Molecular mechanisms underlying structural plasticity of electroconvulsive therapy in major depressive disorder.

Although previous studies reported structural changes associated with electroconvulsive therapy (ECT) in major depressive disorder (MDD), the underlying molecular basis of ECT remains largely unknown. Here, we combined two independent structural MRI datasets of MDD patients receiving ECT and transcriptomic gene expression data from Allen Human Brain Atlas to reveal the molecular basis of ECT for MDD. We performed partial least square regression to explore whether/how gray matter volume (GMV) alterations were associated with gene expression level. Functional enrichment analysis was conducted using Metascape to explore ontological pathways of the associated genes. Finally, these genes were further assigned to seven cell types to determine which cell types contribute most to the structural changes in MDD patients after ECT. We found significantly increased GMV in bilateral hippocampus in MDD patients after ECT. Transcriptome-neuroimaging association analyses showed that expression levels of 726 genes were positively correlated with the increased GMV in MDD after ECT. These genes were mainly involved in synaptic signaling, calcium ion binding and cell-cell signaling, and mostly belonged to excitatory and inhibitory neurons. Moreover, we found that the MDD risk genes of CNR1, HTR1A, MAOA, PDE1A, and SST as well as ECT related genes of BDNF, DRD2, APOE, P2RX7, and TBC1D14 showed significantly positive associations with increased GMV. Overall, our findings provide biological and molecular mechanisms underlying structural plasticity induced by ECT in MDD and the identified genes may facilitate future therapy for MDD.

Exploring the roles and potential therapeutic strategies of inflammation and metabolism in the pathogenesis of vitiligo: a mendelian randomization and bioinformatics-based investigation.

Introduction: Vitiligo, a common autoimmune acquired pigmentary skin disorder, poses challenges due to its unclear pathogenesis. Evidence suggests inflammation and metabolism's pivotal roles in its onset and progression. This study aims to elucidate the causal relationships between vitiligo and inflammatory proteins, immune cells, and metabolites, exploring bidirectional associations and potential drug targets. Methods: Mendelian Randomization (MR) analysis encompassed 4,907 plasma proteins, 91 inflammatory proteins, 731 immune cell features, and 1400 metabolites. Bioinformatics analysis included Protein-Protein Interaction (PPI) network construction, Gene Ontology (GO), and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analysis. Subnetwork discovery and hub protein identification utilized the Molecular Complex Detection (MCODE) plugin. Colocalization analysis and drug target exploration, including molecular docking validation, were performed. Results: MR analysis identified 49 proteins, 39 immune cell features, and 59 metabolites causally related to vitiligo. Bioinformatics analysis revealed significant involvement in PPI, GO enrichment, and KEGG pathways. Subnetwork analysis identified six central proteins, with Interferon Regulatory Factor 3 (IRF3) exhibiting strong colocalization evidence. Molecular docking validated Piceatannol's binding to IRF3, indicating a stable interaction. Conclusion: This study comprehensively elucidates inflammation, immune response, and metabolism's intricate involvement in vitiligo pathogenesis. Identified proteins and pathways offer potential therapeutic targets, with IRF3 emerging as a promising candidate. These findings deepen our understanding of vitiligo's etiology, informing future research and drug development endeavors.

Subchondral bone expansion in advanced knee osteoarthritis: Relation with radiographic severity and role in surgical decision-making.

Background: Joint space width (JSW) is a traditional imaging marker for knee osteoarthritis (OA) severity, but it lacks sensitivity in advanced cases. We propose tibial subchondral bone area (TSBA), a new CT imaging marker to explore its relationship with OA radiographic severity, and to test its performance for classifying surgical decisions between unicompartmental knee arthroplasty (UKA) and total knee arthroplasty (TKA) compared to JSW. Methods: We collected clinical, radiograph, and CT data from 182 patients who underwent primary knee arthroplasty (73 UKA, 109 TKA). The radiographic severity was scored using Kellgren-Lawrence (KL) grading system. TSBA and JSW were extracted from 3D CT-reconstruction model. We used independent t-test to investigate the relationship between TSBA and KL grade, and binary logistic regression to identify factors associated with TKA risk. The accuracy of TSBA, JSW and established classification model in differentiating between UKA and TKA was assessed using AUC. Results: All parameters exhibited inter- and intra-class coefficients greater than 0.966. Patients with KL grade 4 had significantly larger TSBA than those with KL grade 3. TSBA (0.708 of AUC) was superior to minimal/average JSW (0.547/0.554 of AUC) associated with the risk of receiving TKA. Medial TSBA, together with gender and Knee Society Knee Score, emerged as independent classification factors in multivariate analysis. The overall AUC of composite model for surgical decision-making was 0.822. Conclusion: Tibial subchondral bone area is an independent imaging marker for radiographic severity, and is superior to JSW for surgical decision-making between UKA and TKA in advanced OA patients.

