Objective To analyze the effect of releasing the lower pulmonary ligament on right residual lung expansion after right upper lobe resection under different body mass index (BMI) levels. Methods The clinical data of patients who underwent thoracoscopic right upper lobe resection in the First Affiliated Hospital with Nanjing Medical University from 2021 to 2022 were retrospectively analyzed. Patients were divided into a group A (17 kg/m2＜BMI≤23 kg/m2), a group B (23 kg/m2＜BMI≤29 kg/m2) and a group C (BMI＞29 kg/m2) according to BMI. The presence of residual cavity was judged by chest X-ray at 7-10 days after operation, the degree of compensation change of the right main bronchus angle was measured, and the changes in lung volume were determined by CT three-dimensional reconstruction. Results A total of 157 patients who underwent thoracoscopic right upper lobe resection were included, including 71 males and 86 females, with an average age of (59.7±11.2) years. There were 50 patients in the group A, 75 patients in the group B, and 32 patients in the group C. In the group A, compared with those without releasing the lower pulmonary ligament, patients with releasing had a lower incidence of postoperative residual cavity (P=0.016), greater changes in bronchus angle (P<0.001), and smaller changes in lung volume (P<0.001). In the group B and C, there was no significant effect of releasing the lower pulmonary ligament on postoperative residual cavity, bronchus angle, and lung volume changes (P>0.05). Conclusion For patients with thin and long body shape and low BMI, releasing the lower pulmonary ligament is helpful to promote the expansion of the residual lung after right upper lobe resection and reduce the occurrence of postoperative residual cavity in patients.

ObjectiveTo clarify the expression of TRIM28 in non-M3 acute myeloid leukemia （AML） and its correlation with clinical indicators and prognosis， and to further explore the effect of TRIM28 expression levels on the proliferation and apoptosis of AML cells using small interfering RNA. MethodsThe GSE34577 dataset was analyzed using R software to compare TRIM28 expression between healthy controls and non-M3 acute myeloid leukemia （AML） patients. Clinical samples from non-M3 AML patients were collected， with TRIM28 expression levels measured using real-time quantitative PCR （qPCR）. The analysis focused on correlations between TRIM28 expression and various clinical indicators， treatment efficacy， and patient prognosis. Furthermore， small interfering RNA （siRNA） technology was employed to downregulate TRIM28 expression in human primary AML cells （HL60 cell line）. The effects on cell proliferation and apoptosis were then assessed through CCK-8 assays and flow cytometry， respectively. ResultsThe results showed that TRIM28 was up-regulated in non-M3 AML of both online database GSE34577 and clinical samples （P<0.000 1）， TRIM28 expression of new diagnosis group and relapsed refractory group was higher than iron deficiency anemia group （P<0.01）， and there was no significance between different French-American-British classification systems subtype. TRIM28 expression was higher in non-M3 AML patients with a poor genetic prognosis stratified as moderate than in the good prognosis group， and TRIM28 expression was associated with NPM1 combined with the FLT3-ITD mutation， positively correlated with age， bone marrow blast， peripheral blood blast and white blood cell， negatively correlated with hemoglobin. In addition， interference TRIM28 greatly inhibited cell proliferation and promoted cell apoptosis. ConclusionThis study reveals that TRIM28 is highly expressed in non-M3 AML and associated with prognosis， and plays a key role in the proliferation and apoptosis of AML cells， suggesting that TRIM28 may serve as a novel therapeutic target for non-M3 AML.

