An Automatic HFO Detection Method Combining Visual Inspection Features with Multi-Domain Features / 神经科学通报·英文版

As an important promising biomarker, high frequency oscillations (HFOs) can be used to track epileptic activity and localize epileptogenic zones. However, visual marking of HFOs from a large amount of intracranial electroencephalogram (iEEG) data requires a great deal of time and effort from researchers, and is also very dependent on visual features and easily influenced by subjective factors. Therefore, we proposed an automatic epileptic HFO detection method based on visual features and non-intuitive multi-domain features. To eliminate the interference of continuous oscillatory activity in detected sporadic short HFO events, the iEEG signals adjacent to the detected events were set as the neighboring environmental range while the number of oscillations and the peak–valley differences were calculated as the environmental reference features. The proposed method was developed as a MatLab-based HFO detector to automatically detect HFOs in multi-channel, long-distance iEEG signals. The performance of our detector was evaluated on iEEG recordings from epileptic mice and patients with intractable epilepsy. More than 90% of the HFO events detected by this method were confirmed by experts, while the average missed-detection rate was < 10%. Compared with recent related research, the proposed method achieved a synchronous improvement of sensitivity and specificity, and a balance between low false-alarm rate and high detection rate. Detection results demonstrated that the proposed method performs well in sensitivity, specificity, and precision. As an auxiliary tool, our detector can greatly improve the efficiency of clinical experts in inspecting HFO events during the diagnosis and treatment of epilepsy.

Automatic detection and clinical application of semen biochemical markers / 中华男科学杂志

Human seminal plasma is rich in potential biological markers for male infertility and male reproductive system diseases, which have an application value in the diagnosis and treatment of male infertility. The methods for the detection of semen biochemical markers have been developed from the manual, semi-automatic to the present automatic means. The automatic detection of semen biochemical markers is known for its advantages of simple reagent composition and small amount of reagents for each test, simple setting of parameters, whole automatic procedure with few errors, short detection time contributive to batch detection and reduction of manpower cost, simple calibration and quality control procedure to ensure accurate and reliable results, output of results in the order of the samples in favor of clinical diagnosis and treatment, and open reagents applicable to various automatic biochemistry analyzers. At present, the automatic method is applied in the detection of such semen biochemical markers as seminal plasma total and neutral alpha-glucosidase, acid phosphatase, fructose, γ-glutamyl transpeptidase, zinc, citric acid, uric acid, superoxide dismutase and carnitine, sperm acrosin and lactate dehydrogenase C4, and semen free elastase, which can be used to evaluate the secretory functions of the epididymis, seminal vesicle and prostate, sperm acrosome and energy metabolism function, seminal plasma antioxidative function, and infection or silent infection in the male genital tract.

Advances in automatic detection technology for images of thin blood film of malaria parasite / 中国血吸虫病防治杂志

This paper reviews the computer vision and image analysis studies aiming at automated diagnosis or screening of malaria in microscope images of thin blood film smears. On the basis of introducing the background and significance of automatic detection technology,the existing detection technologies are summarized and divided into several steps,including image acqui-sition,pre-processing,morphological analysis,segmentation,count,and pattern classification components. Then,the princi-ples and implementation methods of each step are given in detail. In addition,the promotion and application in automatic detec-tion technology of thick blood film smears are put forwarded as questions worthy of study,and a perspective of the future work for realization of automated microscopy diagnosis of malaria is provided.

Análisis multicanal de un sensor no obstructivo para la detección del Síndrome de Apnea-Hipopnea del Sueño / Multichannel Analysis of an Unobtrusive Sensor for Sleep Apnea-Hypopnea Detection

Este artículo presenta un método no obstructivo para la detección del síndrome de apnea-hipopnea del sueño (SAHS). El flujo respiratorio es medido indirectamente a través de un colchón sensorizado (PBS Pressure Bed Sensor) que incluye 8 transductores de presión. Mediante la transformada de Hilbert se obtiene la amplitud instantánea de las señales respiratorias y se reduce la información a través del análisis de componentes principales (ACP). Los eventos respiratorios (ERs apneas/hipopneas) se localizan como una reducción en la amplitud instantánea resultante y se contabilizan en el índice de eventos respiratorios (IER), un índice de severidad similar al oficial apnea-hypopnea index (AHI). El PBS se analiza agrupando primero la información de pares de canales y después utilizando los 8 canales. Los IER se evalúan comparándolos con el AHI en diferentes niveles de severidad. En el diagnóstico de pacientes sanos y patológicos se obtuvo una sensibilidad, especificidad y exactitud de 92%, 100% y 96% respectivamente, utilizando la información de dos u ocho canales. Con estos resultados podemos proponer el uso del PBS como una alternativa para el diagnóstico del SAHS en ambientes fuera del hospital, ya que no requiere la presencia de un clínico especialista para su uso.

