Objective:To explore the construction of an evaluation model for aortic root anatomy and calcium burden in patients with bicuspid aortic valve (BAV) stenosis before transcatheter aortic valve replacement (TAVR) based on deep learning (DL) algorithms.Methods:A retrospective collection of 362 BAV stenosis patients who underwent TAVR from September 2023 to May 2024 was performed. All patients underwent cardiac CT angiography. The patients were divided into training group ( n=104), internal validation group ( n=206), and external validation group ( n=52). A DL model was trained on the training dataset to assess aortic root anatomy and calcification burden. The evaluation included the segmentation accuracy of the algorithm, the measurement performance of key anatomical structures (i.e., valve leaflets and type-1 and type-2 fusion raphe), and calcification burden, as well as the measurement efficiency. Overall segmentation performance was assessed using the average Dice coefficient (ADC). The fine-scale segmentation quality was validated by the 95th-percentile Hausdorff distance (HD-95) and the average symmetric surface distance (ASSD). The consistency of the measurement results was assessed using the Pearson correlation coefficient and the intraclass correlation coefficient ( ICC) with a two-way mixed model for absolute agreement. In addition, the total time and total mouse movement distance required for manual assessment versus the DL model on the validation datasets were recorded and compared. Results:The algorithm demonstrated excellent segmentation performance on aortic root anatomical targets, achieving outstanding consistency within both internal and external validation datasets (0.955

Objectives:To investigate the relationship between the improvement of lumbar symptoms and imaging parameters in patients with tandem spinal stenosis(TSS)primarily manifesting as cervical spondylotic myelopathy(CSM)after initial cervical decompression surgery,and to explore related imaging predictive factors.Methods:A retrospective analysis was conducted on 69 TSS patients who underwent primary cervical decom-pression surgery,with an average age of 64.3±10.5 years(ranging from 41 to 86 years old)and a follow-up period of 33.8±5.5 months(ranging from 24 to 48 months).Preoperative symptoms and signs,Nurick gait clas-sification,and preoperative and final follow-up Japanese Orthopaedic Association(JOA)scores for both the cer-vical and lumbar spine were recorded and analyzed.The patients were divided into an improvement group(n=37)and a non-improvement group(n=32)based on the improvement conditions of lumbar spine JOA scores at the final follow-up.Imaging parameters were measured including spinal cord compression ratio,cross-sectional area of the dural sac at the narrowest point of the cervical spinal cord,the ratio of the vertebral canal to the vertebral body and the actual spinal canal width from C3 to C7,and the actual width of the vertebral canal from L1 to L5.The conditions of spinal canal stenosis were evaluated according to the grading system of spinal canal stenosis of cervical and lumbar spine proposed by Lee et al,and the number of cervical verte-brae with a stenosis score ≥1,score at the narrowest part of cervical spinal canal,and the total score of cervical stenosis,as well as the number of lumbar vertebrae with a stenosis score ≥1,score at the narrowest part of lumbar spinal canal,and the total score of lumbar stenosis were calculated.Intergroup comparisons were performed using t tests,chi-square tests,and Mann-Whitney U tests.For the statistic data with statisti-cal differences between the two groups,receiver operating characteristic(ROC)curve was used to determine op-timal thresholds for each parameter,and the area under the ROC curve(AUC)and its corresponding 95％ con-fidence interval(CI)were calculated.Multivariate logistic regression analysis was conducted to identify radiolog-ical predictive factors for non-improvement of lumbar symptoms in TSS patients.Results:The non-improvement group was significantly higher than the improvement group in the total score of lumbar stenosis(5.00±1.68 vs 2.68±1.23,P＜0.001),the number of lumbar vertebrae with a stenosis score≥1(2.47±0.84 vs 1.86±0.95,P=0.004),and the prevalence of redundant nerve roots(14/18 vs 6/13,P=0.017).The AUC of the total lumbar stenosis score was 0.864(P＜0.001,95％CI 0.779-0.950),with an optimal threshold of 3.5(sensitivity:81.3％;specificity:75.7％).The AUC of the number of lumbar vertebrae with a stenosis score ≥1 was 0.691(P=0.007;95％CI 0.565-0.817),with an optimal threshold of 1.5(sensitivity:87.5％;specificity:56.8％).Multivariate logistic regression showed that the number of lumbar spinal stenosis＞1.5(OR=1.493;95％CI 0.392-5.686;P=0.557)and presence of redundant nerve roots(OR=2.815;95％CI 0.740-10.711;P=0.129)had no significant relationship with improvement of lumbar symptoms.The total lumbar stenosis score＞3.5 was significantly related with improvement of lumbar symptoms(OR=10.983;95％CI 3.261-36.994;P＜0.001),which was an independent risk factor for non-improvement in lumbar symtoms after initial cervical decompression in TSS patients.Conclusions:When the total score of lumbar spinal stenosis exceeds 3.5 in TSS patients,the possibility of improvement in lumbar symptoms after initial cervical decompression is small.