ObjectiveDiscriminating atypical hepatocellular carcinoma (HCC) from other malignancies in liver nodules classified as Liver Imaging Reporting and Data System category M (LR-M) remains a significant diagnostic challenge on conventional ultrasound examination. The LR-M category, originally intended to capture non-HCC malignancies, paradoxically contains up to 63% of atypical HCCs that deviate from classic enhancement patterns, leading to potential misdiagnosis and suboptimal treatment planning. While deep learning has shown promise in HCC diagnosis, most existing models rely exclusively on single-modality ultrasound, overlooking the diagnostic benefits of integrating complementary information from multiple imaging sources. To address this gap, we propose a novel attention-weighted tri-modal ultrasound network (TUS-Net) that integrates contrast-enhanced ultrasound (CEUS), B-mode ultrasound (BUS), and time-intensity curves (TICs) to improve diagnostic accuracy for these clinically challenging lesions. MethodsOur framework incorporates a three-dimensional convolutional neural network (C3D) backbone to extract spatiotemporal features from CEUS videos, capturing dynamic vascular patterns critical for lesion characterization. To effectively fuse complementary modalities, we introduce a dual-channel feature fusion module (DCFFM) that adaptively combines features from CEUS and BUS through channel-wise attention mechanisms, allowing the model to dynamically weigh the contribution of each modality based on diagnostic relevance. Additionally, we propose a temporal intensity feature fusion module (TIFFM) that leverages quantitative hemodynamic information from TICs to guide the model’s attention toward diagnostically critical temporal phases, such as arterial wash-in and portal venous washout. The model is further enhanced by automated lesion localization using YOLOX and class activation mapping for interpretability, ensuring that predictions align with clinically meaningful imaging features. ResultsEvaluated on a tri-modal ultrasound dataset comprising 161 patients with pathologically confirmed LR-M nodules (131 atypical HCC and 30 non-HCC malignancies), our model achieved an accuracy of 86.83%, a sensitivity of 92.50%, a specificity of 75.50%, and an AUC of 89.32% in screening atypical HCC. Compared to single-modality baselines, TUS-Net demonstrated superior specificity, a clinically critical metric given the higher risk associated with misclassifying non-HCC malignancies. Ablation studies confirmed the contribution of each module, with the full model outperforming both standard C3D and 3D ResNet backbones integrated with attention mechanisms. A reader study involving junior and senior radiologists further validated the clinical utility of AI assistance, showing consistent improvements in specificity and inter-reader consistency, particularly for less experienced clinicians. ConclusionThese results surpass existing benchmark models and demonstrate the potential of our approach to enhance diagnostic precision in clinically specific cases. By intelligently fusing multi-modal ultrasound data with attention-guided mechanisms, TUS-Net offers a reliable and interpretable tool that holds promise for improving the non-invasive diagnosis of atypical HCC in challenging LR-M liver nodules.

ObjectiveDiscriminating atypical hepatocellular carcinoma (HCC) from other malignancies in liver nodules classified as Liver Imaging Reporting and Data System category M (LR-M) remains a significant diagnostic challenge on conventional ultrasound examination. The LR-M category, originally intended to capture non-HCC malignancies, paradoxically contains up to 63% of atypical HCCs that deviate from classic enhancement patterns, leading to potential misdiagnosis and suboptimal treatment planning. While deep learning has shown promise in HCC diagnosis, most existing models rely exclusively on single-modality ultrasound, overlooking the diagnostic benefits of integrating complementary information from multiple imaging sources. To address this gap, we propose a novel attention-weighted tri-modal ultrasound network (TUS-Net) that integrates contrast-enhanced ultrasound (CEUS), B-mode ultrasound (BUS), and time-intensity curves (TICs) to improve diagnostic accuracy for these clinically challenging lesions. MethodsOur framework incorporates a three-dimensional convolutional neural network (C3D) backbone to extract spatiotemporal features from CEUS videos, capturing dynamic vascular patterns critical for lesion characterization. To effectively fuse complementary modalities, we introduce a dual-channel feature fusion module (DCFFM) that adaptively combines features from CEUS and BUS through channel-wise attention mechanisms, allowing the model to dynamically weigh the contribution of each modality based on diagnostic relevance. Additionally, we propose a temporal intensity feature fusion module (TIFFM) that leverages quantitative hemodynamic information from TICs to guide the model’s attention toward diagnostically critical temporal phases, such as arterial wash-in and portal venous washout. The model is further enhanced by automated lesion localization using YOLOX and class activation mapping for interpretability, ensuring that predictions align with clinically meaningful imaging features. ResultsEvaluated on a tri-modal ultrasound dataset comprising 161 patients with pathologically confirmed LR-M nodules (131 atypical HCC and 30 non-HCC malignancies), our model achieved an accuracy of 86.83%, a sensitivity of 92.50%, a specificity of 75.50%, and an AUC of 89.32% in screening atypical HCC. Compared to single-modality baselines, TUS-Net demonstrated superior specificity, a clinically critical metric given the higher risk associated with misclassifying non-HCC malignancies. Ablation studies confirmed the contribution of each module, with the full model outperforming both standard C3D and 3D ResNet backbones integrated with attention mechanisms. A reader study involving junior and senior radiologists further validated the clinical utility of AI assistance, showing consistent improvements in specificity and inter-reader consistency, particularly for less experienced clinicians. ConclusionThese results surpass existing benchmark models and demonstrate the potential of our approach to enhance diagnostic precision in clinically specific cases. By intelligently fusing multi-modal ultrasound data with attention-guided mechanisms, TUS-Net offers a reliable and interpretable tool that holds promise for improving the non-invasive diagnosis of atypical HCC in challenging LR-M liver nodules.

