Objective To evaluate the application value of artificial intelligence (AI) in the quality control of mammographic images and explore its feasibility for improving image quality. Methods A retrospective analysis was conducted on 500 mammographic images from 125 female patients. These images were acquired in December 2024 at the Department of Radiology, Obstetrics and Gynecology Hospital of Tongji University by two junior technologists with qualification certificate for junior radiologic technologists and ≤ 2 months of independent operation. The reference standard was the evaluation by a panel of senior experts comprising one associate chief radiologist and two intermediate radiologic technologists with over 10 years of experience in mammography. The evaluation was based on nine criteria within an AI quality control system. The correlation and consistency (Kappa test) of the assessment outcomes were compared among the junior technologist group, the AI quality control group, and the panel group. Additionally, the differences in the proportions of high-, medium-, and low-quality images rated by the three groups were analyzed. After one month of AI assistance, 200 images from 50 additional patients acquired by the same two junior technologists in January 2025 were collected. The area under the receiver operating characteristic curve and 95% confidence interval (95%CI) were calculated for the assessment performance of the junior technologist group before and after AI assistance. Differences were compared using the DeLong test. Changes in the disqualification rates for the nine criteria were analyzed. Results In consistency analysis, the AI quality control group showed high consistency with the panel group across multiple key criteria, with Kappa values ranging from 0.41 to 1.00. In contrast, the consistency between the junior technologist group and the panel group was generally low, with Kappa values ranging from 0.13 to 0.49. In comparison of image quality classification, no significant differences were observed in image quality classification between the AI group and the panel group (P>0.05). However, the proportion of images rated as high quality by the junior technologist group was significantly higher, while the proportions rated as medium and low quality were significantly lower, compared to those rated by the panel group (P<0.05). After AI assistance, the area under the receiver operating characteristic curve for the assessment performance of junior technologist group increased significantly from 0.56 (95%CI: 0.51-0.61) to 0.91 (95%CI: 0.87-0.94) (P<0.001). The disqualification rates for skin folds, incomplete inclusion of the pectoralis major muscle, and nipple not in profile decreased significantly. Conclusion AI demonstrates assessment capability comparable to the panel group in mammographic quality control. AI effectively enhances the quality of images acquired by junior technologists through real-time, objective feedback.

AIM: To evaluate clinical efficacy of recombinant human epidermal growth factor(rhEGF)combined with adjuvant amniotic membrane transplantation in corneal alkaline burns. METHODS:In the prospective, randomized controlled study, patients with corneal alkaline burns treated in the hospital were enrolled between November 2022 and November 2024. After emergency treatment, patients were divided into combined treatment group and routine treatment group by random number table method. The routine treatment group was given basic treatment(rhEGF), while combined treatment group additionally underwent adjuvant amniotic membrane transplantation. The clinical efficacy, healing time of corneal epithelium, best corrected visual acuity, VAS scores, corneal neovascularization area, break-up time, score of corneal opacity, and levels of inflammatory factors(IL-6, hs-CRP, TNF-α)in the two groups were observed and compared. RESULTS:There were 110 patients(110 eyes)in this study, including 55 cases(55 eyes)in each group. The combination group had a mean age of 46.82±10.38 y, including 26 males and 29 females. The routine treatment group had a mean age of 45.13±11.57 y, with 31 males and 24 females. The total response rate of combined treatment group [94.5%(52/55)] was significantly higher than that of routine treatment group [81.8%(45/55), P<0.05]. The healing time of corneal epithelium in combined treatment group was significantly shorter than that in routine treatment group(P<0.001), and VAS score for pain severity after treatment was significantly lower than that in routine treatment group(P<0.001). The corneal neovascularization area in combined treatment group was significantly smaller than that in routine treatment group(P<0.001), break-up time was significantly longer than that in routine treatment group(P<0.001),and score of corneal opacity was significantly lower than that in routine treatment group(P<0.001). After treatment, levels of inflammatory factors in combined treatment group were significantly lower than those in routine treatment group(all P<0.05). CONCLUSION:Adjuvant amniotic membrane transplantation combined with rhEGF presents prominent clinical advantages in the treatment of alkaline corneal burns. It can enhance therapeutic efficacy, accelerate wound healing, relieve pain, reduce corneal neovascularization, prolong tear film break-up time, alleviate corneal opacification, and reduce the levels of inflammatory factors.

