基于人工智能平台的直肠癌分期识别系统外科临床应用专家建议（2020版）

目前直肠癌分期的术前评估主要依赖影像学检查,影像学阅片结果将直接决定直肠癌患者治疗方案的选择。为了缓解影像科医师的阅片压力,同时进一步提高影像学诊断的效率和准确性,目前已有利用人工智能自动识别系统辅助直肠癌分期影像学评估的相关研究。中华医学会外科学分会结直肠外科学组联合北京航空航天大学提出基于人工智能平台的直肠癌分期识...     

胆囊癌新辅助治疗研究现状

胆囊癌发病率逐年增高,目前治疗效果欠佳,为了改善胆囊癌患者的预后,有必要加强胆囊癌新辅助治疗研究.本文通过回顾已发表和正在开展的胆囊癌新辅助治疗研究,跟踪胆囊癌转化治疗(包括肿瘤化疗、放疗、免疫和靶向治疗)最新研究进展,对胆囊癌新辅助治疗研究现状进行阐述.     

基于深度学习人工智能在结肠镜检查中应用研究

目的 构建人工智能辅助的结肠镜质量评估算法及肠息肉形态分类算法,客观评估肠镜检查质量、息肉形态,实现结肠镜检查的规范化和统一化。方法 收集复旦大学附属中山医院2018年1月至8月,共18 962张肠镜图片。其中7140张用于肠镜质量评估算法建立,11 822张用于肠息肉形态分类算法建立。把肠镜图像作为卷积神经网络（CNN）的输入,端到端训练卷积神经网络,实现肠镜图像的分类任务,从而建立算法。其中包括3个模型：（1）肠道准备质量评分（四分类）。（2）回盲瓣的识别（二分类）。（3）无蒂和有蒂息肉的分类（二分类）。结果 肠镜质量评估模型对回盲瓣识别的准确率为95.27%,受试者工作特征（ROC）曲线下的面积（AUC）为0.9769,对基于波士顿评分标准四分类的图像的识别总精度为76.96%。肠息肉形态分类模型的AUC值为0.8695。结论 该深度学习模型用于肠镜检查质量的评估和肠息肉形态学的分类,具有良好的特异度、敏感度和AUC值,可辅助医师对肠镜检查质量进行评价,并对肠息肉进行分类,实现规范化和统一化。     

腹腔镜胆囊癌根治术的适应证及临床价值

胆囊癌(gallbladder carcinoma,GBC)是临床中较为常见的恶性肿瘤之一,约占肝外胆管恶性肿瘤的25%。据统计,胆囊癌发病率女性高于男性(女∶男约为3∶1)。胆囊癌转移途径以淋巴转移和肝脏直接浸润最为常见。目前,手术仍是胆囊癌最有效的治     

158例原发性胆囊癌根治性手术临床疗效及预后因素分析

目的 探讨经根治性手术治疗的原发性胆囊癌临床疗效及预后影响因素.方法 回顾性分析2012年1月至2019年9月苏州大学附属第一医院收治的158例原发性胆囊癌患者的临床及病理资料.应用Kaplan-Meier法绘制生存曲线计算生存率,单因素分析采用Log-rank检验,多因素分析采用Cox比例风险回归模型.结果 158例...     

三种肿瘤标记物联合检测对胆囊癌的诊断价值

目的：探讨CA199、CEA、CA153联合检测对胆囊癌的诊断价值。方法：选择40例Ⅱ期胆囊癌患者（恶性组）,40例胆囊良性病变患者（良性组）,40例健康体检者（对照组）;检测各组患者CA199、CEA、CA153水平,对检测结果进行统计学分析,检测上述指标单独及联合检测对胆囊癌的诊断价值。结果：恶性组血清CA199、CEA、CA153水平术前1周、术后第1 d、第7 d、2周均明显高于良性组、对照组,差异均有统计学意义（P＜0.05）;恶性组术后2个月CA199、CEA、CA153水平较术前明显下降。结论：CA199、CEA、CA153联合检测对胆囊癌的诊断具有重要价值。     