Objective: To establish a machine learning-based precision blood donor recruitment model at the county level and assess its generalizability and applicability. Methods: A retrospective study was conducted using blood donation and SMS recruitment data from the Taicang Branch of the Suzhou Blood Center between 2019 and 2024. Multiple machine learning algorithms were employed, including extreme gradient boosting, support vector machine, k-nearest neighbor, logistic regression, decision tree, random forest, and multilayer perceptron. These were combined with techniques such as synthetic minority oversampling, undersampling, and cost-sensitive learning (using MFE and MSFE loss functions). Model parameters were optimized through grid search to identify the best-performing model. Results: In a prospective comparative study against conventional methods, the machine learning models increased the recruitment success rate among high-willingness donors by an average of 129.15%, and the recruitment efficiency per SMS improved by 125.02% compared with the traditional method. Under full-scale SMS sending, the recruitment rate per SMS increased by 42.61%, and SMS sending efficiency improved by 31.77%, significantly enhancing recruitment performance. Conclusion: This study represents the first application of a machine learning-based precision donor recruitment model at the county-level in China. The precise recruitment framework not only improves recruitment efficiency and reduces recruitment costs but also demonstrates strong scalability and generalizability. It provides a scientific and feasible intelligent pathway to ensure the safety and sustainability of the blood supply.

Objective:To explore the genetic and clinical characteristics of Guizhou patients with enlarged vestibular aqueduct（EVA） syndrome through combined SLC26A4 variant analysis and clinical phenotype analysis. Methods:Seventy-two EVA patients underwent comprehensive genetic testing using a multiplex PCR-based deafness gene panel and next-generation sequencing（NGS）. The audiological and temporal bone imaging characteristics were compared across mutation subtypes. Results:A total of 27 pathogenic loci of SLC26A4 were detected in 72 patients, including c.919-2A>G in 79.2%（57/72）. A novel deletion（c.1703_1707+6del） was discovered. Among 65 cases, truncated mutations were 89.2%（58/65）, 52.3%（34/65）, 28（43.1%） and 7（10.8%）. No significant differences were observed in the midpoint diameter of the vestibular aqueduct and the incidence of incomplete partitioning typeⅡ（IP-Ⅱ） of the cochlea among the three groups of patients. Moreover, there was no difference in the midpoint diameter of different vestibular pipes or the combination with IP-Ⅱ. Conclusion:The most common mutation site of SLC26A4 in EVA patients in Guizhou is c.919-2A>G, though genotype-phenotype correlations remain elusive. The detection of 27 mutation sites and the discovery of new mutation sites suggested the precise diagnostic significance of NGS technology in EVA patients in Guizhou.
Humans ; Sulfate Transporters ; Vestibular Aqueduct/abnormalities* ; Mutation ; Membrane Transport Proteins/genetics* ; Hearing Loss, Sensorineural/genetics* ; Male ; Female ; Child ; Adolescent ; Child, Preschool ; Adult ; Young Adult ; Phenotype ; High-Throughput Nucleotide Sequencing

BACKGROUND: Immune checkpoint inhibitors (ICIs) have been included in various neoadjuvant therapy (NAT) regimens for non-small cell lung cancer (NSCLC). However, due to the relatively short period for the use of ICIs in NAT, patients' clinical outcomes with different regimens are uncertain. Our study aims to examine the efficacy of neoadjuvant immunotherapy (NAIT) for NSCLC patients and compare the overall survival (OS) and event-free survival (EFS) of patients receiving different NAT regimens. METHODS: This study retrospectively included 308 NSCLC patients treated with different NAT regimens and subsequent surgery in National Cancer Center between August 1, 2016 and July 31, 2022. Kaplan-Meier survival analysis and Cox proportional hazards regression analysis were conducted to evaluate the prognosis of patients. RESULTS: With a median follow-up of 27.5 months, the 1-year OS rates were 98.8% and 96.2%, and the 2-year OS rates were 96.6% and 85.8% in patients of the NAIT and neoadjuvant chemotherapy (NACT) group, respectively (hazard ratio [HR], 0.339; 95% confidence interval [CI], 0.160-0.720; P = 0.003). The 1-year EFS rates were 96.0% and 88.0%, and the 2-year EFS rates were 92.0% and 77.7% for patients in the NAIT and NACT groups, respectively (HR, 0.438; 95% CI, 0.276-0.846; P = 0.010). For patients who did not achieve pathological complete response (pCR), significantly longer OS ( P = 0.012) and EFS ( P = 0.019) were observed in patients receiving NAIT than those receiving NACT. Different NAT regimens had little effect on surgery and the postoperative length of stay (6 [4, 7] days vs . 6 [4, 7] days, Z = -0.227, P = 0.820). CONCLUSIONS NAIT exhibited superior efficacy to NACT for NSCLC, resulting in longer OS and EFS. The OS and EFS benefits were also observed among patients in the NAIT group who did not achieve pCR.
Humans ; Carcinoma, Non-Small-Cell Lung/mortality* ; Male ; Female ; Lung Neoplasms/mortality* ; Middle Aged ; Immune Checkpoint Inhibitors/therapeutic use* ; Neoadjuvant Therapy/methods* ; Retrospective Studies ; Aged ; Adult ; Kaplan-Meier Estimate ; Treatment Outcome ; Immunotherapy/methods*