• <tr id="yyy80"></tr>
  • <sup id="yyy80"></sup>
  • <tfoot id="yyy80"><noscript id="yyy80"></noscript></tfoot>
  • 99热精品在线国产_美女午夜性视频免费_国产精品国产高清国产av_av欧美777_自拍偷自拍亚洲精品老妇_亚洲熟女精品中文字幕_www日本黄色视频网_国产精品野战在线观看 ?

    Artificial intelligence: Emerging player in the diagnosis and treatment of digestive disease

    2022-06-10 07:59:00HaiYangChenPengGeJiaYueLiuJiaLinQuFangBaoCaiMingXuHaiLongChenDongShangGuiXinZhang
    World Journal of Gastroenterology 2022年20期

    Hai-Yang Chen, Peng Ge, Jia-Yue Liu, Jia-Lin Qu, Fang Bao, Cai-Ming Xu, Hai-Long Chen, Dong Shang, Gui-Xin Zhang

    Abstract Given the breakthroughs in key technologies, such as image recognition, deep learning and neural networks, artificial intelligence (AI) continues to be increasingly developed, leading to closer and deeper integration with an increasingly data-, knowledge- and brain labor-intensive medical industry. As society continues to advance and individuals become more aware of their health needs, the problems associated with the aging of the population are receiving increasing attention, and there is an urgent demand for improving medical technology, prolonging human life and enhancing health. Digestive system diseases are the most common clinical diseases and are characterized by complex clinical manifestations and a general lack of obvious symptoms in the early stage.Such diseases are very difficult to diagnose and treat. In recent years, the incidence of diseases of the digestive system has increased. As AI applications in the field of health care continue to be developed, AI has begun playing an important role in the diagnosis and treatment of diseases of the digestive system.In this paper, the application of AI in assisted diagnosis and the application and prospects of AI in malignant and benign digestive system diseases are reviewed.

    Key Words: Artificial intelligence; Digestive disease; Convolutional neural network; Deep learning; Review

    INTRODUCTION

    Artificial intelligence (AI) is a branch of computer science[1 ] inspired by human intelligence that operates in a different way. AI can be considered a set of computing techniques that allow machines to sense, learn, reason, act,etc.AI was first used at the Dartmouth AI Conference in the summer of 1956 ,which is considered the official birth of AI. In the 1990 s, as technology continued to improve, hardware became more affordable, performance became more reliable, computing power, storage capacity and the ability to process data were greatly improved, and AI returned to life. In recent years, the application of AI in the medical field has reached an unprecedented height and scale. To date, great progress has been achieve in the use of AI in medicine and health, including speech recognition, medical imaging,wearable devices, risk management, pathology,etc[2 ].

    The digestive system contains the largest number of organs in the human body and can be divided into the digestive tract and digestive glands. The digestive tract includes the oral cavity, pharynx,esophagus, stomach, duodenum, small intestine, large intestine, colon,etc.The digestive glands comprise the salivary glands, liver, pancreas,etc.The digestive system digests food, takes up nutrients and eliminates waste. The coordination of gastrointestinal physiological activities depends on the completion of the normal physiological function of the digestive system. Digestive system diseases,which are the most common clinical diseases, have complicated clinical manifestations, are interrelated with each other, and form a hot spot in the medical field[3 ]. The incidence of digestive system diseases is high, and often, there are no obvious symptoms in the early stage. Consequently, most digestive diseases are first noted in the middle and late stages; at this point, the prognosis is poor. As AI technology has continued to be developed, its strong computing power and learning ability have been gradually applied to solve complex medical problems. In the field of digestive diseases, such as gastric,liver, and pancreatic cancer and ulcerative colitis, AI can help improve the accuracy and sensitivity of the diagnosis and provide treatment options (Figure 1 ). AI not only improves the diagnostic accuracy of the disease but also provides a plan for clinical treatment.

    In this review, we discuss AI and related technologies, their applications in digestive diseases and their future developments. We used PubMed and Google to search for relevant articles by using the keywords “digestive system diseases”, “artificial intelligence”, “machine learning”, “deep learning”,“computer-aided diagnosis”, “convolutional neural network”, and “endoscopy and endoscope images”for this review.

    AI AUXILIARY DIAGNOSIS

    In China, the development of AI has received considerable attention, particularly in the application of AI in the medical field. The development of AI has laid a solid foundation for precision medicine. In 2017 , the China State Council announced that AI application should be promoted in the health care system. Subsequently, hundreds of new companies dedicated to the application of medical AI have emerged in China, promoting the development of AI in the medical field[4 ]. AI effectively improves the uneven allocation of medical resources, reduces medical costs and enhances medical efficiency. AI algorithms improve the ease of medical work and lead to not only technological innovations but also a transformation of the medical service mode. AI is applied in all fields of medicine and health, especially in the auxiliary diagnosis of diseases, and includes the following three aspects: intelligent guidance,electronic health records and risk monitoring of diagnosis and treatment.

    Figure 1 Artificial intelligence and digestive diseases. AI: Artificial intelligence; GC: Gastric cancer; LC: Liver cancer; PDAC: Pancreatic ductal adenocarcinoma; UC: Ulcerative colitis; AP: Acute pancreatitis; GU: Gastric ulcer.

    Intelligent guidance

    Outpatient triage has gradually transitioned from a traditional manual system to an internet- and intelligence-based system. Most admitted patients lack an understanding of their disease and the hospital. To improve the efficiency and experience of the patients, intelligent guidance systems have been developed. Patients enter the Mini Program through screens on official hospital accounts to describe symptoms or diseases, and guidance assistants intelligently follow up and guide the patients to provide symptoms to accurately match departments, recommend doctors with the most consistent professional direction, and perform online guidance registration in one step. The research and development leading to intelligent guidance systems has led to a reduction in not only the workload of outpatient staff but also the human resource needs and costs of hospitals. These systems can guide patients to seek medical treatment quickly and accurately, improve the accuracy of patient registration and the efficiency of the physician response, increase efficiency at all steps of the patient stay, and effectively provide accurate medical treatment (Figure 2 ).