This manuscript presents an unobtrusive method for sleep apneahypopnea syndrome (SAHS) detection. The airflow is indirectly measured through a sensitive mattress (Pressure Bed sensor, PBS) that incorporates multiple pressure sensors into a bed mattress. The instantaneous amplitude of each sensor signal is calculated through Hilbert transform, and then, the information is reduced via principal component analysis. The respiratory events (ERs -apneas/hypopneas) are detected as a reduction in the resulting instantaneous amplitude and accounted in the respiratory event index (IER), which is a severity indicator similar to the offcial apnea-hypopnea index (AHI). The respiratory signals extracted from PBS are analyzed first by clustering the information coming from channel pairs, and then using the eight channels. The IER performance is compared with the AHI for different severity categories. For the diagnosis of healthy and pathological patients we obtain a sensitivity, specificity and accuracy of 92%, 100% and 96%, respectively using two or eight PBS channels. These results suggest the possibility to propose PBS as an alternative tool for SAHS diagnosis in home environment.

Decomposição e análise dos potenciais evocados auditivos de tronco encefálico / Decomposition and analysis of auditory brainstem response

Os PEATEs são sinais resultantes da combinação de respostas de atividades neurais a estímulos sonoros no córtex. Caracteriza-se por ondas, sendo seus picos nomeados por algarismos romanos (I, II, III, IV, V, VI e VII). O processo clássico de identificação desses picos é baseado na visualização do sinal gerado pela promediação de cada amostra. Nele são identificadas as características morfológicas do sinal e os aspectos temporais relevantes constituídos pelas ondas de Jewett no qual cada onda tem uma relação anatômica com o sítio de origem. No entanto, durante esse processo de identificação visual surgem dificuldades que tornam a análise visual dos PEATE uma fonte constante de dúvidas em relação a fidedignidade e concordância de marcação dos picos pela subjetividade entre os examinadores. Com o objetivo de melhorar o processo de avaliação dos PEATE, foi desenvolvido um sistema de detecção automática para os picos, com capacidade de aprendizado que leva em consideração o perfil de marcação prévia realizado por examinadores, podendo ser considerado também, as marcações futuras de examinadores que utilizarão o software como auxílio em suas análises. Para a detecção de picos foi utilizada a Transformada Wavelet Contínua, associada a um Classificador Probabilístico construído a partir de marcações realizadas pelos examinadores. Para a avaliação do sistema foram utilizadas 748 amostras de PEATE de 11 sujeitos. A avaliação do sistema proposto apresentou uma taxa de acerto 74,3% a 99,7%, entre o sistema e a marcação manual, de acordo com o tipo de onda analisada. O presente estudo foi concebido com a intenção de ser uma ferramenta prática e por isso voltada para a aplicação clínica. Os resultados apresentados mostram uma técnica eficaz e capaz de aperfeiçoar o processo de avaliação dos PEATEs. A técnica proposta se mostra precisa mesmo na presença de ruído, característico de sinais biológicos especialmente no PEATE por ser um sinal de amplitude baixa.

Auditory Brainstem Response (ABR) results from the combination of neural activity responses in the presence of sound stimuli, detected by the cortex and characterized by peaks and valleys. They are identified by Roman numerals (I, II, III, IV, V, VI and VII). The identification of these peaks is carried out by the classical manual process of analysis, which is based on the visual/manual processing of the signals. The morphological and temporal characteristics of the signal carry relevant physiological and anatomical information regarding the auditory system. However, in this visual process of analysis some difficulties may occur, specifically, the results of the analysis may vary according to the type of protocol, settings of equipment employed, and the experience of the examiner. This makes the analysis of ABR subject to the influence of many variables that may interfere on the reliability and agreement of results obtained in distinct research centers and by different examiners. Therefore, the main propose of this study was to develop and assess a system capable of automatically detecting and classifying ABR waves, which are called Jewett waves. A relevant feature of the proposed tool is that it can learn from the experience of examiners continuously. In order to evaluate the system approximately 748 samples of ABR obtained from 11 subjects were analyzed by the automatic system. These results were compared to analyses obtained from five seasoned examiners, and they showed a high level of agreement, ranging for 74.3% to 99.7%, between responses given by the system and the examiners. Thus the proposed technique is proved to be accurate even in the presence of noise, especially characteristic of the ABR that is a sign of low amplitude.

