ObjectiveTo predict the mechanism through which Shasheng Maidong Tang enhances the efficacy of chemotherapy for lung cancer via network pharmacology and validate the prediction results in animal experiments. MethodsThe potential mechanism through which Shasheng Maidong Tang enhances the efficacy of chemotherapy for lung cancer was predicted by network pharmacology， liquid chromatography-mass spectrometry （LC-MS）， and molecular docking methods. C57/BL6 mice were assigned into normal， model， cisplatin， and Shasheng Maidong Tang+cisplatin groups. In addition to the normal group， the remaining groups were injected subcutaneously with 0.2 mL of 1×10⁷ cells·mL^-1 Lewis lung cancer cells to establish the Lewis lung cancer model. The daily gavage dose of Shasheng Maidong Tang was 3.58 g·kg^-1， and the concentration of cisplatin intraperitoneally injected on every other day was 2 mg·kg^-1. Drugs were administered for 14 d. The changes in the tumor volume and the rate of tumor suppression were monitored， and the tumor histopathological changes were observed by hematoxylin-eosin （HE） staining. Enzyme-linked immunosorbent assay was employed to measure the interleukin （IL）-6 and interferon （IFN）-γ levels in peripheral blood. Real-time PCR was performed to quantify the mRNA levels of Janus kinase 2 （JAK2）， signal transducer and activator of transcription 1 （STAT1）， and signal transducer and activator of transcription 3 （STAT3） in the tumor tissue of mice. Western blot was employed to determine the protein levels of JAK2， STAT3， B-cell lymphoma-2 （Bcl-2）， cysteinyl aspartate-specific proteinase-3 （Caspase-3）， and Pim-1 proto1 （PIM1） in the tumor tissue. Immunohistochemistry was employed to detect the expression of Bcl-2 and PIM1 in the tumor tissue. ResultsNetwork pharmacological predictions indicated that Shasheng Maidong Tang might enhance the efficacy of chemotherapy for lung cancer by regulating nitrogen metabolism， AGE-RAGE signaling pathway， cancer pathway， and JAK/STAT signaling pathway. The experimental results demonstrated that tumor volume in the cisplatin group and Shasheng Maidong Tang+cisplatin group was reduced compared with the model group， with statistically distinct differences observed on days 14， 17， 20 post modeling （P<0.05）. Notably， the Shasheng Maidong Tang+cisplatin therapy further decreased tumor volume compared with the cisplatin group， showing marked reductions on days 17 and 20 （P<0.05）， consistent with trends visualized in tumor volume comparison charts. The Shasheng Maidong Tang+cisplatin group exhibited higher tumor inhibition rate than the cisplatin group （P<0.05）. Histopathological analysis via HE staining revealed that the tumors in the model group displayed frequent nuclear mitosis， densely arranged cells， hyperchromatic nuclei， and no necrosis. Cisplatin treatment induced partial necrosis and vacuolization， while the Shasheng Maidong Tang+cisplatin group exhibited extensive necrotic regions， maximal vacuolization， disarranged tumor cells， and minimal mitotic activity. Compared with the model group， the cisplatin group and the Shasheng Maidong Tang+cisplatin group showed elevated level of IFN-γ （P<0.01） and declined level of IL-6 （P<0.01） in the peripheral blood. Compared with the cisplatin group， the Shasheng Maidong Tang+cisplatin group presented elevated level of IFN-γ （P<0.01） and lowered level of IL-6 （P<0.01） in the peripheral blood. Compared with the model group， the cisplatin group and the Shasheng Maidong Tang+cisplatin groups showed down-regulated mRNA levels of JAK2 and STAT3 （P<0.01） and up-regulated mRNA level STAT1 （P<0.01）. Compared with the cisplatin group， the Shasheng Maidong Tang+cisplatin group presented down-regulated mRNA levels of JAK2 and STAT3 （P<0.01） and up-regulated mRNA level of STAT1 （P<0.01）. Compared with the model group， the cisplatin group and the Shasheng Maidong Tang+cisplatin group showed down-regulated protein levels of JAK2 （P<0.01）， Bcl-2 （P<0.01）， PIM1 （P<0.01）， and STAT3 （P<0.05）， and up-regulated protein level of Caspase-3 （P<0.01）. Compared with the cisplatin group， Shasheng Maidong Tang+cisplatin group presented down-regulated protein levels of JAK2 （P<0.01）， Bcl-2 （P<0.01）， PIM1 （P<0.01）， STAT3 （P<0.05）， and up-regulated protein level of Caspase-3 （P<0.01）. The Bcl-2 and PIM1 expression results obtained by immunohistochemistry were consistent with those of Western blot. ConclusionShasheng Maidong Tang may enhance the efficacy of chemotherapy in the mouse model of Lewis lung cancer by regulating the JAK2/STAT3 signaling pathway.