Objective To study the role of photobiomodulation(PBM)in promoting the repair of spinal cord injury(SCI)by regulating microglial cells.Methods Forty-five C57BL/6J mice were randomly divided into the sham operation(Sham)group,surgery(SCI)group and the treatment(SCI+PBM)group,with 15 mice in each.After laminectomy of the T10 vertebral body in the three groups of mice,the SCI group and the SCI+PBM group were used to construct the model of spinal cord hemisection.The SCI+PBM group received immediate PBM treatment after spinal cord injury,while the other two groups did not.On the 1st,3rd,7th,14th,21st and 28th days(D1,D3,D7,D14,D21,D28)after the operation,the Basso Mouse Scale(BMS)was used to assess the recovery of the hind limb motor function of the mice.On the 28th day post operatively,immunofluorescence was used to detect the changes of neurons in the areas of injury in the three groups of mice.Quantitative real-time PCR and Western blotting experiments were used to detect the phenotypic changes of BV2 cells under the interventions of PBM with inflammatory stimulation.Western blotting experiments were conducted to detect the effects of PBM on the nuclear factor kappa-B(NF-κB)pathway.Results On the 28th day after the operation,the results of the mouse motor assessment showed that the BMS scores and related behaviors of the mice in the SCI+PBM group were better than those of the mice in the SCI group(P＜0.05),and the neurons in the SCI+PBM group far outnumbered those in the SCI group(P＜0.05).The results of quantitative real-time PCR and Western blotting experiments showed that on the 14th day after the operation,PBM promoted the activation of M2-type microglial cells in vivo but inhibited the activation of M1-type microglial cells.In vitro experiments confirmed that PBM could promote the polarization of BV2 cells towards M2-type microglial cells.In addition,PBM inhibited the activation of the NF-κB pathway in injured spinal cords and in activated BV2 cells.Conclusion PBM can promote the repair of spinal cord injury in SCI mice by promoting microglial cells through inhibiting the NF-κB pathway.

Microbial communities such as those residing in the human gut are highly diverse and complex, and many with important implications for health and diseases. The effects and functions of these microbial communities are determined not only by their species compositions and diversities but also by the dynamic intra- and inter-cellular states at the transcriptional level. Powerful and scalable technologies capable of acquiring single-microbe-resolution RNA sequencing information in order to achieve a comprehensive understanding of complex microbial communities together with their hosts are therefore utterly needed. Here we report the development and utilization of a droplet-based smRNA-seq (single-microbe RNA sequencing) method capable of identifying large species varieties in human samples, which we name smRandom-seq2. Together with a triple-module computational pipeline designed for the bacteria and bacteriophage sequencing data by smRandom-seq2 in four human gut samples, we established a single-cell level bacterial transcriptional landscape of human gut microbiome, which included 29,742 single microbes and 329 unique species. Distinct adaptive response states among species in Prevotella and Roseburia genera and intrinsic adaptive strategy heterogeneity in Phascolarctobacterium succinatutens were uncovered. Additionally, we identified hundreds of novel host-phage transcriptional activity associations in the human gut microbiome. Our results indicated that smRandom-seq2 is a high-throughput and high-resolution smRNA-seq technique that is highly adaptable to complex microbial communities in real-world situations and promises new perspectives in the understanding of human microbiomes.