    Electronic health record

    Traditional health records are typically kept on paper, which tend to be scattered in hospital archives,limiting their value. The widespread use of the internet has facilitated the creation of electronic health records (EHRs), which are currently widely used worldwide[5 ]. EHRs can improve management processes, overcome problems with paper documentation, and ensure the quality of treatment. Both theoretically and practically, EHRs have guiding and economic value, while their applicative value continues to improve. In addition, EHRs can improve clinical decision-making, collaboration between health care teams, and medical efficiency.

    Risk monitoring of diagnosis and treatment

    Diagnostic risk monitoring systems can improve the diagnostic accuracy and greatly reduce the risk of misdiagnosis, and in this regard, AI has significant advantages over clinical experience. Compared with the United States, domestic equipment is used much more frequently under the same resource allocation[6 ]. This is the main point of medical care in China. Additionally, the large associated workload and high repeatability result in a cumbersome manual analysis and diagnosis. An accurate diagnosis rate is important for ensuring that radiologists can provide high-quality care to patients. A report in 1999 showed that 98000 people die of misdiagnosis each year, and diagnostic errors by radiologists are a key contributor[7 ]. Under a heavy workload, the diagnosis results can only be judged and analyzed by subjective individual experience, leading to high misdiagnosis and missed diagnosis rates. The large market demand for pathologists and diagnostic efficiency have also led to new challenges in the medical service industry. However, digestive system diseases increasingly depend on auxiliary diagnoses based on medical images while continuing to demonstrate a yearly increase in incidence.

    Figure 2 Artificial intelligence and Intelligent guidance. CNN: Convolutional neural network; DL: Deep learning; ML: machine learning; CAD: Computeraided design.

    The emergence of AI has led to its gradual use in digestive diseases. Machine learning (ML) is a branch of AI that aims to predict results by analyzing existing data and performing calculations based on an understanding of these data. Deep learning (DL) is a relatively new branch of ML that imitates learning through machine algorithms and provides a set of possible and reasonable solutions[8 ,9 ]. In esophageal cancer, van der Sommenet al[10 ] developed an automatic algorithm to distinguish early neoplastic lesions. Huanget al[11 ] used 84 images from 30 patients to train an AI-based neural network model to predict Helicobacter pylori infection. DL can be used to share more comprehensive medical diagnosis and treatment information with doctors with lightweight methods. At a higher level, we can comprehensively manage and guide the overall diagnosis and treatment level of the physician team to build a more scientific, accurate and friendly diagnosis and treatment risk monitoring system.

    MALIGNANT DIGESTIVE DISEASES

    The digestive system is a common site for malignant tumors, particularly gastric cancer, liver cancer,colorectal cancer and pancreatic cancer. Given the changes in lifestyle, diet and disease spectrum of the population, the incidence of malignant tumors of the digestive system continues to rise[12 ]. The early diagnosis of malignant tumors is critical for treatment, but patients with malignant tumors often have no obvious symptoms at the early stage, leading to difficulties in early diagnosis. This section summarizes the application of AI in the following three types of malignant tumors with high morbidity and mortality: gastric, liver and pancreatic cancer. The latest clinical studies concerning AI, gastric cancer, liver cancer, and pancreatic ductal adenocarcinoma are summarized in Table 1 .

    Table 1 Recent researches on artificial intelligence in malignant digestive system diseases

    AI and gastric cancer

    Gastric cancer (GC) is the fifth most common cancer and ranks third in cancer mortality worldwide,with more than 1 million new cases and 780000 deaths each year[13 ]. The stage at which GC is diagnosed can greatly affect the prognosis, with a poor prognosis typical in the late stage and a 5 -year survival rate of early GC (EGC) exceeding 90 %[14 ]. There are two difficulties in the early diagnosis of GC. First, EGC is difficult to detect, often presenting with slight reddish bulges or depressions under endoscopy that are not easily distinguished from inflammatory lesions. The second difficulty lies in judging the depth of the invasion of GC. In general, intramucosal GC or GC invading the superficial submucosal layer should be resected endoscopically, while GC invading the deep submucosal layer should be resected with open surgery; otherwise, there could be a risk of lymph node and distant metastasis. However, it is difficult to distinguish among these three forms of GC. The rapid development of DL and ML has led to great progress in AI, whose image recognition has transcended that of humans. By reviewing the published literature, this section discusses the diagnosis, treatment and prognosis of GC with AI.

    Hirasawaet al[15 ] constructed a diagnostic system based on a convolutional neural network (CNN).The authors used 13584 endoscopic images to train the web-based learning model and 2296 GC images from 69 patients to evaluate its performance. The model took 47 s to analyze 2296 images and correctly diagnosed 77 GC lesions with a total sensitivity of 92 %. This web-based learning model for the detection of EGC processes a large number of stored endoscopic images with clinical-related diagnostic capabilities in a very short time and may play a role in real-time gastroscopy[15 ].

    Kubotaet al[16 ] used a back propagation neural network algorithm to analyze the depth of gastric wall infiltration in endoscopic images of 344 GC patients and developed a computer-aided design(CAD) system. The cross-validation results revealed that the diagnostic accuracy of T1 , T2 , T3 and T4 GC was 77 %, 49 %, 51 % and 55 %, respectively. The accuracy in detecting intramucosal carcinoma (T1 a)and submucosal invasive carcinoma (T1 b) is 69 %[16 ]. This study may be used to screen for EGC in the near future.