Objective To evaluate the application value of artificial intelligence (AI) in the quality control of mammographic images and explore its feasibility for improving image quality. Methods A retrospective analysis was conducted on 500 mammographic images from 125 female patients. These images were acquired in December 2024 at the Department of Radiology, Obstetrics and Gynecology Hospital of Tongji University by two junior technologists with qualification certificate for junior radiologic technologists and ≤ 2 months of independent operation. The reference standard was the evaluation by a panel of senior experts comprising one associate chief radiologist and two intermediate radiologic technologists with over 10 years of experience in mammography. The evaluation was based on nine criteria within an AI quality control system. The correlation and consistency (Kappa test) of the assessment outcomes were compared among the junior technologist group, the AI quality control group, and the panel group. Additionally, the differences in the proportions of high-, medium-, and low-quality images rated by the three groups were analyzed. After one month of AI assistance, 200 images from 50 additional patients acquired by the same two junior technologists in January 2025 were collected. The area under the receiver operating characteristic curve and 95% confidence interval (95%CI) were calculated for the assessment performance of the junior technologist group before and after AI assistance. Differences were compared using the DeLong test. Changes in the disqualification rates for the nine criteria were analyzed. Results In consistency analysis, the AI quality control group showed high consistency with the panel group across multiple key criteria, with Kappa values ranging from 0.41 to 1.00. In contrast, the consistency between the junior technologist group and the panel group was generally low, with Kappa values ranging from 0.13 to 0.49. In comparison of image quality classification, no significant differences were observed in image quality classification between the AI group and the panel group (P>0.05). However, the proportion of images rated as high quality by the junior technologist group was significantly higher, while the proportions rated as medium and low quality were significantly lower, compared to those rated by the panel group (P<0.05). After AI assistance, the area under the receiver operating characteristic curve for the assessment performance of junior technologist group increased significantly from 0.56 (95%CI: 0.51-0.61) to 0.91 (95%CI: 0.87-0.94) (P<0.001). The disqualification rates for skin folds, incomplete inclusion of the pectoralis major muscle, and nipple not in profile decreased significantly. Conclusion AI demonstrates assessment capability comparable to the panel group in mammographic quality control. AI effectively enhances the quality of images acquired by junior technologists through real-time, objective feedback.

Objective To evaluate the application value of artificial intelligence (AI) in the quality control of mammographic images and explore its feasibility for improving image quality. Methods A retrospective analysis was conducted on 500 mammographic images from 125 female patients. These images were acquired in December 2024 at the Department of Radiology, Obstetrics and Gynecology Hospital of Tongji University by two junior technologists with qualification certificate for junior radiologic technologists and ≤ 2 months of independent operation. The reference standard was the evaluation by a panel of senior experts comprising one associate chief radiologist and two intermediate radiologic technologists with over 10 years of experience in mammography. The evaluation was based on nine criteria within an AI quality control system. The correlation and consistency (Kappa test) of the assessment outcomes were compared among the junior technologist group, the AI quality control group, and the panel group. Additionally, the differences in the proportions of high-, medium-, and low-quality images rated by the three groups were analyzed. After one month of AI assistance, 200 images from 50 additional patients acquired by the same two junior technologists in January 2025 were collected. The area under the receiver operating characteristic curve and 95% confidence interval (95%CI) were calculated for the assessment performance of the junior technologist group before and after AI assistance. Differences were compared using the DeLong test. Changes in the disqualification rates for the nine criteria were analyzed. Results In consistency analysis, the AI quality control group showed high consistency with the panel group across multiple key criteria, with Kappa values ranging from 0.41 to 1.00. In contrast, the consistency between the junior technologist group and the panel group was generally low, with Kappa values ranging from 0.13 to 0.49. In comparison of image quality classification, no significant differences were observed in image quality classification between the AI group and the panel group (P>0.05). However, the proportion of images rated as high quality by the junior technologist group was significantly higher, while the proportions rated as medium and low quality were significantly lower, compared to those rated by the panel group (P<0.05). After AI assistance, the area under the receiver operating characteristic curve for the assessment performance of junior technologist group increased significantly from 0.56 (95%CI: 0.51-0.61) to 0.91 (95%CI: 0.87-0.94) (P<0.001). The disqualification rates for skin folds, incomplete inclusion of the pectoralis major muscle, and nipple not in profile decreased significantly. Conclusion AI demonstrates assessment capability comparable to the panel group in mammographic quality control. AI effectively enhances the quality of images acquired by junior technologists through real-time, objective feedback.

