Objective:To explore the clinical and imaging features of the concomitant gastric-type endocervical adenocarcinoma(G-EAC)in female patients with Peutz-Jeghers syndrome(PJS),so as to improve the early diagnostic level for PJS.Methods:A retrospective analysis was performed on the clinical and imaging data of 12 patients who were confirmed as PJS with G-EAC at Air Force Medical Center,PLA from June 2021 to December 2024.The 12 patients all received computed tomography(CT)examination before surgery,and 6 cases among of them received magnetic resonance imaging(MRI)examination at the same time.The features of clinical performance,and imaging features of CT and MR in all patients were analyzed.Results:In 12 G-EAC patients,7 cases(58.3%)did not occurred any abnormally relative symptoms of gynaecology and obstetrics,while 5 cases(41.7%)occurred increase of vaginal drainage and/or vaginal bleeding.The results of imaging examination indicated that 12 cases occurred concomitant cyst,including 5 cases(41.7%)with large cysts,6 cases(50.0%)that micro cysts coexisted with large cysts,1 case(8.3%)that solid mass combined with small amount of micro cysts,and 4 cases(33.3%)that combined with small amount of uterine cavity effusion.MR performance was the most of occurrences were quasi-circular object with long T1/T2 signals,and the sequences of diffusion weighted imaging(DWI)appeared there was no diffusion or mild restriction,and apparent diffusion coefficient(ADC)appeared slightly high signal.The tumors that mainly were solid components appeared longer T2 signals,which diffusion was limited,and which ADC values appeared low signals.CT images of them presented enlarged cervixes,and mixed-density cystic and solid nodules and mass shadows at local tissues,and cellular change at local lesions.There was not significant strengthen at the cystic fields of the lesion with enhanced scan,and the solid fields appeared uneven enhancement.The accuracy rates both of preoperative CT and MR diagnosis were 50.0%.Conclusion:The clinical appearance,and imaging futures of CT and MR examinations of PJS female patients with G-EAC are respectively:partial patients occur vaginal drainage and/or vaginal bleeding,the most of tumors often occurs at the entire cervix(includes upper segment),often combines with cystic changes,and often appears infiltrating growth.The clinical PJS appearance,CT and MR examinations contribute to early diagnosis for G-EAC.

Objective:To establish a three-dimensional U-shaped residual coordinated attention network (URCA-Net) based on enhanced CT images for small bowel polyp detection and analyze its application effectiveness in intelligent detection of small bowel polyps.Methods:Abdominal CT data of patients with small bowel polyps were collected from the Air Force Medical Center between June 2019 and July 2023. All patients underwent bowel preparation followed by thin-slice spiral CT scanning to obtain enhanced CT arterial phase images. The data were randomly divided into training, validation and test sets in an 8∶1∶1 ratio. The URCA-Net deep learning model was used for small bowel polyp segmentation. The training set was used for model parameter training, the validation set for hyperparameter adjustment and monitoring of model generalization performance and the test set for final unbiased evaluation of the model. An early intelligent detection model for small bowel polyps was constructed, and its performance was evaluated. Evaluation metrics included pixel-level metrics for the segmentation task [Dice Similarity Coefficient (DSC)], as well as sensitivity and precision for polyp detection. A two-stage segmentation strategy was adopted: the first stage segmented the small bowel region to remove external interference, and the second stage performed polyp segmentation within the small bowel region.Results:A total of 78 subjects were included in the study, with an average age of (54±7) years. A total of 23 400 scan images were extracted, including 136 hyperplastic polyps, 298 hamartomatous polyps, 14 adenomatous polyps, and 4 cancerous polyps. On the test set, the average DSC for the first stage (small bowel segmentation) and the second stage (polyp segmentation) was 0.790 and 0.314, respectively. In the second stage task (polyp segmentation based on small bowel region), the polyp segmentation DSC increased to 0.701, with a precision of 0.836 (95% CI: 0.700-0.972) and a sensitivity of 0.759 (95% CI: 0.631-0.888) for polyp detection. Conclusion:The URCA-Net deep learning technique demonstrates good auxiliary diagnostic effectiveness in small bowel polyp detection and can provide a reference for screening and detection of small bowel polyps. The model is capable of generating high-quality segmentation results, which could facilitate evaluating polyp lesion morphology and provide support for downstream tasks such as preoperative navigation and risk prediction.