    AI and liver cancer

    Liver cancer (LC) is the second leading cause of death worldwide, and its incidence continues to increase[17 ]. In recent years, AI has been used in various aspects of LC diagnosis and treatment,especially in the field of imaging. However, individual differences in liver morphology and the internal anatomy and the highly heterogeneous molecular and pathological features of LC lead to great challenges in the implementation of AI, ML and DL for the diagnosis and treatment of this disease[18 ].

    The following two modes of AI application are commonly used in the diagnosis of LC: DL and radiomics. Imaging plays a key role in the identification and diagnosis of hepatobiliary diseases and the establishment of surgical treatment plans. Radiologists and surgeons demarcate organs and diagnose diseases based on their experience and judgment, which can be subjective, time consuming and unreproducible; AI can address these limitations. DL is mainly used for the diagnosis of LCviatraditional machine learning (TML) and CNNs. In TML, a well-developed anatomical model must be established in advance and manually corrected in the later stages[19 ], while the application of CNNs allows images to be directly used in the learning process, allowing the extraction and utilization of all information contained in the image for DL[20 ]. Shaw Hospital of Zhejiang University developed a DL system for liver tumor diagnosis through a CNN. In addition to learning more than 30000 magnetic resonance (MR) images, the system incorporates patient clinical data (medical records, examination results, etc.) and demonstrates excellent diagnostic performance with a coincidence rate with a final pathological result of 92 %[17 ].

    The application of AI in the treatment of LC has led to new opportunities and challenges, promoting the standardization and intelligence of LC management. Huet al[21 ] used 3 D visualization to evaluate the spatial relationship between tumors and surrounding blood vessels before hepatectomy, which serves as a suitable guide for surgical resection. In the treatment of LC by radiofrequency ablation,fusion imaging can integrate enhanced computed tomography (CT)/MR images with real-time ultrasound imaging by electromagnetic tracking to accurately locate the target lesions[22 -24 ]. AI has been applied to all aspects of LC treatment and auxiliary diagnosis, but further prospective research is needed.

    AI and pancreatic ductal adenocarcinoma

    Pancreatic ductal adenocarcinoma (PDAC) is a rapidly progressive and highly malignant tumor of the digestive tract[25 ]. Although many methods have been developed for the diagnosis and treatment of PDAC in recent years, the effective rate of treatment and prognosis remain poor (the 5 -year survival rate is only 9 %[26 ]). The early detection and accurate treatment of PDAC are important directions requiring urgent solutions.

    Recently, rapid developments have been achieved in the AI-based screening and diagnosis of PDAC,leading to acceptable effects. Ansariet al[27 ] applied artificial neural networks (ANNs) to a long-term survival prediction of patients after radical surgery for PDAC for the first time and achieved a consistency index of 0 .79 , indicating that their ANN could predict the survival rate of PDAC patients after radical surgery. Fine needle aspiration (FNA) biopsy is an elaborate approach used to diagnose solid masses of the pancreas. Due to the small number of cases, its development is limited. Momeni-Boroujeniet al[28 ] used a multilayer-perceptron neural network (MNN) to evaluate 277 cell mass images from 75 pancreatic FNA patients and achieved an accuracy of 100 % in the classification of benign and malignant tumors. In particular, the sensitivity and specificity of MNN in identifying atypical cases were 80 % and 75 %, respectively. Intraductal papillary mucinous neoplasm (IPMN), a papillary mucinous tumor with many subtypes, has particular malignant potential. Endoscopic ultrasonography(EUS) can reveal the structure of the pancreas and the dilation of the pancreatic duct and can be used to evaluate the degree of malignancy of IPMN. Indeed, Kuwaharaet al[29 ] used AI to build a system to perform this function. The authors uploaded 3970 EUS images of 50 patients to the system for DL analysis. The endpoint of their system was the accuracy in diagnosing the malignancy degree of IPMNs by AI. The results showed that the AI system had significantly better value in diagnosing malignant IPMNs than benign IPMNs, with an area under the receiver operating characteristic curve of 0 .91 in diagnosing malignant IPMNs. In addition, a three-dimensional depth supervised segmentation network has been developed to classify CT images from PDAC patients and control groups. Chuet al[30 ]standardized the number of cases, the sizes of the segmented images, and the selection of organs and then segmented the boundaries of the abdominal organs and pancreatic tumors in 575 control subjects and 750 patients with PDAC. The results showed that the sensitivity and specificity of the algorithm in detecting PDAC in patients were 94 .1 % and 98 .5 %, respectively. The early diagnosis of PDAC is a problem that many physicians find difficult. Appelbaumet al[31 ] developed a risk model for the prediction of PDAC based on patient EHRs that could identify high-risk groups one year in advance,suggesting that their risk scores could also be used as an initial filter for PDAC.

    BENIGN DIGESTIVE DISEASES

    In addition to gastric cancer, liver cancer and other malignant tumors, other digestive system diseases include ulcerative colitis, pancreatitis, gastric ulcer, gastritis, intestinal polyp and other benign digestive system diseases. We summarize the application of AI for the benign digestive system diseases discussed below. The latest applications of AI in ulcerative colitis, severe acute pancreatitis, gastric ulcers, gastritis and intestinal polyps are summarized in Table 2 .