Two new species of the mealybug genus Paracoccus from Jiangxi, South China (Hemiptera, Coccomorpha, Pseudococcidae).

Two new mealybug species, Paracoccusgillianwatsonae Zhang, sp. nov. and P.wui Zhang, sp. nov., collected from Jiangxi, South China, are described and illustrated based on the morphology of adult females. Paracoccusgillianwatsonae is similar to P.burnerae (Brain, 1915), but it differs in having fewer pairs of cerarii, and in lacking both ventral oral collar tubular ducts on the margins of the head and translucent pores on the hind femur. Paracoccuswui resembles P.keralae Williams, 2004 and P.neocarens (Lit, 1992), but it differs in lacking ventral oral collar tubular ducts on the margins of the head and in having multilocular disc-pores usually in double rows at the posterior edges of abdominal segments V and VI. A key to the Paracoccus species found in China is provided.

Band-like transport in solution-processed perylene diimide dianion films with high Hall mobility.

It is crucial to prepare high-mobility organic polycrystalline film through solution processing. However, the delocalized carrier transport of polycrystalline films in organic semiconductors has rarely been investigated through Hall-effect measurement. This study presents a strategy for building strong intermolecular interactions to fabricate solution-crystallized p-type perylene diimide (PDI) dianion films with a closer intermolecular π-π stacking distance of 3.25 Å. The highly delocalized carriers enable a competitive Hall mobility of 3 cm2 V-1 s-1, comparable to that of the reported high-mobility organic single crystals. The PDI dianion films exhibit a high electrical conductivity of 17 S cm-1 and typical band-like transport, as evidenced by the negative temperature linear coefficient of mobility proportional to T-3/2. This work demonstrates that, as the intermolecular π-π interactions become strong enough, they will display high mobility and conductivity, providing a new approach to developing high-mobility organic semiconductor materials.

Pro-cancer role of CD276 as a novel biomarker for clear cell renal cell carcinoma.

OBJECTIVE: Renal cell carcinoma (RCC) is a common malignant tumor with a high incidence in males and the elderly, and clear cell RCC (ccRCC) is the most common RCC subtype. ccRCC is highly metastatic with a poor prognosis. Therefore, it is crucial to obtain a detailed understanding of the molecular mechanism of ccRCC and to identify suitable biomarkers to realize early diagnosis and improve prognosis. METHODS: We analyzed data from the Cancer Genome Atlas, investigated the overall differential expression of CD276 in ccRCC, and evaluated the influence of CD276 on patient survival and prognosis. We also performed gene set enrichment analysis (GSEA) and pathway enrichment analysis and investigated cell infiltration and drug responsiveness to further assess the regulatory effect of CD276 on ccRCC. Furthermore, we verified CD276 expression in RCC cell lines and control cell lines. RESULTS: The CD276 expression level in ccRCC samples was higher than that in corresponding samples adjacent to the tumors. Moreover, high CD276 expression levels were positively correlated with poor prognosis in patients with RCC. GSEA revealed that CD276 was significantly involved in immune-related pathways, and the level of CD276 expression was confirmed as associated with immune cell infiltration to some extent. Notably, some drugs were predicted to act on CD276, and this was confirmed by molecular docking. Furthermore, high levels of CD276 expression in RCC cell lines were verified. CONCLUSION: CD276 expression was significantly increased in ccRCC tissues and cells and positively correlated with patient prognosis. CD276 is a potential prognostic biomarker of ccRCC. Overall, this study provides a potential therapeutic strategy for ccRCC.

Global responses of wetland methane emissions to extreme temperature and precipitation.

