Incidence of bone metastases in breast cancer patients in the United Kingdom: Results of a multi-database linkage study using the general practice research database

BackgroundBone is a frequent site for metastases among women with breast cancer. We conducted a study using the General Practice Research Database (GPRD), with linkage to the National Cancer Registry (NCR) and Hospital Episode Statistics (HES), to estimate the incidence of bone metastases in women with breast cancer in the United Kingdom.MethodsWe identified all women in the GPRD aged 20–99 with a first-time diagnosis of breast cancer between 2000 and 2006. To address potential underreporting, we developed and validated an algorithm to serve as a proxy for bone metastases. Bone metastases were defined as (1) a bone cancer diagnosis code on the same day or following breast cancer diagnosis date, or (2) another metastasis code plus codes consistent with bone metastases diagnosis or treatment using the algorithm. We sent questionnaires to a sample of general practitioners to validate these definitions.ResultsWe included 13,207 breast cancer patients (median age at diagnosis of 61 years) who contributed 70,885 person-years of follow-up. The majority of patients had stage 1 or 2 breast cancer (90.4%), and 2.6% had metastatic breast cancer at diagnosis. We identified 788 women (6.0%) with bone metastases after a median follow-up of 5.4 years. Questionnaire results validated the diagnosis of bone metastases in 88% of patients with a bone cancer code and for 70% identified with the algorithm.ConclusionThis is the first time the GPRD has been linked to HES and NCR to study the epidemiology of bone metastases, adding important information on the burden of bone metastasis.     

Potentialities of transabdominal ultrasound study in the diagnosis of gastric peptic ulcer

The results of examination in 44 patients with gastric peptic ulcer were used to consider the potentialities of a transabdominal ultrasound study in the diagnosis and monitoring of gastric ulcerations. The ultrasound semiotics of gastric ulcers is described in the paper. A role of transabdominal ultrasound study in the algorithm of radiation and instrumental studies of gastric ulcer is defined. The inclusion of this study into the algorithm of diagnosis and monitoring of gastric peptic ulcer will make it possible not only to diagnose gastric ulcerations better, but to follow up their cicatrization. It is expedient to include a transabdominal ultrasound study as one of the diagnostic techniques for gastric peptic ulcer.     

Early detection of precancerous lesions in dysplasias of the lung by rapid DNA image cytometry

Hematoxylin-and-eosin-stained cytologic smears of sputum from 28 patients with dysplastic and suspicious cell findings were subjected to DNA image cytometry after Feulgen restaining. The nuclear DNA contents were measured with a TV-based image-analysis system, the Leitz TAS plus, combined with an automatic microscope. Computation of DNA data was performed according to an algorithm for the diagnosis and grading of malignancy. Of the 19 cases that were proven to be malignant in the follow-up, either by histologic examination, sputum cytology, fine needle aspiration biopsy or autopsy, the algorithm identified 17 as malignant in a stage (dysplasia) in which cytology was not yet able to present a definite diagnosis of malignancy. Only two cases of bronchial carcinoma were not detected in the state of dysplasia by this procedure. The periods between the DNA diagnosis of malignancy in dysplasia and the morphologic evidence of cancer varied from three days up to six months. Of the 11 cases that had been classified as benign by the algorithm, 9 were confirmed as benign during the clinical follow-up. Rapid DNA image cytometry appears able to separate squamous dysplasias of the lung into precancerous and nonprecancerous lesions.     

Automatic liver segmentation in MRI images using an iterative watershed algorithm and artificial neural network