    AI and ulcerative colitis

    Ulcerative colitis (UC) is a common chronic intestinal disease; however, there is no single gold standard for the diagnosis of this disease. Combining clinical, laboratory, imaging, endoscopic and histopathological findings, the diagnosis is made by excluding infectious and other noninfectious forms of colitis[32 ]. Endoscopy is essential, but the accuracy and precision of the diagnosis are limited by doctors’subjectivity. Yaoet al[33 ] established a fully automatic endoscopic disease grading video analysis system through AI. These authors used a CNN to train models to predict the amount of information in still images and, thus, determine the severity of the disease. Then, the authors examined 51 and 264 videos from developed high-resolution and multicenter clinical trial test sets, respectively. The results showed that the static image information classification system had good performance, with a sensitivity of 0 .902 and specificity of 0 .870 . For the high-resolution videos, the fully automated methods correctly predicted the Mayo endoscopic score (MES) in 78 %. The automated MES grading of the clinical trial videos (often low resolution) correctly distinguished remittedvsactive disease in 83 .7 %. To analyze endoscopic images of UC more accurately, Takenakaet al[34 ] developed a deep neural network system and tested 40758 colonoscopy images and 6885 biopsy results from 2012 UC patients. The results identified endoscopic remission with 90 .1 % accuracy and histologic remission with 92 .9 % accuracy. In addition,Maedaet al[35 ] developed a CAD system to predict persistent histologic inflammation using endocytoscopy and evaluated its accuracy using 12900 endocytoscopy images. The results showed that the CAD system provided a diagnostic sensitivity, specificity, and accuracy of 74 %, 97 % and 91 %, respectively. In recent years, great progress has been achieved in the treatment of UC, but surgery remains important[36 ]. These results show that AI has great potential in the diagnosis and treatment of UC.

    AI and pancreatitis

    Acute pancreatitis (AP) is a common clinical acute abdomen disease with a complex and variable presentation. Severe AP (SAP) is often life threatening, with multiple organ dysfunction induced by SAP being a particularly difficult clinical problem[37 ]. Qiu et al[38 ] developed three ML algorithms to predict the risk of organ failure in moderate SAP (MSAP) and SAP. These authors inputted 16 parameters from 263 patients with MSAP and SAP into a support vector machine (SVM), logical regression analysis (LRA) and ANN models. The results showed that the SVM, LRA and ANN models could effectively predict the risk of multiorgan failure in MSAP and SAP. Respiratory failure is the main cause of early death in SAP. The early prediction of acute lung injury (ALI) is beneficial for reducing mortality from SAP. The ANN model established by Feiet al[39 ] can effectively predict the occurrence of ALI induced by SAP, with the accuracy of predicting severe acute respiratory distress syndrome reaching 82 .8 %. Abdominal infection is an important risk factor for organ failure induced by SAP.Compared with logistic regression analyses, the ANN model developed by Qiuet al[40 ] can more accurately predict abdominal infection in MSAP and SAP, with a sensitivity and specificity of 80 .99 %and 89 .44 %, respectively. Fei et al[41 ] constructed and verified an ANN model based on clinical and laboratory data from 72 patients with AP. Notably, the sensitivity, specificity, positive predictive value and negative predictive value of the ANN model for portosplenomesenteric venous thrombosis(PSMVT) were 80 %, 85 .7 %, 77 .6 % and 90 .7 %, respectively. Thus, this model provides a good reference for the clinical prediction of the occurrence of PSMVT. The recurrence rate after the first attack of AP is approximately 22 %, but few indicators can predict this recurrence. Chen et al[42 ] developed a quantitative radiology model based on contrast-enhanced CT. The results of the verification analysis showed that the model can predict the recurrence of AP well in the main and verification populations,with accuracies of 87 .1 % and 89 .0 %, respectively. This finding suggests that their model may be a good quantitative method for the prediction of recurrence in patients with AP. Chronic pancreatitis (CP),which is another common clinical digestive system disease, is an important factor in inducing pancreatic cancer. Although traditional pancreaticoduodenectomy, distal pancreatectomy, and the Frey and Beger procedures have achieved considerable success in relieving CP pain, the approaches are often accompanied by serious complications. Therefore, minimally invasive surgery and robot platforms are gradually being applied in the surgical treatment of CP. A retrospective study based on 812 cases of robotic pancreatectomy and reconstruction showed that the robotic platform is safe and feasible in performing complex pancreatectomy to alleviate the sequelae of CP[43 ]. Autoimmune pancreatitis (AIP)is a rare and special type of chronic pancreatitis, and its diagnosis is clinically challenging. Maryaet al[44 ] developed and validated a CNN model based on a database containing 174461 EUS images and videos from 583 patients. After training, the model could accurately distinguish AIP from PDAC and other benign pancreatic diseases with a sensitivity and specificity of 90 % and 85 %, respectively.

    Table 2 Recent researches on artificial intelligence in benign digestive system diseases

    AI and other diseases

    AI has been used in numerous applications for other diseases, such as gastric ulcers, gastritis and colorectal polyps. Namikawaet al[45 ] developed an advanced CNN (A-CNN) based on the original convolutional neural network and evaluated its applicability in the classification of gastric ulcers. These authors used 720 images from 120 patients with gastric ulcers to evaluate the diagnostic performance of the A-CNN. The results showed that the sensitivity, specificity, and positive predictive value of the ACNN in classifying gastric ulcers were 93 .3 %, 99 .0 %, and 99 .1 %, respectively. There are several subtypes of gastritis, including autoimmune, bacterial, and chemical. Steinbusset al[46 ] evaluated the ability of a CNN to classify the common gastritis subtypes using a small data set of 1230 gastric antrum and corpus biopsy images. The results showed that the overall accuracy in the test set was 84 %, and the sensitivity and specificity for bacterial gastritis were 100 % and 93 %, respectively. Ozawa et al[47 ] constructed a deep CNN architecture and trained the CNN using 16418 images from 4752 colorectal polyps and 4013 normal colorectal images. Then, the performance of the trained CNN was verified with 7077 additional colonoscopy images. The results showed that the sensitivity of the CNN was 92 %, and the positive predictive value was 86 %, proving that it has excellent potential as a colonoscopy CP-diagnosis support system based on AI.

