Dual-ligand quasi-2D perovskites with chiral-induced spin selectivity for room temperature spin-LEDs.

Spin-LEDs have been a central topic in semiconductor spintronics research and represent a promising avenue for advanced optoelectronic devices and applications. The future advancements of spin-LEDs will undoubtedly hinge on the generation and manipulation of spin-polarized population at room temperature. In this research, we elucidate the development of room-temperature spin-LEDs using quasi-2D perovskites, based on the chiral-induced spin selectivity (CISS) effect. During the carrier transfer from the chiral n2 phase to the randomly oriented high-n phase caused by the bandgap gradient distribution, CISS works to generate non-equilibrium spin population, leading to room-temperature spin-polarized fluorescence. A spin-polarization of ∼93% is observed for the films. Finally, we realize spin-LEDs at room temperature, exhibiting a |gCP-EL| value of 0.05 and an EQE of 3.8%. This work highlights the potential of integrating dual ligands to optimize the phase distribution and crystalline orientation in quasi-2D films to achieve efficient CISS for spin-LED applications.

Karyotype and LTR-RTs analysis provide insights into oak genomic evolution.

BACKGROUND: Whole-genome duplication and long terminal repeat retrotransposons (LTR-RTs) amplification in organisms are essential factors that affect speciation, local adaptation, and diversification of organisms. Understanding the karyotype projection and LTR-RTs amplification could contribute to untangling evolutionary history. This study compared the karyotype and LTR-RTs evolution in the genomes of eight oaks, a dominant lineage in Northern Hemisphere forests. RESULTS: Karyotype projections showed that chromosomal evolution was relatively conservative in oaks, especially on chromosomes 1 and 7. Modern oak chromosomes formed through multiple fusions, fissions, and rearrangements after an ancestral triplication event. Species-specific chromosomal rearrangements revealed fragments preserved through natural selection and adaptive evolution. A total of 441,449 full-length LTR-RTs were identified from eight oak genomes, and the number of LTR-RTs for oaks from section Cyclobalanopsis was larger than in other sections. Recent amplification of the species-specific LTR-RTs lineages resulted in significant variation in the abundance and composition of LTR-RTs among oaks. The LTR-RTs insertion suppresses gene expression, and the suppressed intensity in gene regions was larger than in promoter regions. Some centromere and rearrangement regions indicated high-density peaks of LTR/Copia and LTR/Gypsy. Different centromeric regional repeat units (32, 78, 79 bp) were detected on different Q. glauca chromosomes. CONCLUSION: Chromosome fusions and arm exchanges contribute to the formation of oak karyotypes. The composition and abundance of LTR-RTs are affected by its recent amplification. LTR-RTs random retrotransposition suppresses gene expression and is enriched in centromere and chromosomal rearrangement regions. This study provides novel insights into the evolutionary history of oak karyotypes and the organization, amplification, and function of LTR-RTs.

CO intermediate-assisted dynamic Cu sintering during electrocatalytic CO2 reduction on Cu‒N‒C catalysts.

The electrochemical CO2 reduction reaction (eCO2RR) to multicarbon products has been widely recognized for Cu-based catalysts. However, the structural changes in Cu-based catalysts during the eCO2RR pose challenges to achieving an in-depth understanding of the structure-activity relationship, thereby limiting catalyst development. Herein, we employ constant-potential density functional theory calculations to investigate the sintering process of Cu single atoms of Cu-N-C single-atom catalysts into clusters under eCO2RR conditions. Systematic constant-potential ab initio molecular dynamics simulations revealed that the leaching of Cu-(CO)x moieties and subsequent agglomeration into clusters can be facilitated by synergistic adsorption of H and eCO2RR intermediates (e.g., CO). Increasing the Cu2+ concentration or the applied potential can efficiently suppress Cu sintering. Both microkinetic simulations and experimental results further confirm that sintered Cu clusters play a crucial role in generating C2 products. These findings provide significant insights into the dynamic evolution of Cu-based catalysts and the origin of their activity toward C2 products during the eCO2RR.

Flowering genes identification, network analysis, and database construction for 837 plants.

