Medical image recognition is a technology that utilizes computer algorithms to process,analyze and understand medical images,aiming to identify various patterns,targets and objects,thereby aiding doctors in more accurate diagnosis and treatment.Current researches in medical image recognition mainly focuses on medical image classification,lesion location and segmentation,image registration and fusion,content-based image retrieval,as well as three-dimensional reconstruction and visualization.The review provides a summary of the research directions and trends in medical image recognition,introducing concepts and technologies such as deep learning,multimodal fusion,three-dimensional reconstruction and visualization.It also highlights the applications of medical image recognition in medical imaging diagnosis,pathological analysis and radiotherapy planning,while pointing out the existing problems and challenges.Furthermore,the future developments and challenges of medical image recognition technology are put forward for providing a reference for medical image recognition research and clinical medical image analysis.

BACKGROUND: Video-assisted thoracoscopic surgery (VATS) lobectomy is the primary surgical treatment for lung cancer. A significant factor affecting postoperative recovery is prolonged air leak (PAL). Despite numerous clinical strategies could prevent and manage postoperative PAL, its incidence remains high. Phrenic nerve cryotherapy (PNC) temporarily inhibits phrenic nerve function, causing diaphragm elevation, which reduces thoracic cavity volume, enhances pleural apposition, and mitigates air leakage. This study investigates the efficacy of PNC in preventing postoperative PAL during VATS lobectomy. METHODS: A total of 108 eligible lung cancer patients who underwent surgery at the Department of Thoracic Surgery, The Affiliated Hospital of Inner Mongolia Medical University, from June 2023 to January 2025, were enrolled and randomly assigned to the control group (n=54) and the experimental group (n=54). The patients in both the two groups received VATS lobectomy and systematic lymph node dissection, with the experimental group also undergoing PNC during the operation. The baseline characteristics, intraoperative, postoperative indicators and dynamic changes in air leakage between the two groups were compared. RESULTS: The baseline clinical characteristics were comparable between the two groups (P>0.05). The incidence of pulmonary air leakage at 24 h after surgery (31.5% vs 29.6%) and the incidence of postoperative PAL (20.4% vs 14.8%) showed no significant differences between the two groups (P>0.05). The intraoperative air leak test to 24 hours after surgery revealed that air leakage ceased in 8 cases (32.0%) in the control group, compared to 14 cases (46.7%) in the experimental group. Moreover, during the progression from air leakage at 24 hours post-surgery to postoperative PAL, air leakage ceased in 6 cases (35.3%) in the control group and 8 cases (50.0%) in the experimental group, with a statistically significant difference (P<0.001). Compared to the control group, the patients in the experimental group exhibited more pronounced postoperative diaphragmatic elevation that recovered to a slightly higher than preoperative level by 3 mon after surgery. CONCLUSIONS The combination of PNC and active lung repair can serve as an important intervention for patients at high risk of intraoperative air leakage, reducing the occurrence of postoperative PAL.
Humans ; Thoracic Surgery, Video-Assisted/adverse effects* ; Male ; Female ; Middle Aged ; Lung Neoplasms/surgery* ; Aged ; Phrenic Nerve/physiopathology* ; Cryotherapy ; Pneumonectomy/adverse effects* ; Postoperative Complications/etiology* ; Adult

Medical image recognition is a technology that utilizes computer algorithms to process,analyze and understand medical images,aiming to identify various patterns,targets and objects,thereby aiding doctors in more accurate diagnosis and treatment.Current researches in medical image recognition mainly focuses on medical image classification,lesion location and segmentation,image registration and fusion,content-based image retrieval,as well as three-dimensional reconstruction and visualization.The review provides a summary of the research directions and trends in medical image recognition,introducing concepts and technologies such as deep learning,multimodal fusion,three-dimensional reconstruction and visualization.It also highlights the applications of medical image recognition in medical imaging diagnosis,pathological analysis and radiotherapy planning,while pointing out the existing problems and challenges.Furthermore,the future developments and challenges of medical image recognition technology are put forward for providing a reference for medical image recognition research and clinical medical image analysis.