    CONCLUSION

    With the steady development of AI and its heavy integration in the medical industry, AI has received increasing attention in the fields of medicine and health. Digestive system AI technology differs from other AI technologies because of the nonstandard nature of most digestive endoscopic images and the large number of influencing factors, resulting in difficulty in developing such technology. Currently, AI plays an important role in digestive system diseases, particularly in its gradual application in diagnosis and treatment in the clinic. AI has broad prospects in the field of medicine and health, but the cooperation of medical workers and computer experts is needed to develop more intelligent applications and higher-quality services for patients. In summary, as an emerging player, AI will continue to play an increasingly important role in future development. The close combination of AI and medicine can address problems, such as the insufficient supply and uneven distribution of medical resources and low degree of medical efficiency. More in-depth research should be performed to investigate the application of AI in digestive system diseases from various perspectives to obtain additional diagnosis and treatment measures, promote diagnosis, optimize treatment, improve patient prognosis, and gradually achieve intelligent and accurate medical treatment.

    FOOTNOTES

    Author contributions:Chen HY, Ge P, Liu JY contributed equally to the manuscript; Chen HY conceived this review and drafted the manuscript; Ge P, Liu JY, Bao F and Qu JL are responsible for the figure drawing and literature collation; Xu CM, Chen HL and Shang D edited and finalized the manuscript for submission; Zhang GX reviewed and approved the submitted manuscript.

    Supported byKey Discipline of Liaoning Traditional Chinese Medicine Clinical Ability Promote Construction Project,No. LNZYXZY201903 ; and Development Guidance Plan Projects in Liaoning Province, No. 2019 JH-8 /10300028 .

    Conflict-of-interest statement:There is no conflict of interest associated with any of the senior author or other coauthors contributed their efforts in this manuscript.

    Open-Access:This article is an open-access article that was selected by an in-house editor and fully peer-reviewed by external reviewers. It is distributed in accordance with the Creative Commons Attribution NonCommercial (CC BYNC 4 .0 ) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited and the use is noncommercial. See: https://creativecommons.org/Licenses/by-nc/4 .0 /

    Country/Territory of origin:China

    ORCID number:Hai-Yang Chen 0000 -0002 -6705 -2249 ; Peng Ge 0000 -0002 -2647 -2474 ; Jia-Yue Liu 0000 -0001 -9294 -7493 ;Jia-Lin Qu 0000 -0003 -2020 -4783 ; Fang Bao 0000 -0002 -1609 -2953 ; Cai-Ming Xu 0000 -0001 -7794 -2301 ; Hai-Long Chen 0000 -0001 -5247 -7343 ; Dong Shang 0000 -0002 -4300 -359 X; Gui-Xin Zhang 0000 -0002 -6171 -394 X.