Flowering is one of the most important biological phenomena in the plant kingdom, which not only has important ecological significance, but also has substantial horticultural ornamental value. In this study, we undertook an exhaustive review of the advancements in our understanding of plant flowering genes. We delved into the identification and conducted comparative analyses of flowering genes across virtually all sequenced angiosperm plant genomes. Furthermore, we established an extensive angiosperm flowering atlas, encompassing a staggering 183 720 genes across eight pathways, along with 10 155 ABCDE mode genes, which play a pivotal role in plant flowering regulation. Through the examination of expression patterns, we unveiled the specificities of these flowering genes. An interaction network between flowering genes of the ABCDE model and their corresponding upstream genes offered a blueprint for comprehending their regulatory mechanisms. Moreover, we predicted the miRNA and target genes linked to the flowering processes of each species. To culminate our efforts, we have built a user-friendly web interface, named the Plant Flowering-time Gene Database (PFGD), accessible at http://pfgd.bio2db.com/. We firmly believe that this database will serve as a cornerstone in the global research community, facilitating the in-depth exploration of flowering genes in the plant kingdom. In summation, this pioneering endeavor represents the first comprehensive collection and comparative analysis of flowering genes in plants, offering valuable resources for the study of plant flowering genetics.

G6PD maintains the VSMC synthetic phenotype and accelerates vascular neointimal hyperplasia by inhibiting the VDAC1-Bax-mediated mitochondrial apoptosis pathway.

BACKGROUND: Glucose-6-phosphate dehydrogenase (G6PD) plays an important role in vascular smooth muscle cell (VSMC) phenotypic switching, which is an early pathogenic event in various vascular remodeling diseases (VRDs). However, the underlying mechanism is not fully understood. METHODS: An IP‒LC‒MS/MS assay was conducted to identify new binding partners of G6PD involved in the regulation of VSMC phenotypic switching under platelet-derived growth factor-BB (PDGF-BB) stimulation. Co-IP, GST pull-down, and immunofluorescence colocalization were employed to clarify the interaction between G6PD and voltage-dependent anion-selective channel protein 1 (VDAC1). The molecular mechanisms involved were elucidated by examining the interaction between VDAC1 and apoptosis-related biomarkers, as well as the oligomerization state of VDAC1. RESULTS: The G6PD level was significantly elevated and positively correlated with the synthetic characteristics of VSMCs induced by PDGF-BB. We identified VDAC1 as a novel G6PD-interacting molecule essential for apoptosis. Specifically, the G6PD-NTD region was found to predominantly contribute to this interaction. G6PD promotes VSMC survival and accelerates vascular neointimal hyperplasia by inhibiting VSMC apoptosis. Mechanistically, G6PD interacts with VDAC1 upon stimulation with PDGF-BB. By competing with Bax for VDAC1 binding, G6PD reduces VDAC1 oligomerization and counteracts VDAC1-Bax-mediated apoptosis, thereby accelerating neointimal hyperplasia. CONCLUSION: Our study showed that the G6PD-VDAC1-Bax axis is a vital switch in VSMC apoptosis and is essential for VSMC phenotypic switching and neointimal hyperplasia, providing mechanistic insight into early VRDs.

Large-scale analysis of the ARF and Aux/IAA gene families in 406 horticultural and other plants.

The auxin response factor (ARF) and auxin/indole-3-acetic acid (Aux/IAA) family of genes are central components of the auxin signaling pathway and play essential roles in plant growth and development. Their large-scale analysis and evolutionary trajectory of origin are currently not known. Here, we identified the corresponding ARF and Aux/IAA family members and performed a large-scale analysis by scanning 406 plant genomes. The results showed that the ARF and Aux/IAA gene families originated from charophytes. The ARF family sequences were more conserved than the Aux/IAA family sequences. Dispersed duplications were the common expansion mode of ARF and Aux/IAA families in bryophytes, ferns, and gymnosperms; however, whole-genome duplication was the common expansion mode of the ARF and Aux/IAA families in basal angiosperms, magnoliids, monocots, and dicots. Expression and regulatory network analyses revealed that the Arabidopsis thaliana ARF and Aux/IAA families responded to multiple hormone, biotic, and abiotic stresses. The APETALA2 and serum response factor-transcription factor gene families were commonly enriched in the upstream and downstream genes of the ARF and Aux/IAA gene families. Our study provides a comprehensive overview of the evolutionary trajectories, structural functions, expansion mechanisms, expression patterns, and regulatory networks of these two gene families.

The mechanism of water oxidation using transition metal-based heterogeneous electrocatalysts.