Objective:To investigate the characteristics and determinants of total scores of cerebral small vessel disease (CSVD) and to analyze the factors associated with enlarged perivascular space (EPVS) grading in pilots.Methods:The physical examination data of 72 pilots who were hospitalized and diagnosed with CSVD by MRI in the Air Force Medical Center (General Hospital of Air Force) between 2019 and 2022 was retrospectively analyzed. The pilots were grouped by the total CSVD score (0, 1, 2, 3, 4 points), and the distribution of CSVD imaging biomarkers was compared across groups. The severity of EPVS was classified into 3 levels: none or mild (0-10), moderate (11-20), and severe (>20). The impact of vascular risk factors on the total CSVD score and EPVS grading was analyzed.Results:The results of the total CSVD score showed that there were 19 cases (26.39%) with a score of 0, 43 cases (59.72%) with a score of 1, 10 cases (13.89%) with a score of 2, and 0 case with scores of 3 or 4. Among those who scored 1, there were 2 cases (4.65%) of lacunar infarction (LA), 1 case (2.33%) of moderate to severe white matter hyperintensity (WMH), 2 cases (4.65%) of cerebral microbleed (CMB), and 38 cases (88.37%) of moderate and severe EPVS. Among those who scored 2, there were 7 cases (70.00%) of LA combined with EPVS, 2 cases (20.00%) of CMB combined with EPVS, and 1 case (10.00%) of WMH combined with EPVS. According to the CSVD imaging classification of these pilots, there were 9 cases (12.50%) of LA, 52 cases (72.22%) of WMH, 4 cases (5.60%) of CMB and 61 cases (84.72%) of EPVS. Multiple ordered Logistic regression analysis showed that systolic blood pressure ( OR=1.068, 95% CI: 1.016-1.122) and high-density lipoprotein cholesterol ( OR=0.111, 95% CI: 0.015-0.843) made a difference in the total CSVD score. High-density lipoprotein cholesterol ( OR=0.166, 95% CI: 0.031-0.893) could affect the EPVS grading. Spearman′s correlation analysis showed that the systolic blood pressure level was positively correlated with the total CSVD score ( r=0.299, P=0.011), while the high-density lipoprotein cholesterol level was negatively correlated with the total CSVD score and EPVS grading ( r=-0.313, -0.263, P=0.041, 0.026). Conclusions:The total CSVD score of pilots is at a mild level with EPVS as the leading contributor. The systolic blood pressure and the high-density lipoprotein cholesterol level are determinants for the total CSVD score, while the high-density lipoprotein cholesterol level is a determinant for the EPVS grading of pilots. Blood pressure control and lipid regulation can go a long way towards preventing CSVD in pilots. The total CSVD score is of value for stratified evaluation and individual identification of pilots with CSVD.

Objective:To analyze the degree of intervertebral disc degeneration above and below the vertebral body in pilots with lumbar spondylolysis.Methods:The medical records of 66 pilots who underwent lumbar imaging examinations at the Air Force Medical Center between September 2011 and January 2025 were retrospectively analyzed. The degree of intervertebral disc degeneration was compared between 33 pilots with lumbar spondylolysis and another 33 age-matched pilots without spondylolysis. The spondylolysis group was divided into subgroups with/without spondylolisthesis and unilateral/bilateral subgroups. The degree of disc degeneration above and below the vertebral body was compared between these subgroups using the modified Pfirrmann grading system.Results:The modified Pfirrmann scores of the discs above and below the spondylolytic vertebral body in the spondylolysis group were significantly higher than those at the corresponding segments in the non-spondylolysis group ( Z=-2.39, -4.41, P=0.017,<0.001). In pilots with spondylolysis accompanied by spondylolisthesis, the modified Pfirrmann score of the disc below the slipped vertebral body was significantly higher than that in pilots without spondylolisthesis ( Z=-3.02, P=0.003). However, there was no statistically significant difference in the modified Pfirrmann score of the disc above the slipped vertebral body between pilots with and without spondylolisthesis ( P>0.05). No significant differences were observed in the modified Pfirrmann scores of the discs above and below the vertebral body between pilots with unilateral and bilateral spondylolysis (both P>0.05). Conclusions:Pilots with lumbar spondylolysis exhibit severe intervertebral disc degeneration above and below the affected vertebral body. Spondylolisthesis can continue to exacerbate degeneration in the disc inferior to the affected vertebra.