Peri-ictal complexity loss as determined by approximate entropy analysis in the electrocorticogram obtained from chronic subdural recordings in patients with refractory temporal lobe epilepsy

RATIONALE: The development of closed-loop devices suitable for use in the treatment of epileptic patients would very likely rely on the adequate development of paradigms able to forecast the occurrence of seizures. In this paper, we studied the usefulness of approximate enthropy, of a non-linear paradigm, in this patient population. METHODS: We applied approximate entropy (ApEn) analysis to study the variability in the complexity of the peri-ictal electrocorticogram (ECoG) of patients with refractory epileptic seizures of the temporal lobe origin. Three patients were implanted with chronic subdural grids. The ApEn algorithm measured the complexity of interictal, peri-ictal and ictal phases. We selected one representative channel disclosing interictal activity for each patient and two channels per patient with ictal recordings. RESULTS: In all patients, we found one channel where the interictal activity registered in the ECoG was associated with high complexity and where ApEn was higher than 0.59. But in the other two channels, for each patient that presented interictal/ictal transitions, clinical manifestations of epileptic seizures occurred around 3.5 seconds after the entropy drop, when entropy was below 0.5. In contrast, when entropy was higher than 0.5, clinical manifestation occurred 9.5 seconds after the entropy drop. The 3.5 seconds shorter delay possibly indicates focal activity in the channel analyzed. CONCLUSIONS: Our results suggest that ApEn may be a useful instrument for early detection of epileptic activity. Its application may be indicated for prevention and diagnosis of epileptic seizures.

RACIONAL: O desenvolvimento de aparatos retroalimentáveis para o tratamento de pacientes epilépticos dependerá em grande parte do desenvolvimento adequado de paradigmas que possam antever as crises. Neste trabalho, estudamos a utilidade da entropia aproximada (ApEn), um paradigma não-linear, em pacientes portadores de epilepsia. MÉTODOS: Aplicamos a análise de entropia aproximada (ApEn) no estudo de variabilidade da complexidade do eletrocorticograma (ECoG) de pacientes com epilepsia refratária com origem no lobo temporal. Três pacientes foram implantados com matrizes de eletrodos subdurais. O algoritmo ApEn mediu a complexidade das fases interictal, peri-ictal e ictal. Selecionamos um canal representativo de cada paciente manifestando atividade interictal e dois canais de cada paciente com registro ictal. RESULTADOS: Em cada paciente, encontramos um canal cuja atividade interictal registrada no ECoG foi associada a alta complexidade com ApEn maior que 0.59. Nos outros dois canais, para cada paciente que apresentou transição interictal/ictal, as manifestações clínicas das crises epilépticas ocorreram cerca de 3.5 segundos depois após a queda da entropia abaixo de 0.5. Em comparação, quando a entropia foi maior que 0.5, as manifestações clínicas ocorreram 9,5 segundos após a queda da entropia. A curta latência (3.5 segundos) indicou possivelmente o local de início da atividade focal. CONCLUSÕES: Nossos resultados sugerem que ApEn pode ser um instrumento útil na detecção precoce da atividade epiléptica. Sua aplicação pode estar indicada na prevenção ou diagnóstico das crises epilépticas.

Detection of abnormalities in digital mammograms based on Support Vector Machines / 医疗卫生装备

Objective To search an approach based on Support Vector Machine (SVM) for detection of different abnormalities including micro-calcifications and masses from digital mammograms. Methods Such detections were formulated as supervised-learning problems and SVM was applied to the detection algorithm. After the regions of interest were pre-processed by specific rectangular windows, three kinds of parameters were extracted, including the direct pixel value parameter, the parameters from Spatial Grey Level Dependency (SGLD) matrices and from Discrete Cosine Transform (DCT). At first, each kind of parameter was taken as the input of SVM to train and test the machine respectively. Then all the parameters were incorporated into the input of SVM. Results the classification accuracy is 92.28%, 90.35% and 91.12% respectively when only one parameter input. The classification accuracy reaches 99.23% when all the parameter incorporated. Conclusion The parameters extracted from the regions of interest in digital mammograms can reflect the characteristics of different regions and SVM is a powerful tool for the detection of abnormalities from digital mammograms.

A Study on an Automatic Detection of Uterine Cervical Pap-smears by Image Processing / 대한세포병리학회지

Cancer of the cervix is the most common malignancy in women in developing countries and the second most common cancer in women throughout the world with approximately 500,000 new cases each year. Prevention of this large number of premature deaths among women is, therefore, a goal worthy of urgent and serious consideration. In this thesis, an automatic cancerous nucleus detection method essential to a screening system with Papanicolaou stained specimens called Pap-smear is proposed which employs image processing techniques. It uses edge information to segment objects and morphologic as well as densitometric information to distinguish cancerous nuclei from dirts or normal nuclei. It has produced useful results in our study.