泌尿系结石CT征象与手术方式的相关性：NLP研究

目的:以自然语言处理(NLP)方法研究泌尿系结石CT报告征象与临床手术方式的相关性.方法:回顾性选取HIS中因泌尿系结石行CT检查、并在本院行外科处理的住院患者资料,包括CT报告、出院小结中记录的诊疗经过,形成记录文档.使用不同NLP模型研究CT报告中结石的影像特征与手术方式的相关性.结果:共纳入371例连续患者的资料用于分析,其中行经皮肾镜碎石取石术(PNL) 142例,输尿镜碎石术(URL) 190例,输尿管软镜碎石术(IRS) 39例.NLP提取“结石”、“炎症”、“输尿管形态”为关键CT特征,十折交叉验证结果显示,经优化后的NLP对结石手术(URL和PNL)分类符合率为0.730,ROC曲线下面积为0.741.结论:NLP用于CT结石特征分析是可行的,可为临床决策提供一定的帮助.     

自然语言处理对泌尿系结石CT特征的提取：与人工诊断结果的对照研究

目的:研究自然语言处理(NLP)对泌尿系结石CT特征的提取效果.方法:回顾性分析379例泌尿系结石(392个)行手术治疗患者的CT报告,以人工和NLP方法分别进行结石相关图像特征的分析.NLP分析过程:结合人工校正,进行文本信息的提取和加工,通过机器学习制定原则,得到关键特征,交叉验证这些关键特征与不同手术方式的相关性.专家分析过程:三位医师分析CT图像,人工确定需提取的关键特征,分析各种特征与手术方式的相关性.结果:NLP分析所得关键特征为“结石”、“炎症”和“输尿管形态”相关信息,其预测手术方式的符合率为0.456,ROC下面积为0.608.专家分析所得关键特征中,“结石上下位置”、“肾周索条影”、“输尿管壁增厚”和“结石大小”这4个征象与手术方式的选择有相关性(r=0.192、-0.318、-0.285和-0.359,P＜0.05).结论:NLP提取的泌尿系结石的关键CT特征与专家评估的结果类似,其对手术方式的预测效能得到初步肯定.     

一水草酸钙结石的碎石脆性研究

 目的 探讨CT在预测一水草酸钙结石(COM)的碎石脆性中的价值.方法 选择50例开放手术取出的、经红外光谱法证实的COM标本行体外冲击波碎石,患者术前均行CT扫描结石,观察其结构特征并采用双盲法对其进行结构异质性分类,同时测量CT值,最后对COM的结构特征、CT值与碎石次数进行相关性分析.结果 对COM进行结构异质性分类有高度可重复性(K=0.83),同质COM所需碎石冲击次数为(1 883±813)次,异质COM所需碎石冲击次数为(908±527)次,同质COM较异质COM所需碎石冲击次数更多(P＜0.05),而CT值与COM的碎石脆性无相关性(P =0.82).结论 一水草酸钙结石的碎石脆性是由其结构决定的,与其CT值无相关性.     

非增强螺旋CT与B超在泌尿系结石诊断中的价值比较

目的:探讨非增强螺旋CT(NCHCT)对泌尿系结石的诊断价值.方法:对50例急性腰腹部绞痛而怀疑泌尿系结石患者行NCHCT检查,并同时行泌尿系B超检查作对照,对检查结果进行临床随访,随访3天～3个月(平均0.5个月).结果:38例患者被证实为泌尿系结石(3例保守治疗后自行排出结石,28例经体外冲击波碎石后排出结石证实,7例手术取出结石),NCHCT诊断泌尿系结石38例;B超诊断泌尿系结石28例,1例假阳性.NCHCT与B超诊断泌尿系结石的敏感度分别为100%、73.7%,特异度分别为100%、91.7%,阳性预测值分别为100%、96.6%,阴性预测值分别为100%、52.4%,约登指数(正确指数)分别为1.0、0.65,NCHCT与B超相比较(u=3.23,P＜0.01),差异具有显著性意义.结论:NCHCT诊断泌尿系结石比B超具有更高的敏感度和特异度,可作为临床怀疑泌尿系结石、尤其是急性肾绞痛患者的常规检查方法.     