Humans ; Gastrointestinal Microbiome/genetics* ; Bacteriophages/physiology* ; High-Throughput Nucleotide Sequencing ; Sequence Analysis, RNA/methods* ; Bacteria/virology*

Objectives:To investigate the relationship between the improvement of lumbar symptoms and imaging parameters in patients with tandem spinal stenosis(TSS)primarily manifesting as cervical spondylotic myelopathy(CSM)after initial cervical decompression surgery,and to explore related imaging predictive factors.Methods:A retrospective analysis was conducted on 69 TSS patients who underwent primary cervical decom-pression surgery,with an average age of 64.3±10.5 years(ranging from 41 to 86 years old)and a follow-up period of 33.8±5.5 months(ranging from 24 to 48 months).Preoperative symptoms and signs,Nurick gait clas-sification,and preoperative and final follow-up Japanese Orthopaedic Association(JOA)scores for both the cer-vical and lumbar spine were recorded and analyzed.The patients were divided into an improvement group(n=37)and a non-improvement group(n=32)based on the improvement conditions of lumbar spine JOA scores at the final follow-up.Imaging parameters were measured including spinal cord compression ratio,cross-sectional area of the dural sac at the narrowest point of the cervical spinal cord,the ratio of the vertebral canal to the vertebral body and the actual spinal canal width from C3 to C7,and the actual width of the vertebral canal from L1 to L5.The conditions of spinal canal stenosis were evaluated according to the grading system of spinal canal stenosis of cervical and lumbar spine proposed by Lee et al,and the number of cervical verte-brae with a stenosis score ≥1,score at the narrowest part of cervical spinal canal,and the total score of cervical stenosis,as well as the number of lumbar vertebrae with a stenosis score ≥1,score at the narrowest part of lumbar spinal canal,and the total score of lumbar stenosis were calculated.Intergroup comparisons were performed using t tests,chi-square tests,and Mann-Whitney U tests.For the statistic data with statisti-cal differences between the two groups,receiver operating characteristic(ROC)curve was used to determine op-timal thresholds for each parameter,and the area under the ROC curve(AUC)and its corresponding 95％ con-fidence interval(CI)were calculated.Multivariate logistic regression analysis was conducted to identify radiolog-ical predictive factors for non-improvement of lumbar symptoms in TSS patients.Results:The non-improvement group was significantly higher than the improvement group in the total score of lumbar stenosis(5.00±1.68 vs 2.68±1.23,P＜0.001),the number of lumbar vertebrae with a stenosis score≥1(2.47±0.84 vs 1.86±0.95,P=0.004),and the prevalence of redundant nerve roots(14/18 vs 6/13,P=0.017).The AUC of the total lumbar stenosis score was 0.864(P＜0.001,95％CI 0.779-0.950),with an optimal threshold of 3.5(sensitivity:81.3％;specificity:75.7％).The AUC of the number of lumbar vertebrae with a stenosis score ≥1 was 0.691(P=0.007;95％CI 0.565-0.817),with an optimal threshold of 1.5(sensitivity:87.5％;specificity:56.8％).Multivariate logistic regression showed that the number of lumbar spinal stenosis＞1.5(OR=1.493;95％CI 0.392-5.686;P=0.557)and presence of redundant nerve roots(OR=2.815;95％CI 0.740-10.711;P=0.129)had no significant relationship with improvement of lumbar symptoms.The total lumbar stenosis score＞3.5 was significantly related with improvement of lumbar symptoms(OR=10.983;95％CI 3.261-36.994;P＜0.001),which was an independent risk factor for non-improvement in lumbar symtoms after initial cervical decompression in TSS patients.Conclusions:When the total score of lumbar spinal stenosis exceeds 3.5 in TSS patients,the possibility of improvement in lumbar symptoms after initial cervical decompression is small.

