Biomedical subjects

K Papik

Publications and source records attributed to K Papik.

7 recordsLinked to original sources

PubMed2000

Development of a speech-based dialogue system for report dictation and machine control in the endoscopic laboratory.

BACKGROUND AND STUDY AIMS: Reporting and machine control based on speech technology can enhance work efficiency in the gastrointestinal endoscopy laboratory. MATERIALS AND METHODS: The status and activation of endoscopy laboratory equipment were described as a multivariate parameter and function system. Speech recognition, text evaluation and action definition engines were installed. Special programs were developed for the grammatical analysis of command sentences, and a rule-based expert system for the definition of machine answers. A speech backup engine provides feedback to the user. Techniques were applied based on the "Hidden Markov" model of discrete word, user-independent speech recognition and on phoneme-based speech synthesis. Speech samples were collected from three male low-tone investigators. RESULTS: The dictation module and machine control modules were incorporated in a personal computer (PC) simulation program. Altogether 100 unidentified patient records were analyzed. The sentences were grouped according to keywords, which indicate the main topics of a gastrointestinal endoscopy report. They were: "endoscope", "esophagus", "cardia", "fundus", "corpus", "antrum", "pylorus", "bulbus", and "postbulbar section", in addition to the major pathological findings: "erosion", "ulceration", and "malignancy". "Biopsy" and "diagnosis" were also included. We implemented wireless speech communication control commands for equipment including an endoscopy unit, video, monitor, printer, and PC. The recognition rate was 95%. CONCLUSIONS: Speech technology may soon become an integrated part of our daily routine in the endoscopy laboratory. A central speech and laboratory computer could be the most efficient alternative to having separate speech recognition units in all items of equipment.

Artificial Intelligence↗

PubMed2000

Quantitative DNA and morphometric analysis of gastroscopic brush smears by TV image analysis.

OBJECTIVES: To determine quantitative nuclear morpho-and densitometric classifiers and classification techniques for analysis of gastric, Feulgen-stained brush smears. DESIGN: TV image analysis-based quantitative DNA and morphometric analysis of gastric brush smears in a prospective study. PATIENTS AND METHODS: Ninety-eight (11 normal, 77 gastritis (17 with intestinal metaplasia) and 10 adenocarcinoma) Feulgen-Schiff-stained gastric brush smears were analysed by TV image analysis. The classification of the smears was based on parallel histological examination. For standards, DNA content of lymphocyte cell cultures was determined by the image and by flow cytometry. From every nucleus, six morphometric (surface, layers, minimum diameter, maximum diameter, perimeter and form factor) and six densitometric (integrated optical density (IOD), average density, sigma density, minimum and maximum density and density range) parameters were simultaneously determined. The smear parameters (object cells CV, DNA index, 2c deviation index, 5c exceeding rate, G1 -S-G2 ratio) were analysed together with the mean and SD values of the nuclear parameters by discriminant analysis and back-propagation neural networks. RESULT: The normal smears were all diploid and their S + G2 ratio was 15.24+/-7.75% (mean +/- SD). The gastritis smears were all diploid with a proliferation fraction of 20.89+/-6.75%. The tumours were aneuploid in eight of the ten cases with 5c exceeding rate > 6.23%, the S + G2 fraction ratio was 34.72+/-10.12%. The mean nuclear surface area was 46+/-20, 58+/-20 and 74+/-22 microm2 in normal, gastritis and malignant groups, respectively. Significant differences (P<0.05) were found in nuclear surface, minimum and maximum diameter, and perimeter parameters. Using linear discriminant analysis, 100% of the non-malignant cases and 70% of the tumour cases were correctly classified. Using 30 non-malignant and five malignant cases as a training set, the neural networks classified 95% of the remaining cases correctly. The DNA index increased significantly (P<0.05) in Helicobacter pylori-positive cases compared to the negative ones. In gastritis with intestinal metaplasia, the proliferation ratio decreased significantly (P<0.05). CONCLUSIONS: The image analysis is a useful tool for quantitative gastric cytology. The combination of nuclear morphometric parameters and neural network classifiers with multivariate quantitative DNA analysis is suggested for gastric brush smear quantitative cytology analysis.

Adenocarcinoma↗

PubMed1999

Automated prozone effect detection in ferritin homogeneous immunoassays using neural network classifiers.