Oral squamous cell carcinoma (OSCC) is a common head and neck malignancy. Approximately 50% to 60% of patients with OSCC are diagnosed at a locally advanced stage (clinical staging III-IVa). Even with comprehensive and sequential treatment primarily based on surgery, the 5-year overall survival rate remains below 50%, and patients often suffer from postoperative functional impairments such as difficulties with speaking and swallowing. Programmed death receptor-1 (PD-1) inhibitors are increasingly used in the neoadjuvant treatment of locally advanced OSCC and have shown encouraging efficacy. However, clinical practice still faces key challenges, including the definition of indications, optimization of combination regimens, and standards for efficacy evaluation. Based on the latest research advances worldwide and the clinical experience of the expert group, this expert consensus systematically evaluates the application of PD-1 inhibitors in the neoadjuvant treatment of locally advanced OSCC, covering combination strategies, treatment cycles and surgical timing, efficacy assessment, use of biomarkers, management of special populations and immune related adverse events, principles for immunotherapy rechallenge, and function preservation strategies. After multiple rounds of panel discussion and through anonymous voting using the Delphi method, the following consensus statements have been formulated: 1) Neoadjuvant therapy with PD-1 inhibitors can be used preoperatively in patients with locally advanced OSCC. The preferred regimen is a PD-1 inhibitor combined with platinum based chemotherapy, administered for 2-3 cycles. 2) During the efficacy evaluation of neoadjuvant therapy, radiographic assessment should follow the dual criteria of Response Evaluation Criteria in Solid Tumors (RECIST) version 1.1 and immune RECIST (iRECIST). After surgery, systematic pathological evaluation of both the primary lesion and regional lymph nodes is required. For combination chemotherapy regimens, PD-L1 expression and combined positive score need not be used as mandatory inclusion or exclusion criteria. 3) For special populations such as the elderly (≥ 70 years), individuals with stable HIV viral load, and carriers of chronic HBV/HCV, PD-1 inhibitors may be used cautiously under the guidance of a multidisciplinary team (MDT), with close monitoring for adverse events. 4) For patients with a poor response to neoadjuvant therapy, continuation of the original treatment regimen is not recommended; the subsequent treatment plan should be adjusted promptly after MDT assessment. Organ transplant recipients and patients with active autoimmune diseases are not recommended to receive neoadjuvant PD-1 inhibitor therapy due to the high risk of immune related activation. Rechallenge is generally not advised for patients who have experienced high risk immune related adverse events such as immune mediated myocarditis, neurotoxicity, or pneumonitis. 5) For patients with a good pathological response, individualized de escalation surgery and function preservation strategies can be explored. This consensus aims to promote the standardized, safe, and precise application of neoadjuvant PD-1 inhibitor strategies in the management of locally advanced OSCC patients.