Objective:To summarize the clinical characteristics of elderly patients with stage Ⅰ diffuse large B-cell lymphoma (DLBCL) and analyze the factors associated with prognosis.Methods:A case series study was conducted by retrospectively collecting clinical data from patients aged over 60 years with newly diagnosed stage Ⅰ DLBCL across 20 medical centers in Jiangsu Province, China, between June 2010 and April 2023. The involved site, classification and treatment plan were summarized. The primary endpoints were progression-free survival (PFS) and overall survival (OS). Statistical analyses were performed using the Kaplan-Meier method, and Cox regression model.Results:The study included 255 patients with a median age of 69 years, of whom 130 (51.0%) were male, 66 (25.9%) were aged ≥75 years and 26 (10.1%) had a high Charlson Comorbidity Index (CCI) score of ≥2. Extranodal involvement was observed in 163 (63.9%) patients, with the stomach (37.4%, 61/163), intestine (19.0%, 31/163), testes (11.0%, 18/163), and breast (7.4%, 12/163) being the most frequently affected sites. The non-germinal center B-cell (non-GCB) subtype was prevalent in 63.7% of patients (142/223), with no significant difference between the nodal and extranodal groups ( P=0.681). Furthermore, 73.9% (184/249) and 11.7% (29/249) of patients received the R-CHOP (rituximab, cyclophosphamide, doxorubicin, vincristine, prednisone) and R-miniCHOP regimen, respectively. The overall 3-year PFS rate was 81.5%, and the 3-year OS rate was 85.6%. Patients aged ≥75 years ( HR=2.910, 95% CI 1.565-5.408, P=0.001) and/or with a CCI score ≥2 ( HR=2.324, 95% CI 1.141-4.732, P=0.020) had a significantly poorer PFS. Incorporating age ≥75 years and CCI score ≥2 into the stage-modified international prognostic index (sm-IPI) can better stratify the prognosis of elderly patients with stage Ⅰ DLBCL. The 3-year PFS rate was 48.7% in the high-risk group versus 85.7% in the low-risk group ( P<0.001). Conclusions:Our findings show that the elderly patients with stage Ⅰ DLBCL were predominantly characterized by extranodal involvement (particularly in the stomach and intestinal tract) and non-GCB subtype. Age ≥75 years and CCI ≥2 were identified as independent prognostic factors. The newly established sm-IPI-75-CCI incorporating these factors demonstrated superior prognostic discrimination compared to conventional risk assessment systems.

Objectives:To evaluate the clinical values of cervical vertebral bone quality(CVBQ)score and cervical endplate bone quality(CEBQ)score in predicting the settlement of Zero Profile(Zero-P)cage after an-terior cervical discectomy and fusion(ACDF).Methods:A retrospective analysis was performed on 72 patients who underwent ACDF with Zero-P cage in the Second Affiliated Hospital of Soochow University.General pa-tient information(including sex,age,comorbidity),laboratory parameters(such as blood calcium and blood glu-cose),surgical details(surgical level and cage type),and imaging data(preoperative cervical MRI and anteropos-terior and lateral X-rays within one week and after more than three months)were collected.On the lateral X-rays taken within one week and＞3 months postoperatively,the heights of the upper and lower margins of vertebrae were measured,and the difference between was defined as the cage subsidence distance.Patients with a subsidence distance ≥ 2mm were assigned to the subsidence group,and those with＜2mm subsidence distance were divided to the non-subsidence group.On preoperative cervical sagittal T1-weighted MRI,plac-ing regions of interest(ROIs)in the medullary region of adjacent vertebral bodies,the subchondral bone region of the endplates,and the cerebrospinal fluid(CSF)in the cerebellomedullary cistern.CVBQ and CEBQ values were the ratios of the average signal intensity of the medullary region of the surgical adjacent vertebral bodies(for CVBQ)and the subchondral bone region of the endplates(for CEBQ)to the signal intensity of the cere-brospinal fluid in the cerebellomedullary cistern.A stratified analysis by gender was conducted to further clarify whether the predictive value of bone quality scores for subsidence is influenced by gender factors.The Pearson correlation coefficient was used to assess the relationship of CVBQ and CEBQ with cage subsidence distance.Receiver operating characteristic(ROC)curves were applied to evaluate the diagnostic efficacy of CVBQ and CEBQ for cage subsidence.Univariate logistic regression analysis was performed to screen for po-tential risk factors,after that age and diabetes,which showed statistical significance,along with CVBQ and CEBQ,were incorporated into the multivariate analysis to assess their independent effects.Results:Cage sub-sidence occurred in 14 patients(subsidence rate:19.4％).Compared with the non-subsidence group,the subsi-dence group of patients was older(male:61.4±16.5 years vs 51.1±10.8 years,P=0.049;female:62.6±13.1 years vs 51.2±7.8 years,P=0.005)and had a higher proportion of patients with diabetes(male:42.9％vs 3.4％,P=0.018;female:42.9％vs 6.9％,P=0.040).Both CVBQ and CEBQ were significantly higher in the subsidence group(CVBQ-male:2.75±0.73 vs 2.02±0.53,P=0.004;female:2.84±0.69 vs 2.00±0.40,P=0.005;CEBQ-male:2.82±0.688 vs 2.05±0.56,P=0.004;female:2.94±0.68 vs 2.05±0.42,P=0.002).Pearson correlation analysis re-vealed a moderate positive correlation between both CVBQ(r=0.58,P＜0.001)and CEBQ(r=0.59,P＜0.001)with subsidence distance.ROC curve analysis indicated that both CVBQ(AUC=0.83)and CEBQ(AUC=0.85)had good predictive values for subsidence,with CEBQ showing slightly better predictive performance.Univariate logistic regression analysis identified age,diabetes,CEBQ,and CVBQ as risk factors for subsidence(P＜0.05).Multivariate analysis showed that after adjusting for age and diabetes,both CEBQ(OR=11.466,P=0.004)and CVBQ(OR=8.804,P=0.005)remained independent risk factors for subsidence,while age and diabetes lost in-dependent significance.The strength of association with subsidence was greater in CEBQ than in CVBQ.Conclusions:Patients with higher CVBQ and CEBQ scores are more likely to experience fusion cage subsi-dence,and both CEBQ and CVBQ can be used to predict cage subsidence in patients after single-level ACDF,CEBQ has better predictive ability than CVBQ.

