Hernâni Gonçalves

Automatic Image Registration Through Image Segmentation and SIFT

Automatic image registration (AIR) is still a present challenge for the remote sensing community. Although a wide variety of AIR methods have been proposed in the last few years, there are several drawbacks which avoid their common use in practice. The recently proposed scale invariant feature transform (SIFT) approach has already revealed to be a powerful tool for the obtention of tie points in general image processing tasks, but it has a limited performance when directly applied to remote sensing images. In this paper, a new AIR method is proposed, based on the combination of image segmentation and SIFT, complemented by a robust procedure of outlier removal. This combination allows for an accurate obtention of tie points for a pair of remote sensing images, being a powerful scheme for AIR. Both synthetic and real data have been considered in this work for the evaluation of the proposed methodology, comprising medium and high spatial resolution images, and single-band, multispectral, and hyperspectral images. A set of measures which allow for an objective evaluation of the geometric correction process quality has been used. The proposed methodology allows for a fully automatic registration of pairs of remote sensing images, leading to a subpixel accuracy for the whole considered data set. Furthermore, it is able to account for differences in spectral content, rotation, scale, translation, different viewpoint, and change in illumination.

Linear and nonlinear fetal heart rate analysis of normal and acidemic fetuses in the minutes preceding delivery

Linear and nonlinear fetal heart rate (FHR) indices, namely mean FHR, interval index (II), very low, low and high frequencies, approximate (ApEn) and sample entropy (SampEn), were computed, immediately before delivery, in the initial and final FHR tracing segments, from 48 normal, 10 mildly acidemic and 10 moderate-to-severely acidemic fetuses. Progression of labor was associated with a significant increase in linear frequency domain indices whereas nonlinear indices were significantly decreased. Moderate-to-severe fetal acidemia was associated with a significant decrease in nonlinear indices. The best discrimination between moderate-to-severe acidemic fetuses and the remaining cases was obtained combining II and ApEn(2,0.15), with a specificity of 71% and a sensitivity of 80%. These findings support the hypothesis of increased autonomic nervous system activity in the final minutes of labor and of decreased central nervous system activity, both in the final minutes of labor and in moderate-to-severe acidemic fetuses.

Measures for an Objective Evaluation of the Geometric Correction Process Quality

The geometric correction process is a crucial step in remote sensing applications. This process is frequently manually performed-which is a laborious task in many situations-as automatic image registration methods are still far from being broadly applied. One of the reasons that justify the absence of a broad application of automatic image registration methods is the lack of measures for an objective and automated analysis of the image registration process quality. The root mean square (RMS) of the residuals is the only quantitative evaluation which is generally used in this process, with the final validation of the geometric correction process being a qualitative analysis. Therefore, in both ldquohumanrdquo and automatic image registration processes, an objective evaluation of its quality is required. In this letter, we propose several measures for an objective evaluation of the geometric correction process, as a complement to the traditional RMS of the residuals and visual inspection. Two scenarios of control point distribution and the most common residual distributions were considered. With the proposed measures, we intend to cover the most common qualitative analysis aspects. This has particular importance under the scope of automatic image registration methods, where an automatic evaluation of the results is also required.

Internal versus external intrapartum foetal heart rate monitoring: the effect on linear and nonlinear parameters.

The effect of foetal heart rate (FHR) acquisition mode on linear and nonlinear parameters is still largely unknown. In 33 normal labouring women, FHR signals were acquired simultaneously by an external ultrasound sensor applied to the maternal abdomen and an internal scalp electrode, in the minutes preceding delivery. For each case, the initial and final 5, 10 and 20 min segments were analysed, considering FHR signals at a frequency of 4 Hz (the frequency at which they are transmitted by the majority of commercialized foetal monitors). Several time and frequency domain linear and nonlinear FHR indices were computed in these segments, namely mean FHR, very low frequency (VLF), low frequency (LF), high frequency (HF), approximate entropy (ApEn) and sample entropy (SampEn). Parametric confidence intervals, statistical tests and correlation coefficients were calculated in order to evaluate the effect of internal versus external FHR monitoring modes on the considered indices. The whole evaluation was repeated using FHR signals at a frequency of 2 Hz. Most time domain linear indices were similar with external and internal monitoring in the initial and final segments of the tracings. However, linear frequency domain indices were poorly correlated in the final segments and had significantly different mean values in the initial segments. Nonlinear indices were significantly different in both initial and final segments. The correlation between 4 and 2 Hz sampled parameters was high for both linear and nonlinear indices (most correlation coefficient values ranging between 0.95 and 1) but nonlinear index values were significantly higher at 2 Hz. In conclusion, the mode used to acquire FHR signals and the sampling rate employed can significantly affect most FHR indices.

