A computer-aided method based on geometrical texture features for a precocious detection of fetal Hydrocephalus in ultrasound images

BACKGROUD

Hydrocephalus is the most common anomaly of the fetal head characterized by an excessive accumulation of fluid in the brain processing. The diagnostic process of fetal heads using traditional evaluation techniques are generally time consuming and error prone. Usually, fetal head size is computed using an ultrasound (US) image around 20-22 weeks, which is the gestational age (GA). Biometrical measurements are extracted and compared with ground truth charts to identify normal or abnormal growth.

METHODS

In this paper, an attempt has been made to enhance the Hydrocephalus characterization process by extracting other geometrical and textural features to design an efficient recognition system. The superiority of this work consists of the reduced time processing and the complexity of standard automatic approaches for routine examination. This proposed method requires practical insidiousness of the precocious discovery of fetuses' malformation to alert the experts about the existence of abnormal outcome. The first task is devoted to a proposed pre-processing model using a standard filtering and a segmentation scheme using a modified Hough transform (MHT) to detect the region of interest. Indeed, the obtained clinical parameters are presented to the principal component analysis (PCA) model in order to obtain a reduced number of measures which are employed in the classification stage.

RESULTS

Thanks to the combination of geometrical and statistical features, the classification process provided an important ability and an interesting performance achieving more than 96% of accuracy to detect pathological subjects in premature ages.

CONCLUSIONS

The experimental results illustrate the success and the accuracy of the proposed classification method for a factual diagnostic of fetal head malformation.

Scientific basis for standardization of fetal head measurements by ultrasound: a reproducibility study

OBJECTIVE

To compare the standard methods for ultrasound measurement of fetal head circumference (HC) and biparietal diameter (BPD) (outer-to-outer (BPDoo) vs outer-to-inner (BPDoi) caliper placement), and compare acquisition of these measurements in transthalamic (TT) vs transventricular (TV) planes.

METHODS

This study utilized ultrasound images acquired from women participating in the Oxford arm of the INTERGROWTH-21(st) Project. In the first phase of the study, BPDoo and BPDoi were measured on stored images. In the second phase, real-time measurements of BPD, occipitofrontal diameter (OFD) and HC in TT and TV planes were obtained by pairs of sonographers. Reproducibility of measurements made by the same (intraobserver) and by different (interobserver) sonographers, as well as the reproducibility of caliper placement and measurements obtained in different planes, was assessed using Bland-Altman plots.

RESULTS

In Phase I, we analyzed ultrasound images of 108 singleton fetuses. The mean intraobserver and interobserver differences were < 2% (1.34 mm) and the 95% limits of agreement were < 5% (3 mm) for both BPDoo and BPDoi. Neither method for measuring BPD showed consistently better reproducibility. In Phase II, we analyzed ultrasound images of 100 different singleton fetuses. The mean intraobserver and interobserver differences were < 1% (2.26 mm) and the 95% limits of agreement were < 8% (14.45 mm) for all fetal head measurements obtained in TV and TT planes. Neither plane for measuring fetal head showed consistently better reproducibility. Measurement of HC using the ellipse facility was as reproducible as HC calculated from BPD and OFD. OFD by itself was the least reproducible of all fetal head measurements.

CONCLUSIONS

Measurements of BPDoi and BPDoo are equally reproducible; however, we believe BPDoo should be used in clinical practice as it allows fetal HC to be measured and compared with neonatal HC. For all head measurements, TV and TT planes provide equally reproducible values at any gestational age, and HC values are similar in both planes. Fetal head measurement in the TT plane is preferable as international standards in this plane are available; however, measurements in the TV plane can be plotted on the same standards. Copyright © 2016 ISUOG. Published by John Wiley & Sons Ltd.

The cavum septi pellucidi in euploid and aneuploid fetuses

OBJECTIVE

To examine whether the cavum septi pellucidi (CSP) is larger in second- and third-trimester fetuses with chromosomal abnormalities than in euploid fetuses.

METHODS

This was a retrospective study utilizing stored two-dimensional images of second- and third-trimester fetuses between 18 and 40 weeks' gestation from three centers in Germany. The width of the CSP was measured by placing the calipers on the inner portion of its lateral borders. Two operators, both of whom were blinded to the fetal karyotype and to the measurements obtained by the other, measured the CSP width. The normal range in euploid fetuses was computed based on the biparietal diameter (BPD) by applying univariate regression analysis. The CSP width in euploid and aneuploid fetuses was transformed into Z-scores and compared using Student's t-test. Univariate regression analysis was used to determine the dependency of Z-score on head biometry.

RESULTS

The study population consisted of 406 singleton pregnancies, 267 with euploid fetuses, 81 with trisomy 21, 50 with trisomy 18 and eight with trisomy 13. In the euploid group, the mean CSP width was 4.5 (range, 1.8-7.4) mm. Regression analysis showed a significant dependency of CSP width on BPD (CSP width = 0.658 + (0.064 × BPD), r = 0.781, P < 0.0001; both parameters in mm). The mean CSP width increased from 3.2 to 7.1 mm for BPD values of 40 to 100 mm, respectively. In the groups of fetuses with trisomy 21, 18 and 13, mean CSP width was 5.7 (range, 2.8-10.5), 7.9 (range, 3.5-12.8) and 5.8 (range, 4.0-9.0) mm, respectively. In 42.0% of the fetuses with trisomy 21, CSP width was above the 95(th) centile. In trisomy 18 and 13, CSP width was above the 95(th) centile in 92.0% and 37.5% of cases, respectively.

CONCLUSION

A large CSP width should prompt a detailed ultrasound examination to further assess the risk for chromosomal abnormalities.