Two-stage approach for risk estimation of fetal trisomy 21 and other aneuploidies using computational intelligence systems.

OBJECTIVE: To estimate the risk of fetal trisomy 21 (T21) and other chromosomal abnormalities (OCA) at 11-13 weeks' gestation using computational intelligence classification methods. METHODS: As a first step, a training dataset consisting of 72 054 euploid pregnancies, 295 cases of T21 and 305 cases of OCA was used to train an artificial neural network. Then, a two-stage approach was used for stratification of risk and diagnosis of cases of aneuploidy in the blind set. In Stage 1, using four markers, pregnancies in the blind set were classified into no risk and risk. No-risk pregnancies were not examined further, whereas the risk pregnancies were forwarded to Stage 2 for further examination. In Stage 2, using seven markers, pregnancies were classified into three types of risk, namely no risk, moderate risk and high risk. RESULTS: Of 36 328 unknown to the system pregnancies (blind set), 17 512 euploid, two T21 and 18 OCA were classified as no risk in Stage 1. The remaining 18 796 cases were forwarded to Stage 2, of which 7895 euploid, two T21 and two OCA cases were classified as no risk, 10 464 euploid, 83 T21 and 61 OCA as moderate risk and 187 euploid, 50 T21 and 52 OCA as high risk. The sensitivity and the specificity for T21 in Stage 2 were 97.1% and 99.5%, respectively, and the false-positive rate from Stage 1 to Stage 2 was reduced from 51.4% to ∼1%, assuming that the cell-free DNA test could identify all euploid and aneuploid cases. CONCLUSION: We propose a method for early diagnosis of chromosomal abnormalities that ensures that most T21 cases are classified as high risk at any stage. At the same time, the number of euploid cases subjected to invasive or cell-free DNA examinations was minimized through a routine procedure offered in two stages. Our method is minimally invasive and of relatively low cost, highly effective at T21 identification and it performs better than do other existing statistical methods. Copyright © 2017 ISUOG. Published by John Wiley & Sons Ltd.

Electronic Health Record Application Support Service Enablers.

There is a huge need for open source software solutions in the healthcare domain, given the flexibility, interoperability and resource savings characteristics they offer. In this context, this paper presents the development of three open source libraries - Specific Enablers (SEs) for eHealth applications that were developed under the European project titled "Future Internet Social and Technological Alignment Research" (FI-STAR) funded under the "Future Internet Public Private Partnership" (FI-PPP) program. The three SEs developed under the Electronic Health Record Application Support Service Enablers (EHR-EN) correspond to: a) an Electronic Health Record enabler (EHR SE), b) a patient summary enabler based on the EU project "European patient Summary Open Source services" (epSOS SE) supporting patient mobility and the offering of interoperable services, and c) a Picture Archiving and Communications System (PACS) enabler (PACS SE) based on the dcm4che open source system for the support of medical imaging functionality. The EHR SE follows the HL7 Clinical Document Architecture (CDA) V2.0 and supports the Integrating the Healthcare Enterprise (IHE) profiles (recently awarded in Connectathon 2015). These three FI-STAR platform enablers are designed to facilitate the deployment of innovative applications and value added services in the health care sector. They can be downloaded from the FI-STAR cataloque website. Work in progress focuses in the validation and evaluation scenarios for the proving and demonstration of the usability, applicability and adaptability of the proposed enablers.

An overview of recent end-to-end wireless medical video telemedicine systems using 3G.

Advances in video compression, network technologies, and computer technologies have contributed to the rapid growth of mobile health (m-health) systems and services. Wide deployment of such systems and services is expected in the near future, and it's foreseen that they will soon be incorporated in daily clinical practice. This study focuses in describing the basic components of an end-to-end wireless medical video telemedicine system, providing a brief overview of the recent advances in the field, while it also highlights future trends in the design of telemedicine systems that are diagnostically driven.

Color multiscale texture classification of hysteroscopy images of the endometrium.

The objective of this study was to investigate the diagnostic performance of a Computer Aided Diagnostic (CAD) system based on color multiscale texture analysis for the classification of hysteroscopy images of the endometrium, in support of the early detection of gynaecological cancer. A total of 416 Regions of Interest (ROIs) of the endometrium were extracted (208 normal and 208 abnormal) from 45 subjects. RGB images were gamma corrected and were converted to the YCrCb color system. The following texture features were extracted from the Y, Cr and Cb channels: (i) Statistical Features (SF), (ii) Spatial Gray Level Dependence Matrices (SGLDM), and (iii) Gray Level Difference Statistics (GLDS). The Probabilistic Neural Network (PNN), statistical learning and the Support Vector Machine (SVM) neural network classifiers were also applied for the investigation of classifying normal and abnormal ROIs in different scales. Results showed that the highest percentage of correct classification (%CC) score was 79% and was achieved for the SVM models trained with the SF and GLDS features for the 1x1 scale. This %CC was higher by only 2% when compared with the CAD system developed, based on the SF and GLDS feature sets computed from the Y channel only. Further increase in scale from 2x2 to 9x9, dropped the %CC in the region of 60% for the SF, SGLDM, and GLDS, feature sets, and their combinations. Concluding, a CAD system based on texture analysis and SVM models can be used to classify normal and abnormal endometrium tissue in difficult cases of gynaecological cancer. The proposed system has to be investigated with more cases before it is applied in clinical practise.