Objective To investigate the clinical efficacy of the traditional Chinese medicine(TCM)throat opening and brightening method in treating unilateral vocal cord paralysis(UVCP).Methods Sixty patients with UVCP were prospectively collected and randomly assigned to two groups:the Chinese herbal medicine group(trea-ted with Buyang Huanwu Decoction,n=30)and the throat opening and brightening method group(treated with TCM throat opening and brightening method,n=30).The clinical studies that had utilized injection laryngoplasty for the treatment of UVCP(historical control group).Evaluation indicators included the voice handicap index-10(VHI-10),GRBAS-G,objective acoustic measurements of voice(vocal intensity,F0,shimmer,jitter,HNR),and aerodynamic measurements(maximum phonation time,MPT).Results Before treatment,no significant differences were observed between the two groups in all the evaluation indicators(P＞0.05).Post-treatment,the throat open-ing and brightening method group demonstrated significant improvements in VHI-10,GRBAS-G,shimmer,jitter,HNR,and MPT compared to pre-treatment values(P＜0.01),and these improvements were superior to those in the Chinese herbal medicine group.Pre-treatment VHI-10,GRBAS-G,and shimmer scores in the throat opening and brightening method group were significantly higher than those in the historical literature group(P＜0.01).Af-ter treatment,no significant differences were noted in any assessed parameters between the two groups(P＞0.05).Conclusion The TCM throat opening and brightening method significantly enhances phonatory function and quality of life in patients with UVCP,showing comparable efficacy to injection laryngoplasty.

Breast cancer is a highly heterogeneous malignant tumor,and different individuals have great differences in pathological manifestations,tissue structure,morphology,texture characteristics and treatment effects.Evaluation of breast cancer heterogeneity is of great significance for the design of individualized treatment plan and the prediction of curative effect.At present,multi-modal MRI can sensitively evaluate the extent,shape,margin,internal enhancement mode,time signal intensity curve,apparent diffusion coefficient value and other information of the lesion,which is expected to effectively predict the heterogeneity of breast cancer.In particular,artificial intelligence has high clinical guiding significance in the evaluation of breast cancer heterogeneous multimodal MRI imaging.The purpose of this paper is to review the research progress of artificial intelligence-based multimodal MRI evaluation of breast cancer heterogeneity,so as to improve the level of individualized diagnosis and treatment of breast cancer.

Objective To investigate the clinical efficacy of the traditional Chinese medicine(TCM)throat opening and brightening method in treating unilateral vocal cord paralysis(UVCP).Methods Sixty patients with UVCP were prospectively collected and randomly assigned to two groups:the Chinese herbal medicine group(trea-ted with Buyang Huanwu Decoction,n=30)and the throat opening and brightening method group(treated with TCM throat opening and brightening method,n=30).The clinical studies that had utilized injection laryngoplasty for the treatment of UVCP(historical control group).Evaluation indicators included the voice handicap index-10(VHI-10),GRBAS-G,objective acoustic measurements of voice(vocal intensity,F0,shimmer,jitter,HNR),and aerodynamic measurements(maximum phonation time,MPT).Results Before treatment,no significant differences were observed between the two groups in all the evaluation indicators(P＞0.05).Post-treatment,the throat open-ing and brightening method group demonstrated significant improvements in VHI-10,GRBAS-G,shimmer,jitter,HNR,and MPT compared to pre-treatment values(P＜0.01),and these improvements were superior to those in the Chinese herbal medicine group.Pre-treatment VHI-10,GRBAS-G,and shimmer scores in the throat opening and brightening method group were significantly higher than those in the historical literature group(P＜0.01).Af-ter treatment,no significant differences were noted in any assessed parameters between the two groups(P＞0.05).Conclusion The TCM throat opening and brightening method significantly enhances phonatory function and quality of life in patients with UVCP,showing comparable efficacy to injection laryngoplasty.