ObjectiveTo construct a quantitative prediction model of three indicators（moisture absorption rate， film thickness and coating weight gain） during the coating process of Vitamin C Yinqiao tablets（VCYT） by near-infrared spectroscopy（NIRS）， and to realize the endpoint judgment. MethodReal-time NIRS data of 4 batches of VCYT during the coating process were collected by diffuse reflection method. The coating method employed was the rolling coating method， and the samples were obtained at the spray stage from the coater's sampling port every 10 minutes， and 57 batches of samples（about 1 800 tablets） were collected at various coating times， the tablets were embedded in molten paraffin， cut longitudinally， and observed by stereomicroscope. The film thickness， with a target value of 38 μm， was then measured using Motic Images Advanced 3.2 software. Furthermore， the mositure absorption rate of samples， aiming for a target value of 3%， was determined in accordance with guiding principles for drug hygroscopicity testing in the 2020 edition of Chinese Pharmacopoeia， and 3 samples were randomly selected from each batch（10 tablets per batch）， and the coating weight gain was calculated（target value of 4%）. Partial least squares regression（PLSR） was used to construct a quantitative model of the 3 coating indicators， and the predicted values of the coating indicators were smoothed using the moving average method and used to determine the coating endpoints. ResultThe prediction determination coefficients（R_p²） for moisture absorption rate， film thickness and coating weight gain were 0.933 4， 0.932 6 and 0.965 9， the root mean square errors of prediction（RMSEP） were 0.163 5%， 1.870 9 μm and 0.240 3%， the relative percent deviations（RPD） were 3.711 0， 2.760 7 and 5.415 8， respectively. The results of the external validation set demonstrated that the real-time predicted values obtained by the models exhibited the same trend as the measured values， and the coating endpoint could be accurately predicted（with a prediction error of less than 7.32 min and a relative error of less than 5.63%）. ConclusionThe established NIRS model exhibits excellent predictive performance and can be used for quality control of VCYT during the coating process.

During coronavirus disease 2019 epidemic, the treatment of severe trauma has been impacted. The Consensus on emergency surgery and infection prevention and control for severe trauma patients with 2019 novel corona virus pneumonia was published online on February 12, 2020, providing a strong guidance for the emergency treatment of severe trauma and the self-protection of medical staffs in the early stage of the epidemic. With the Joint Prevention and Control Mechanism of the State Council renaming "novel coronavirus pneumonia" to "novel coronavirus infection" and the infection being managed with measures against class B infectious diseases since January 8, 2023, the consensus published in 2020 is no longer applicable to the emergency treatment of severe trauma in the new stage of epidemic prevention and control. In this context, led by the Chinese Traumatology Association, Chinese Trauma Surgeon Association, Trauma Medicine Branch of Chinese International Exchange and Promotive Association for Medical and Health Care, and Editorial Board of Chinese Journal of Traumatology, the Chinese expert consensus on emergency surgery for severe trauma and infection prevention during coronavirus disease 2019 epidemic ( version 2023) is formulated to ensure the effectiveness and safety in the treatment of severe trauma in the new stage. Based on the policy of the Joint Prevention and Control Mechanism of the State Council and by using evidence-based medical evidence as well as Delphi expert consultation and voting, 16 recommendations are put forward from the four aspects of the related definitions, infection prevention, preoperative assessment and preparation, emergency operation and postoperative management, hoping to provide a reference for severe trauma care in the new stage of the epidemic prevention and control.

Cardiomyopathy, Dilated/metabolism* ; Humans ; Microfilament Proteins/metabolism* ; Models, Cardiovascular ; Mutation ; Myocytes, Cardiac ; Pluripotent Stem Cells/metabolism* ; Transcription Factors/metabolism* ; Troponin T/metabolism*