输尿管镜下钬激光碎石术治疗输尿管结石

正目的:探讨输尿管镜下钬激光碎石术治疗输尿管结石的方法。方法:回顾分析近年来输尿管结石患者500例的临床资料,包括术前基本情况、手术情况、术后情况。所有患者均行输尿管镜下钬激光碎石术,部分合并炎性息肉组织者予钬激光适当烧灼。碎石手术后常规留置双J管。结果:500例患者均成功置入输尿管镜,手术顺利,术后恢复顺利。475例(95%)结石完全碎石,18例(3.6%)结石     

气压弹道碎石术的术前准备及术中术后的观察与护理

气压弹道碎石术是在输尿管镜下应用气压弹道碎石机进行碎石的一种腔内碎石新技术,使大多数患者免于开刀之苦。我院自2 0 0 1年11月至今,应用德国R .WOLF输尿管镜及瑞士EMS气压弹道碎石机对12 2例泌尿系结石进行原位碎石,取得满意效果,现将术前准备及术中术后的观察与护理体会报告如下。1　临床资料本组12 2例,男74例,女4 8例,年龄16～6 8岁,平均38岁。膀胱结石12例,输尿管上段结石18例,输尿管下段结石6 6例,输尿管中段结石2 2例,双侧输尿管结石4例,其中10例曾行体外震波冲击碎石(ESWL)未能治愈。2　术前准备及术中护理术前1小时常规摄…     

不同类型输尿管结石治疗方法的探讨

目的：探讨不同类型输尿管结石治疗方法选择.方法：根据结石的大小、病程、肾积水情况、结石在输尿管的部位及输尿管本身的病变,对700例输尿管结石进行分类,并对其治疗方法进行回顾性分析.结果：本组均行饮水和药物排石其中Ⅰ类结石4周内结石排净率98.6%,4例行体外冲击波碎石（ESWL）治疗;Ⅱa类结石均行ESWL治疗,4周内结石排净率94.6%,转输尿管镜下碎石1例,开放手术8例;Ⅱb类结石行ESWL治疗者99例,周内结石排净率66.6%.转开放手术28例（当时无输尿管镜设备）,转输尿管镜下碎石5例,行输尿管镜下碎石56例,4周内结石排净率96.4%,失败2例转开放手术;Ⅲ类结石行输尿管镜下碎石5例,失败2例转开放手术,1例结合ESWL后治愈,开放手术8例,全部成功.结论：Ⅰ类输尿管结石,因结石小,病程短,肾积水轻,首选饮水和药物排石治疗;Ⅱa类输尿管结石首选ESWL;Ⅱb类输尿管结石位于输尿管中下段,输尿管镜操作容易,因此首选输尿管镜气压弹道碎石;Ⅲ类输尿管结石需尽快解除梗阻,有经验的术者可尝试榆尿管镜气压弹道碎石,但以开放手术为妥.     

输尿管结石的超声诊断与X线检查的对比分析

目的:探讨超声诊断对输尿管结石的临床应用价值,并与X线检查对比.方法:回顾本院2004年10月～2005年10月输尿管结石120例,其中单侧输尿管结石196例,双侧输尿管结石4例.全部病例中2例经手术证实,11例经输尿管镜证实,107例经体外排石证实.全部病例均行超声检查,并与腹部X线平片(KUB)、静脉肾盂造影(IVP)结果相比.结果:超声诊断输尿管结石的符合率较高(92.7%),明显高于KUB、IVP检查(62.0%);同时,超声可以为临床提供更多泌尿系的直接表现及伴发信息.结论:输尿管结石的首诊方法为超声.     

输尿管镜处理大于2cm输尿管下段结石的临床体会

目的评价输尿管镜处理输尿管下段大结石的安全性与有效性,并总结此术式的经验。方法从2006年6月~2009年5月,我们采用输尿管镜处理输尿管下段大于2cm结石共38例,术中应用气压弹道碎石(13例)和钬激光碎石术(25例)。男22例,女16例,年龄24～55岁,平均39岁。结石平均长径为2.28cm(2.0~2.8cm)。38例中有5例曾行体外冲击波碎石术(ESWL)失败而再行输尿管镜处理。结果患者术后均行泌尿系平片(KUB)复查残石情况。在38例患者中,有32例(84.2%)通过一次输尿管镜达到结石清除。4例(10.5%)需行ESWL辅助碎石,其中2例(5.3%)因结石上移至肾内而行ESWL。2例(5.3%)一期行经皮肾镜术取出结石。2例(5.3%)见术中输尿管假道并发症,均发生于采用气压弹道碎石术的患者。均未见术后并发症。术后1个月再复查B超及KUB,均未见有结石残留。结论输尿管镜结合钬激光碎石是处理输尿管下段2cm结石安全有效的方法之一。     