Objective·To explore the function and potential mechanism of suppressor of zeste 12(SUZ12)in hepatocellular carcinoma(HCC).Methods·The expression of SUZ12 in HCC patients was analyzed using R language in liver cancer datasets,and relevant survival curves were drawn.Stable knockdown of SUZ12 was established in the liver cancer cell lines LM3 and Huh7.The knockdown efficiency of SUZ12 was assessed using quantitative real-time PCR(qPCR)and Western blotting.Cell proliferation ability was assessed using CCK-8 assay and colony formation assay.Using the hydrodynamic tail vein injection(HTVI)method,Suz12 was knocked out in the livers of fully immunocompetent mice to explore its tumorigenic function in vivo.The molecular mechanism of SUZ12 regulating HCC was explored using The Cancer Genome Atlas(TCGA)database.R language was used to analyze the relationship between SUZ12 and the expression of cancer stem cell(CSC)markers as well as key glycolysis-related genes.Findings were validated in liver cancer cell lines and mouse tumor tissues.Results·The expression of SUZ12 in liver cancer tissues was higher than in adjacent non-tumor tissues,and its expression increased with higher tumor stage.HCC patients with high SUZ12 expression had poorer prognoses.In LM3 and Huh7 liver cancer cell lines,stable knockdown of SUZ12 reduced cell proliferation ability.In the de novo MYC/Trp53-/-mouse liver cancer model,tumor nodule number and size,and tumor burden in liver tissue were reduced after endogenous knockout of Suz12.TCGA analysis showed that high SUZ12 expression in HCC was enriched in multiple tumor proliferation-and metabolism-related pathways.The expression of SUZ12 was positively correlated with CSC markers and key genes in glycolysis pathway.The mRNA levels of CSC markers and key genes in glycolysis pathway were decreased in liver cancer cell lines with stable SUZ12 knockdown and Suz12 knockout mouse HCC tissues.Conclusion·The expression of SUZ12 is significantly increased in HCC patients and is associated with poor prognosis.Stable knockdown of SUZ12 weakens the proliferative ability of liver cancer cells.Knockout of Suz12 in mice in vivo can suppress the occurrence and development of HCC.The high expression of SUZ12 maintains the CSC pool,induces metabolic reprogramming,and promotes the occurrence and progression of HCC.SUZ12 can serve as a potential biomarker for poor prognosis and a novel target for potential therapeutic intervention in HCC.

