognostic factors for OS. The predictive nomogram model exhibited acceptable performance with a C-index of 0.744 (0.639-0.805) through bootstrapping. Conclusion: Combining chemotherapy with targeted therapy enhances the survival of pNEC patients with liver metastasis. The modified nomogram model and predictive score table offer valuable references and insights for both clinicians and patients.

Multiomics integration reveals NETosis heterogeneity and TLR2 as a prognostic biomarker in pancreatic cancer.

Pancreatic ductal adenocarcinoma (PDAC) is a highly malignant neoplasm characterized by a poor prognosis and limited therapeutic strategy. The PDAC tumor microenvironment presents a complex heterogeneity, where neutrophils emerge as the predominant constituents of the innate immune cell population. Leveraging the power of single-cell RNA-seq, spatial RNA-seq, and multi-omics approaches, we included both published datasets and our in-house patient cohorts, elucidating the inherent heterogeneity in the formation of neutrophil extracellular traps (NETs) and revealed the correlation between NETs and immune suppression. Meanwhile, we constructed a multi-omics prognostic model that suggested the patients exhibiting downregulated expression of NETs may have an unfavorable outcome. We also confirmed TLR2 as a potent prognosis factor and patients with low TLR2 expression had more effective T cells and an overall survival extension for 6 months. Targeting TLR2 might be a promising strategy to reverse immunosuppression and control tumor progression for an improved prognosis.

E3 ubiquitin ligase RBCK1 confers ferroptosis resistance in pancreatic cancer by facilitating MFN2 degradation.

Ferroptosis, a novel form of iron-dependent non-apoptotic cell death, plays an active role in the pathogenesis of diverse diseases, including cancer. However, the mechanism through which ferroptosis is regulated in pancreatic ductal adenocarcinoma (PDAC) remains unclear. Here, our study, via combining bioinformatic analysis with experimental validation, showed that ferroptosis is inhibited in PDAC. Genome-wide sequencing further revealed that the ferroptosis activator imidazole ketone erastin (IKE) induced upregulation of the E3 ubiquitin ligase RBCK1 in PDAC cells at the transcriptional or translational level. RBCK1 depletion or knockdown rendered PDAC cells more vulnerable to IKE-induced ferroptotic death in vitro. In a mouse xenograft model, genetic depletion of RBCK1 increased the killing effects of ferroptosis inducer on PDAC cells. Mechanistically, RBCK1 interacts with and polyubiquitylates mitofusin 2 (MFN2), a key regulator of mitochondrial dynamics, to facilitate its proteasomal degradation under ferroptotic stress, leading to decreased mitochondrial reactive oxygen species (ROS) production and lipid peroxidation. These findings not only provide new insights into the defense mechanisms of PDAC cells against ferroptotic death but also indicate that targeting the RBCK1-MFN2 axis may be a promising option for treating patients with PDAC.

The new era of pancreatic cancer treatment: Application of nanotechnology breaking through bottlenecks.

Since the advent of nanomedicine, physicians have harnessed these approaches for the prophylaxis, detection, and therapy of life-threatening diseases, particularly cancer. Nanoparticles have demonstrated notable efficacy in cancer therapy, showcasing the primary application of nanotechnology in targeted drug delivery. Pancreatic cancer stands out as the most lethal solid tumour in humans. The low survival rate is attributed to its highly aggressive nature, intrinsic resistance to chemotherapeutics, and the lack of successful therapies, compounded by delayed diagnosis due to nonspecific symptoms and the absence of rapid diagnostic strategies. Despite these challenges, nanotechnology-based carrier methods have been successfully employed in imaging and therapy approaches. Overcoming drug resistance in pancreatic cancer necessitates a comprehensive understanding of the microenvironment associated with the disease, paving the way for innovative nanocarriers. Hindered chemotherapy infiltration, attributed to inadequate vascularization and a dense tumour stroma, is a major hurdle that nanotechnology addresses. Intelligent delivery techniques, based on the Enhanced Permeability and Retention effect, form the basis of recently developed anticancer nanocarriers. These advancements aim to enhance drug accumulation in tumour locations, offering a potential solution to the treatment-resistant nature of cancer. Addressing the challenges in pancreatic cancer treatment demands innovative therapies, and the emergence of active nanocarriers presents a promising avenue for enhancing outcomes. This review specifically delves into the latest advancements in nanotechnology for the treatment of pancreatic cancer.

FBXO32 Stimulates Protein Synthesis to Drive Pancreatic Cancer Progression and Metastasis.