The water oxidation reaction, a crucial process for solar energy conversion, has garnered significant research attention. Achieving efficient energy conversion requires the development of cost-effective and durable water oxidation catalysts. To design effective catalysts, it is essential to have a fundamental understanding of the reaction mechanisms. This review presents a comprehensive overview of recent advancements in the understanding of the mechanisms of water oxidation using transition metal-based heterogeneous electrocatalysts, including Mn, Fe, Co, Ni, and Cu-based catalysts. It highlights the catalytic mechanisms of different transition metals and emphasizes the importance of monitoring of key intermediates to explore the reaction pathway. In addition, advanced techniques for physical characterization of water oxidation intermediates are also introduced, for the purpose of providing information for establishing reliable methodologies in water oxidation research. The study of transition metal-based water oxidation electrocatalysts is instrumental in providing novel insights into understanding both natural and artificial energy conversion processes.

Integrative Single Cell Atlas Revealed Intratumoral Heterogeneity Generation from an Adaptive Epigenetic Cell State in Human Bladder Urothelial Carcinoma.

Intratumor heterogeneity (ITH) of bladder cancer (BLCA) contributes to therapy resistance and immune evasion affecting clinical prognosis. The molecular and cellular mechanisms contributing to BLCA ITH generation remain elusive. It is found that a TM4SF1-positive cancer subpopulation (TPCS) can generate ITH in BLCA, evidenced by integrative single cell atlas analysis. Extensive profiling of the epigenome and transcriptome of all stages of BLCA revealed their evolutionary trajectories. Distinct ancestor cells gave rise to low-grade noninvasive and high-grade invasive BLCA. Epigenome reprograming led to transcriptional heterogeneity in BLCA. During early oncogenesis, epithelial-to-mesenchymal transition generated TPCS. TPCS has stem-cell-like properties and exhibited transcriptional plasticity, priming the development of transcriptionally heterogeneous descendent cell lineages. Moreover, TPCS prevalence in tumor is associated with advanced stage cancer and poor prognosis. The results of this study suggested that bladder cancer interacts with its environment by acquiring a stem cell-like epigenomic landscape, which might generate ITH without additional genetic diversification.

Regulation of nitrogen transformation and microbial community by inoculation during livestock manure composting.

This study examined the effects of three Bacillus strains and one Saccharomyces cerevisiae strain on nitrogen transformation and microbial communities in pig and chicken manure compost. The findings revealed that the use of compound microbial inoculants increased the compost temperature, accelerated moisture reduction, enhanced cellulase activity, and stimulated the accumulation of NH4 +-N, NO3 --N, and total nitrogen (TN), resulting in a 9% increase in TN content. The abundance of Firmicutes decreased by 3.95% at the maturation phase, while Actinobacteria and Bacteroidetes increased by 1.64% and 1.85%, respectively. Inoculation led to an increase in amoA, nxrA and nifH gene copy numbers, while simultaneously reducing the abundance of nirK, nosZ and nirS genes. It also resulted in an increase in functional enzyme levels, specifically nif and amo, with a corresponding decrease in nor. Clostridium, Phascolarctobacterium, Eubacterium and Faecalibacterium from the class Clostridium, which have a significant correlation with nifH and nxrA genes, suggest their likely crucial role in nitrogen retention and fixation. Inoculation aided in the removal of pathogenic bacteria and antibiotic resistance genes (ARGs) like fluoroquinolones, nucleosides and nitroimidazole. This study provides effective theoretical support for the mechanism of nitrogen retention and fixation, and for improving the quality of compost.

DeepFGRN: inference of gene regulatory network with regulation type based on directed graph embedding.

The inference of gene regulatory networks (GRNs) from gene expression profiles has been a key issue in systems biology, prompting many researchers to develop diverse computational methods. However, most of these methods do not reconstruct directed GRNs with regulatory types because of the lack of benchmark datasets or defects in the computational methods. Here, we collect benchmark datasets and propose a deep learning-based model, DeepFGRN, for reconstructing fine gene regulatory networks (FGRNs) with both regulation types and directions. In addition, the GRNs of real species are always large graphs with direction and high sparsity, which impede the advancement of GRN inference. Therefore, DeepFGRN builds a node bidirectional representation module to capture the directed graph embedding representation of the GRN. Specifically, the source and target generators are designed to learn the low-dimensional dense embedding of the source and target neighbors of a gene, respectively. An adversarial learning strategy is applied to iteratively learn the real neighbors of each gene. In addition, because the expression profiles of genes with regulatory associations are correlative, a correlation analysis module is designed. Specifically, this module not only fully extracts gene expression features, but also captures the correlation between regulators and target genes. Experimental results show that DeepFGRN has a competitive capability for both GRN and FGRN inference. Potential biomarkers and therapeutic drugs for breast cancer, liver cancer, lung cancer and coronavirus disease 2019 are identified based on the candidate FGRNs, providing a possible opportunity to advance our knowledge of disease treatments.