ObjectiveThe widespread adoption of portable fundus cameras for primary care and community screening is hindered by limitations in current autofocus(AF) technologies. Image-based methods relying on sharpness evaluation require iterative searches, resulting in slow convergence, while projection-based techniques are susceptible to optical artifacts and calibration errors. To address these challenges, this study introduces a novel AF system based on direct wavefront sensing, designed to deliver simultaneous high speed, high precision, and operational robustness within the compact form factor essential for portable ophthalmic devices. MethodsOur approach fundamentally reimagines the AF process by directly measuring the ocular wavefront aberration. We developed a custom portable fundus camera integrating a miniaturized Shack-Hartmann wavefront sensor (SHWS) into the optical path. An 850 nm laser diode projects a point source onto the retina via oblique illumination to minimize corneal reflections. Light scattered from this spot carries the eye’s refractive error through the imaging optics and is directed to the SHWS, positioned at a plane optically conjugate to the primary color CMOS imaging sensor. A microlens array within the SHWS samples the incident wavefront, generating a pattern of focal spots on a CCD. Real-time centroid analysis of these spots provides a map of local wavefront slopes. These measurements are processed through a singular value decomposition (SVD) algorithm to fit a Zernike polynomial basis set, enabling real-time reconstruction of the wavefront phase. The defocus component (S) is extracted from the second-order Zernike coefficients, providing a direct, quantitative measure of the refractive error in diopters. This value serves as a precise error signal in a closed-loop control system, which commands a voice-coil actuated focusing lens to its null position in a single, deterministic step, eliminating the need for iterative search algorithms. ResultsComprehensive evaluation demonstrated the system’s high performance. Testing on a calibrated model eye (OEMI-7) established a highly linear relationship between the computed defocus S and the focusing lens position across a ±20 Diopter (D) compensation range, achievable within a 5 mm mechanical travel. The system achieved a focusing precision of 0.08 D, corresponding to an 18-fold improvement over a conventional projection spot-size method tested under identical conditions. The total focus acquisition time, encompassing wavefront measurement, computation, and lens actuation, averaged under 0.5 s. Clinical validation with 25 human volunteers (50 eyes, refractive range -15 D to +10 D) confirmed practical efficacy. The wavefront-sensing AF succeeded in 92% of attempts with a mean time of 0.5 s, substantially outperforming a projection-based benchmark which achieved only a 32% success rate with an average time of 4.25 s. The system provided instantaneous directional guidance and maintained stability during minor ocular movements. Objective assessment of image quality, via amplitude contrast of retinal vasculature, showed consistent and significant enhancement following AF correction across the entire tested diopter range. ConclusionThis work successfully implements and validates a direct wavefront-sensing autofocus paradigm for portable fundus cameras. By directly quantifying and compensating for the optical defocus aberration, this method bypasses the fundamental limitations of image-processing and projection-based techniques, enabling rapid, precise, and deterministic diopter compensation. The developed system delivers an exceptional combination of a wide operational range (±20 D), high accuracy (0.08 D), fast convergence (0.5 s), and a compact physical footprint. This technology provides a practical and high-performance focusing solution capable of enhancing the reliability, throughput, and diagnostic utility of portable retinal imaging in large-scale screening applications. Future efforts will be directed towards system cost optimization and performance adaptation for diverse ocular conditions.

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.

ObjectiveTo construct and validate a clinical prediction model for Qi deficiency and blood stasis syndrome in chronic heart failure （CHF），aiming to assist clinical diagnosis and provide tools and methods for individualized treatment of CHF. MethodsThe clinical data of patients with chronic heart failure treated at Dongzhimen Hospital of Beijing University of Chinese Medicine from January 2022 to January 2024 were retrospectively collected. The patients were randomly divided into a training group and a validation group with a ratio of 7∶3. First， the least absolute shrinkage and selection operator （LASSO） regression analysis was used to preliminarily screen the predictive factors affecting the diagnosis of Qi deficiency and blood stasis syndrome in CHF. Subsequently， the Logistic regression method was applied to conduct a more in-depth and detailed analysis of these factors. Variables with P<0.05 in the results of the multi-factor Logistic regression were carefully selected and included. Based on the regression coefficients obtained from this analysis， a model was constructed， and a nomogram was accurately drawn. Using R software，the receiver operating characteristic （ROC） curve，calibration curve，and decision curve analysis （DCA） were precisely drawn. These analyses were used to comprehensively evaluate the model from three crucial aspects： discrimination，calibration，and clinical applicability. Additionally， the accuracy，specificity，sensitivity，positive predictive value，and negative predictive value of the model were meticulously calculated to conduct a more all-round and comprehensive assessment. ResultsIn total， 168 cases were successfully obtained in the training group， and 71 cases were included in the validation group. After a thorough comparison， it was found that there were no statistically significant differences in the baseline data between the two groups. After being rigorously screened by the LASSO-multivariate logistic regression method， dark red tongue，smoking history，cardiac troponin I，and N-terminal pro-B-type natriuretic peptide （NT-ProBNP） were identified as the influencing factors for diagnosing patients with the Qi deficiency and blood stasis syndrome in CHF. The constructed model demonstrated an area under the curve （AUC） of 0.812 in the training group and 0.719 in the validation group. The calibration curve showed that the predicted curve of the model was close to the actual observed curve. DCA indicated that the model could provide substantial clinical benefits for patients at the decision thresholds ranging from 0.2 to 0.9. ConclusionThe clinical prediction model for Qi deficiency and blood stasis syndrome in chronic heart failure constructed in this study shows good performance. It has certain application value in clinical practice， which may contribute to the improvement of the diagnosis and treatment of CHF patients with this syndrome.