As global warming continues, events of extreme heat or heavy precipitation will become more frequent, while events of extreme cold will become less so. How wetlands around the globe will react to these extreme events is unclear yet critical, because they are among the greatest natural sources of methane. Here we use seven indices of extreme climate and the rate of methane emission from global wetlands during 2000-2019 simulated by 12 published models as input data. Our analyses suggest that extreme cold (particularly extreme low temperatures) inhibits methane emissions from wetlands, whereas extreme heat (particularly extreme high temperatures) accelerates methane emission from wetland(WME). Our results also suggest that daily precipitation > 10 mm accelerates emission from wetlands, while much higher daily precipitation levels can slow emission. The correlation of extreme high temperature and precipitation with rate of methane emission became stronger during the study period, while the correlation between extreme low temperature and emission rate became weaker.

Cytokinin oxidase gene CKX5 is modulated in the immunity of Arabidopsis to Botrytis cinerea.

In our previous work, cytokinin (CK) signaling and biosynthesis were found to be modulated during Arabidopsis defense against infection by the necrotrophic pathogen Botrytis cinerea. Notably, the expression level of CYTOKININ OXIDASE/DEHYDROGENASE 5 (CKX5) was significantly induced in B. cinerea-infected leaves and later in distant B. cinerea-untreated leaves of the same plant. To confirm and determine how CKX5 is involved in the response to B. cinerea infection, transcript levels of CKX family genes were analyzed in B. cinerea-inoculated leaves, and only CKX5 was remarkably induced by B. cinerea infection. Furthermore, CKX5-overexpressing Arabidopsis plants were more resistant to B. cinerea than wild-type plants. Transcription factors (TFs) binding to the CKX5 promoter were then screened by yeast one-hybrid assays. Quantitative Real-Time Reverse Transcription PCR (qRT-PCR) analysis further showed that genes encoding TFs, including WRKY40, WRKY33, ERF6, AHL15, AHL17, ANAC003, TCP13 and ANAC019, were also strongly induced in infected leaves, similar to CKX5. Analysis of ERF6-overexpressing plants and ERF6-and AHL15-knockout mutants indicated that ERF6 and AHL15 are involved in plant immunity to B. cinerea. Furthermore, CKX5 upregulation by B. cinerea infection was affected when ERF6 or AHL15 levels were altered. Our work suggests that CKX5 levels are controlled by the plant defense system to defend against attack by the pathogen B. cinerea.

Research on dynamic characteristics of cutter breaking frozen soil and optimal drum rotation speed of the new shaft tunneling machine.

To improve the efficiency of frozen soil excavation, the new shaft tunneling machine was developed. The new shaft tunneling machine exerts pressure on the frozen soil through the cutter under the joint action of its own gravity, the drum rotational force and the inertia force, and the frozen soil is damaged. By unique way of breaking frozen soil to improve the efficiency of frozen soil excavation, the drum rotation speed is one of the factors affecting the performance of frozen soil excavation. This article applies SolidWorks software to establish the model of cutter breaking frozen soil, takes advantage of Hyper Mesh finite element software coupled with LS-DYNA solver to acquire the regular pattern of change in the force change, frozen soil stress-strain and specific energy of cutter crushing frozen soil, etc., which analyzes the destruction of frozen soil when the drum of the new shaft tunneling machine is rotating at the speed of 25-40 rpm. Combine with field test to investigate the mechanism of cutter breaking frozen soil under the optimal drum rotation speed. The investigation results demonstrate that: when frozen soil's self-bearing capacity is lower than the force of cutter, it breaks up and detaches from the soil body, and frozen soil undergoes tensile, compressive and shear damages. For this research, it is instructive for practical engineering.

Spatial multi-attention conditional neural processes.

Spatial prediction tasks are challenging when observed samples are sparse and prediction samples are abundant. Gaussian processes (GPs) are commonly used in spatial prediction tasks and have the advantage of measuring the uncertainty of the interpolation result. However, as the sample size increases, GPs suffer from significant overhead. Standard neural networks (NNs) provide a powerful and scalable solution for modeling spatial data, but they often overfit small sample data. Based on conditional neural processes (CNPs), which combine the advantages of GPs and NNs, we propose a new framework called Spatial Multi-Attention Conditional Neural Processes (SMACNPs) for spatial small sample prediction tasks. SMACNPs are a modular model that can predict targets by employing different attention mechanisms to extract relevant information from different forms of sample data. The task representation is inferred by measuring the spatial correlation contained in different sample points and the relationship contained in attribute variables, respectively. The distribution of the target variable is predicted by GPs parameterized by NNs. SMACNPs allow us to obtain accurate predictions of the target value while quantifying the prediction uncertainty. Experiments on spatial prediction tasks on simulated and real-world datasets demonstrate that this framework flexibly incorporates spatial context and correlation into the model, achieving state-of-the-art results in spatial small sample prediction tasks in terms of both predictive performance and reliability. For example, on the California housing dataset, our method reduces MAE by 8% and MSE by 7% compared to the second-best method. In addition, a spatiotemporal prediction task to forecast traffic speed further confirms the effectiveness and generality of our method.