Linear and complex heart rate dynamics vary with sex in relation to fetal behavioural states

BACKGROUND A better understanding of gender influences on fetal heart rate can help to improve analysis of the latter and perhaps elucidate the increased risk of perinatal death that occurs in males. AIM To assess differences in linear and complex heart rate dynamics according to fetal sex, in the antepartum period of normal term pregnancies, for patterns associated with fetal behavioural states. STUDY DESIGN AND SUBJECTS One hundred and eighty seven fetal heart rate segments of 10-minute duration, acquired with a system for computerized analysis of cardiotocograms and classified into fetal behavioural patterns A, B, C or D were analysed. They had been acquired from 24 female and 23 male term fetuses, with uneventful perinatal outcomes. Four different comparative studies between female and male fetuses were conducted, considering different adjustments for gestational age, weight and FHR pattern. OUTCOME MEASURES Indices of linear and nonlinear fetal heart rate variability, namely, long-term irregularity index, very low, low and high frequency spectral indices, approximate entropy and sample entropy. RESULTS Pattern B was the most frequent, both in female and male fetuses. Pattern A was more likely to be associated to female than male fetuses, whereas the opposite occurred with patterns C and D. Linear indices were significantly higher in male than in female fetuses, whereas the opposite occurred with nonlinear indices. CONCLUSIONS Male fetuses exhibited significantly more linear and significantly less complex fetal heart rate activity than female fetuses, expressing signs of a more active autonomous nervous system and of less active complexity control systems. These aspects may need to be considered when interpreting FHR tracings.

Sex differences in linear and complex fetal heart rate dynamics of normal and acidemic fetuses in the minutes preceding delivery.

Abstract Aim: To assess linear and complex heart rate dynamics in relation to fetal gender in normal and acidemic fetuses during the minutes preceding delivery. Methods: Linear and non-linear fetal heart rate indices, namely mean FHR, long-term irregularity index, short-term variability, low and high frequency spectral indices, approximate and sample entropy, were assessed in 36 female and 30 male fetuses, adjusted for gestational age and weight, during the minutes preceding delivery. Analysis was performed in the initial and final minutes of each tracing in fetuses with umbilical artery blood pH at delivery ≥7.20, 7.11–7.19 and ≤7.10. Results: Progression of labor was associated with a significant decrease in non-linear indices and an increase in almost all linear indices, both in female and male fetuses, but changes were more marked in female fetuses. Non-acidemic females showed higher mean FHR in the final minutes of labor, compared with males. Acidemic females had higher linear indices when compared to similar male fetuses. Conclusions: During the minutes preceding delivery, female fetuses express higher linear indices than male fetuses, suggesting greater activation of the autonomic nervous system, while maintaining similar complexity indices, which suggests different reaction and adaptation capabilities to stress and distress.

Gender-specific heart rate dynamics in severe intrauterine growth-restricted fetuses

BACKGROUND Management of intrauterine growth restriction (IUGR) remains a major issue in perinatology. AIMS The objective of this paper was the assessment of gender-specific fetal heart rate (FHR) dynamics as a diagnostic tool in severe IUGR. SUBJECTS FHR was analyzed in the antepartum period in 15 severe IUGR fetuses and 18 controls, matched for gestational age, in relation to fetal gender. OUTCOME MEASURES Linear and entropy methods, such as mean FHR (mFHR), low (LF), high (HF) and movement frequency (MF), approximate, sample and multiscale entropy. Sensitivities and specificities were estimated using Fisher linear discriminant analysis and the leave-one-out method. RESULTS Overall, IUGR fetuses presented significantly lower mFHR and entropy compared with controls. However, gender-specific analysis showed that significantly lower mFHR was only evident in IUGR males and lower entropy in IUGR females. In addition, lower LF/(MF+HF) was patent in IUGR females compared with controls, but not in males. Rather high sensitivities and specificities were achieved in the detection of the FHR recordings related with IUGR male fetuses, when gender-specific analysis was performed at gestational ages less than 34 weeks. CONCLUSIONS Severe IUGR fetuses present gender-specific linear and entropy FHR changes, compared with controls, characterized by a significantly lower entropy and sympathetic-vagal balance in females than in males. These findings need to be considered in order to achieve better diagnostic results.

