A novel framework for high resolution air quality index prediction with interpretable artificial intelligence and uncertainties estimation.

Accurate air quality index (AQI) prediction is essential in environmental monitoring and management. Given that previous studies neglect the importance of uncertainty estimation and the necessity of constraining the output during prediction, we proposed a new hybrid model, namely TMSSICX, to forecast the AQI of multiple cities. Firstly, time-varying filtered based empirical mode decomposition (TVFEMD) was adopted to decompose the AQI sequence into multiple internal mode functions (IMF) components. Secondly, multi-scale fuzzy entropy (MFE) was applied to evaluate the complexity of each IMF component and clustered them into high and low-frequency portions. In addition, the high-frequency portion was secondarily decomposed by successive variational mode decomposition (SVMD) to reduce volatility. Then, six air pollutant concentrations, namely CO, SO2, PM2.5, PM10, O3, and NO2, were used as inputs. The secondary decomposition and preliminary portion were employed as the outputs for the bidirectional long short-term memory network optimized by the snake optimization algorithm (SOABiLSTM) and improved Catboost (ICatboost), respectively. Furthermore, extreme gradient boosting (XGBoost) was applied to ensemble each predicted sub-model to acquire the consequence. Ultimately, we introduced adaptive kernel density estimation (AKDE) for interval estimation. The empirical outcome indicated the TMSSICX model achieved the best performance among the other 23 models across all datasets. Moreover, implementing the XGBoost to ensemble each predicted sub-model led to an 8.73%, 8.94%, and 0.19% reduction in RMSE, compared to SVM. Additionally, by utilizing SHapley Additive exPlanations (SHAP) to assess the impact of the six pollutant concentrations on AQI, the results reveal that PM2.5 and PM10 had the most notable positive effects on the long-term trend of AQI. We hope this model can provide guidance for air quality management.

Development of a personalized dendritic cell vaccine and single-cell RNA sequencing-guided assessment of its cell type composition.

BACKGROUND AIMS: Dendritic cell (DC)-based immunotherapy is a promising approach to treat cancer; however, there is no consensus on the manufacturing processes. Cell type heterogeneity in products manufactured by various methods is understudied and may elicit safety concerns from the regulatory perspective. METHODS: We characterized the cell type composition of a recently developed DC vaccine, CUD-002, consisting of DCs loaded with mRNA encoding personalized tumor neoantigens (NCT05270720). RESULTS: Using single-cell transcriptomic analysis as an unbiased approach, we found that >80% cells in the final product were DCs and the rest primarily comprised myelocytes and lymphocytes. Subsequent fluorescence-activated cell sorting analyses confirmed these cellular identities. These results indicate that unintended cells originate from leukapheresis, the first step of the manufacturing process, and thus likely safe. Consistently, no overt toxicity or tumorigenicity was observed in mice inoculated with CUD-002. CONCLUSIONS: Considering that leukapheresis is a widely used procedure for collecting diverse peripheral blood cell types to manufacture various cytotherapies, this study establishes a workflow to analyze and address regulatory considerations on cell type heterogeneity.

Diagnosis of cholangiocarcinoma from microscopic hyperspectral pathological dataset by deep convolution neural networks.

This paper focuses on automatic Cholangiocarcinoma (CC) diagnosis from microscopic hyperspectral (HSI) pathological dataset with deep learning method. The first benchmark based on the microscopic hyperspectral pathological images is set up. Particularly, 880 scenes of multidimensional hyperspectral Cholangiocarcinoma images are collected and manually labeled each pixel as either tumor or non-tumor for supervised learning. Moreover, each scene from the slide is given a binary label indicating whether it is from a patient or a normal person. Different from traditional RGB images, the HSI acquires pixels in multiple spectral intervals, which is added as an extension on the channel dimension of 3-channel RGB image. This work aims at fully exploiting the spatial-spectral HSI data through a deep Convolution Neural Network (CNN). The whole scene is first divided into several patches. Then they are fed into CNN for the tumor/non-tumor binary prediction and the tumor area regression. The further diagnosis on the scene is made by random forest based on the features from patch prediction. Experiments show that HSI provides a more accurate result than RGB image. Moreover, a spectral interval convolution and normalization scheme are proposed for further mining the spectral information in HSI, which demonstrates the effectiveness of the spatial-spectral data for CC diagnosis.