Healthcare telematic applications in Cyprus.

OBJECTIVES: a) To present a review of ongoing health telematic applications in Cyprus. b) To promote the use of these health telematic applications in the Cyprus region. c) To help in the spin off of other health telematic applications thus enabling the offering of a better health service to the citizens. METHODS AND RESULTS: The health telematics applications include a medical system for emergency telemedicine (AMBULANCE and EMERGENCY-112 projects), a system for the evaluation of the risk of stroke by telemedicine (EROS), a diagnostic telepathology network in gynaecological cancer (TELEGYN), a collaborative virtual medical team for home healthcare of cancer patients (DITIS), and a health telematics training network (HEALTHNET). The paper refers to the set-up and characteristics of these applications and tries to relate them with the health policies that should be applied in Cyprus. CONCLUSIONS: It is anticipated that this paper will promote the importance of health telematics applications for Cyprus and increase the awareness on the possibilities that these applications offer for health policies in all levels of health related human resources.

Content-based retrieval of breast cancer biopsy slides.

The Biopsy Analysis Support System (BASS), previously used for image analysis of immunohistochemically stained sections of breast carcinoma, has been extended to include indexing and content-based retrieval of biopsy slide images from a database of 57 captured cases. Images from histopathological biopsy slides are described and these are accessed in terms of the properties of either individual nuclei or groups of cell nuclei present in the slide. Visual similarity of cases is specified in terms of a diagnostic index, commonly known as the H-score, which incorporates the heterogeneity of nuclear staining intensity, as well as the percentage of nuclei staining at specific intensities. The system provides a platform that can be exploited in telepathology and teleconsultation, but further research is needed to explore its full potential and accuracy in a diagnostic clinical environment.

Computer-aided detection of breast cancer nuclei.

A computer-aided detection system for tissue cell nuclei in histological sections is introduced and validated as part of the Biopsy Analysis Support System (BASS). Cell nuclei are selectively stained with monoclonal antibodies, such as the anti-estrogen receptor antibodies, which are widely applied as part of assessing patient prognosis in breast cancer. The detection system uses a receptive field filter to enhance negatively and positively stained cell nuclei and a squashing function to label each pixel value as belonging to the background or a nucleus. In this study, the detection system assessed all biopsies in an automated fashion. Detection and classification of individual nuclei as well as biopsy grading performance was shown to be promising as compared to that of two experts. Sensitivity and positive predictive value were measured to be 83% and 67.4%, respectively. One major advantage of BASS stems from the fact that the system simulates the assessment procedures routinely employed by human experts; thus it can be used as an additional independent expert. Moreover, the system allows the efficient accumulation of data from large numbers of nuclei in a short time span. Therefore, the potential for accurate quantitative assessments is increased and a platform for more standardized evaluations is provided.

Learning systems in biosignal analysis.

In biosignal analysis, the utility of artificial neural networks (ANN) in classifying electromyographic (EMG) data trained with the momentum back propagation algorithm has recently been demonstrated. In the current study, the self-organizing feature map algorithm, the genetics-based machine learning (GBML) paradigm, and the K-means nearest neighbour clustering algorithm are applied on the same set of data. The aim of this exercise is to show how these three paradigms can be used in practice, given that their diagnostic performance is problem- and parameter-dependent. A total of 720 macro EMG recordings were carried out from four groups, from seven normal, nine motor neuron disease, 14 Becker's muscular dystrophy, and six spinal muscular atrophy subjects, respectively. Twenty-three of the subjects were used for training and 13 for evaluating the various models. For each subject, the mean and the standard deviation of the parameters (i) amplitude, (ii) area, (iii) average power and (iv) duration were extracted. The feature vector was structured in two different ways for input to the models: an eight-input feature vector that consisted of both the mean and the standard deviation of the four parameters measured, and a four-input feature vector that included only the mean of the parameters. Also, due to the heterogenous nature of the spinal muscular atrophy group, three class models that excluded this group were investigated. In general, self-organizing feature map and GBML models resulted in comparable diagnostic performance of the order of 80-90% correct classifications (CCs) score for the evaluation set, whereas the K-means nearest neighbour algorithm models gave lower percentage CCs. Furthermore, for all three learning paradigms: better diagnostic performance was obtained for the three class models compared with the four class models; similar diagnostic performance was obtained for both the eight- and four-input feature vectors. Finally, it is claimed that the proposed methodology followed in this work can be applied for the development of diagnostic systems in the analysis of biosignals.

Computer-aided classification of breast cancer nuclei.