Electromagnetic fields can regulate the fundamental biological processes involved in bone remodeling. As a non-invasive physical therapy, electromagnetic fields with specific parameters have demonstrated therapeutic effects on bone remodeling diseases, such as fractures and osteoporosis. Electromagnetic fields can be generated by the movement of charged particles or induced by varying currents. Based on whether the strength and direction of the electric field change over time, electromagnetic fields can be classified into static and time-varying fields. The treatment of bone remodeling diseases with static magnetic fields primarily focuses on fractures, often using magnetic splints to immobilize the fracture site while studying the effects of static magnetic fields on bone healing. However, there has been relatively little research on the prevention and treatment of osteoporosis using static magnetic fields. Pulsed electromagnetic fields, a type of time-varying field, have been widely used in clinical studies for treating fractures, osteoporosis, and non-union. However, current clinical applications are limited to low-frequency, and research on the relationship between frequency and biological effects remains insufficient. We believe that different types of electromagnetic fields acting on bone can induce various “secondary physical quantities”, such as magnetism, force, electricity, acoustics, and thermal energy, which can stimulate bone cells either individually or simultaneously. Bone cells possess specific electromagnetic properties, and in a static magnetic field, the presence of a magnetic field gradient can exert a certain magnetism on the bone tissue, leading to observable effects. In a time-varying magnetic field, the charged particles within the bone experience varying Lorentz forces, causing vibrations and generating acoustic effects. Additionally, as the frequency of the time-varying field increases, induced currents or potentials can be generated within the bone, leading to electrical effects. When the frequency and power exceed a certain threshold, electromagnetic energy can be converted into thermal energy, producing thermal effects. In summary, external electromagnetic fields with different characteristics can generate multiple physical quantities within biological tissues, such as magnetic, electric, mechanical, acoustic, and thermal effects. These physical quantities may also interact and couple with each other, stimulating the biological tissues in a combined or composite manner, thereby producing biological effects. This understanding is key to elucidating the electromagnetic mechanisms of how electromagnetic fields influence biological tissues. In the study of electromagnetic fields for bone remodeling diseases, attention should be paid to the biological effects of bone remodeling under different electromagnetic wave characteristics. This includes exploring innovative electromagnetic source technologies applicable to bone remodeling, identifying safe and effective electromagnetic field parameters, and combining basic research with technological invention to develop scientifically grounded, advanced key technologies for innovative electromagnetic treatment devices targeting bone remodeling diseases. In conclusion, electromagnetic fields and multiple physical factors have the potential to prevent and treat bone remodeling diseases, and have significant application prospects.

Objective: To compare quality control (relative purity and specific activity) and process control [plasminogen (Pg) antigen recovery and potency recovery] indexes of samples before and after adding the Q chromatography step to the full chromatography process of human Pg, thereby determining whether the addition of this step could improve Pg recovery by affinity chromatography. Methods: A Q chromatography step was added before the Pg affinity chromatography in the original Pg chromatography process. The loading solution, flow through solution and eluate of Q chromatography and Pg affinity chromatography were collected. The potency of coagulation factor Ⅱ (FⅡ), Ⅶ (FⅦ), Ⅷ (FⅧ), Ⅸ (FⅨ), and Ⅹ(FⅩ) were detected by the coagulation method, the total protein content was detected by the BCA method, and the Pg potency was detected by the chromogenic substrate method. The content of specific plasma proteins was detected by immunoturbidimetry, the potency recovery of coagulation factors was calculated, and the flow direction of coagulation factors was analyzed. The recovery of different plasma protein antigens were calculated, and the distribution of impurity proteins was analyzed. The relative purity and specific activity of Pg, antigen content, and potency recovery in the target fractions were calculated and compared with the original process indicators, so as to determine the effect of adding Q chromatography on the original process. Furthermore, the reproducibility after process modification was assessed. Results: 100% of FⅡ, FⅩ, and FⅨ, 87.81% of FⅧ, and 40.44% of FⅦ in filtered plasma were removed by Q chromatography. The residual FⅦ (53.26%) and FⅧ (13.30%) in Q flow-through fraction were completely removed by Pg affinity chromatography. In both the original process (without Q-chromatography) and the modified process (with Q-chromatography), non-target plasma proteins mainly existed in the flow-through fraction of Pg affinity chromatography. The antigen recovery of IgM, ceruloplasmin (CER), and fibronectin (FNC) in Q-chromatography