直肠癌淋巴结转移的深度神经网络评判研究进展

正目前,临床上对于直肠癌常用的影像评估方法有MRI、螺旋CT、PET-CT、直肠腔内超声(ERUS)等。而MRI作为首选检查方式,对肿瘤位置、浸润深度、淋巴结转移、血管侵犯、环周切缘及周围器官侵犯等方面的评估均具有明显优势~([1-2])。通过MRI诊断淋巴结的方法通常是影像科医师逐层浏览每一幅图像,从中识别淋巴结的形状、界限及密度来判断,这种传统方式耗时较长且存在主观偏倚,导致     

基于CT图像的深度学习算法在诊断结直肠癌同时性腹膜转移中的应用价值

目的:对结直肠癌同时性腹膜转移患者进行精准诊断和分期依旧困难。本研究旨在利用人工智能的ResNet-3D算法构建一种矢量向量模型（SVM）分类器,来预测结直肠癌同时性腹膜转移。方法:由放射科医生按原始格式,回顾性提取2017年1月至2018年5月期间,在中山大学附属第六医院经病理确诊的同时性腹膜转移或无腹膜转移的结直肠...     

胆囊癌相关基础研究现状与展望

胆囊癌是胆道系统常见恶性肿瘤,其恶性程度高,早期诊断困难,根治性切除率低,放化疗等现有综合治疗效果不理想,预后极差.因此,加强胆囊癌相关基础与临床转化研究具有重要意义.应加强在胆囊癌领域的多中心合作,进一步完善生物样本、临床病理学、预后及生物信息等多维度的大数据平台建设,结合数据分析手段,以期实现胆囊癌的早期诊断,个体...     

基于深度学习情感分类模型的个性化抑郁症护理策略

目的 探讨人工智能技术在个性化抑郁症护理中的应用,实现精准护理以加速抑郁症患者的康复。方法 将60例抑郁症患者按病种和病情分层随机分配为对照组和观察组各30例.对照组采用传统护理方法;观察组采用基于深度学习情感分类模型分类后的个性化护理方案,即利用脑电图像（EEG）采集设备获取大量带标记的脑电信号数据构建EEG情感训练库,标记抑郁症类型;通过深度学习情感分类模型识别抑郁症患者EEG信号对应的情感类别;根据其识别结果,采取相应的个性化护理措施。对两组患者在住院期间进行等间隔的抑郁量化评估和护理满意率调查。结果 干预4周时,观察组汉密尔顿抑郁量表（HAMD）和自评抑郁量表（SDS）的评分显著低于对照组（均P<0.05）;观察组干预8周时的康复率高于对照组,但两组比较,差异无统计学意义（P>0.05）。结论 基于深度学习情感分类模型的个性化护理方法能显著缓减患者的抑郁程度,加快抑郁症患者的康复速度。     

Detecting total hip replacement prosthesis design on plain radiographs using deep convolutional neural network

Identifying the design of a failed implant is a key step in the preoperative planning of revision total joint arthroplasty. Manual identification of the implant design from radiographic images is time-consuming and prone to error. Failure to identify the implant design preoperatively can lead to increased operating room time, more complex surgery, increased blood loss, increased bone loss, increased recovery time, and overall increased healthcare costs. In this study, we present a novel, fully automatic and interpretable approach to identify the design of total hip replacement (THR) implants from plain radiographs using deep convolutional neural network (CNN). CNN achieved 100% accuracy in the identification of three commonly used THR implant designs. Such CNN can be used to automatically identify the design of a failed THR implant preoperatively in just a few seconds, saving time and improving the identification accuracy. This can potentially improve patient outcomes, free practitioners' time, and reduce healthcare costs.     