Risk factors for gestational trophoblastic neoplasia development of singleton normal fetus with partial hydatidiform mole pregnancy: A retrospective cohort and literature review.

INTRODUCTION: Singleton normal fetus with partial hydatidiform mole (PHM) pregnancy is a rare phenomenon. No previous reports have investigated the risk factors of gestational trophoblastic neoplasia (GTN) progression following this condition. METHODS: We retrospectively enrolled cases of singleton normal fetuses with PHM pregnancies at West China Second University Hospital, Sichuan University, from 2005 to 2017. Other cases were identified from PubMed databases during 1975 to 2021 for the cohort study. Cox proportional hazards models were applied to evaluate risk factors for GTN progression based on the patient's clinical characteristics. RESULTS: Overall, 36 cases of singleton normal fetuses with PHM pregnancies were enrolled. After a median follow-up of 4.0 (0.8-12.0) months, nine (25.0%) patients progressed to GTN. Gestational age at pregnancy termination (hazard ratio [HR] 0.88; 95% confidence interval [CI] 0.78-0.99, p = 0.032), hyperthyroidism (HR 5.75; 95% CI, 1.16-28.50, p = 0.032), and reasons for pregnancy termination (medical indications vs. patients' choice; HR 0.25; 95% CI, 0.06-0.99, p = 0.049) were significantly correlated with GTN progression. Area under the receiver operating characteristic curve (AUC) of gestational age at pregnancy termination to predict non-progression to GTN was 0.784 (95% CI, 0.615-0.903, p < 0.001). A clinically significant cutoff value, that is, gestational age of 24 weeks, was determined by comprehensively considering the cutoff values of AUC and clinical significance of gestational age. CONCLUSIONS: Compared to gestational age of pregnancy termination <24 weeks, ≥24 weeks was a protective factor for GTN. Therefore, there is enough evidence to continue pregnancy, except for uncontrolled severe complications, without increasing the risk of GTN progression.

Hyperlipidemia patients carrying LDLR splicing mutation c.1187-2A>G respond favorably to rosuvastatin and PCSK9 inhibitor evolocumab.

Mutations in the LDL receptor gene LDLR cause familial hypercholesterolemia (FH); however, the pharmacogenomics of specific LDLR mutations remains poorly understood. The goals of this study were to identify the genetic cause of a three-generation Chinese family affected with autosomal dominant FH, and to investigate the response of FH patients in the family to statin and evolocumab. Whole exome sequencing of the FH family with four patients and six unaffected members identified a heterozygous splicing mutation (c.1187-2A>G) in LDLR. The mutation co-segregated with FH in the family, providing strong genetic evidence to support its pathogenicity. The proband was a 48-year-old male FH patient who had an acute myocardial infarction (MI) and ventricular fibrillation (VF), and showed LDL-C of 5.23 mmol/L. A combination of life style modifications on food and exercise and treatment with rosuvastatin reduced his LDL-C to 2.05-2.80 mmol/L. Addition of ezetimibe did not improve rosuvastatin therapy, but addition of evolocumab further reduced LDL-C by 70% to 0.7 mmol/L at the first time and by 67% to 1.31 mmol/L at the second time. Rosuvastatin also reduced LDL-C for proband's father and sister by 40% and 43-63%, respectively. Lovastatin alone or addition to rosuvastatin treatment did not have any effect on LDL-C for the proband and his son. Both patients carry ApoE 3/4 genotype and SLCO1B1 rs4149056 TT genotype. These results suggest that combined treatment with rosuvastatin (but not lovastatin or ezetimibe) and evolocumab can control LDL-C to meet the LDL-C treatment goal for patients with LDLR splicing mutation c.1187-2A>G.

Myocardial microvascular function assessed by CMR first-pass perfusion in patients treated with chemotherapy for gynecologic malignancies.