Objective:To observe the effect of miR-217 on angiotensin II (AngII)-induced hepatic stellate cells (HSCs) activation, and carbon tetrachloride (CCl4)-induced overexpression in mice, so as to clarify miR-217 role in liver fibrosis.Methods:HSCs were stimulated with AngⅡ and the changes condition in the expression level of miR-217 were detected. HSCs were divided into control group, AngII-treated group and AngⅡ+miR-217-treated group. The expression levels of alpha-smooth muscle actin, fibroblast-specific protein 1 and collagen Ⅰ (Collagen Ⅰ) in each group were detected. The target gene of mir-217 was screened and verified by Targetscan and Dual luciferase gene reporter assay. Real-time quantitative PCR and Western blot were used to detect the effect of miR-217 on the expression level of transforming growth factor beta type Ⅱ receptor (TGFBR2). A CCl4-induced mouse liver fibrosis model was constructed. Masson staining and Sirius red staining were used to detect the effect of miR-217 overexpression on the progression of liver fibrosis in CCl4 mice. Data of two groups were compared using t-test. Data of multiple groups were statistically analyzed with one-way ANOVA. Results:The expression level of miR-217 was downregulated by AngⅡ-stimulated HSC cells. The expression levels of α-smooth muscle actin, fibroblast-specific protein 1 and Collagen Ⅰ induced by AngⅡ was inhibited by miR-217 mimics transfection. The 3'-UTR of TGFBR2 had specifically bind miR-217. The mRNA and protein expression levels of TGFBR2 was inhibited with miR-217 mimics transfection in HSCs. The overexpression of miR-217 had inhibited the expression levels of Collagen Ⅰ and Ⅲ in CCl4 mice and alleviated the progression of liver fibrosis .Conclusion:miR-217 regulates liver fibrosis by targeting TGFBR2, inhibits AngII-induced HSC activation, and slows down the process of liver fibrosis in CCl4 mice, suggesting that miR-217 may have an inhibitory effect on liver fibrosis.

Objective:To investigate the correlation between collateral circulation and infarct pattern and outcome in acute ischemic stroke patients with anterior circulation intracranial atherosclerosis.Methods:Acute ischemic stroke patients with anterior circulation intracranial atherosclerotic severe stenosis or occlusion admitted to the Department of Neurology, the First Affiliated Hospital of Xinxiang Medical College from September 2018 to March 2020 were included prospectively. According to diffusion-weighted imaging, the infarct patterns were divided into perforator pattern, territorial pattern, watershed pattern, and mixed pattern. At 90 d after onset, the modified Rankin Scale was used to evaluate the outcome. 0-2 was defined as good outcome, and >2 was defined as poor outcome. Multivariate logistic regression analysis was used to determine the independent influencing factors of clinical outcome. Results:A total of 89 patients were enrolled, 50 (56.2%) had good collateral circulation and 39 (43.8%) had poor collateral circulation. The distribution patterns of infarct: 22 patients (24.7%) were perforator pattern, 26 (29.2%) were territorial pattern, 17 (19.1%) were watershed pattern, and 24 (30.0%) were mixed pattern. The proportion of patients with good collateral circulation was 81.8%, 65.4%, 29.4% and 41.7%, respectively in the perforator pattern group, territorial pattern group, watershed pattern group, and mixed pattern group. Good collateral circulation was more common in the perforator pattern group, and poor collateral circulation was more common in the watershed pattern group. At 90 d after onset, 53 patients (59.6%) had a good outcome and 36 (40.4%) had a poor outcome. The baseline homocysteine level in the good outcome group was significantly lower than that in the poor outcome group (17.91±4.62 μmol/L vs. 20.35±4.67 μmol/L; t=2.436, P=0.017), and the proportion of patients with good collateral circulation was significantly higher than that of patients with poor outcome (73.6% vs. 30.6%; χ2=16.124, P<0.001). Multivariate logistic regression analysis showed that higher homocysteine level was an independent risk factor for poor outcome (odds ratio 1.174, 95% confidence interval 1.061-1.298; P=0.002) and good collateral circulation was an independent protective factor for good outcome (odds ratio 0.095, 95% confidence interval 0.038-0.239; P<0.001). Conclusions:Good collateral circulation was more common in patients with perforator pattern, and poor collateral circulation was more common in patients with watershed pattern. Good collateral circulation was independently associated with the good clinical outcome in acute ischemic stroke patients with anterior circulation intracranial atherosclerosis.

