Recording system and data fusion algorithm for enhancing the estimation of the respiratory rate from photoplethysmogram.

The respiratory rate is a vital parameter that can provide valuable information about the health condition of a patient. The extraction of respiratory information from photoplethysmographic signal (PPG) was actually encouraged by the reported results, our main goal being to obtain accurate respiratory rate estimation from the PPG signal. We developed a fusion algorithm that identifies the best derived respiratory signals, from which is possible to extract the respiratory rate; based on these, a global respiratory rate is computed using the proposed fusion algorithm. The algorithm is qualitatively tested on real PPG signals recorded by an acquisition system we implemented, using a reflection pulse oximeter sensor. Its performance is also statistically evaluated using benchmark dataset publically available from CapnoBase.Org.

Monitoring the fetal heart rate variations by means of time-variant multivariate analysis.

The analysis of the fetal heart rate (fHR) is important in detecting the fetal distress related with hypoxic episodes, noticed sometimes during the uterine activity, which can severely affect the fetus. Occasional synchrony between the fHR and the maternal heart rate (mHR) was reported and the mHR shows some variations during pregnancy and labor, especially when the contractions are very strong. The current study proposes a new strategy to investigate the relations between the fHR, the mHR and the uterine activity, by applying the time-variant Partial Directed Coherence (tvPDC).

The event synchronous canceller algorithm removes maternal ECG from abdominal signals without affecting the fetal ECG.

Fetal monitoring using abdominally recorded signals (ADS) allows physicians to detect occurring changes in the well-being state of the fetus from the beginning of pregnancy. Mainly based on the fetal electrocardiogram (fECG), it provides the long-term fetal heart rate (fHR) and assessment of the fetal QRS morphology. But the fECG component in ADS is obscured by the maternal ECG (mECG), thus removal of the mECG from ADS improves fECG analysis. This study demonstrates the performance of the event-synchronous interference canceller (ESC) in mECG removal from ADS data, recorded during pregnancy and labor. Its advantage as a compensation method for extended ADS processing is discussed.

Comparison and evaluation of existing methods for the extraction of low amplitude electrocardiographic signals: a possible approach to transabdominal fetal ECG.

Analysis of the fetal ECG (fECG) allows physicians to detect changes in the well-being state of the fetus. But when assessing the fECG through the abdominal signals (ADS), its very low amplitude causes a problem, as the fECG representation in the ADS is buried in a mixture of other signals with stronger energy. Different methods have been proposed in the past to extract the transabdominal fECG for instantaneous fetal heart rate (fHR) computation; four representatives of them are selected for an accurate comparison of their performance in fECG extraction and in fHR estimation. A model for the ADS including all the possible disturbances is developed within this study to generate simulated data as they are required for the quantitative comparison of the algorithms. Their performances and limits considering both the enhancement of the fECG and the ability to preserve fECG morphology are analyzed using the simulated data. The results clearly show that linear methods for maternal ECG removal provide better results with respect to the extraction of the fECG morphology. The algorithms are then tested on real ADS data recorded during labor. Finally, the advantage of considering linear methods for ADS processing is discussed.

A Self Organizing Map approach to breast cancer detection.

Detection and characterization of cancer tumors in mammograms is vital in daily clinical practice. The problem of detecting possible cancer areas is very complex due, on one hand, to the diversity in shape of the ill tissue and on the other hand to the poorly defined border between the healthy and the cancerous zone. Even though it has been studied for many years, there are still remaining challenges and directions for future research such as developing better enhancement and segmentation algorithms. The performance of the Self Organizing Map (SOM) in detecting the cancer suspicious regions in digitized mammograms is revealed in this study. In order to achieve the best results we firstly apply the preprocessing algorithms proposed in section II of the study.