OBJECTIVES: Cancer chemotherapy potentially increases the risk of myocardial ischemia. This study assessed myocardial microvascular function by cardiac magnetic resonance (CMR) first-pass perfusion in patients treated with chemotherapy for gynecologic malignancies. METHODS: A total of 81 patients treated with chemotherapy for gynecologic malignancies and 39 healthy volunteers were prospectively enrolled and underwent CMR imaging. Among the patients, 32 completed CMR follow-up, with a median interval of 6 months. The CMR sequences comprised cardiac cine, rest first-pass perfusion, and late gadolinium enhancement. RESULTS: There were no significant differences in the baseline characteristics between the patients and normal controls (all p > 0.05). Compared with the normal controls, the patients had a lower myocardial perfusion index (PI) (13.62 ± 2.01% vs. 12% (11 to 14%), p = 0.001) but demonstrated no significant variation with an increase in the number of chemotherapy cycles at follow-up (11.79 ± 2.36% vs. 11.19 ± 2.19%, p = 0.234). In multivariate analysis with adjustments for clinical confounders, a decrease in the PI was independently associated with chemotherapy treatment (ß = - 0.362, p = 0.002) but had no correlation with the number of chemotherapy cycles (r = - 0.177, p = 0.053). CONCLUSION: Myocardial microvascular dysfunction was associated with chemotherapy treatment in patients with gynecologic malignancies, and can be assessed and monitored by rest CMR first-pass perfusion. KEY POINTS: • Chemotherapy was associated with but did not aggravate myocardial microvascular dysfunction in patients with gynecologic malignancies. • Rest CMR first-pass perfusion is an ideal modality for assessing and monitoring alterations in myocardial microcirculation during chemotherapy treatment.

Long non-coding RNA GClnc1 knockdown suppresses progression of epithelial ovarian cancer by recruiting FOXC2 to disrupt the NOTCH1/NF-κB/Snail pathway.

PURPOSE: Epithelial ovarian cancer (EOC) is a highly fatal gynecological cancer. A long noncoding RNA (lncRNA) gastric cancer-associated lncRNA1 (GClnc1) has been revealed to play critical roles in metastasis. Therefore, the present study aims to explore the correlation between GClnc1 and the metastasis and progression of EOC. METHODS: First, 57 paired EOC and paracancerous tissues were collected to detect GClnc1 expression by RT-qPCR. Subsequently, OVC1 and SKOV3 cells with GClnc1 silencing/overexpression were developed to detect changes in cell activity, apoptosis, migration and invasion abilities. Then, the subcellular localization of GClnc1 was detected by nuclear/cytoplasmic fractionation, ISH and FISH assays. The binding relationships between GClnc1 and forkhead box protein C2 (FOXC2), and between FOXC2 and NOTCH1 were predicted and verified. RESULTS: GClnc1 was significantly overexpressed in EOC tissues, and knockdown of GClnc1 inhibited cell viability and promoted apoptosis. Moreover, GClnc1 in the nucleus bound to the transcription factor FOXC2, thereby activating the transcription of NOTCH1. NOTCH1 overexpression enhanced the proliferation and epithelial-mesenchymal transition of SKOV3 and OVC1 cells. Moreover, NOTCH1 activated the NF-κB/Snail signaling. Finally, in vivo experiments demonstrated that GClnc1 knockdown suppressed the growth and metastasis of SKOV3 and OVC1 cells in vivo. CONCLUSIONS: GClnc1 promoted NOTCH1 transcription by recruiting FOXC2, thereby activating the NF-κB/Snail signaling and promoting EOC cell growth and metastasis.

Face Mask Assistant: Detection of Face Mask Service Stage Based on Mobile Phone.