    S-Editor:Wang JL

    L-Editor:A

    P-Editor:Wang JL

    91aial.com中文字幕在线观看| 2018国产大陆天天弄谢| 亚洲第一区二区三区不卡| 午夜影院在线不卡| 久久久久网色| 97在线视频观看| 亚洲激情五月婷婷啪啪| 欧美+日韩+精品| 香蕉精品网在线| 久久国产亚洲av麻豆专区| 亚洲综合色网址| 日韩av免费高清视频| 欧美bdsm另类| 看非洲黑人一级黄片| 久久人妻熟女aⅴ| 久久久久久久久久久免费av| 日韩视频在线欧美| 精品亚洲成a人片在线观看| 久久久久国产精品人妻一区二区| 精品卡一卡二卡四卡免费| 最近中文字幕高清免费大全6| 精品第一国产精品| 亚洲伊人久久精品综合| 只有这里有精品99| 99精国产麻豆久久婷婷| 97超碰精品成人国产| 日本欧美视频一区| 飞空精品影院首页| 少妇熟女欧美另类| 国产精品一区www在线观看| 精品国产国语对白av| 亚洲内射少妇av| 香蕉国产在线看| 成人亚洲欧美一区二区av| 日韩欧美一区视频在线观看| 亚洲精品456在线播放app| av卡一久久| 男女高潮啪啪啪动态图| 国产欧美日韩综合在线一区二区| 免费观看在线日韩| 亚洲精品一二三| 久热这里只有精品99| 欧美xxxx性猛交bbbb| 一级毛片我不卡| 亚洲精品av麻豆狂野| 国产精品久久久久久av不卡| 国产精品人妻久久久影院| 一区二区三区精品91| 亚洲av日韩在线播放| 日韩精品免费视频一区二区三区 | 毛片一级片免费看久久久久| xxx大片免费视频| 国产精品无大码| 天堂中文最新版在线下载| 国产伦理片在线播放av一区| 午夜福利视频在线观看免费| 久久人人爽人人片av| videossex国产| 国产精品一区二区在线不卡| 国产激情久久老熟女| 国产一区二区三区av在线| 寂寞人妻少妇视频99o| 99国产综合亚洲精品| 国产高清不卡午夜福利| 欧美激情 高清一区二区三区| 亚洲图色成人| 在线观看人妻少妇| 久久久久人妻精品一区果冻| 国产精品人妻久久久影院| 26uuu在线亚洲综合色| 亚洲一区二区三区欧美精品| 99视频精品全部免费 在线| 99re6热这里在线精品视频| 国产亚洲欧美精品永久| 亚洲一级一片aⅴ在线观看| 亚洲 欧美一区二区三区| 国产老妇伦熟女老妇高清| 亚洲图色成人| 成年人免费黄色播放视频| 两性夫妻黄色片 | 性色avwww在线观看| 国产精品蜜桃在线观看| 亚洲人成网站在线观看播放| 免费黄频网站在线观看国产| 成年女人在线观看亚洲视频| 国产黄色视频一区二区在线观看| 黄片播放在线免费| 十分钟在线观看高清视频www| 国产精品无大码| 亚洲av欧美aⅴ国产| 国产av精品麻豆| 亚洲人成网站在线观看播放| 国产日韩欧美在线精品| videos熟女内射| 巨乳人妻的诱惑在线观看| 999精品在线视频| 中文字幕精品免费在线观看视频 | 久久国产精品男人的天堂亚洲 | 精品福利永久在线观看| 亚洲成色77777| 一本—道久久a久久精品蜜桃钙片| 香蕉精品网在线| 99热全是精品| 久久久精品区二区三区| 性色av一级| 一边摸一边做爽爽视频免费| 日韩一区二区三区影片| 亚洲成人一二三区av| 欧美丝袜亚洲另类| 亚洲国产精品成人久久小说| 成人无遮挡网站| av在线播放精品| 亚洲精品av麻豆狂野| 校园人妻丝袜中文字幕| 久久影院123| 一级a做视频免费观看| 爱豆传媒免费全集在线观看| 精品一区二区三区四区五区乱码 | 黄色 视频免费看| 99热这里只有是精品在线观看| 国产片特级美女逼逼视频| 最后的刺客免费高清国语| 免费观看无遮挡的男女| 人人妻人人添人人爽欧美一区卜| 久久ye,这里只有精品| 国产亚洲午夜精品一区二区久久| 五月玫瑰六月丁香| 精品国产一区二区久久| 久久这里只有精品19| 十分钟在线观看高清视频www| 亚洲内射少妇av| 国产成人免费观看mmmm| 久久精品国产自在天天线| 如日韩欧美国产精品一区二区三区| 在线观看免费日韩欧美大片| 超色免费av| 日韩av在线免费看完整版不卡| 欧美日韩一区二区视频在线观看视频在线| 99国产精品免费福利视频| 男女无遮挡免费网站观看| 国产又爽黄色视频| 天天影视国产精品| 国产一区有黄有色的免费视频| 精品人妻一区二区三区麻豆| 日韩制服丝袜自拍偷拍| 自线自在国产av| 飞空精品影院首页| 女人被躁到高潮嗷嗷叫费观| 久热久热在线精品观看| 妹子高潮喷水视频| 妹子高潮喷水视频| 自线自在国产av| 久久精品国产a三级三级三级| 国产爽快片一区二区三区| 香蕉精品网在线| 香蕉精品网在线| 纯流量卡能插随身wifi吗| 久热久热在线精品观看| 久久精品国产a三级三级三级| 飞空精品影院首页| 精品亚洲成a人片在线观看| 亚洲精品久久成人aⅴ小说| 日本wwww免费看| 交换朋友夫妻互换小说| 亚洲av中文av极速乱| 日本wwww免费看| 亚洲一级一片aⅴ在线观看| av一本久久久久| 日韩成人av中文字幕在线观看| 国产熟女午夜一区二区三区| 免费女性裸体啪啪无遮挡网站| 婷婷色综合www| 精品少妇久久久久久888优播| 中文字幕最新亚洲高清| 国产精品女同一区二区软件| 亚洲,一卡二卡三卡| 日韩欧美精品免费久久| 亚洲欧美清纯卡通| 9热在线视频观看99| 蜜桃国产av成人99| 久久久久久人人人人人| 亚洲精品成人av观看孕妇| 激情视频va一区二区三区| 如何舔出高潮| 九九爱精品视频在线观看| 国产乱人偷精品视频| 99久久人妻综合| 午夜影院在线不卡| 两个人免费观看高清视频| 国产精品不卡视频一区二区| 18禁国产床啪视频网站| 亚洲精品美女久久av网站| 亚洲成色77777| 欧美xxⅹ黑人| 久久久久久伊人网av| 少妇的丰满在线观看| 精品久久蜜臀av无| av一本久久久久| 精品少妇久久久久久888优播| 在线观看免费高清a一片| 性色avwww在线观看| 亚洲国产精品成人久久小说| 一二三四在线观看免费中文在 | 九九爱精品视频在线观看| 日韩欧美一区视频在线观看| 伦精品一区二区三区| 亚洲欧美一区二区三区黑人 | 男的添女的下面高潮视频| 精品国产一区二区久久| 国产精品免费大片| 日本爱情动作片www.