Automated liver tumor detection in abdominal ultrasonography with a modified faster region-based convolutional neural networks (Faster R-CNN) architecture

BackgroundAlthough diagnostic ultrasound can non-invasively capture the image of abdominal viscera, diagnosis of the continuous ultrasound liver images to detect a liver tumor effectively and to determine whether the detected is benign or malignant is nontrivial. In order to minimize the gaps in diagnostic accuracy depending on doctor’s proficiency, we built an automated system to support the ultrasonography of liver tumors by employing deep learning technologies.MethodsWe constructed a neural network model for the automated detection of tumor tissues and blood vessels from the sequential liver ultrasound images. Faster region-based convolutional neural networks (Faster R-CNN) is employed as a base model for the object detection, which can output the detection results in 4 frames per second and enable the system to be particularly suitable for the real time ultrasonography. Moreover, we proposed a new neural network architecture feeding both the current and previous images into Faster R-CNN. For training the models, intraoperative ultrasound images obtained from one hepatocellular carcinoma (HCC) patient were used. The obtained image was a multifaceted observation of the liver and includes one HCC and some blood vessels. We labeled 91 images with the help of a liver specialist. We compared the tumor detection performance of the plain Faster R-CNN model with that of the proposed model.ResultsWe find that both the models performed well in detecting HCC and blood vessels, after training with 400 epochs using Adam. However, the mean precision of our model reaches 0.549, which is 0.019 better than that of the plain Faster R-CNN, and the mean sensitivity of our model about HCC reaches 0.623±0.385 for 30 scenes of sequential liver ultrasound images, which is also 0.146 better than that of the plain Faster R-CNN model.ConclusionsThe comparison between the proposed model and the plain Faster R-CNN model shows that we achieved better accuracy in tumor detection, in terms of the mean precision as well as the mean sensitivity, with the proposed model.     

胆囊癌和胆囊结石相关危险性的分析

目的 明确胆囊癌和胆囊结石之间的相关关系。方法 回顾性调查了全国28个省市的3922例胆囊癌，结合病例对照方法研究胆囊结石的病程，胆囊结石大小和胆囊癌的关系。结果 (1)胆囊癌合并胆囊结石的发生率为46．7％，胆囊癌伴发胆囊结石的相对危险度为13．7。(2)合并胆囊结石的病程平均为10～15年。(3)胆囊结石直径大于3cm比结石直径在1cm内的风险高8．8倍。结论 直径大于3cm，病程达10～15年的胆囊结石是胆囊癌发生的高危险因素，建议对这类病人进行手术治疗。     

2011年—2020年深度学习用于医学影像学研究文献分析

搜索2011年-2020年Web of Science核心合集（WoSCC）数据库中关于深度学习在医学影像学研究领域中的应用的文献,以VOSviewer 1.6.13软件分析数据并构建知识图谱,评估该领域最具影响力的文献和科研热点。     

胆囊的解剖学特点及胆囊癌浸润转移途径

胆囊癌的侵袭转移与胆囊的解剖特点密切相关。胆囊具有直接连接肝床、薄弱的黏膜下肌层、丰富多向的淋巴回流和神经支配、胆囊静脉直接汇入门静脉、与周围脏器关系密切等解剖特点。肝转移和淋巴转移是最常见的浸润转移方式,胆管转移多表现为直接浸润并且常伴有神经侵犯。周围脏器侵犯、腹腔播散和远处转移是胆囊癌的晚期表现。从解剖和病理生理的角度认识胆囊癌的浸润转移特性,将有助于理解不同部位、类型、不同进展期胆囊癌的临床表现,制定治疗方案及评估预后。     