Radiomics signature of osteoarthritis: Current status and perspective.

Osteoarthritis (OA) is one of the fast-growing disability-related diseases worldwide, which has significantly affected the quality of patients' lives and brings about substantial socioeconomic burdens in medical expenditure. There is currently no cure for OA once the bone damage is established. Unfortunately, the existing radiological examination is limited to grading the disease's severity and is insufficient to precisely diagnose OA, detect early OA or predict OA progression. Therefore, there is a pressing need to develop novel approaches in medical image analysis to detect subtle changes for identifying early OA development and rapid progressors. Recently, radiomics has emerged as a unique approach to extracting high-dimensional imaging features that quantitatively characterise visible or hidden information from routine medical images. Radiomics data mining via machine learning has empowered precise diagnoses and prognoses of disease, mainly in oncology. Mounting evidence has shown its great potential in aiding the diagnosis and contributing to the study of musculoskeletal diseases. This paper will summarise the current development of radiomics at the crossroads between engineering and medicine and discuss the application and perspectives of radiomics analysis for OA diagnosis and prognosis. The translational potential of this article: Radiomics is a novel approach used in oncology, and it may also play an essential role in the diagnosis and prognosis of OA. By transforming medical images from qualitative interpretation to quantitative data, radiomics could be the solution for precise early OA detection, progression tracking, and treatment efficacy prediction. Since the application of radiomics in OA is still in the early stages and primarily focuses on fundamental studies, this review may inspire more explorations and bring more promising diagnoses, prognoses, and management results of OA.

Optimal intraventricular hemorrhage volume cutoff for predicting poor outcome in patients with intracerebral hemorrhage.

BACKGROUND AND OBJECTIVES: The prognosis of patients with spontaneous intracerebral hemorrhage (ICH) is often influenced by hematoma volume, a well-established predictor of poor outcome. However, the optimal intraventricular hemorrhage (IVH) volume cutoff for predicting poor outcome remains unknown. METHODS: We analyzed 313 patients with spontaneous ICH not undergoing evacuation, including 7 cases with external ventricular drainage (EVD). These patients underwent a baseline CT scan, followed by a 24-hour CT scan for measurement of both hematoma and IVH volume. We defined hematoma growth as hematoma growth > 33 % or 6 mL at follow-up CT, and poor outcome as modified Rankin Scale score≥3 at three months. Cutoffs with optimal sensitivity and specificity for predicting poor outcome were identified using receiver operating curves. RESULTS: The receiver operating characteristic analysis identified 6 mL as the optimal cutoff for predicting poor outcome. IVH volume> 6 mL was observed in 53 (16.9 %) of 313 patients. Patients with IVH volume>6 mL were more likely to be older and had higher NIHSS score and lower GCS score than those without. IVH volume>6 mL (adjusted OR 2.43, 95 % CI 1.13-5.30; P = 0.026) was found to be an independent predictor of poor clinical outcome at three months in multivariable regression analysis. CONCLUSIONS: Optimal IVH volume cutoff represents a powerful tool for improving the prediction of poor outcome in patients with ICH, particularly in the absence of clot evacuation or common use of EVD. Small amounts of intraventricular blood are not independently associated with poor outcome in patients with intracerebral hemorrhage. The utilization of optimal IVH volume cutoffs may improve the clinical trial design by targeting ICH patients that will obtain maximal benefit from therapies.

Control of two insect pests by expression of a mismatch corrected double-stranded RNA in plants.