Pancreatic ductal adenocarcinoma (PDAC) is one of the leading causes of cancer-related death worldwide, primarily due to its rapid progression. The current treatment options for PDAC are limited, and a better understanding of the underlying mechanisms responsible for PDAC progression is required to identify improved therapeutic strategies. In this study, we identified FBXO32 as an oncogenic driver in PDAC. FBXO32 was aberrantly upregulated in PDAC, and high FBXO32 expression was significantly associated with an unfavorable prognosis in patients with PDAC. FRG1 deficiency promoted FBXO32 upregulation in PDAC. FBXO32 promoted cell migration and invasion in vitro and tumor growth and metastasis in vivo. Mechanistically, FBXO32 directly interacted with eEF1A1 and promoted its polyubiquitination at the K273 site, leading to enhanced activity of eEF1A1 and increased protein synthesis in PDAC cells. Moreover, FBXO32-catalyzed eEF1A1 ubiquitination boosted the translation of ITGB5 mRNA and activated focal adhesion kinase (FAK) signaling, thereby facilitating focal adhesion assembly and driving PDAC progression. Importantly, interfering with the FBXO32-eEF1A1 axis or pharmaceutical inhibition of FAK by defactinib, an FDA-approved FAK inhibitor, substantially inhibited PDAC growth and metastasis driven by aberrantly activated FBXO32-eEF1A1 signaling. Overall, this study uncovers a mechanism by which PDAC cells rely on FBXO32-mediated eEF1A1 activation to drive progression and metastasis. FBXO32 may serve as a promising biomarker for selecting eligible patients with PDAC for treatment with defactinib. Significance: FBXO32 upregulation in pancreatic cancer induced by FRG1 deficiency increases eEF1A1 activity to promote ITGB5 translation and stimulate FAK signaling, driving cancer progression and sensitizing tumors to the FAK inhibitor defactinib.

Recent Advances in Tactile Sensory Systems: Mechanisms, Fabrication, and Applications.

Flexible electronics is a cutting-edge field that has paved the way for artificial tactile systems that mimic biological functions of sensing mechanical stimuli. These systems have an immense potential to enhance human-machine interactions (HMIs). However, tactile sensing still faces formidable challenges in delivering precise and nuanced feedback, such as achieving a high sensitivity to emulate human touch, coping with environmental variability, and devising algorithms that can effectively interpret tactile data for meaningful interactions in diverse contexts. In this review, we summarize the recent advances of tactile sensory systems, such as piezoresistive, capacitive, piezoelectric, and triboelectric tactile sensors. We also review the state-of-the-art fabrication techniques for artificial tactile sensors. Next, we focus on the potential applications of HMIs, such as intelligent robotics, wearable devices, prosthetics, and medical healthcare. Finally, we conclude with the challenges and future development trends of tactile sensors.

The NF-κB/NUAK2 signaling axis regulates pancreatic cancer progression by targeting SMAD2/3.

Nuclear factor kappa B (NF-κB) plays a pivotal role in the development of pancreatic cancer, and its phosphorylation has previously been linked to the regulation of NUAK2. However, the regulatory connection between NF-κB and NUAK2, as well as NUAK2's role in pancreatic cancer, remains unclear. In this study, we observed that inhibiting NUAK2 impeded the proliferation, migration, and invasion of pancreatic cancer cells while triggering apoptosis. NUAK2 overexpression partially resisted apoptosis and reversed the inhibitory effects of the NF-κB inhibitor. NF-κB transcriptionally regulated NUAK2 transcription by binding to the promoter region of NUAK2. Mechanistically, NUAK2 knockdown remarkably reduced the expression levels of p-SMAD2/3 and SMAD2/3, resulting in decreased nuclear translocation of SMAD4. In SMAD4-negative cells, NUAK2 knockdown impacted FAK signaling by downregulating SMAD2/3. Moreover, NUAK2 knockdown heightened the sensitivity of pancreatic cancer cells to gemcitabine, suggesting that NUAK2 inhibitors could be a promising strategy for pancreatic cancer treatment.

Solid pseudopapillary neoplasm (SPN) of the pancreas: current understanding on its malignant potential and management.

Solid pseudopapillary neoplasms (SPN) of the pancreas are presently recognized as low-grade malignant tumors that are frequently observed in young females. This tumor has a low incidence and is associated with an excellent prognosis following surgical resection. Typical SPNs primarily affect the pancreas and tend to have moderate or asymptomatic manifestations. Based on retrospective research, it is anticipated that patients with SPN can achieve disease-free survival, even in cases when metastasis is detected during inspection. However, the incidence of malignant SPN has been consistently underestimated, as evidenced by recent research findings. Malignancy of SPN primarily encompasses invasion and infiltration, metastasis, and recurrence after R0 resection. Imaging technologies such as Ultrasound, Computed Tomography, Magnetic Resonance Imaging, and Position Emission Tomography are capable of preliminarily identifying malignant SPN, which is primarily based on its invasive clinical features. Research on risk factors of malignant SPN revealed that larger tumor size, Ki-67 index, and several other parameters had significant correlations with invasive tumor behavior. Pathologic features of malignant SPNs overlay other pancreatic tumors, nevertheless they can provide valuable assistance in the process of diagnosis. Several confirmed specific pathologic biomarkers are related to its cellular origin, characteristic gene mutation, and cell proliferation. Considering the invasiveness of malignant SPN, it is imperative to enhance the comprehensiveness of its therapy. Tumor resection remains a suggested course of action in line with typical SPN, and additional lymph node dissection is seen as reasonable. Compared to benign SPNs, malignant SPNs have worse prognosis, underscoring the necessity of early identification and treatment in comprehensive medical centers to get improved clinical outcomes.