Reporting form and content of research priorities identified in knee osteoarthritis clinical practice guidelines: a methodological literature analysis.

OBJECTIVES: Clinical practice guideline (CPG) developers conduct systematic summaries of research evidence, providing them great capacity and ability to identify research priorities. We systematically analysed the reporting form and content of research priorities in CPGs related to knee osteoarthritis (KOA) to provide a valuable reference for guideline developers and clinicians. DESIGN: A methodological literature analysis was done and the characteristics of the reporting form and the content of the research priorities identified in KOA CPGs were summarised. DATA SOURCES: Six databases (PubMed, Embase, China National Knowledge Infrastructure, VIP Database for Chinese Technical Periodicals, Wanfang and Chinese Biomedical Literature Database) were searched for CPGs published from 1 January 2017 to 4 December 2022. The official websites of 40 authoritative orthopaedic societies, rheumatology societies and guideline development organisations were additionally searched. ELIGIBILITY CRITERIA: We included all KOA CPGs published in English or Chinese from 1 January 2017 that included at least one recommendation for KOA. We excluded duplicate publications, older versions of CPGs as well as guidance documents for guideline development. DATA EXTRACTION AND SYNTHESIS: Reviewers worked in pairs and independently screened and extracted the data. Descriptive statistics were used, and absolute frequencies and proportions of related items were calculated. RESULTS: 187 research priorities reported in 41 KOA CPGs were identified. 24 CPGs reported research priorities, of which 17 (41.5%) presented overall research priorities for the entire guideline rather than for specific recommendations. 110 (58.8%) research priorities were put forward due to lack of evidence. Meanwhile, more than 70% of the research priorities reflected the P (population) and I (intervention) structural elements, with 135 (72.2%) and 146 (78.1%), respectively. More than half of the research priorities (118, 63.8%) revolved around evaluating the efficacy of interventions. Research priorities primarily focused on physical activity (32, 17.3%), physical therapy (30, 16.2%), surgical therapy (27, 14.6%) and pharmacological treatment (26, 14.1%). CONCLUSIONS: Research priorities reported in KOA CPGs mainly focused on evaluating non-pharmacological interventions. There exists considerable room for improvement for a comprehensive and standardised generation and reporting of research priorities in KOA CPGs.

De-aberration for transcranial photoacoustic computed tomography through an adult human skull.

Noninvasive transcranial photoacoustic computed tomography (PACT) of the human brain, despite its clinical potential, remains impeded by the acoustic distortion induced by the human skull. The distortion, which is attributed to the markedly different material properties of the skull relative to soft tissue, results in heavily aberrated PACT images -- a problem that has remained unsolved in the past two decades. Herein, we report the first successful experimental demonstration of the de-aberration of PACT images through an ex-vivo adult human skull using a homogeneous elastic model for the skull. Using only the geometry, position, and orientation of the skull, we accurately de-aberrate the PACT images of light-absorbing phantoms acquired through an ex-vivo human skull, in terms of the recovered phantom features, for different levels of phantom complexity and positions. Our work addresses the longstanding challenge of skull-induced aberrations in transcranial PACT and advances the field towards unlocking the full potential of transcranial human brain PACT.

Exploring research hotspots and future directions in neural tube defects field by bibliometric and bioinformatics analysis.