RNA interference (RNAi) has emerged as an efficient technology for pest control by silencing the essential genes of targeted insects. Owing to its nucleotide sequence-guided working mechanism, RNAi has a high degree of species-specificity without impacts on non-target organisms. However, as plants are inevitably under threat by two or more insect pests in nature, the species-specific mode of RNAi-based technology restricts its wide application for pest control. In this study, we artificially designed an intermediate dsRNA (iACT) targeting two ß-Actin (ACT) genes of sap-sucking pests Bemisia tabaci and Myzus persicae by mutual correction of their mismatches. When expressing hairpin iACT (hpiACT) from tobacco nuclear genome, transgenic plants are well protected from both B. tabaci and M. persicae, either individually or simultaneously, as evidenced by reduced fecundity and suppressed ACT gene expression, whereas expression of hpRNA targeting BtACT or MpACT in transgenic tobacco plants could only confer specific resistance to either B. tabaci or M. persicae, respectively. In sum, our data provide a novel proof-of-concept that two different insect species could be simultaneously controlled by artificial synthesis of dsRNA with sequence optimization, which expands the range of transgenic RNAi methods for crop protection.

Radiomics analysis of patellofemoral joint improves knee replacement risk prediction: Data from the Multicenter Osteoarthritis Study (MOST).

Objective: Knee replacement (KR) is the last-resort treatment for knee osteoarthritis. Although radiographic evidence of tibiofemoral joint has been widely adopted for prognostication, patellofemoral joint has gained little attention and may hold additional value for further improvements. We aimed to quantitatively analyse patellofemoral joint through radiomics analysis of lateral view radiographs for improved KR risk prediction. Design: From the Multicenter Osteoarthritis Study dataset, we retrospectively retrieved the initial-visit lateral left knee radiographs of 2943 patients aged 50 to 79. They were split into training and test cohorts at a 2:1 ratio. A comprehensive set of radiomic features were extracted within the best-performing subregion of patellofemoral joint and combined into a radiomics score (RadScore). A KR risk score, derived from Kellgren-Lawrence grade (KLG) of tibiofemoral joint and RadScore of patellofemoral joint, was developed by multivariate Cox regression and assessed using time-dependent area under receiver operating characteristic curve (AUC). Results: While patellofemoral osteoarthritis (PFOA) was insignificant during multivariate analysis, RadScore was identified as an independent risk factor (multivariate Cox p-value < 0.001) for KR. The subgroup analysis revealed that RadScore was particularly effective in predicting rapid progressor (KR occurrence before 30 months) among early- (KLG < 2) and mid-stage (KLG â€‹= â€‹2) patients. Combining two joints radiographic information, the AUC reached 0.89/0.87 for predicting 60-month KR occurrence. Conclusions: The RadScore of the patellofemoral joint on lateral radiographs emerges as an independent prognostic factor for improving KR prognosis prediction. The KR risk score could be instrumental in managing progressive knee osteoarthritis interventions.

Novel drimane-type sesquiterpenoids and nucleosides from the Helicoma septoconstrictum suppress the growth of ovarian cancer cells.

Four new drimane-type sesquiterpenoids and two new nucleoside derivatives (1-6), were isolated from the fungus Helicoma septoconstrictum. Their structures were determined based on the combination of the analysis of their HR-ESI-MS, NMR, ECD calculations data and acid hydrolysis. All the isolated compounds were detected for their bio-activities against MDA-MB-231, A549/DDP, A2780 and HepG2 cell lines. Helicoside C (4) exhibited superior cytotoxicity against the A2780 cell line with IC50 7.5 ± 1.5 µM. The analysis of reactive oxygen species (ROS) revealed that Helicoside C induced an increase in intracellular ROS. Furthermore, the flow cytometry and mitochondrial membrane potential (MMP) analyses unveiled that Helicoside C mediated mitochondrial-dependent apoptosis in A2780 cells. The western blotting test showed that Helicoside C could suppress the STAT3's phosphorylation. These findings offered crucial support for development of H. septoconstrictum and highlighted the potential application of drimane-type sesquiterpenoids in pharmaceuticals.

An optimized water table depth detected for mitigating global warming potential of greenhouse gas emissions in wetland of Qinghai-Tibetan Plateau.

Climate change and human activities have intensified variations of water table depth (WTD) in wetlands around the world, which may strongly affect greenhouse gas emissions. Here, we analyzed how emissions of CO2, CH4, and N2O from the Zoige wetland on the Qinghai-Tibetan Plateau (QTP) vary with the WTD. Our data indicate that the wetland shows net positive global warming potential (11.72 tCO2-e ha-1 yr-1), and its emissions of greenhouse gases are driven primarily by WTD. Our analysis suggests that an optimal WTD exists, which at our study site was approximately 18 cm, for mitigating increases in global warming potential from the wetland. Our study provides insights into how climate change and human acitivies affect greenhouse gas emissions from alpine wetlands, and they suggest that water table management may be effective at mitigating future increases in emissions.