输尿管硬镜下气压弹道碎石术治疗输尿管中下段结石的体会

目的:探讨输尿管硬镜下气压弹道碎石技术治疗输尿管中下段结石的临床应用效果,提高治疗水平.方法:对183例经B超、静脉尿路造影、CT检查确诊为输尿管中下段结石的患者,行输尿管硬镜下气压弹道碎石治疗。结果:所有病例中180例一次性碎石成功,2例中段结石逆行进入肾盂,1例因输尿管结石远端先天性狭窄明显,术中输尿管镜插入困难而改为开放手术治疗,术中未发生输尿管穿孔、撕脱等严重并发症,术后肾积水改善明显,肾功逐步恢复正常。结论:输尿管硬镜下气压弹道碎石术仍是治疗输尿管中下段结石的有效方法。     

Natural Language Processing of Radiology Reports in Patients With Hepatocellular Carcinoma to Predict Radiology Resource Utilization

ObjectiveRadiology is a finite health care resource in high demand at most health centers. However, anticipating fluctuations in demand is a challenge because of the inherent uncertainty in disease prognosis. The aim of this study was to explore the potential of natural language processing (NLP) to predict downstream radiology resource utilization in patients undergoing surveillance for hepatocellular carcinoma (HCC).Materials and MethodsAll HCC surveillance CT examinations performed at our institution from January 1, 2010, to October 31, 2017 were selected from our departmental radiology information system. We used open source NLP and machine learning software to parse radiology report text into bag-of-words and term frequency–inverse document frequency (TF-IDF) representations. Three machine learning models—logistic regression, support vector machine (SVM), and random forest—were used to predict future utilization of radiology department resources. A test data set was used to calculate accuracy, sensitivity, and specificity in addition to the area under the curve (AUC).ResultsAs a group, the bag-of-word models were slightly inferior to the TF-IDF feature extraction approach. The TF-IDF + SVM model outperformed all other models with an accuracy of 92%, a sensitivity of 83%, and a specificity of 96%, with an AUC of 0.971.ConclusionsNLP-based models can accurately predict downstream radiology resource utilization from narrative HCC surveillance reports and has potential for translation to health care management where it may improve decision making, reduce costs, and broaden access to care.     

Coronal reconstruction of unenhanced abdominal CT for correct ureteral stone size classification

Purpose  

To determine whether size measurement of a urinary calculus in coronal reconstruction of computed tomography (CT) differs from stone size measured in the axial plane, and whether the difference alters clinical decision making.     

Value of CT in the preoperative assessment of lung cancer: a survey of thoracic surgeons

Practicing thoracic surgeons were randomly surveyed to evaluate how computed tomography (CT) has influenced the preoperative evaluation of bronchogenic carcinoma. Thirty-six percent of the 529 respondents routinely requested CT and 62% did so selectively. Approximately 40% indicated that CT provided useful information in most cases. Nearly all surgeons (98.7%) do not rely on the identification of enlarged lymph nodes with CT to spare the patient surgical staging; however, 77.5% are influenced by CT results in their staging procedures. Fifty-seven percent reported that a negative CT study eliminates surgical staging entirely unless the patient has a "coin lesion," in which case 75% are willing to proceed directly to thoracotomy. For surgeons who use CT selectively, an abnormal mediastinal contour on the radiograph was the most frequent radiologic abnormality to prompt CT (85%). Thirty-seven percent are influenced by tumor histology in their decision to request CT. There was little difference in the pattern of CT use between university and community hospital surgeons.     

Percutaneous Imaging-Guided Access for the Treatment of Calculi in Continent Urinary Reservoirs

Purpose: To describe our long-term experience with percutaneous access to continent urinary reservoirs for calculus removal. Patients and Methods: A retrospective study of 13 procedures in 10 patients was performed. In 2 of the 13 procedures, access and calculus removal was performed in a single session. In the other 11 procedures, initial access was obtained using ultrasonography, fluoroscopy, and/or computed tomography. The patients then returned at a later date for a second step where the access was dilated and the calculi were removed. Results: Access was achieved successfully in all cases with no complications. At mean follow-up time of 13.6 months (range 1–94 months) one patient had died of complications unrelated to her continent urinary reservoir. Another patient had been placed on suppressive antibiotics for recurrent calculi. The remaining patients were stone free and without late complication. Conclusions: Percutaneous removal of reservoir calculi can be performed safely, avoiding potential injury to the continence valve mechanism by a direct cystoscopic approach. We propose a two-stage procedure using CT guidance for initial access as the preferred technique.     