Coronavirus Disease 2019 (COVID-19) has spread all over the world since it broke out massively in December 2019, which has caused a large loss to the whole world. Both the confirmed cases and death cases have reached a relatively frightening number. Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the cause of COVID-19, can be transmitted by small respiratory droplets. To curb its spread at the source, wearing masks is a convenient and effective measure. In most cases, people use face masks in a high-frequent but short-time way. Aimed at solving the problem that we do not know which service stage of the mask belongs to, we propose a detection system based on the mobile phone. We first extract four features from the gray level co-occurrence matrixes (GLCMs) of the face mask's micro-photos. Next, a three-result detection system is accomplished by using K Nearest Neighbor (KNN) algorithm. The results of validation experiments show that our system can reach an accuracy of 82.87% (measured by macro-measures) on the testing dataset. The precision of Type I 'normal use' and the recall of type III 'not recommended' reach 92.00% and 92.59%. In future work, we plan to expand the detection objects to more mask types. This work demonstrates that the proposed mobile microscope system can be used as an assistant for face mask being used, which may play a positive role in fighting against COVID-19.

Automated Pleural Line Detection Based on Radon Transform Using Ultrasound.

It is of vital importance to identify the pleural line when performing lung ultrasound, as the pleural line not only indicates the interface between the chest wall and lung, but offers additional diagnostic information. In the current clinical practice, the pleural line is visually detected and evaluated by clinicians, which requires experiences and skills with challenges for the novice. In this study, we developed a computer-aided technique for automated pleural line detection using ultrasound. The method first utilized the Radon transform to detect line objects in the ultrasound images. The relation of the body mass index and chest wall thickness was then applied to estimate the range of the pleural thickness, based on which the pleural line was detected together with the consideration of the ultrasonic properties of the pleural line. The proposed method was validated by testing 83 ultrasound data sets collected from 21 pneumothorax patients. The pleural lines were successfully identified in 76 data sets by the automated method (successful detection rate 91.6%). In those successful cases, the depths of the pleural lines measured by the automated method agreed with those manually measured as confirmed with the Bland-Altman test. The measurement errors were below 5% in terms of the pleural line depth. As a conclusion, the proposed method could detect the pleural line in an automated manner in the defined data set. In addition, the method may potentially act as an alternative to visual inspection after further tests on more diverse data sets are performed in future studies.

Automated Ultrasound Measurement of the Inferior Vena Cava: An Animal Study.

Because of continuous movement and variation in diameter of the inferior vena cava (IVC) with respiration, the measurements on IVC are labor-intensive and with considerable inter-operator variations. Some computer-assisted techniques have been developed to track the movement of the IVC semi-automatically. However, existing methods predominantly rely on reference marker selection and require many manual inputs. In this study, we developed a cross-correlation (CC)-based method for automated IVC movement tracking and measurement, which requires minimal manual input and avoids manual selection of reference markers. Based on the CC method, two approaches, named direct and relative approaches, were used to calculate the maximum, minimum, and variation of the IVC diameter, and compared with the manual measurement. Fifty-four ultrasound cine-loops collected from nine pigs were tested. The results reveal that both the proposed approaches were well agreed with the manual measurement. The errors of the direct approach were less than 9%, while those of relative approach were as high as 26.7%. It is concluded that the proposed direct approach is superior for IVC diameter measurements, which can be comparable with manual counterpart, serving as an alternative to traditional IVC measurement.

The distribution and prevalence of human papillomavirus in women in mainland China.

We conducted a systematic review of the epidemiology of high-risk human papillomavirus (HPV) infections in mainland Chinese women to provide a general profile for the application and subsequent effectiveness evaluation of HPV vaccines. The PubMed, Web of Science, Medline (Ovid), China National Knowledge Infrastructure, and Wanfang databases were used for the literature search. The epidemiological studies published from January 2000 to June 2018 on high-risk HPVs in mainland Chinese women were investigated to systematically evaluate their epidemiological status. A total of 198 eligible studies were included. The results of meta-analysis showed that the overall infection rate of high-risk HPVs in mainland Chinese women was 19.0% (95% confidence interval [CI], 17.1%-20.9%), and the top 5 subtypes with the highest infection rates were 16, 52, 58, 53, and 18. The overall infection rates of cervical intraepithelial neoplasia I (CINI), CINII+, and cervical cancer patients were 59.6% (95% CI, 52.7%-66.4%), 84.8% (95% CI, 81.2%-88.5%), and 89.9% (95% CI, 86.6%-93.1%), respectively. The high-risk HPV infections and common subtypes in women of various ages in various regions were different, and the high-risk HPVs and subtypes in cervical cancer patients in various regions were also different. In conclusion, we systematically analyzed the HPV infections in women who live on the Chinese mainland. The epidemiology of high-risk HPVs in mainland Chinese women is basically consistent with that for the rest of the world. The HPV vaccines currently licensed in China could cover the major prevalent high-risk HPV subtypes in China, providing a basis for the development of a cervical cancer screening strategy and vaccine implementation in China.