flow-through fraction were reduced. In contrast, antigen recovery of other plasma proteins [IgG, IgA, Pg, albumin (AlB), alpha-1-antitrypsin (AAT), and fibrinogen (Fg)] were all >90%, which were consistent with the protein composition and proportion in the original affinity chromatography loading solution. Compared with the recovery rate of Pg antigen in the original process (74.4%), the total recovery of Pg antigen in the modified process was significantly increased (89.97%). Compared with the recovery of IgG (97.48%) and Fg (95.32%) in the Pg affinity flows-through fraction of the original process, the modified process resulted in a slight reduction in the recovery of IgG (94.60%), while the recovery of Fg was not affected (95.05%). The potency recovery rate, specific activity, and relative purity of Pg after Q chromatography were 99.3%, 0.016 U/mg, and 0.15%. These values were the same as those of Pg affinity chromatography loading solution by the original process, indicating that introduction of Q chromatography did not affect subsequent Pg affinity chromatography. Compared with the recovery of Pg antigen in three batches of the original process (66.49±1.02)%, the recovery of Pg antigen in the affinity chromatography eluent of the modified process [five batches; (77.43±4.43)%] was significantly improved. Furthermore, the potency recovery was (86.80±4.28)%, the relative purity was (81.99±1.25)%, the specific activity was (8.679±1.073)U/mg, and the process was reproducible. Conclusion: The addition of Q chromatography could improve the recovery of Pg affinity chromatography in the full chromatography process.

Objective To investigate the effectiveness of the integrated schistosomiasis control programme in Sichuan Province during the stage moving from transmission interruption to elimination (2015—2023), so as to provide insights into formulation of the schistosomiasis control measures during the post-elimination stage. Methods Schistosomiasis control data were retrospectively collected from departments of health, agriculture and rural affairs, forestry and grassland, water resources, and natural resources in Sichuan Province from 2015 to 2023, and a database was created to document examinations and treatments of human and livestock schistosomiasis, and snail survey and control, conversion of paddy fields to dry fields, ditch hardening, rivers and lakes management and building of forests for snail control and schistosomiasis prevention. The completion of schistosomiasis control measures was investigated, and the effectiveness was evaluated. Results A total of 20 545 155 person-times received human schistosomiasis examinations in Sichuan Province during the period from 2015 to 2023, and 232 157 person-times were seropositive, with a reduction in the seroprevalence from 2.10% (44 299/2 107 003) in 2015 to 1.12% (9 361/837 896) in 2023 (χ² = 7.68, P < 0.001). The seroprevalence of human schistosomiasis appeared a tendency towards a decline in Sichuan Province over years from 2015 to 2023 (b = −8.375, t = −10.052, P < 0.001); however, no egg positive individuals were identified during the period from 2018 to 2023, with the prevalence of human Schistosoma japonicum infections maintained at 0. Expanded chemotherapy was administered to 2 754 515 person-times, and medical assistance of advanced schistosomiasis was given to 6 436 persontimes, with the treatment coverage increasing from 46.80% (827/1 767) in 2015 to 64.87% (868/1 338) in 2023. Parasitological tests for livestock schistosomiasis were performed in 35 113 herd-times, and expanded chemotherapy was administered to 513 043 herd-times, while the number of fenced livestock decreased from 121 631 in 2015 to 103 489 in 2023, with a reduction of 14.92%. Snail survey covered 433 621.80 hm² in Sichuan Province from 2015 to 2023, with 204 602.81 hm² treated by chemical control and 4 637.74 hm² by environmental modifications. The area of snail habitats decreased from the peak of 5 029.80 hm² in 2016 to 3 709.72 hm² in 2023, and the actual area of snail habitats decreased from the peak of 8 585.48 hm² in 2016 to 473.09 hm² in 2023. The mean density of living snails remained low across the study period except in 2017 (0.62 snails/0.1 m²). Schistosomiasis control efforts by departments of agriculture and rural affairs in Sichuan Province included conversion of paddy fields to dry fields covering 153 346.93 hm², hardening of 6 110.31 km ditches, building of 70 356 biogas digesters, replacement of cattle with 227 161 sets of machines, and captive breeding of 21 161 070 livestock from 2015 to 2023, and the control efforts by departments of water resources included rivers and lakes management measuring 5 676.92 km and renovation of 2 331 irrigation areas, while the control efforts by departments of forestry and grassland included building of forests for snail control and schistosomiasis prevention covering 23 913.33 hm², renovation of snail control forests covering 8 720 hm² and newly building of shelterbelts covering 764 686.67 hm². All 63 endemic counties (cities and districts) had achieved the criterion for schistosomiasis elimination criteria in Sichuan Province by the end of 2023. Conclusion Following the integrated control efforts from 2015 to 2023, remarkable achievements have been obtained in the schistosomiasis control programme in Sichuan Province, with all endemic counties successfully attaining the schistosomiasis elimination target at the county level.