Objective:To compare the clinical efficacy of autologous bone grafting or bioceramic bone grafting combined with locking compression plate (LCP) internal fixation in the treatment of Schatzker type II and III tibial plateau fractures.Methods:A retrospective analysis was conducted on 104 patients with Schatzker type II and III tibial plateau fractures who underwent surgical treatment at the Department of Orthopedics, PLA Central Theater Command General Hospital from January 2010 to December 2021. The cohort comprised 55 males and 49 females, with an average age of 49.13±13.80 years (range 18-73 years). All fractures were unilateral: 55 on the left and 49 on the right. According to the Schatzker classification, 59 were Type II and 45 were Type III. Causes of injury included traffic accidents (48 cases), falls from height (3 cases), sprains or falls (45 cases), and other causes (8 cases). During surgery, bioceramic material or allograft bone tissue was implanted into the collapsed tibial plateau region to restore articular surface flatness. Based on graft type, patients were divided into the allograft bone group (63 cases) and the bioceramic group (41 cases). All cases underwent proximal lateral tibial LCP internal fixation. The two groups were compared in terms of operative time, intraoperative blood loss, bone graft volume, length of hospital stay, fracture healing time, and postoperative complications. The Rasmussen radiographic collapse score was used to evaluate fracture reduction, and the Hospital for Special Surgery (HSS) score system was used to assess knee joint function.Results:All patients were followed up for 12(12, 13) months (range 12-16 months). The fracture healing time in the allograft bone group was 13.70±1.36 weeks (range 11-16 weeks), which was significantly shorter than that in the bioceramic group: 14.59±1.73 weeks (range 11-19 weeks) ( t=2.911, P=0.004). The time to full weight-bearing in the allograft group was 15.0(14.0, 17.0) weeks (range 13-23 weeks), which was shorter than the 16.0 (15.5, 18.5) weeks (range 12-24 weeks) in the bioceramic group, showing a statistically significant difference ( Z=-3.019, P=0.002). At 12 months postoperatively, the Rasmussen radiographic collapse score was 1(0, 1) in the bioceramic group, significantly lower than the 1(1, 2) score in the allograft group ( Z=-2.083, P=0.037). No statistically significant differences were observed between the two groups in bone graft volume, surgical duration, intraoperative blood loss, hospitalization duration, or HSS scores at 6 and 12 months postoperatively ( P>0.05). The complication rate was 6.3% (4/63) in the allograft group and 2.4% (1/41) in the bioceramic group, with no statistically significant difference (χ 2=0.830, P=0.362). Conclusions:For Schatzker type II and III tibial plateau fractures, the use of allograft bone or bioceramic combined with LCP internal fixation can achieve good results. Allograft bone has advantages in terms of fracture healing speed and early weight-bearing recovery, while bioceramic is more effective in maintaining joint surface stability.

Objective To propose a liver ultraound image classification model based on bimodal fusion and deep residual network to enhance the diagnosis accuracy of space-occupying lesions(SOLs)of liver.Methods Firstly,a liver ultrasound dataset containing 164 lesions from 100 patients was constructed,including the ultrasound and ultrasonography videos of the patients.Secondly,the parallel residual block was introduced to improve the ResNet-18 network,and the simple attention module and coordinate attention mechanism were used to extract the image features of ultrasound and echography videos,respectively.Finally,a bimodal fusion network was developed with the image features of ultrasound and sonography videos,which was combined with the improved ResNet-18 network to form an ultrasound image classification model.The ultrasound image classification model proposed underwent performance verification by ablation experiment,application evaluation,diagnosis efficacy evaluation,significance evaluation for assisting surgical operation and comparison with the existing classification models in terms of image classification ability.Results The ablation experiment results showed that the proposed model performed the best in classification speed and accuracy when compared with the existing classification models,with a floating-point operation speed of 5.328×109/s,an average accuracy of 0.941 and a calculation speed of 245.266 frames/s.The application evaluation results indicated when compared with the existing classification models the proposed model had the best convergence performance of the loss function curve and the lowest misdiagnosis rate of 7.03%.The diagnosis efficacy evaluation results proved the proposed model gained advantages over other models in diagnostic efficacy,with a sensitivity of 89.38%,a specificity of 94.12%,an accuracy of 90.85%,a positive predictive value of 97.12%and a negative predictive value of 80.00%.The significance evaluation for assisting surgical operation found when compared with the existing classification models the proposed model had the shortest end-to-end delay of 723 ms;laparoscopic hepatectomy assisted with the proposed model had the blood loss reduced by 109.832 mL when compared with the traditional laparoscopic procedure,with the difference being statistically significant(P<0.05).Conclusion The proposed model enhances the diagnosis efficiency and accuracy of ultrasond SOLs of liver,providing support for clinical diagnosis and surgical assistance.[Chinese Medical Equipment Journal,2025,46(10):9-16]

Three failures of YLY-020Y acidic oxidation potential water generator were introduced,and the causes and specific troubleshooting measures were explored.References were provided for engineers to treat similar failures.[Chinese Medical Equipment Journal,2025,46(10):118-120]