LncRNA DANCR promotes tumor growth and angiogenesis in ovarian cancer through direct targeting of miR-145.

Differentiation antagonizing non-protein coding RNA (DANCR) is a newly identified oncogenic long noncoding RNA found in various cancers. However, the functional role of DANCR in tumor angiogenesis and the underlying mechanisms are still unclear. The expression of DANCR was determined in ovarian malignant tissues and cell lines. The functional role of DANCR in tumor angiogenesis was revealed by the following methods: CD31 staining of ovarian tumor tissues, matrigel-plug assay tissues, HUVEC-related tube formation assay, and invasion assay. Enzyme-linked immunosorbent assay, Western blotting, luciferase assay, and rescue experiments were used to investigate the underlying mechanisms of DANCR-regulating angiogenesis. DANCR was upregulated in ovarian malignant tissues and ovarian cancer cells. Knockdown of DANCR efficiently impaired ovarian tumor growth through inhibition of tumor angiogenesis. Furthermore, the conditional culture medium from DANCR-knockdown ovarian cells significantly inhibited tube formation and invasion of HUVEC in vitro. Mechanistic investigation indicated that vascular endothelial growth factor A (VEGF-A, VEGF) plays a crucial role during DANCR inhibition of tumor angiogenesis in ovarian cancer. Further results demonstrated that miR-145 is the direct binding target of DANCR during regulation of VEGF expression and tumor angiogenesis in ovarian cancer cells. Collectively, DANCR plays a promotional role in tumor angiogenesis in ovarian cancer through regulation of miR-145/VEGF axis. Therefore, DANCR may be a novel therapy target for ovarian cancer.

Improved synaptic and cognitive function in aged 3 × Tg-AD mice with reduced amyloid-ß after immunotherapy with a novel recombinant 6Aß15-TF chimeric vaccine.

Alzheimer's disease (AD) is the most common progressive neurodegenerative disorder impairing memory and cognition. In this study, we describe the immunogenicity and protective efficacy of the novel recombinant 6Aß15-TF chimeric antigen as a subunit protein vaccine for AD. Recombinant 6Aß15-TF chimeric vaccine induced strong Aß-specific humoral immune responses without Aß-specific T cell immunity in C57/BL6 and 3 × Tg-AD mice at different ages. As an early immunotherapy model for AD, this vaccine induced high titers of long-lasting anti-Aß42 antibodies in aged 3 × Tg-AD mice, which led to improve behavioral performance and markedly reduced the levels of insoluble and soluble Aß and Aß oligomers. In agreement with these findings, immunotherapy with 6Aß15-TF prevented the Aß-induced decrease of presynaptic and postsynaptic proteins in aged 3 × Tg-AD mice. Our results suggest that this novel and highly immunogenic recombinant 6Aß15-TF chimeric vaccine provides neuroprotection in AD mice and can be considered an effective AD candidate vaccine.

Estradiol inhibits Th17 cell differentiation through inhibition of RORγT transcription by recruiting the ERα/REA complex to estrogen response elements of the RORγT promoter.