Objective:To establish a three-dimensional U-shaped residual coordinated attention network (URCA-Net) based on enhanced CT images for small bowel polyp detection and analyze its application effectiveness in intelligent detection of small bowel polyps.Methods:Abdominal CT data of patients with small bowel polyps were collected from the Air Force Medical Center between June 2019 and July 2023. All patients underwent bowel preparation followed by thin-slice spiral CT scanning to obtain enhanced CT arterial phase images. The data were randomly divided into training, validation and test sets in an 8∶1∶1 ratio. The URCA-Net deep learning model was used for small bowel polyp segmentation. The training set was used for model parameter training, the validation set for hyperparameter adjustment and monitoring of model generalization performance and the test set for final unbiased evaluation of the model. An early intelligent detection model for small bowel polyps was constructed, and its performance was evaluated. Evaluation metrics included pixel-level metrics for the segmentation task [Dice Similarity Coefficient (DSC)], as well as sensitivity and precision for polyp detection. A two-stage segmentation strategy was adopted: the first stage segmented the small bowel region to remove external interference, and the second stage performed polyp segmentation within the small bowel region.Results:A total of 78 subjects were included in the study, with an average age of (54±7) years. A total of 23 400 scan images were extracted, including 136 hyperplastic polyps, 298 hamartomatous polyps, 14 adenomatous polyps, and 4 cancerous polyps. On the test set, the average DSC for the first stage (small bowel segmentation) and the second stage (polyp segmentation) was 0.790 and 0.314, respectively. In the second stage task (polyp segmentation based on small bowel region), the polyp segmentation DSC increased to 0.701, with a precision of 0.836 (95% CI: 0.700-0.972) and a sensitivity of 0.759 (95% CI: 0.631-0.888) for polyp detection. Conclusion:The URCA-Net deep learning technique demonstrates good auxiliary diagnostic effectiveness in small bowel polyp detection and can provide a reference for screening and detection of small bowel polyps. The model is capable of generating high-quality segmentation results, which could facilitate evaluating polyp lesion morphology and provide support for downstream tasks such as preoperative navigation and risk prediction.

Breast cancer is a highly heterogeneous malignant tumor,and different individuals have great differences in pathological manifestations,tissue structure,morphology,texture characteristics and treatment effects.Evaluation of breast cancer heterogeneity is of great significance for the design of individualized treatment plan and the prediction of curative effect.At present,multi-modal MRI can sensitively evaluate the extent,shape,margin,internal enhancement mode,time signal intensity curve,apparent diffusion coefficient value and other information of the lesion,which is expected to effectively predict the heterogeneity of breast cancer.In particular,artificial intelligence has high clinical guiding significance in the evaluation of breast cancer heterogeneous multimodal MRI imaging.The purpose of this paper is to review the research progress of artificial intelligence-based multimodal MRI evaluation of breast cancer heterogeneity,so as to improve the level of individualized diagnosis and treatment of breast cancer.

Objective:To explore the clinical and imaging features of the concomitant gastric-type endocervical adenocarcinoma(G-EAC)in female patients with Peutz-Jeghers syndrome(PJS),so as to improve the early diagnostic level for PJS.Methods:A retrospective analysis was performed on the clinical and imaging data of 12 patients who were confirmed as PJS with G-EAC at Air Force Medical Center,PLA from June 2021 to December 2024.The 12 patients all received computed tomography(CT)examination before surgery,and 6 cases among of them received magnetic resonance imaging(MRI)examination at the same time.The features of clinical performance,and imaging features of CT and MR in all patients were analyzed.Results:In 12 G-EAC patients,7 cases(58.3%)did not occurred any abnormally relative symptoms of gynaecology and obstetrics,while 5 cases(41.7%)occurred increase of vaginal drainage and/or vaginal bleeding.The results of imaging examination indicated that 12 cases occurred concomitant cyst,including 5 cases(41.7%)with large cysts,6 cases(50.0%)that micro cysts coexisted with large cysts,1 case(8.3%)that solid mass combined with small amount of micro cysts,and 4 cases(33.3%)that combined with small amount of uterine cavity effusion.MR performance was the most of occurrences were quasi-circular object with long T1/T2 signals,and the sequences of diffusion weighted imaging(DWI)appeared there was no diffusion or mild restriction,and apparent diffusion coefficient(ADC)appeared slightly high signal.The tumors that mainly were solid components appeared longer T2 signals,which diffusion was limited,and which ADC values appeared low signals.CT images of them presented enlarged cervixes,and mixed-density cystic and solid nodules and mass shadows at local tissues,and cellular change at local lesions.There was not significant strengthen at the cystic fields of the lesion with enhanced scan,and the solid fields appeared uneven enhancement.The accuracy rates both of preoperative CT and MR diagnosis were 50.0%.Conclusion:The clinical appearance,and imaging futures of CT and MR examinations of PJS female patients with G-EAC are respectively:partial patients occur vaginal drainage and/or vaginal bleeding,the most of tumors often occurs at the entire cervix(includes upper segment),often combines with cystic changes,and often appears infiltrating growth.The clinical PJS appearance,CT and MR examinations contribute to early diagnosis for G-EAC.