Mapping individual structural covariance network in development brain with dynamic time warping.

A conspicuous property of brain development or maturity is coupled with coordinated or synchronized brain structural co-variation. However, there is still a lack of effective approach to map individual structural covariance network. Here, we developed a novel individual structural covariance network method using dynamic time warping algorithm and applied it to delineate developmental trajectories of topological organizations of structural covariance network from childhood to early adulthood with a large sample of 655 individuals from Human Connectome Project-Development dataset. We found that the individual structural covariance network exhibited small-worldness property and the network global topological characteristics including small-worldness, global efficiency, local efficiency, and modularity linearly increase with age while the shortest path length linearly decreases with age. The nodal topological properties including betweenness and degree increased with age in language and emotion regulation related brain areas, while it decreased with age mainly in visual cortex, sensorimotor area, and hippocampus. Moreover, the topological attributes of structural covariance network as features could predict the age of each individual. Taken together, our results demonstrate that dynamic time warping can effectively map individual structural covariance network to uncover the developmental trajectories of network topology, which may facilitate future investigations to establish the links of structural co-variations with respect to cognition and disease vulnerability.

Learning nonequilibrium statistical mechanics and dynamical phase transitions.

Nonequilibrium statistical mechanics exhibit a variety of complex phenomena far from equilibrium. It inherits challenges of equilibrium, including accurately describing the joint distribution of a large number of configurations, and also poses new challenges as the distribution evolves over time. Characterizing dynamical phase transitions as an emergent behavior further requires tracking nonequilibrium systems under a control parameter. While a number of methods have been proposed, such as tensor networks for one-dimensional lattices, we lack a method for arbitrary time beyond the steady state and for higher dimensions. Here, we develop a general computational framework to study the time evolution of nonequilibrium systems in statistical mechanics by leveraging variational autoregressive networks, which offer an efficient computation on the dynamical partition function, a central quantity for discovering the phase transition. We apply the approach to prototype models of nonequilibrium statistical mechanics, including the kinetically constrained models of structural glasses up to three dimensions. The approach uncovers the active-inactive phase transition of spin flips, the dynamical phase diagram, as well as new scaling relations. The result highlights the potential of machine learning dynamical phase transitions in nonequilibrium systems.

Deep learning-based bronchial tree-guided semi-automatic segmentation of pulmonary segments in computed tomography images.

Background: Pulmonary segments are valuable because they can provide more precise localization and intricate details of lung cancer than lung lobes. With advances in precision therapy, there is an increasing demand for the identification and visualization of pulmonary segments in computed tomography (CT) images to aid in the precise treatment of lung cancer. This study aimed to integrate multiple deep-learning models to accurately segment pulmonary segments in CT images using a bronchial tree (BT)-based approach. Methods: The proposed segmentation method for pulmonary segments using the BT-based approach comprised the following five essential steps: (I) segmentation of the lung using a U-Net (R231) (public access) model; (II) segmentation of the lobes using a V-Net (self-developed) model; (III) segmentation of the airway using a combination of a differential geometric approach method and a BronchiNet (public access) model; (IV) labeling of the BT branches based on anatomical position; and (V) segmentation of the pulmonary segments based on the distance of each voxel to the labeled BT branches. This five-step process was applied to 14 high-resolution breath-hold CT images and compared against manual segmentations for evaluation. Results: For the lung segmentation, the lung mask had a mean dice similarity coefficient (DSC) of 0.98±0.03. For the lobe segmentation, the V-Net model had a mean DSC of 0.94±0.06. For the airway segmentation, the average total length of the segmented airway trees per image scan was 1,902.8±502.1 mm, and the average number of the maximum airway tree generations was 8.5±1.3. For the segmentation of the pulmonary segments, the proposed method had a DSC of 0.73±0.11 and a mean surface distance of 6.1±2.9 mm. Conclusions: This study demonstrated the feasibility of combining multiple deep-learning models for the auxiliary segmentation of pulmonary segments on CT images using a BT-based approach. The results highlighted the potential of the BT-based method for the semi-automatic segmentation of the pulmonary segment.