The symptoms of vaginal candidiasis exacerbate in the second half of the menstrual cycle in premenopausal women when the serum estradiol level is elevated. Estradiol has been shown to inhibit Th17 differentiation and production of antifungal IL-17 cytokines. However, little is known about the mechanisms. In the present study, we used mouse splenocytes and found that estradiol inhibited Th17 differentiation through downregulation of Rorγt mRNA and protein expression. Estradiol activated estrogen receptor (ER)α to recruit repressor of estrogen receptor activity (REA) and form the ERα/REA complex. This complex bound to three estrogen response element (ERE) half-sites on the Rorγt promoter region to suppress Rorγt expression. Estradiol induced Rea mRNA and protein expression in mouse splenocytes. Using Rea small interfering RNA to knock down Rea expression enhanced Rorγt expression and Th17 differentiation. Alternatively, histone deacetylase 1 and 2 bound to the three ERE half-sites, independent of estradiol. Histone deacetylase inhibitor MS-275 dose- and time-dependently increased Rorγt expression and subsequently enhanced Th17 differentiation. In 15 healthy premenopausal women, high serum estradiol levels are correlated with low RORγT mRNA levels and high REA mRNA levels in the vaginal lavage. These results demonstrate that estradiol upregulates REA expression and recruits REA via ERα to the EREs on the RORγT promoter region, thus inhibiting RORγT expression and Th17 differentiation. This study suggests that the estradiol/ERα/REA axis may be a feasible target in the management of recurrent vaginal candidiasis.

The First Nationwide Multicenter Prevalence Study of Germline BRCA1 and BRCA2 Mutations in Chinese Ovarian Cancer Patients.

OBJECTIVE: Subjects with germline BRCA1/2 mutations (gBRCAm) have an increased risk of developing ovarian cancer and enhanced sensitivity to platinum-containing agents and PARP (poly[ADP-ribose] polymerase) inhibitors. BRCA mutations in Asian patients are poorly understood compared with other populations. We aimed to investigate gBRCAm prevalence and characteristics in Chinese ovarian cancer patients. METHODS: We conducted the first nationwide multicenter gBRCAm prevalence study in China. Eight hundred twenty-six unselected ovarian cancer patients from 5 clinical centers were enrolled and tested for gBRCAm status. Medical data including age, family history, previous treatments, clinical diagnosis, histopathologic diagnosis, tumor grade, platinum sensitivity, and CA-125 test result were reviewed and collected. RESULTS: Prevalence rate or gBRCAm was determined as 28.5%, with 20.8% of patients harboring BRCA1 mutation and 7.6% harboring BRCA2 mutation. The group had a higher percentage of high-grade serous (73.0%), late-stage (III and IV [85.5%]) patients and a younger median age at diagnosis (52 years) compared with other reported studies. Twnety-seven BRCA1 and 17 BRCA2 mutations have not been reported previously in public databases or the literature. Statistically significant correlations were observed between gBRCAm status and family history (P < 0.001), gBRCAm status, and tumor stage (P = 0.02). A numerical higher prevalence of gBRCAm in patients with high-grade serous histopathology (30.9%), platinum-sensitive phenotype (34%), and late-line chemotherapy was observed. CONCLUSIONS: Germline BRCA1/2 mutations is common in Chinese ovarian cancer patients. This study implies that all ovarian patients should be tested for gBRCAm status regardless of family history and histopathology.

Co-administration of antigen with chemokine MCP-3 or MDC/CCL22 enhances DNA vaccine potency.

We evaluated the utility of chemokine MCP-3 and MDC/CCL22 as molecular adjuvants of DNA vaccines for botulinum neurotoxin serotype A (BoNT/A) in a Balb/c mouse model. Notably, the immunogenicity of the DNA vaccine against BoNT/A was not enhanced using a fusion of the AHc-C antigen with the MCP-3 or MDC/CCL22. Nevertheless, the potency of the DNA vaccine was significantly modulated and enhanced by co-administration of the AHc-C antigen with MCP-3 or MDC/CCL22. This strategy elicited high levels of humoral immune responses and protection against BoNT/A. The enhanced potency was further boosted by co-administration of the AHc-C antigen with both MCP-3 and MDC/CCL22 in Balb/c mice, but not by co-administration of AHc-C antigen with the MCP-3-MDC/CCL22 fusion. Co-immunization with both the MCP-3 and MDC/CCL22 constructs induced the highest levels of humoral immunity and protective potency against BoNT/A. Our results indicated that MCP-3 and MDC/CCL22 are effective molecular adjuvants of the immune responses induced by the AHc-C-expressing DNA vaccine when delivered by co-administration of the individual chemokines, but not when delivered in the form of a chemokine/antigen fusion. Thus, we describe an alternative strategy to the design and optimization of DNA vaccine constructs based on co-administration of the antigen with the chemokine rather than in the form of a chemokine/antigen fusion.