Precise liver segmentation in abdominal MRI images is one of the most important steps for the computer-aided diagnosis of liver pathology. The first and essential step for diagnosis is automatic liver segmentation, and this process remains challenging. Extensive research has examined liver segmentation; however, it is challenging to distinguish which algorithm produces more precise segmentation results that are applicable to various medical imaging techniques. In this paper, we present a new automatic system for liver segmentation in abdominal MRI images. The system includes several successive steps. Preprocessing is applied to enhance the image (edge-preserved noise reduction) by using mathematical morphology. The proposed algorithm for liver region extraction is a combined algorithm that utilizes MLP neural networks and watershed algorithm. The traditional watershed transformation generally results in oversegmentation when directly applied to medical image segmentation. Therefore, we use trained neural networks to extract features of the liver region. The extracted features are used to monitor the quality of the segmentation using the watershed transform and adjust the required parameters automatically. The process of adjusting parameters is performed sequentially in several iterations. The proposed algorithm extracts liver region in one slice of the MRI images and the boundary tracking algorithm is suggested to extract the liver region in other slices, which is left as our future work. This system was applied to a series of test images to extract the liver region. Experimental results showed positive results for the proposed algorithm.     

The necessity of complex use of radiation and endoscopic techniques in the differential diagnosis of gastric ulcerations

The results of examination of 156 patients were used to consider whether radiation and endoscopic techniques might be used in the differential diagnosis of gastric ulcerations. The necessity of their complex use is shown. Evidence is provided for that the understanding of intramural changes at the site of ulceration should underlie the interpretation of visual changes in the gastric mucosa. An algorithm has been developed for the rational and effective use of radiation and endoscopic techniques in the differential diagnosis of gastric ulcerations. The algorithm is shown to be highly effective in the correct interpretation of the pattern of an identified ulceration (98.4% specificity). Ultrasound and computed tomographic semiotics of benign and malignant gastric ulcerations is presented.     

An immune network inspired evolutionary algorithm for the diagnosis of Parkinson's disease

This paper presents a novel evolutionary algorithm inspired by protein/substrate binding exploited in enzyme genetic programming (EGP) and artificial immune networks. The immune network-inspired evolutionary algorithm has been developed in direct response to an application in clinical neurology, the diagnosis of Parkinson's disease. The inspiration for, and implementation of the algorithm is described and its performance to the application area considered.     

Joint classifier and feature optimization for comprehensive cancer diagnosis using gene expression data.

Recent research has demonstrated quite convincingly that accurate cancer diagnosis can be achieved by constructing classifiers that are designed to compare the gene expression profile of a tissue of unknown cancer status to a database of stored expression profiles from tissues of known cancer status. This paper introduces the JCFO, a novel algorithm that uses a sparse Bayesian approach to jointly identify both the optimal nonlinear classifier for diagnosis and the optimal set of genes on which to base that diagnosis. We show that the diagnostic classification accuracy of the proposed algorithm is superior to a number of current state-of-the-art methods in a full leave-one-out cross-validation study of five widely used benchmark datasets. In addition to its superior classification accuracy, the algorithm is designed to automatically identify a small subset of genes (typically around twenty in our experiments) that are capable of providing complete discriminatory information for diagnosis. Focusing attention on a small subset of genes is useful not only because it produces a classifier with good generalization capacity, but also because this set of genes may provide insights into the mechanisms responsible for the disease itself. A number of the genes identified by the JCFO in our experiments are already in use as clinical markers for cancer diagnosis; some of the remaining genes may be excellent candidates for further clinical investigation. If it is possible to identify a small set of genes that is indeed capable of providing complete discrimination, inexpensive diagnostic assays might be widely deployable in clinical settings.     

Possibilities of CT and US in the diagnosis of colonic cancer

The data of examination of 59 patients with colonic cancer were used to consider the potentialities of transabdominal, transrectal ultrasonography and X-ray computed tomography and to assess their value in diagnosing colonic cancer, including its "minor" forms. The paper describes the ultrasound and computed tomographic semiotics of colonic cancer and determines a place of the above techniques in the algorithm of radiation and instrumental studies. Inclusion of these techniques into the diagnostic algorithm may solve a range of differentially diagnostic problems and allows a preliminary analysis to be made in a tumor lesion according to the International TNM classification. Ultrasonography and X-ray computed tomography should be included into a range of basic methods for diagnosis of colonic cancer.     