Xanthogranulomatous pyelonephritis in adults: clinical and radiological findings in diffuse and focal forms

AIM: To describe the clinical and radiological features of focal and diffuse xanthogranulomatous pyelonephritis (XGP) in adults. MATERIALS AND METHODS: A retrospective review of the clinical data, laboratory findings, imaging features, and surgical treatment of 13 cases of histologically proven XGP diagnosed between January 1993 and December 2005 was undertaken. There were 10 women and three men with a mean age of 55.2 years (range 30-87 years). All patients underwent both sonography and computed tomography (CT) of the kidneys. Magnetic resonance imaging (MRI) was performed in two patients. RESULTS: XGP was diffuse in 11 patients and focal in two patients. Fever, anorexia and weight loss, urinary symptoms, and flank pain were the most common manifestations. Urinary tract infection was found in eight patients. Sonography and CT showed diffuse kidney enlargement in seven cases and atrophy in five cases; a solitary solid mass was found in two patients. Hydronephrosis was noted in nine cases, staghorn calculus in six, and extensive pararenal disease in six. MRI failed to provide the preoperative diagnosis in the two patients with focal XGP. Total or partial nephrectomy was performed without postoperative complications. CONCLUSION: Although rare, XGP is the main differential diagnosis of malignant renal neoplasia. The definitive diagnosis depends on histological examination of the operative specimen. Preoperatively, the diagnosis can often be suspected based on imaging studies, primarily CT.     

The Reliability of a Standardized Reporting System for the Diagnosis of Appendicitis

Purpose

Computed tomography (CT) is a fast and ubiquitous tool to evaluate intra-abdominal organs and diagnose appendicitis. However, traditional CT reporting does not necessarily capture the degree of uncertainty and indeterminate findings are still common. The purpose of this study was to evaluate the reproducibility of a standardized CT reporting system for appendicitis across a large population and the system's impact on radiologists' certainty in diagnosing appendicitis.

Natural Language Processing in Radiology: Update on Clinical Applications

Radiological reports are a valuable source of information used to guide clinical care and support research. Organizing and managing this content, however, frequently requires several manual curations because of the more common unstructured nature of the reports. However, manual review of these reports for clinical knowledge extraction is costly and time-consuming. Natural language processing (NLP) is a set of methods developed to extract structured meaning from a body of text and can be used to optimize the workflow of health care professionals. Specifically, NLP methods can help radiologists as decision support systems and improve the management of patients’ medical data. In this study, we highlight the opportunities offered by NLP in the field of radiology. A comprehensive review of the most commonly used NLP methods to extract information from radiological reports and the development of tools to improve radiological workflow using this information is presented. Finally, we review the important limitations of these tools and discuss the relevant observations and trends in the application of NLP to radiology that could benefit the field in the future.     

Intraoperative Navigation in der Nasennebenhöhlenchirurgie mit dem Philips „Neuroguide”-System

OBJECTIVE: To investigate the feasibility, precision and usefulness of computer aided surgery in ENT-sinus surgery. MATERIAL AND METHODS: 5 Patients with chronic sinus pathology and an indication for sinus surgery were elected. For intraoperative navigation we used a Philips "NEUROGUIDE" system and surgical instruments with LED's. Navigation procedures are described in detail in the paper, the system's precision was measured by pointing at anatomical landmarks. The accuracy was measured as the distance in millimeter between the bony structures of the CT scan on screen and the haircross of the pointer's tip on the screen. Another parameter of the systems accuracy was calculated by the system itself as the root mean square error in millimeter (RMSE) between the registered markers position and the marker position in the CT data set. RESULTS: Axial 3/3/1 mm spiral CT provided sufficient resolution, data transfer via optical disk was practicable. Positioning of the navigation equipment required some experience and the registration of the patients head position needed attention, as the markers have to be pointed at precisely. During operation, the head tracking system must not change its position on the patients head to ensure a correct navigation display. The main advantage of the computed navigation system was the constant orientation during the sinus surgical procedure. Frontiers and critical anatomical structures could be identified in the corresponding CT data set, thus enabling the surgeon to decide on the further procedure. At present stage, the operation time was increased through the handling of the navigation system for at about 15 min, resulting in additional time of narcosis. CONCLUSION: We found the computed navigation system Philips "NEUROGUIDE" system to be an established technical aid, ready to use for ENT sinus surgery, in our cases with a precision between 1 and 3 mm. These results were similar to results obtained with a SPOCS Navigation System from Aesculap, as previously published by us [17].