Background: Neural tube defects (NTDs) is the most common birth defect of the central nervous system (CNS) which causes the death of almost 88,000 people every year around the world. Much efforts have been made to investigate the reasons that contribute to NTD and explore new ways to for prevention. We trawl the past decade (2013-2022) published records in order to get a worldwide view about NTDs research field. Methods: 7,437 records about NTDs were retrieved from the Web of Science (WOS) database. Tools such as shell scripts, VOSviewer, SCImago Graphica, CiteSpace and PubTator were used for data analysis and visualization. Results: Over the past decade, the number of publications has maintained an upward trend, except for 2022. The United States is the country with the highest number of publications and also with the closest collaboration with other countries. Baylor College of Medicine has the closest collaboration with other institutions worldwide and also was the most prolific institution. In the field of NTDs, research focuses on molecular mechanisms such as genes and signaling pathways related to folate metabolism, neurogenic diseases caused by neural tube closure disorders such as myelomeningocele and spina bifida, and prevention and treatment such as folate supplementation and surgical procedures. Most NTDs related genes are related to development, cell projection parts, and molecular binding. These genes are mainly concentrated in cancer, Wnt, MAPK, PI3K-Akt and other signaling pathways. The distribution of NTDs related SNPs on chromosomes 1, 3, 5, 11, 14, and 17 are relatively concentrated, which may be associated with high-risk of NTDs. Conclusion: Bibliometric analysis of the literature on NTDs field provided the current status, hotspots and future directions to some extant. Further bioinformatics analysis expanded our understanding of NTDs-related genes function and revealed some important SNP clusters and loci. This study provided some guidance for further studies. More extensive cooperation and further research are needed to overcome the ongoing challenge in pathogenesis, prevention and treatment of NTDs.

Quantum imaging of biological organisms through spatial and polarization entanglement.

Quantum imaging holds potential benefits over classical imaging but has faced challenges such as poor signal-to-noise ratios, low resolvable pixel counts, difficulty in imaging biological organisms, and inability to quantify full birefringence properties. Here, we introduce quantum imaging by coincidence from entanglement (ICE), using spatially and polarization-entangled photon pairs to overcome these challenges. With spatial entanglement, ICE offers higher signal-to-noise ratios, greater resolvable pixel counts, and the ability to image biological organisms. With polarization entanglement, ICE provides quantitative quantum birefringence imaging capability, where both the phase retardation and the principal refractive index axis angle of an object can be remotely and instantly quantified without changing the polarization states of the photons incident on the object. Furthermore, ICE enables 25 times greater suppression of stray light than classical imaging. ICE has the potential to pave the way for quantum imaging in diverse fields, such as life sciences and remote sensing.

Covalent Tethering of Cobalt Porphyrins on Phenolic Resins for Electrocatalytic Oxygen Reduction and Evolution Reactions.

The front cover artwork is provided by Rui Cao's group at Shaanxi Normal University. The image shows the design of Co-porphyrin-engineered phenolic resins with intramolecular phenolic hydroxyl groups to facilitate proton and electron transfers for efficient oxygen electrocatalysis, which is bioinspired by cytochrome c oxidases, and shows the excellent performance of Zn-air batteries assembled with the hybrid material. Read the full text of the Research Article at 10.1002/cphc.202400017.

Emphasis should be placed on identifying and reporting research priorities to increase research value: An empirical analysis.

OBJECTIVES: To compared the presentation of research priorities in the GRADE (Grading of Recommendations Assessment, Development, and Evaluation) clinical practice guidelines (CPGs) developed under the guidance of the GRADE working group or its two co-chair, and the Chinese CPGs. METHODS: This was a methodological empirical analysis. We searched PubMed, Embase, and four Chinese databases (Wanfang, VIP Database for Chinese Technical Periodicals, China National Knowledge Infrastructure and Chinese Biomedical Literature Database) and retrieved nine Chinese guideline databases or Society websites as well as GRADE Pro websites. We included all eligible GRADE CPGs and a random sample of double number of Chinese CPGs, published 2018 to 2022. The reviewers independently screened and extracted the data, and we summarized and analyzed the reporting on the research priorities in the CPGs. RESULTS: Of the 135 eligible CPGs (45 GRADE CPGs and 90 Chinese CPGs), 668, 138 research priorities were identified respectively. More than 70% of the research priorities in GRADE CPGs and Chinese CPGs had population and intervention (PI) structure. 99 (14.8%) of GRADE CPG research priorities had PIC structures, compared with only 4(2.9%) in Chinese. And 28.4% (190) GRADE CPG research priorities reflected comparisons between PICO elements, approximately double those in Chinese. The types of research priorities among GRADE CPGs and Chinese CPGs were mostly focused on the efficacy of interventions, and the type of comparative effectiveness in the GRADE research priorities was double those in Chinese. CONCLUSIONS: There was still considerable room for improvement in the developing and reporting of research priorities in Chinese CPGs. Key PICO elements were inadequately presented, with more attention on intervention efficacy and insufficient consideration given to values, preferences, health equity, and feasibility. Identifying and reporting of research priorities deserves greater effort in the future.

Electrocatalytic Oxygen Reduction Reaction of Peripheral Functionalized Cobalt Porphyrins(2.1.2.1).