Ribosome profiling: a powerful tool in oncological research.

Neoplastic cells need to adapt their gene expression pattern to survive in an ever-changing or unfavorable tumor microenvironment. Protein synthesis (or mRNA translation), an essential part of gene expression, is dysregulated in cancer. The emergence of distinct translatomic technologies has revolutionized oncological studies to elucidate translational regulatory mechanisms. Ribosome profiling can provide adequate information on diverse aspects of translation by aiding in quantitatively analyzing the intensity of translating ribosome-protected fragments. Here, we review the primary currently used translatomics techniques and highlight their advantages and disadvantages as tools for translatomics studies. Subsequently, we clarified the areas in which ribosome profiling could be applied to better understand translational control. Finally, we summarized the latest advances in cancer studies using ribosome profiling to highlight the extensive application of this powerful and promising translatomic tool.

Pancreatic ductal adenocarcinoma chemoresistance: From metabolism reprogramming to novel treatment.

ABSTRACT: As pancreatic cancer (PC) is highly malignant, its patients tend to develop metastasis at an early stage and show a poor response to conventional chemotherapies. First-line chemotherapies for PC, according to current guidelines, include fluoropyrimidine- and gemcitabine-based regimens. Accumulating research on drug resistance has shown that biochemical metabolic aberrations in PC, especially those involving glycolysis and glutamine metabolism, are highly associated with chemoresistance. Additionally, lipid metabolism is a major factor in chemoresistance. However, emerging compounds that target these key metabolic pathways have the potential to overcome chemoresistance. This review summarizes how PC develops chemoresistance through aberrations in biochemical metabolism and discusses novel critical targets and pathways within cancer metabolism for new drug research.

Development and validation of an interpretable Markov-embedded multilabel model for predicting risks of multiple postoperative complications among surgical inpatients: a multicenter prospective cohort study.

BACKGROUND: When they encounter various highly related postoperative complications, existing risk evaluation tools that focus on single or any complications are inadequate in clinical practice. This seriously hinders complication management because of the lack of a quantitative basis. An interpretable multilabel model framework that predicts multiple complications simultaneously is urgently needed. MATERIALS AND METHODS: The authors included 50 325 inpatients from a large multicenter cohort (2014-2017). The authors separated patients from one hospital for external validation and randomly split the remaining patients into training and internal validation sets. A MARKov-EmbeDded (MARKED) multilabel model was proposed, and three models were trained for comparison: binary relevance, a fully connected network (FULLNET), and a deep neural network. Performance was mainly evaluated using the area under the receiver operating characteristic curve (AUC). The authors interpreted the model using Shapley Additive Explanations. Complication-specific risk and risk source inference were provided at the individual level. RESULTS: There were 26 292, 6574, and 17 459 inpatients in the training, internal validation, and external validation sets, respectively. For the external validation set, MARKED achieved the highest average AUC (0.818, 95% CI: 0.771-0.864) across eight outcomes [compared with binary relevance, 0.799 (0.748-0.849), FULLNET, 0.806 (0.756-0.856), and deep neural network, 0.815 (0.765-0.866)]. Specifically, the AUCs of MARKED were above 0.9 for cardiac complications [0.927 (0.894-0.960)], neurological complications [0.905 (0.870-0.941)], and mortality [0.902 (0.867-0.937)]. Serum albumin, surgical specialties, emergency case, American Society of Anesthesiologists score, age, and sex were the six most important preoperative variables. The interaction between complications contributed more than the preoperative variables, and formed a hierarchical chain of risk factors, mild complications, and severe complications. CONCLUSION: The authors demonstrated the advantage of MARKED in terms of performance and interpretability. The authors expect that the identification of high-risk patients and the inference of the risk source for specific complications will be valuable for clinical decision-making.

PFENet++: Boosting Few-Shot Semantic Segmentation With the Noise-Filtered Context-Aware Prior Mask.

In this work, we revisit the prior mask guidance proposed in "Prior Guided Feature Enrichment Network for Few-Shot Segmentation". The prior mask serves as an indicator that highlights the region of interests of unseen categories, and it is effective in achieving better performance on different frameworks of recent studies. However, the current method directly takes the maximum element-to-element correspondence between the query and support features to indicate the probability of belonging to the target class, thus the broader contextual information is seldom exploited during the prior mask generation. To address this issue, first, we propose the Context-aware Prior Mask (CAPM) that leverages additional nearby semantic cues for better locating the objects in query images. Second, since the maximum correlation value is vulnerable to noisy features, we take one step further by incorporating a lightweight Noise Suppression Module (NSM) to screen out the unnecessary responses, yielding high-quality masks for providing the prior knowledge. Both two contributions are experimentally shown to have substantial practical merit, and the new model named PFENet++ significantly outperforms the baseline PFENet as well as all other competitors on three challenging benchmarks PASCAL-5 i, COCO-20 i and FSS-1000. The new state-of-the-art performance is achieved without compromising the efficiency, manifesting the potential for being a new strong baseline in few-shot semantic segmentation.