[Nerve classification with hyperspectral imaging technology].

In surgical nerve repair surgery, the identification of nerve fascicles is a key to a good repair of their broken end. Some of the existing nerve fascicles identification method are not ideal. Hyperspectral imaging (HSI) technology provides information of images and spectra of biological tissue at the same time. It can supply a qualitative, quantitative and positioning description of the test objectives, and identify different biological tissues by biochemical characteristic difference, and classify and position these tissues in the image. Compared to other medical imaging technology, this techriology has unique advantages. In this study, the hyperspectral imaging technology is used in the identification and classification of the nerve fascicles by the spectral characteristics of different nerve fascicles, and in determining the orientation of the nerve fascicles in the image by the image spectral information in order to better help surgical personnel to carry out the nerve repair surgery. The significance of this paper is: the first to propose a new method of identification and location of the nerve fascicles and assist surgical staff to improve the efficacy of nerve repair; the second to reserve hyperspectral imaging techniques used in qualitative and quantitative and orientation research combined with biological organization, and speed up the molecular hyperspectral imaging technology to the practical stage.

Targeting WEE1 Kinase in Gynecological Malignancies.

WEE1 kinase is involved in the G2/M cell cycle checkpoint control and DNA damage repair. A functional G2/M checkpoint is crucial for DNA repair in cancer cells with p53 mutations since they lack a functional G1/S checkpoint. Targeted inhibition of WEE1 kinase may cause tumor cell apoptosis, primarily, in the p53-deficient tumor, via bypassing the G2/M checkpoint without properly repairing DNA damage, resulting in genome instability and chromosomal deletion. This review aims to provide a comprehensive overview of the biological role of WEE1 kinase and the potential of WEE1 inhibitor (WEE1i) for treating gynecological malignancies. We conducted a thorough literature search from 2001 to September 2023 in prominent databases such as PubMed, Scopus, and Cochrane, utilizing appropriate keywords of WEE1i and gynecologic oncology. WEE1i has been shown to inhibit tumor activity and enhance the sensitivity of chemotherapy or radiotherapy in preclinical models, particularly in p53-mutated gynecologic cancer models, although not exclusively. Recently, WEE1i alone or combined with genotoxic agents has confirmed its efficacy and safety in Phase I/II gynecological malignancies clinical trials. Furthermore, it has become increasingly clear that other inhibitors of DNA damage pathways show synthetic lethality with WEE1i, and WEE1 modulates therapeutic immune responses, providing a rationale for the combination of WEE1i and immune checkpoint blockade. In this review, we summarize the biological function of WEE1 kinase, development of WEE1i, and outline the preclinical and clinical data available on the investigation of WEE1i for treating gynecologic malignancies.

I3Net: Inter-Intra-slice Interpolation Network for Medical Slice Synthesis.

Medical imaging is limited by acquisition time and scanning equipment. CT and MR volumes, reconstructed with thicker slices, are anisotropic with high in-plane resolution and low through-plane resolution. We reveal an intriguing phenomenon that due to the mentioned nature of data, performing slice-wise interpolation from the axial view can yield greater benefits than performing super-resolution from other views. Based on this observation, we propose an Inter-Intra-slice Interpolation Network (I3Net), which fully explores information from high in-plane resolution and compensates for low through-plane resolution. The through-plane branch supplements the limited information contained in low through-plane resolution from high in-plane resolution and enables continual and diverse feature learning. In-plane branch transforms features to the frequency domain and enforces an equal learning opportunity for all frequency bands in a global context learning paradigm. We further propose a cross-view block to take advantage of the information from all three views online. Extensive experiments on two public datasets demonstrate the effectiveness of I3Net, and noticeably outperforms state-of-the-art super-resolution, video frame interpolation and slice interpolation methods by a large margin. We achieve 43.90dB in PSNR, with at least 1.14dB improvement under the upscale factor of ×2 on MSD dataset with faster inference.