在线观看| 国语对白做爰xxxⅹ性视频网站| 三级国产精品片| 国产日韩欧美亚洲二区| 国产高清不卡午夜福利| 亚洲在久久综合| 国产女主播在线喷水免费视频网站| 天天操日日干夜夜撸| 一区二区三区精品91| 亚洲av成人精品一二三区| 亚洲精品乱久久久久久| 男女高潮啪啪啪动态图| 久久99热这里只频精品6学生| 女性被躁到高潮视频| 亚洲成人手机| 在线 av 中文字幕| 黄网站色视频无遮挡免费观看| 中文字幕制服av| 91成人精品电影| 少妇的逼水好多| 岛国毛片在线播放| 国产成人精品久久久久久| 亚洲精品日韩在线中文字幕| 最黄视频免费看| 自拍欧美九色日韩亚洲蝌蚪91| 亚洲国产最新在线播放| 国产精品蜜桃在线观看| 亚洲丝袜综合中文字幕| 国产av码专区亚洲av| 如日韩欧美国产精品一区二区三区| xxx大片免费视频| 亚洲综合精品二区| 香蕉精品网在线| 亚洲欧美色中文字幕在线| 熟女av电影| 亚洲欧美一区二区三区黑人 | 波野结衣二区三区在线| av网站免费在线观看视频| 看非洲黑人一级黄片| 大片电影免费在线观看免费| 夫妻午夜视频| 最近中文字幕高清免费大全6| 高清欧美精品videossex| 国产色爽女视频免费观看| 亚洲欧美一区二区三区黑人 | 久久人人爽人人爽人人片va| 久久精品夜色国产| 免费大片黄手机在线观看| 最近中文字幕2019免费版| 亚洲激情五月婷婷啪啪| 精品一区二区免费观看| 国产视频首页在线观看| 国产免费一区二区三区四区乱码| 久久精品夜色国产| 国产在线一区二区三区精| 亚洲精品一二三| 国产男女超爽视频在线观看| 欧美bdsm另类| 久久久久久久精品精品| 欧美 亚洲 国产 日韩一| 内地一区二区视频在线| 99国产精品免费福利视频| freevideosex欧美| 狂野欧美激情性xxxx在线观看| 一区二区三区乱码不卡18| 国产在线一区二区三区精| 欧美+日韩+精品| 永久网站在线| 搡女人真爽免费视频火全软件| 久久青草综合色| 激情视频va一区二区三区| 亚洲国产看品久久| 90打野战视频偷拍视频| 中文欧美无线码| 日韩av免费高清视频| 毛片一级片免费看久久久久| 999精品在线视频| 午夜福利乱码中文字幕| 伦理电影大哥的女人| 中文欧美无线码| 国国产精品蜜臀av免费| 精品国产国语对白av| 亚洲美女搞黄在线观看| 成人亚洲欧美一区二区av| 99热国产这里只有精品6| 国产精品一区二区在线不卡| 国内精品宾馆在线| 国产精品久久久av美女十八| 亚洲成av片中文字幕在线观看 | 久久99热6这里只有精品| 日韩视频在线欧美| 天堂中文最新版在线下载| 色吧在线观看| 精品国产国语对白av| 欧美丝袜亚洲另类| 在线观看免费视频网站a站| www.av在线官网国产| a级毛片在线看网站| 亚洲一级一片aⅴ在线观看| 亚洲欧美日韩卡通动漫| 欧美成人午夜精品| 欧美97在线视频| 99精国产麻豆久久婷婷| 国产熟女午夜一区二区三区| 91久久精品国产一区二区三区| 日本欧美国产在线视频| 久久久久久久国产电影| 日韩成人伦理影院| 边亲边吃奶的免费视频| 亚洲国产精品专区欧美| 色视频在线一区二区三区| 丝袜脚勾引网站| 久久久a久久爽久久v久久| 亚洲中文av在线| 制服诱惑二区| 国国产精品蜜臀av免费| 国产精品嫩草影院av在线观看| 晚上一个人看的免费电影| 蜜桃在线观看..| 国产精品偷伦视频观看了| 欧美国产精品一级二级三级| 狂野欧美激情性bbbbbb| 免费少妇av软件| 午夜福利网站1000一区二区三区| 午夜激情久久久久久久| 欧美 亚洲 国产 日韩一| 国产深夜福利视频在线观看| 国产精品一区二区在线观看99| 只有这里有精品99| 在线观看美女被高潮喷水网站| 国产精品一二三区在线看| 亚洲精品久久成人aⅴ小说| 男女下面插进去视频免费观看 | 国产无遮挡羞羞视频在线观看| 国产成人午夜福利电影在线观看| 伊人亚洲综合成人网| 色哟哟·www| 在线 av 中文字幕| 日本欧美视频一区| 男的添女的下面高潮视频| 精品一区在线观看国产| 韩国av在线不卡| 欧美变态另类bdsm刘玥| 永久免费av网站大全| 777米奇影视久久| 99久国产av精品国产电影| 91成人精品电影| 99视频精品全部免费 在线| 欧美bdsm另类| 日本av手机在线免费观看| 欧美丝袜亚洲另类| 人妻一区二区av| 国产黄频视频在线观看| 亚洲av电影在线观看一区二区三区| 建设人人有责人人尽责人人享有的| 热99久久久久精品小说推荐| 男女边摸边吃奶| 久久人人爽av亚洲精品天堂| 亚洲精品456在线播放app| 久久久精品免费免费高清| 男人操女人黄网站| 高清欧美精品videossex| 中文字幕最新亚洲高清| 侵犯人妻中文字幕一二三四区| 日韩一区二区视频免费看| 成人毛片60女人毛片免费| 国产精品人妻久久久影院| 丰满乱子伦码专区| 亚洲av免费高清在线观看| 国产精品国产三级国产专区5o| 精品亚洲成a人片在线观看| 熟女电影av网| av又黄又爽大尺度在线免费看| 国产精品熟女久久久久浪| 一级爰片在线观看| 最近最新中文字幕大全免费视频 | 男女啪啪激烈高潮av片| 久久综合国产亚洲精品| 中文字幕免费在线视频6| 国产av码专区亚洲av| 国产一区亚洲一区在线观看| 久久久久网色| 精品人妻在线不人妻| 一级,二级,三级黄色视频| 国产视频首页在线观看| 久久久久久久大尺度免费视频| 免费高清在线观看日韩| 国产成人精品婷婷| 麻豆精品久久久久久蜜桃| 久久鲁丝午夜福利片| 亚洲综合色惰| 精品一区二区三区视频在线| 国产午夜精品一二区理论片| 