The application of turbidimetric homogeneous immunoassays made the determination of several plasma components widely available. The sensitivity and accuracy of these assays are appropriate enough for routine laboratory use; however, in the case of many pathologically high concentration samples, prozone effect (high dose hook effect) can be observed, that leads to false-negative determination. Up to the present there are no cost-effective algorithms available for the safe detection of the prozone effect. Pathological serum ferritin values can be elevated up to 5000 ng/ml, while the measuring range covers only the 0-440 ng/ml range by a commercial assay. The determination of samples with ferritin concentration higher than 1500 ng/ml results in false-negative values because of the overlapping measuring range and prozone effect range. The prozone effect can be recognised by analysis of reaction kinetics after measurement. We have developed a neural network classifier system to analyse reaction kinetics of the measurements and check the prozone effect. One thousand five hundred determinations and 77 patient samples were used for neural network training and test. Using the trained neural networks, false-negative results can be filtered immediately after the determination, without re-run; thus, the sensitivity of plasma ferritin determination may become reliable enough, even in the case of high concentration samples. Applying this new technology, false-negative serum ferritin determinations can be avoided, thus even a relatively high hook effect rate (5-12% in different patient groups) can be handled safely.

Blood Chemical Analysis↗

PubMed1998

[Biologic detection methods in the comparison of circulating tumor cells and micrometastases].

Early studies could not prove any diagnostic or prognostic value of the presence of tumor cells in the circulation. Recent knowledge in the field of molecular and cellular pathology provided better understanding of mechanisms of metastasis formation therefore advanced detection of circulating cancer cells has been suggested as a supplementary method of staging metastatic cancer. Beside the widely used immunocytochemical methods the reverse transcriptase-polymerase chain reaction (RT-PCR) is now the most relevant technique in studying micrometastases of solid tumors. Magnetic activated cell sorting (MACS) is a recently developed method for the enrichment of different cells from suspensions by magnetic labelling of their surface antigens. RT-PCR seems to be the most sensitive to detect circulating cancer cells or micrometastases, but it is possible by MACS to purify cells for further immunological, biochemical or genetic analysis. The aim of this review is to give a brief summary of recently used methods and to discuss the clinical relevance of the attainable results.

Biomarkers, Tumor↗

PubMed1998

[Incidence and elimination of false-negative results of ferritin determination].

Introduction of turbidimetric homogeneous immunoassays made the determination of plasma ferritin concentration wide-ranging available. However, high-dose hook effect or prozone effect occurring at samples with high ferritin concentration can lead to false-negative results. According to the authors, this phenomenon has considerable clinical significance, in patients with iron-overload disorders false-negative laboratory values may result in inaccurate diagnosis. The prozone effect can be eliminated by reaction kinetic analysis of measurements. The authors developed a neural network classification procedure based on artificial intelligence technology for the recognition of the reactions with differing kinetic flow, and made a computer software for helping the application of the classification system. False-negative results can be filtered using this new technology following the laboratory determination, thus sensitivity of plasma ferritin determination may become safe enough even in case of high concentration samples.

False Negative Reactions↗

PubMed1998

[Computerized speech recognition-based endoscopic findings].

Discrete, Hidden Markov model based speech recognition and phoneme based speech synthesis techniques were applied for gastroscopy reporting and machine control. The authors developed a special program for grammatical analysis of the sentences. Altogether 100 patient findings were grammatically analysed. The sentences were grouped according to the topographical order of the investigation: oesophagus, cardia, fundus, corpus, antrum, pylorus, bulbus, postbulbar section, and the pathological findings: erosion, ulceration, malignancy. Speech samples from 3 deep voiced male investigators were collected. The recognition rate was above 95%. A simulation program was also developed for dictation and controlling of the different equipment (monitor, printer, video, endoscope) in the gastroscopy laboratory by speech recognition. Speech synthesis was applied for the evaluation of understanding. This module artificially synthesizes the answer of the system giving backup for the understood information. With additional developments the discrete word speech 'recognition' achieved the level of routine application in medical reporting. However, ready-to-use developments need the joint activity of speech technology and endoscopy industry with end-user teams.

Diagnosis, Computer-Assisted↗

PubMed1998

[Medical use of artificial neural networks].

The main aim of the research in medical diagnostics is to develop more exact, cost-effective and handsome systems, procedures and methods for supporting the clinicians. In their paper the authors introduce a new method that recently came into the focus referred to as artificial neural networks. Based on the literature of the past 5-6 years they give a brief review--highlighting the most important ones--showing the idea behind neural networks, what they are used for in the medical field. The definition, structure and operation of neural networks are discussed. In the application part they collect examples in order to give an insight in the neural network application research. It is emphasised that in the near future basically new diagnostic equipment can be developed based on this new technology in the field of ECG, EEG and macroscopic and microscopic image analysis systems.

Artificial Intelligence↗