OBJECTIVE：To estab lish“TCM Data Analysis Platform Based on Strategy Pattern ”（TCMDP），and to analyze the medication rules of TCM prescription against primary hepatic carcinoma （PHC），so as to provide reference for TCM prescription screening. METHODS ：According to the idea of strategy pattern ，TCMDP software was developed ，and the frequency statistics，association，clustering，classification and other methods and the different algorithms covered were encapsulated. Effective TCM prescriptions against PHC were collected and screened from 4 tertiary-grade class-A hospitals in Nanchang city and CNKI ， PubMed. A database of prescriptions for PHC （PDOPHC）was established ，and TCM prescriptions in the data base were put into TCMDP. Clustering algorithm modified by CMC-DD ，modified WD-Get Rules algorithm after merging depth and width search and frequency statistics were used to analyze the distribution of prescription syndrome. Taking phlegm-blood stasis syndrome type （TYPHC）as example ，data mining was carried out on drug efficacy category ，four properties ，five flavors and channel tropism ， drug property combination ，key couplet medicines and key drug combination. RESULTS ：A total of 907 TCM prescriptions against PHC were collected ，mainly involving 10 syndrome types ，such as phlegm-blood stasis syndrome ，deficiency of the vital essential and blood stasis syndrome and liver and spleen blood stasis syndrome. TCM related to TYPHC commonly used in pre- scriptions were tonifying deficiency medicine ， phlegm-re- solving medicine ，promoting blood circulation and removing blood stasi s medicine ，etc．Four properties were mostly cold ，warm and calm ；the five flavors were most ly swe et，bitter and pungent ；channel tropism were mostly spleen ，liver，stomach， lung，heart and kidney ；drug combination were mostly warming-sweet-spleen ，warming-pungent-spleen and cold-bitter-liver ，etc.； there were 36 couplet medicines with frequency ≥30 times；there were 31 strong association rules and 8 key drug combinations in the prescriptions. WD-Get Rules results showed that in the TCM prescriptions against PHC ，Atractylodes macrocephala ，Codonopsis pilosula，Poria cocos and Glycyrrhiza uralensis were in the key position. They were often combined with many kinds of drugs ， which were related to the effect of Sijunzi decoction on strengthening Qi and tonifying spleen. CMC-DD results showed that therapy for TYPHC focused on strengthening the spleen and stomach ，replenishing Qi and blood ；and at the same time ，it treated TYPHC with phlegm-blood stasis syndrome from multiple angles ，such as soothing the liver and regulating Qi ，eliminating phlegm ，clearing heat and detoxification ，promoting blood circulation and nourishing Yin. CONCLUSIONS ：Clinical treatment of TYPHC mainly adopts the methods of invigorating the spleen and replenishing Qi ，soothing the liver and regulating Qi ，promoting blood circulation and removing blood stasis ，which conforms to the medication principle of “strengthening the body and eliminating pathogenic factors”. The application of TCMDP can realize the data mining and analysis of TCM in multi-level and multi-directional way ， which provides a new and effective way for the mining and research of compatibility rules of TCM prescriptions.

Treatment for disorders of consciousness (DOCs) is still a Gordian knot. Evidence-based guidelines on the treatment of DOC patients are not currently available, while neuromodulation techniques are seen as a potential treatment. Multiple neuromodulation therapies have been applied. This article reviews the most relevant studies in the literature in order to describe a clear picture of the current state of neuromodulation therapies that could be used to treat DOC patients. Both invasive and non-invasive brain stimulation is discussed. Significant behavioral improvements in prolonged DOCs under neuromodulation therapies are rare. The efficacy of various such therapies remains a matter of debate. Further clinical investigations of existing techniques in larger samples properly controlling for spontaneous recovery are needed, and new approaches are awaited.
Brain ; drug effects ; physiopathology ; surgery ; Consciousness ; physiology ; Consciousness Disorders ; therapy ; Humans ; Neurotransmitter Agents ; therapeutic use ; Transcranial Magnetic Stimulation ; methods ; Treatment Outcome