Analysis of heart rate variability in a rat model of induced pulmonary hypertension

Monocrotaline (MCT) is commonly used to experimentally induce pulmonary hypertension (PH), which might lead to chronic heart failure. In this study, linear and non-linear heart rate (HR) dynamics were weekly assessed in MCT-treated and non-treated Wistar rats. The HR of 10 adult Wistar rats injected with MCT (MCT group) and of 10 similar rats injected with vehicle (non-MCT group), anesthetized with Ketamine, was weekly recorded during 4 weeks. The first four segments of 1-min length of each HR recording were analysed using linear, time and frequency domains, and approximate (ApEn) and sample (SampEn) entropy indices, considering recently proposed values for the threshold parameter of ApEn and SampEn. Statistical analysis was performed using 95% confidence intervals and statistical tests. Along the study period, an overall weekly maintenance of HR indices, or a decrease, namely in weeks 1-2, was manifest, in the MCT group, except for LF and LF/HF, in week 1, denoting a short-term increase in sympathetic activity without any other changes. On the other hand, a maintenance of HR indices, or an increase, namely on week 4, was observed in the non-MCT group, except for LF/HF, denoting a long-term increase of the overall activity of HR control systems, with a parasympathetic like dominance. Studies on long-term HR dynamics should be performed in very carefully controlled experimental settings, as significant weekly changes may occur, both among anesthetized MCT-treated and non-treated rats.

Entropy and compression: two measures of complexity.

RATIONALE, AIMS AND OBJECTIVES Traditional complexity measures are used to capture the amount of structured information present in a certain phenomenon. Several approaches developed to facilitate the characterization of complexity have been described in the related literature. Fetal heart rate (FHR) monitoring has been used and improved during the last decades. The importance of these studies lies on an attempt to predict the fetus outcome, but complexity measures are not yet established in clinical practice. In this study, we have focused on two conceptually different measures: Shannon entropy, a probabilistic approach, and Kolmogorov complexity, an algorithmic approach. The main aim of the current investigation was to show that approximation to Kolmogorov complexity through different compressors, although applied to a lesser extent, may be as useful as Shannon entropy calculated by approximation through different entropies, which has been successfully applied to different scientific areas. METHODS To illustrate the applicability of both approaches, two entropy measures, approximate and sample entropy, and two compressors, paq8l and bzip2, were considered. These indices were applied to FHR tracings pertaining to a dataset composed of 48 delivered fetuses with umbilical artery blood (UAB) pH in the normal range (pH ≥ 7.20), 10 delivered mildly acidemic fetuses and 10 moderate-to-severe acidemic fetuses. The complexity indices were computed on the initial and final segments of the last hour of labour, considering 5- and 10-minute segments. RESULTS In our sample set, both entropies and compressors were successfully utilized to distinguish fetuses at risk of hypoxia from healthy ones. Fetuses with lower UAB pH presented significantly lower entropy and compression indices, more markedly in the final segments. CONCLUSIONS The combination of these conceptually different measures appeared to present an improved approach in the characterization of different pathophysiological states, reinforcing the theory that entropies and compressors measure different complexity features. In view of these findings, we recommend a combination of the two approaches.

Statistical Techniques for Correlating Total Suspended Matter Concentration with Seawater Reflectance Using Multispectral Satellite Data

Abstract The transport and distribution of sediments driven by mechanisms such as tides and waves, river discharges, wind stress, and turbidity currents and the sediment transport effects can be studied by remote sensing techniques. The study of total suspended matter concentration has ecological importance since it is the main carrier of various inorganic and organic processes. The main objective of this work was to evaluate the performance of different statistical methodologies in the estimation of total suspended matter concentration, in the breaking zone and in its adjacent area, using multispectral satellite images from TERRA/ASTER, SPOT/HRVIR, and Landsat/TM. These images cover a particular area of the northwest coast of Portugal. The relationship between the total suspended matter concentration and the spectral response of the seawater, in the visible and near-infrared regions of the electromagnetic spectrum, was quantified through simulations on different beaches of the study area. Seven images of TERRA/ASTER, SPOT/HRVIR, and Landsat/TM sensors were calibrated and atmospherically and geometrically corrected. Linear single-band models, linear multiple regressions, and artificial neural networks were applied to the visible and near-infrared bands of these sensors in order to estimate the total suspended matter concentration. Statistical analysis using determination coefficients and error estimation was employed, aiming to evaluate the most accurate approach in the estimation of total suspended matter concentration. The analysis of the root-mean-square error achieved by both linear and nonlinear models supports the hypothesis that the relationship between seawater reflectance and total suspended matter concentration is clearly nonlinear. Artificial neural networks have been shown to be useful in estimating the total suspended matter concentration from reflectance of visible and near-infrared bands with images of ASTER, HRVIR, and TM sensors, with better results for ASTER and HRVIR sensors. The artificial neural network approach was further applied to the seven processed images, and maps of total suspended matter concentration for all satellite images processed were produced.