Age-related macular degeneration (AMD) represents a predominant cause of blindness among older adults, with limited therapeutic options currently available. Oxidative stress, inflammation, and retinal pigment epithelium injury are recognized as key contributors to the pathogenesis of AMD. Regulated cell death plays a pivotal role in mediating cellular responses to stress, maintaining tissue homeostasis, and contributing to disease progression. Recent research has elucidated several regulated cell death pathways-such as apoptosis, ferroptosis, pyroptosis, necroptosis, and autophagy-that may contribute to the progression of AMD owing to cell death in the retinal pigment epithelium. These discoveries open new avenues for therapeutic interventions in patients with AMD. In this review, we provide a comprehensive summary and analysis of the latest advancements regarding the relationship between regulated cell death and AMD. Moreover, we examined the therapeutic potential of targeting regulated cell death pathways for the treatment and prevention of AMD, highlighting their roles as promising targets for future therapeutic strategies.

Traumatic brain injury (TBI), as a significant central nervous system damage disease with high frequency in the world, leads to a huge number of patients with impaired health and lower quality of life every year. Lung injury is a common and dangerous consequence, which dramatically raises the mortality of patients. Discovering the pathophysiology of lung injury after TBI and discovering viable therapeutic targets has become an important need for clinical diagnosis and therapy. Neurotransmitters, as the fundamental chemical agents of the nervous system for signal transmission, not only govern neuronal activity and apoptosis in TBI but also significantly influence the pathophysiological mechanisms of lung injury subsequent to TBI. The imbalance is intricately linked to the onset and progression of lung damage. This paper systematically reviews the clinical characteristics and predominant pathogenesis of lung injury following TBI, emphasizing the role of key neurotransmitters, including glutamate (Glu), γ-aminobutyric acid (GABA), norepinephrine (NE), dopamine (DA), and acetylcholine (ACh), in lung injury post-TBI. It examines their influence on inflammatory response, vascular permeability, and pulmonary circulation function. Additionally, the paper evaluates the research advancements and potential applications of targeted therapeutic strategies for various neurotransmitter systems, such as receptor antagonists, transporter inhibitors, and neurotransmitter analogues. This research aims to offer a theoretical framework for clarifying the neural regulatory mechanisms of lung injury following TBI and to establish a basis for the development of novel therapeutic strategies and enhancement of the prognosis of the patients.
Humans ; Brain Injuries, Traumatic/metabolism* ; Neurotransmitter Agents/metabolism* ; Lung Injury/metabolism* ; gamma-Aminobutyric Acid/metabolism* ; Glutamic Acid/metabolism* ; Norepinephrine/metabolism* ; Dopamine/metabolism* ; Acetylcholine/metabolism*

OBJECTIVE: Circadian rhythm disruption (CRD) is a risk factor that correlates with poor prognosis across multiple tumor types, including hepatocellular carcinoma (HCC). However, its mechanism remains unclear. This study aimed to define HCC subtypes based on CRD and explore their individual heterogeneity. METHODS: To quantify CRD, the HCC CRD score (HCCcrds) was developed. Using machine learning algorithms, we identified CRD module genes and defined CRD-related HCC subtypes in The Cancer Genome Atlas liver HCC cohort (n = 369), and the robustness of this method was validated. Furthermore, we used bioinformatics tools to investigate the cellular heterogeneity across these CRD subtypes. RESULTS: We defined three distinct HCC subtypes that exhibit significant heterogeneity in prognosis. The CRD-related subtype with high HCCcrds was significantly correlated with worse prognosis, higher pathological grade, and advanced clinical stages, while the CRD-related subtype with low HCCcrds had better clinical outcomes. We also identified novel biomarkers for each subtype, such as nicotinamide n-methyltransferase and myristoylated alanine-rich protein kinase C substrate-like 1. CONCLUSION We classify the HCC patients into three distinct groups based on circadian rhythm and identify their specific biomarkers. Within these groups greater HCCcrds was associated with worse prognosis. This approach has the potential to improve prediction of an individual's prognosis, guide precision treatments, and assist clinical decision making for HCC patients. Please cite this article as: Li XJ, Chang L, Mi Y, Zhang G, Zhu SS, Zhang YX, et al. Integrated-omics analysis defines subtypes of hepatocellular carcinoma based on circadian rhythm. J Integr Med. 2025; 23(4): 445-456.
Humans ; Carcinoma, Hepatocellular/pathology* ; Liver Neoplasms/pathology* ; Circadian Rhythm/genetics* ; Prognosis ; Male ; Female ; Biomarkers, Tumor/genetics* ; Middle Aged ; Machine Learning ; Computational Biology