ObjectivePrimary liver cancer, predominantly hepatocellular carcinoma (HCC), is a significant global health issue, ranking as the sixth most diagnosed cancer and the third leading cause of cancer-related mortality. Accurate and early diagnosis of HCC is crucial for effective treatment, as HCC and non-HCC malignancies like intrahepatic cholangiocarcinoma (ICC) exhibit different prognoses and treatment responses. Traditional diagnostic methods, including liver biopsy and contrast-enhanced ultrasound (CEUS), face limitations in applicability and objectivity. The primary objective of this study was to develop an advanced, light-weighted classification network capable of distinguishing HCC from other non-HCC malignancies by leveraging the automatic analysis of brightness changes in CEUS images. The ultimate goal was to create a user-friendly and cost-efficient computer-aided diagnostic tool that could assist radiologists in making more accurate and efficient clinical decisions. MethodsThis retrospective study encompassed a total of 161 patients, comprising 131 diagnosed with HCC and 30 with non-HCC malignancies. To achieve accurate tumor detection, the YOLOX network was employed to identify the region of interest (ROI) on both B-mode ultrasound and CEUS images. A custom-developed algorithm was then utilized to extract brightness change curves from the tumor and adjacent liver parenchyma regions within the CEUS images. These curves provided critical data for the subsequent analysis and classification process. To analyze the extracted brightness change curves and classify the malignancies, we developed and compared several models. These included one-dimensional convolutional neural networks (1D-ResNet, 1D-ConvNeXt, and 1D-CNN), as well as traditional machine-learning methods such as support vector machine (SVM), ensemble learning (EL), k-nearest neighbor (KNN), and decision tree (DT). The diagnostic performance of each method in distinguishing HCC from non-HCC malignancies was rigorously evaluated using four key metrics: area under the receiver operating characteristic (AUC), accuracy (ACC), sensitivity (SE), and specificity (SP). ResultsThe evaluation of the machine-learning methods revealed AUC values of 0.70 for SVM, 0.56 for ensemble learning, 0.63 for KNN, and 0.72 for the decision tree. These results indicated moderate to fair performance in classifying the malignancies based on the brightness change curves. In contrast, the deep learning models demonstrated significantly higher AUCs, with 1D-ResNet achieving an AUC of 0.72, 1D-ConvNeXt reaching 0.82, and 1D-CNN obtaining the highest AUC of 0.84. Moreover, under the five-fold cross-validation scheme, the 1D-CNN model outperformed other models in both accuracy and specificity. Specifically, it achieved accuracy improvements of 3.8% to 10.0% and specificity enhancements of 6.6% to 43.3% over competing approaches. The superior performance of the 1D-CNN model highlighted its potential as a powerful tool for accurate classification. ConclusionThe 1D-CNN model proved to be the most effective in differentiating HCC from non-HCC malignancies, surpassing both traditional machine-learning methods and other deep learning models. This study successfully developed a user-friendly and cost-efficient computer-aided diagnostic solution that would significantly enhances radiologists’ diagnostic capabilities. By improving the accuracy and efficiency of clinical decision-making, this tool has the potential to positively impact patient care and outcomes. Future work may focus on further refining the model and exploring its integration with multimodal ultrasound data to maximize its accuracy and applicability.