欧美精品一区二区免费开放| 亚洲成人手机| 在线观看一区二区三区激情| 亚洲av日韩在线播放| 亚洲av电影在线观看一区二区三区| 成人二区视频| 亚洲久久久国产精品| 黑人高潮一二区| 少妇 在线观看| 大陆偷拍与自拍| 2018国产大陆天天弄谢| 少妇人妻精品综合一区二区| 国产在线视频一区二区| 亚洲欧洲国产日韩| 国产精品熟女久久久久浪| av视频免费观看在线观看| 亚洲天堂av无毛| 丰满少妇做爰视频| 国产免费又黄又爽又色| 日产精品乱码卡一卡2卡三| 国产免费视频播放在线视频| 国产日韩欧美在线精品| 在线观看免费日韩欧美大片| 美女内射精品一级片tv| 午夜影院在线不卡| 这个男人来自地球电影免费观看 | 成年动漫av网址| 亚洲av中文av极速乱| xxxhd国产人妻xxx| 涩涩av久久男人的天堂| 精品福利永久在线观看| 欧美性感艳星| 熟妇人妻不卡中文字幕| 在线看a的网站| 久久热在线av| 国产深夜福利视频在线观看| 天堂中文最新版在线下载| 伦理电影免费视频| 中文字幕亚洲精品专区| 中文字幕另类日韩欧美亚洲嫩草| 午夜激情久久久久久久| 丰满饥渴人妻一区二区三| 国产成人精品在线电影| 亚洲av男天堂| 国产黄色视频一区二区在线观看| 亚洲精品美女久久久久99蜜臀 | 国产精品秋霞免费鲁丝片| 大香蕉97超碰在线| 宅男免费午夜| 日本vs欧美在线观看视频| www日本在线高清视频| 亚洲精品一二三| 精品一区二区免费观看| 日韩 亚洲 欧美在线| 免费看光身美女| 激情五月婷婷亚洲| 欧美成人午夜免费资源| 亚洲一区二区三区欧美精品| 99九九在线精品视频| 久久亚洲国产成人精品v| 999精品在线视频| 久久久国产欧美日韩av| 1024视频免费在线观看| 精品久久久精品久久久| 高清视频免费观看一区二区| 亚洲精品色激情综合| 另类精品久久| 中文字幕人妻丝袜制服| 久久ye,这里只有精品| 亚洲图色成人| 亚洲精品视频女| 好男人视频免费观看在线| 国产精品国产av在线观看| 日本wwww免费看| 最近的中文字幕免费完整| 国产在线免费精品| 亚洲欧洲日产国产| 自线自在国产av| 91午夜精品亚洲一区二区三区| 午夜福利视频精品| 少妇被粗大的猛进出69影院 | 伦理电影免费视频| 亚洲精品一区蜜桃| 极品人妻少妇av视频| 国产日韩欧美视频二区| 日本免费在线观看一区| 综合色丁香网| 丁香六月天网| 婷婷色麻豆天堂久久| 又黄又粗又硬又大视频| 97超碰精品成人国产| 少妇的丰满在线观看| 18禁观看日本| 亚洲天堂av无毛| 免费黄色在线免费观看| 亚洲成色77777| 欧美少妇被猛烈插入视频| 精品人妻一区二区三区麻豆| av免费观看日本| av女优亚洲男人天堂| 精品人妻熟女毛片av久久网站| 日本猛色少妇xxxxx猛交久久| 狠狠精品人妻久久久久久综合| 大话2 男鬼变身卡| 日日爽夜夜爽网站| 人妻 亚洲 视频| 我的女老师完整版在线观看| 999精品在线视频| 国产精品 国内视频| 午夜老司机福利剧场| 欧美激情国产日韩精品一区| 国产亚洲欧美精品永久| 精品99又大又爽又粗少妇毛片| 美女大奶头黄色视频| 美女内射精品一级片tv| 人妻一区二区av| 国产精品免费大片| 乱人伦中国视频| 日本色播在线视频| 黄色视频在线播放观看不卡| 成人亚洲欧美一区二区av| 观看美女的网站| 80岁老熟妇乱子伦牲交| 各种免费的搞黄视频| 久久人人97超碰香蕉20202| 欧美日韩成人在线一区二区| 国产片特级美女逼逼视频| 久久女婷五月综合色啪小说| 久久人人爽av亚洲精品天堂| 男女无遮挡免费网站观看| 极品人妻少妇av视频| 香蕉精品网在线| 免费人妻精品一区二区三区视频| 久久久久网色| 国产精品久久久久久久电影| 久久久久网色| 免费观看在线日韩| 欧美 亚洲 国产 日韩一| 亚洲av欧美aⅴ国产| 国产精品久久久久久av不卡| 99re6热这里在线精品视频| 伦理电影免费视频| 亚洲国产看品久久| 国产欧美另类精品又又久久亚洲欧美| 国产欧美日韩一区二区三区在线| 亚洲精品久久久久久婷婷小说| 黄色视频在线播放观看不卡| 91午夜精品亚洲一区二区三区| 十八禁网站网址无遮挡| 午夜激情久久久久久久| tube8黄色片| 午夜av观看不卡| 欧美亚洲日本最大视频资源| 日韩av在线免费看完整版不卡| 亚洲国产精品成人久久小说| 亚洲欧美一区二区三区黑人 | 制服人妻中文乱码| 亚洲精品一二三| av一本久久久久| 80岁老熟妇乱子伦牲交| 有码 亚洲区| 成人综合一区亚洲| 国产精品人妻久久久影院| 十八禁高潮呻吟视频| 精品国产一区二区久久| 自线自在国产av| 少妇被粗大猛烈的视频| 美女视频免费永久观看网站| 国产精品偷伦视频观看了| a级毛色黄片| 蜜臀久久99精品久久宅男| 欧美精品亚洲一区二区| 国产永久视频网站| 午夜激情av网站| 精品人妻偷拍中文字幕| 亚洲欧美中文字幕日韩二区| 国产高清不卡午夜福利| 亚洲精品av麻豆狂野| 精品酒店卫生间| 国产av国产精品国产| 日本黄色日本黄色录像| 搡老乐熟女国产| 熟女av电影| 观看美女的网站| 99国产精品免费福利视频| 久久人人爽av亚洲精品天堂| 亚洲久久久国产精品| 久久99热这里只频精品6学生| 日韩,欧美,国产一区二区三区| 免费观看性生交大片5| 欧美激情极品国产一区二区三区 | 日韩一区二区视频免费看| 亚洲国产欧美在线一区| 熟妇人妻不卡中文字幕| 日本wwww免费看| 97在线人人人人妻| 中国三级夫妇交换| 国产日韩欧美在线精品| 亚洲av福利一区| 成年动漫av网址| 多毛熟女@视频| 免费看不卡的av| 久久人人爽av亚洲精品天堂| 99re6热这里在线精品视频| 日本爱情动作片www.在线观看| 免费大片黄手机在线观看| 国产免费视频播放在线视频| 亚洲av电影在线进入| 亚洲精品国产av成人精品| 制服丝袜香蕉在线| 丝袜脚勾引网站| 汤姆久久久久久久影院中文字幕|