Predictors of bacterial meningitis in resource-limited contexts: an Angolan case

Background

Despite the great morbidity and mortality that childhood bacterial meningitis (BM) is experiencing in Africa, diagnosis of BM in resource-limited contexts is still a challenge. Several algorithms and clinical predictors have been proposed to help physicians in decision-making but a lot of these markers used variables that are calculable only in well-equipped laboratories. Predictors or algorithm based on parameters that can be easily performed in basic laboratories can help significantly in BM diagnosis, even in resource-limited settings, rural hospitals or health centers.

Results

This retrospective study examined 145 cerebral-spinal fluid (CSF) specimens from children from 2 months to 14 years. CSF specimens were divided into two groups, according to the presence or not of a clinical diagnosis of BM. For each specimen, CSF aspect, CSF white blood cells (WBC) count, CSF glucose and protein concentration were analyzed and statistical analysis were performed. CSF WBC count ≥10/µl is no more a valuable predictor of BM. CSF protein concentration ≥50 mg/dl has a better sensitivity for BM diagnosis and when used with CSF glucose concentration ≤40 mg/dl, can help to diagnose correctly almost all the BM cases. An algorithm including CSF protein concentration, glucose concentration and WBC count has been proposed to rule out BM and to correctly diagnose it.

Conclusions

In resource-limited health centers, the availability of a combination of easy-to-obtain parameters can significantly help physicians in BM diagnosis. The prompt identification of a BM case can be rapid treated or transferred to adequate structures and can modify the outcome in the patient.     

Magnetic resonance imaging in the diagnosis of gastric cancer: X-ray versus MRI anatomic findings

The paper assesses the present-day role of MRI in the diagnosis of gastric cancer. The authors consider the major prerequisites for the main aim of their study to be: 1) a dramatic incidence of diffuse (endophytic) gastric carcinoma, which requires significant correction of today's approaches to its diagnosis and 2) a rather biased and, in the authors' opinion, present-day mainly negative attitude towards MRI of the stomach as a diagnostic method for its tumor lesions. By applying the X-ray-MRI anatomic principle to the comparative study of MRI findings in 50 patients with predominantly gastric intramural carcinoma and in 25 patients without gastric tumors (controls), the authors present their methods for gastric MRI, the MRI semiotics of gastric cancer by concurrently touching upon a variety of problems that characterize the potentialities of MRI of the stomach in the diagnosis of its tumor lesions, including their differential diagnosis. As a result, the authors highly appreciate gastric MRI and consider this method to be included into the diagnostic algorithm of radiation techniques used in the diagnosis of gastric cancer, which should occupy its definite diagnostic place.     

基于粗糙集的数据挖掘技术及其在临床医学诊断中的应用

数据挖掘是一个利用各种分析工具在海量数据中发现模型和数据间关系的过程。临床医学上大量的数据中蕴含着丰富的信息,利用数据挖掘技术,特别是基于粗糙集理论的数据挖掘技术,通过数据训练集所训练得到的算法模型能够有效应用于疾病诊断。并获得很高的准确率,本文简单介绍了数据挖掘技术的基本原理和主要方法,以及粗糙集理论的基本原理,并给出了一个利用数据挖掘技术对肺部肿瘤进行诊断评价的应用实例。     

DNA-cytometric diagnosis of prospective malignancy in borderline lesions of the uterine cervix

Interactive DNA cytometry was used for the diagnosis of prospective malignancy in 48 smears with borderline lesions (mild and moderate dysplasias) of the uterine cervix. In addition, 183 smears with benign squamous epithelia, 38 with carcinoma in situ and 7 with invasive squamous carcinoma were also measured. Nuclear Feulgen-DNA measurements were performed using various methods, and the resulting data were analyzed by an algorithm for a DNA-cytophotometric diagnosis of malignancy. The results were compared with the data on follow-up and subsequent histologic studies in these cases. There was no false-positive diagnosis in the 183 benign smears and only 1 false-negative diagnosis in the 76 histologically proven squamous-cell carcinomas, which yields a specificity of 100% and a sensitivity of 98.6%. The sensitivity for the detection of subsequent histologically proven malignancy in cases with cytologically mild or moderate dysplasia amounted to 97%. In 13 borderline cases, there was a mean interval of 21 months between the taking of the cytologic smear on which the DNA diagnosis of malignancy was made and the date on which the histologic confirmation of malignancy was made. In 17% of the cytologically dysplastic cases, the DNA diagnosis of malignancy was not verified by subsequent histologic investigation. These results indicate that interactive DNA cytometry is able to detect prospective malignancy in smears from borderline lesions of the uterine cervix with a high sensitivity.     