胆囊癌外科治疗与临床预后分析

目的 研究胆囊癌临床特征,分析探讨影响其预后的有关因素,为提高胆囊癌预后提供临床依据。方法 选取我院2008年1月至2014年12月96例胆囊癌患者的临床资料,采用Kplan-Meier法对确定的单因素进行生存分析,用Cox回归法进行多因素分析。结果 单因素生存分析显示,手术方式（x²=32.209,P<0.001）、TNM分期（x²=109.408,P<0.001）、淋巴结转移（x²=69.691,P<0.001）、肿瘤部位（x²=10.667,P= 0.014）、p53（P<0.05）、MSH2（P<0.05）和CK7（P<0.05）影响胆囊癌预后,而年龄（x²=10.039,P=0.844）、性别（x²=0.664,P=0.415）等与胆囊癌预后无关。Cox多因素分析发现：TNM分期（P<0.001）、手术方式（P= 0.004）、淋巴结转移（P=0.008）为影响胆囊癌预后的独立危险因素。结论 胆囊癌呈现发病隐匿、临床症状无特异性、恶性程度高且预后差等特点。其中多数患者伴有腹痛、胆囊结石、黄疸、淋巴结转移,TNM分期越高的患者预后更差,根治性切除术可改善患者的预后。多因素分析表明TNM分期、手术方式、淋巴结转移为影响胆囊癌预后的独立危险因素。     

加速康复外科在胆囊癌根治手术中的应用

目的:探讨加速康复外科理念(ERAS)在胆囊癌根治术中的应用价值。方法:选取2013年1月至2018年12月行胆囊癌根治术的50例患者为研究对象,按围手术期是否采用加速康复外科处理措施分为实验组(n=25)与对照组(n=25),比较两组手术时间、术中出血量、术毕转入ICU例数、术后肛门排气时间、术后进食时间、下床活动时间、引流管拔除时间、住院时间、住院费用、疼痛评分、术后肿瘤复发转移率、病死率及胆漏、腹腔出血、切口感染、肺部感染等并发症情况。结果:实验组术后肛门排气时间、术后进食时间、下床活动时间、引流管拔除时间、住院时间、住院费用、疼痛评分均优于对照组,差异有统计学意义(P<0.05);两组手术时间、术中出血量、术毕转入ICU例数差异无统计学意义(P>0.05);两组术后胆漏、腹腔出血、切口感染、肺部感染情况差异亦无统计学意义(P>0.05)。随访期内,两组肿瘤复发转移率、死亡率差异无统计学意义(P>0.05)。结论:加速康复外科理念在胆囊癌根治术中具有不影响原有疗效,但可减轻患者痛苦、减少创伤、加速康复的重要价值。     

Incidence and management of gallbladder cancer in cholecystectomy specimens: a 5-year tertiary centre experience

Background

Gallbladder cancer (GBC) is an uncommon, but highly aggressive cancer. Half of these cases are diagnosed pre-operatively, and the remaining cases are discovered incidentally on post-cholecystectomy specimens. There is a significant geographical variability in GBC incidence, with increasing age, female sex, and prolonged duration of cholelithiasis being risk factors for GBC. The primary aim was to define the overall local incidence of GBC incidental GBC and management of these cases. The secondary aim was to determine any pertinent risk factors in our case population.

Methods

A retrospective observational study was performed on all the cholecystectomy specimens at the Gold Coast Hospital and Health Service from 1 January 2016 to 2 December 2021. Data was collected via the electronic medical record. The incidence and management of gallbladder cancers was calculated, and association with body mass index (BMI), smoking status, diabetes, inflammatory bowel disease (IBD) was identified.

Results

3904 cholecystectomy specimens were reviewed. GBC was identified in 0.46% of cholecystectomies. 50% of these cases were found incidentally. Abdominal pain was the most common presenting complaint (94.4%). GBC was associated with increased age and BMI and female sex. There was no association between smoking status, diabetes or IBD with an increased incidence of cancer. Tumour staging guided surgical and/or adjuvant chemotherapy.

Conclusion

GBC is rare. Patients with symptoms are associated with a poor prognosis. Incidental cancers are common, and negative margin resection based on the T stage of the cancer is the most reliable curative option.