Breast cancer is the most common malignancy affecting the female population in industrialized countries. Prognostic factors, such as steroid receptors visualized in biopsy slides, provide critical information to oncologists regarding the hormonal status of the individual tumors. These factors influence the choice of treatment and help in predicting patient survival and probability of recurrence. The objective of this paper is to introduce a new computer-aided system for the classification of breast cancer nuclei based on neural networks. Currently, medical experts assess steroid receptors in breast cancer biopsy slides mostly manually using four- or five-level grading schemes. These schemes are based on the assessment of two parameters: number of nuclei positive and their staining intensity. Available computerized systems define their own grading schemes based on automated measurements of low-level features, such as optical density, texture, area, and others. However, the findings produced by these systems may not be readily comprehensible by the majority of medical experts who have been accustomed to manual assessment schemes. Moreover, findings from one system cannot be directly compared to findings obtained from other computerized systems. To date, no standardized assessment scheme exists for computerized systems, while interobserver and intraobserver variabilities limit the utility of the routinely used manual assessment schemes. In this paper a new system for computer-aided biopsy analysis is introduced. Here, we focus on the system's nuclear classification module. The input to this module consists of a set of six local and global features: optical density, two chromaticity indices, a variance based texture measure, global nuclei density mean, and variance. The output of the nuclei classification module consists of a membership label in a zero to four grading scheme for each detected nucleus. The classification module is based on a feedforward neural network trained in a supervised fashion to classify the nuclear feature vectors. The sample data comprises 3015 nuclei from 28 images that were classified by a human expert. A Sammon plot visualization of the six dimensional input feature space shows that the classification problem is quite difficult. The neural network used in the classification module achieved 72% accuracy. Our result indicate that by using a nuclear classification module such as the one introduced in this paper it is possible to translate low-level system measurements into a vocabulary that is familiar to medical experts. Thus, a contribution is made to the standardization of grading schemes in addition to improving the accuracy in grading breast cancer nuclei.

Genetics-based machine learning for the assessment of certain neuromuscular disorders.

Clinical electromyography (EMG) provides useful information for the diagnosis of neuromuscular disorders. The utility of artificial neural networks (ANN's) in classifying EMG data trained with backpropagation or Rohonen's self-organizing feature maps algorithm has recently been demonstrated. The objective of this study is to investigate how genetics-based machine learning (GBML) can be applied for diagnosing certain neuromuscular disorders based on EMG data. The effect of GBML control parameters on diagnostic performance is also examined. A hybrid diagnostic system is introduced that combines both neural network and GBML models. Such a hybrid system provides the end-user with a robust and reliable system, as its diagnostic performance relies on more than one learning principle. GBML models demonstrated similar performance to neural-network models, but with less computation. The diagnostic performance of neural network and GBML models is enhanced by the hybrid system.

Medical diagnostic systems: a case for neural networks.

Recent advances in computer technology offer to the medical profession specialized tools for gathering medical data, processing power, as well as fast storing and retrieving capabilities. Artificial intelligence (AI), an emerging field of computer science is studying the issues of human problem solving and decision making. Furthermore, rule-based systems and knowledge-based systems that are other fields of AI have been adopted by many scientists in an effort to develop intelligent medical diagnostic systems. In this study artificial neural networks (ANN) are introduced as a tool for building an intelligent diagnostic system; the system does not attempt to replace the physician from being the decision maker but to enhance ones facilities for reaching a correct decision. An integrated diagnostic system for assessing certain neuromuscular disorders is used in this study as an example for demonstrating the proposed methodology. The diagnostic system is composed of modules that independently provide numerical data to the system from the clinical examination of a patient, and from various laboratory tests that are performed. The examination procedure has been standardized by developing protocols for each specialized area, in cooperation with experts in the area. At the conclusion of the clinical examination and laboratory tests, data in the form of a numerical vector represents a medical examination snapshot of the subject. Artificial neural network (ANN) models were developed using the unsupervised self-organizing feature maps algorithm. Data from 71 subjects were collected. The ANN models were trained with the data from 41 subjects, and tested with the data from the remaining 30 subjects. Two sets of models were developed; those trained with the data from only the clinical examinations; and those trained by combining the clinical and the laboratory test data. The diagnostic yield that was obtained for the unknown cases is in the region of 73 to 93% for the models trained with only the clinical data, and in the region of 73 to 100% for those trained by combining both the clinical and laboratory data. The pictorial representation of the diagnostic models through the self organized two dimensional feature maps provide the physician with a friendly human-computer interface and a comprehensive tool that can be used for further observations, for example in monitoring disease progression of a subject.

Artificial neural nets in computer-aided macro motor unit potential classification.

The use of macro electromyography to obtain a macro motor unit potential (MMUP) is described. At least 20 potentials are measured from a single muscle to obtain a reasonable estimate of the parameters of an average motor unit potential. The MMUP data are analyzed by means of the peak-to-peak amplitude and the integral of the central 50 ms of the signal. The possibility of using artificial neural networks (ANNs) to analyze the macro data in a way that makes no assumptions about the relationships between the parameters and without recourse to conventional modeling methods is discussed. The results of an analysis carried out on 820 MMUPs recorded from 41 subjects who were classified on the basis of a clinical opinion and the appearance of a muscle biopsy are presented and discussed.