ROMA在卵巢上皮性癌早期诊断中的研究进展

卵巢上皮性癌（Epithelial ovarian cancer,EOC）死亡率居妇科恶性肿瘤首位,早期诊断可明显改善患者预后。人附睾上皮分泌蛋白（human epididymis protein 4,HE4）对早期EOC的检测敏感性高,有助于对EOC高危患者的筛选,与CA125可互补,增加盆腔包块患者中EOC早期诊断力度。HE4与CA125联合检测及结合绝经状态预测盆腔包块患者中卵巢恶性肿瘤的发病风险模型（Risk of Ovarian Malignancy Algorithm,ROMA）,能成功预测盆腔包块患者中EOC高风险个体,对卵巢良恶性肿瘤的鉴别预测更为准确且更易被接受,有较大的临床应用价值。     

基于小波变换的心电信号去噪算法

目的:去除在心电信号采集过程中混入的肌电干扰、工频干扰、基线漂移等噪声信号,避免噪声对心电信号特征点的识别和提取造成误判和漏判。方法:首先利用coif4小波对心电信号按Mallat算法进行分解,然后采用软、硬阈值折衷与小波重构的算法进行去噪。结果:采用MIT/BIH Arrhythmia Database中的心电信号进行仿真、验证,有效去除了三种常见的噪声信号。结论:本方法实时性好,为临床分析与诊断奠定了基础。     

Digital ischemia of the upper extremity: a systematic approach for evaluation and treatment

Symptomatic upper extremity digital ischemia is an uncommon disorder reflecting diverse etiologies. Herein we present an algorithm to aid in evaluation and treatment of digital ischemia. This approach seeks to establish the diagnosis and lead to appropriate treatment while minimizing testing and therapy. Practical application of the algorithm is demonstrated through illustrative cases.     

Identification of highly specific electroencephalographic patterns in patients with neuroepithelial tumors of the III ventricle by algorithmic methods

An algorithm was suggested for identifying highly specific electroencephalographic (EEG) patterns in neurooncologic patients. The algorithm provides selection of patients with their further classification into main and control groups based on the already existing database of EEG indicators; requests to it; generation of mono-indicator candidates for EEG-patterns on the basis of a 4-dipole table for selecting and verifying sensitive and specific EEG patterns and outlining the best ones. Our material included 368 patients with basal-diencephalic tumors. Algorithmic methods revealed new EEG patterns in patients with different anatomical and topographical variants of neuroepithelial tumors in the III ventricle. We think it reasonable to use the revealed syndromes to improve diagnosis and identify pathophysiological basis of clinical syndromes.     

Systems biology in unruptured intracranial aneurysm: a metabolomics study in serum for the detection of biomarkers

Intracranial aneurysm (IA) is a common devastating condition occurs in up to 6 % of the population. It is asymptomatic but potentially fatal because of the progressive enlargement and rupturing leads to subarachnoid hemorrhage. Early diagnosis of IA is more valuable before it ruptures and hemorrhage. The diagnosis of IA is usually carried out using computerized tomography or magnetic resonance imaging. However, there is no biochemical test or a marker available for diagnosis. Serum metabolites were analyzed from normal and unruptured intracranial aneurysms patients (UIA) by NMR spectroscopy to identify the presence of serum markers, which could provide a clue for diagnosis and altered metabolic pathways in UIA condition. Analysis of proton spectra revealed significant perturbations in 20 serum metabolites in UIA. Multivariate analysis showed a distinct separation of normal from UIA based on 17 most contributing metabolites, and the scoring algorithm determines the perturbed metabolic pathways in UIA (urea cycle, citric acid cycle and ammonia recycling). Also, the gene expression analysis shows the significant (p ≤ 0.05) change in ARG, CPS1 and OTC genes leading to dysregulation in the urea cycle. Further, estimation of urea showed a significant increase in serum urea, which provides the prospect of rapid diagnosis. Overall, this study demonstrates the promise of developing biomarkers for the diagnosis of UIA from serum. In addition, the implementation of systems biological approach in metabolomic context gained an understanding about UIA that reflects the numerous metabolic pathways identified to be affected in disease condition.     