Two peripheral functionalized clamp-shaped cobalt porphyrin(2.1.2.1) complexes were synthesized, and their electrocatalytic ORR abilities were investigated. The crystal data and optical and redox properties of them were revised by peripheral modification. The ORR capacities and DFT calculations of F5PhCo and F5NCo suggest superior selectivity for the 4e- ORR pathway. This work further confirms the clamp-shaped cobalt porphyrin complexes are ideal Co-N4 ORR catalysts.

Subject-Independent Emotion Recognition Based on EEG Frequency Band Features and Self-Adaptive Graph Construction.

Emotion is one of the most important higher cognitive functions of the human brain and plays an important role in transaction processing and decisions. In traditional emotion recognition studies, the frequency band features in EEG signals have been shown to have a high correlation with emotion production. However, traditional emotion recognition methods cannot satisfactorily solve the problem of individual differences in subjects and data heterogeneity in EEG, and subject-independent emotion recognition based on EEG signals has attracted extensive attention from researchers. In this paper, we propose a subject-independent emotion recognition model based on adaptive extraction of layer structure based on frequency bands (BFE-Net), which is adaptive in extracting EEG map features through the multi-graphic layer construction module to obtain a frequency band-based multi-graphic layer emotion representation. To evaluate the performance of the model in subject-independent emotion recognition studies, extensive experiments are conducted on two public datasets including SEED and SEED-IV. The experimental results show that in most experimental settings, our model has a more advanced performance than the existing studies of the same type. In addition, the visualization of brain connectivity patterns reveals that some of the findings are consistent with previous neuroscientific validations, further validating the model in subject-independent emotion recognition studies.

Cu/Biochar Bifunctional Catalytic Removal of COS and H2S:H2O Dissociation and CuO Anchoring Enhanced by Pyridine N.

Economic and environmentally friendly strategies are needed to promote the bifunctional catalytic removal of carbonyl sulfide (COS) by hydrolysis and hydrogen sulfide (H2S) by oxidation. N doping is considered to be an effective strategy, but the essential and intrinsic role of N dopants in catalysts is still not well understood. Herein, the conjugation of urea and biochar during Cu/biochar annealing produced pyridine N, which increased the combined COS/H2S capacity of the catalyst from 260.7 to 374.8 mg·g-1 and enhanced the turnover frequency of H2S from 2.50 × 10-4 to 5.35 × 10-4 s-1. The nucleophilic nature of pyridine N enhances the moderate basic sites of the catalyst, enabling the attack of protons and strong H2O dissociation. Moreover, pyridine N also forms cavity sites that anchor CuO, improving Cu dispersion and generating more reactive oxygen species. By providing original insight into the pyridine N-induced bifunctional catalytic removal of COS/H2S in a slightly oxygenated and humid atmosphere, this study offers valuable guidance for further C═S and C-S bond-breaking in the degradation of sulfur-containing pollutants.

The Segmentation of Multiple Types of Uterine Lesions in Magnetic Resonance Images Using a Sequential Deep Learning Method with Image-Level Annotations.

Fully supervised medical image segmentation methods use pixel-level labels to achieve good results, but obtaining such large-scale, high-quality labels is cumbersome and time consuming. This study aimed to develop a weakly supervised model that only used image-level labels to achieve automatic segmentation of four types of uterine lesions and three types of normal tissues on magnetic resonance images. The MRI data of the patients were retrospectively collected from the database of our institution, and the T2-weighted sequence images were selected and only image-level annotations were made. The proposed two-stage model can be divided into four sequential parts: the pixel correlation module, the class re-activation map module, the inter-pixel relation network module, and the Deeplab v3 + module. The dice similarity coefficient (DSC), the Hausdorff distance (HD), and the average symmetric surface distance (ASSD) were employed to evaluate the performance of the model. The original dataset consisted of 85,730 images from 316 patients with four different types of lesions (i.e., endometrial cancer, uterine leiomyoma, endometrial polyps, and atypical hyperplasia of endometrium). A total number of 196, 57, and 63 patients were randomly selected for model training, validation, and testing. After being trained from scratch, the proposed model showed a good segmentation performance with an average DSC of 83.5%, HD of 29.3 mm, and ASSD of 8.83 mm, respectively. As far as the weakly supervised methods using only image-level labels are concerned, the performance of the proposed model is equivalent to the state-of-the-art weakly supervised methods.