Objectives:To evaluate the clinical values of cervical vertebral bone quality(CVBQ)score and cervical endplate bone quality(CEBQ)score in predicting the settlement of Zero Profile(Zero-P)cage after an-terior cervical discectomy and fusion(ACDF).Methods:A retrospective analysis was performed on 72 patients who underwent ACDF with Zero-P cage in the Second Affiliated Hospital of Soochow University.General pa-tient information(including sex,age,comorbidity),laboratory parameters(such as blood calcium and blood glu-cose),surgical details(surgical level and cage type),and imaging data(preoperative cervical MRI and anteropos-terior and lateral X-rays within one week and after more than three months)were collected.On the lateral X-rays taken within one week and＞3 months postoperatively,the heights of the upper and lower margins of vertebrae were measured,and the difference between was defined as the cage subsidence distance.Patients with a subsidence distance ≥ 2mm were assigned to the subsidence group,and those with＜2mm subsidence distance were divided to the non-subsidence group.On preoperative cervical sagittal T1-weighted MRI,plac-ing regions of interest(ROIs)in the medullary region of adjacent vertebral bodies,the subchondral bone region of the endplates,and the cerebrospinal fluid(CSF)in the cerebellomedullary cistern.CVBQ and CEBQ values were the ratios of the average signal intensity of the medullary region of the surgical adjacent vertebral bodies(for CVBQ)and the subchondral bone region of the endplates(for CEBQ)to the signal intensity of the cere-brospinal fluid in the cerebellomedullary cistern.A stratified analysis by gender was conducted to further clarify whether the predictive value of bone quality scores for subsidence is influenced by gender factors.The Pearson correlation coefficient was used to assess the relationship of CVBQ and CEBQ with cage subsidence distance.Receiver operating characteristic(ROC)curves were applied to evaluate the diagnostic efficacy of CVBQ and CEBQ for cage subsidence.Univariate logistic regression analysis was performed to screen for po-tential risk factors,after that age and diabetes,which showed statistical significance,along with CVBQ and CEBQ,were incorporated into the multivariate analysis to assess their independent effects.Results:Cage sub-sidence occurred in 14 patients(subsidence rate:19.4％).Compared with the non-subsidence group,the subsi-dence group of patients was older(male:61.4±16.5 years vs 51.1±10.8 years,P=0.049;female:62.6±13.1 years vs 51.2±7.8 years,P=0.005)and had a higher proportion of patients with diabetes(male:42.9％vs 3.4％,P=0.018;female:42.9％vs 6.9％,P=0.040).Both CVBQ and CEBQ were significantly higher in the subsidence group(CVBQ-male:2.75±0.73 vs 2.02±0.53,P=0.004;female:2.84±0.69 vs 2.00±0.40,P=0.005;CEBQ-male:2.82±0.688 vs 2.05±0.56,P=0.004;female:2.94±0.68 vs 2.05±0.42,P=0.002).Pearson correlation analysis re-vealed a moderate positive correlation between both CVBQ(r=0.58,P＜0.001)and CEBQ(r=0.59,P＜0.001)with subsidence distance.ROC curve analysis indicated that both CVBQ(AUC=0.83)and CEBQ(AUC=0.85)had good predictive values for subsidence,with CEBQ showing slightly better predictive performance.Univariate logistic regression analysis identified age,diabetes,CEBQ,and CVBQ as risk factors for subsidence(P＜0.05).Multivariate analysis showed that after adjusting for age and diabetes,both CEBQ(OR=11.466,P=0.004)and CVBQ(OR=8.804,P=0.005)remained independent risk factors for subsidence,while age and diabetes lost in-dependent significance.The strength of association with subsidence was greater in CEBQ than in CVBQ.Conclusions:Patients with higher CVBQ and CEBQ scores are more likely to experience fusion cage subsi-dence,and both CEBQ and CVBQ can be used to predict cage subsidence in patients after single-level ACDF,CEBQ has better predictive ability than CVBQ.

Objective:To explore the construction of an evaluation model for aortic root anatomy and calcium burden in patients with bicuspid aortic valve (BAV) stenosis before transcatheter aortic valve replacement (TAVR) based on deep learning (DL) algorithms.Methods:A retrospective collection of 362 BAV stenosis patients who underwent TAVR from September 2023 to May 2024 was performed. All patients underwent cardiac CT angiography. The patients were divided into training group ( n=104), internal validation group ( n=206), and external validation group ( n=52). A DL model was trained on the training dataset to assess aortic root anatomy and calcification burden. The evaluation included the segmentation accuracy of the algorithm, the measurement performance of key anatomical structures (i.e., valve leaflets and type-1 and type-2 fusion raphe), and calcification burden, as well as the measurement efficiency. Overall segmentation performance was assessed using the average Dice coefficient (ADC). The fine-scale segmentation quality was validated by the 95th-percentile Hausdorff distance (HD-95) and the average symmetric surface distance (ASSD). The consistency of the measurement results was assessed using the Pearson correlation coefficient and the intraclass correlation coefficient ( ICC) with a two-way mixed model for absolute agreement. In addition, the total time and total mouse movement distance required for manual assessment versus the DL model on the validation datasets were recorded and compared. Results:The algorithm demonstrated excellent segmentation performance on aortic root anatomical targets, achieving outstanding consistency within both internal and external validation datasets (0.955