Magnetic resonance imaging in the diagnosis of different forms of endometriosis

The present paper examines the capacities of non-invasive MRI in the diagnosis of endometriosis. A standardized study algorithm is proposed, indications and methodology for MRI in different forms of endometriosis (EM) are specified. It is shown that in the diagnosis of different types of EM there are specific changes in the MR pattern of small pelvic organs, which allow one to make a differential diagnosis of this disease with a higher sensitivity (96%) and specificity (87%) as compared with ultrasound study. MRI makes it possible to assess the degree of invasion of endometrioid heterotopies into the wall of the intestine and cervix uteri with a high degree of accuracy and to judge the degree and extent of intestinal luminal narrowing. Diagnostic errors in solving these problems (as well as those associated with the detection of extragenital foci of EM in the small pelvis) are due first of all to movement artefacts a (respiration and intestinal motility) particularly in the presence of a significant adhesive process and/or after surgical intervention. MRI does not virtually yield false-negative conclusions in the diagnosis of different forms of genital endometriosis (less than 3%), which, in the authors' opinion, rather justifies some hyperdiagnosis (about 11%) made by this method in the diagnosis of endometriosis of the rectovaginal septum. MRI is a closing, specifying stage of instrumental diagnosis of not only EM, but also other small pelvic diseases.     

Five-Year Prognosis Model of Esophageal Cancer Based on Genetic Algorithm Improved Deep Neural Network

ObjectivesEsophageal cancer is a high occult malignant tumor. Even with good diagnosis and treatment, the 5-year survival rate of esophageal cancer patients is still less than 30%. Considering the influence of clinical characteristics on postoperative esophageal cancer patients, the construction of a neural network model will help improve the poor prognosis of patients in the five years.Material and methodsIn this study, genetic algorithm optimized deep neural network is exploited to the clinical dataset of esophageal cancer. The independent prognostic factors are screened by Relief algorithm and Cox proportional risk regression. FTD prognostic staging system is established to assess the risk level of esophageal cancer patients.ResultsFTD staging system and independent prognostic factors are integrated into the genetic algorithm optimized deep neural network. The Area Under Curve (AUC) of FTD staging system is 0.802. FTD staging system is verified by the Kaplan-Meier survival curve, and the median survival time is divided for different risk grades. The FTD staging system is superior to the TNM stages in the prognosis effect. The AUC of deep neural network optimized by genetic algorithm is 0.91.ConclusionThe deep neural network optimized by genetic algorithm has good performance in predicting the 5-year survival status of esophageal cancer patients. The FTD staging system has a significant prognostic effect. The FTD staging system and genetic algorithm optimized deep neural network can be successfully availed in clinical diagnosis and treatment.     

Detecting mouse squamous cell carcinoma from submicron full-field optical coherence tomography images by deep learning

The standard medical practice for cancer diagnosis requires histopathology, which is an invasive and time-consuming procedure. Optical coherence tomography (OCT) is an alternative that is relatively fast, noninvasive, and able to capture three-dimensional structures of epithelial tissue. Unlike most previous OCT systems, which cannot capture crucial cellular-level information for squamous cell carcinoma (SCC) diagnosis, the full-field OCT (FF-OCT) technology used in this paper is able to produce images at sub-micron resolution and thereby facilitates the development of a deep learning algorithm for SCC detection. Experimental results show that the SCC detection algorithm can achieve a classification accuracy of 80% for mouse skin. Using the sub-micron FF-OCT imaging system, the proposed SCC detection algorithm has the potential for in-vivo applications.