Académique Documents
Professionnel Documents
Culture Documents
278–291, 2018
Copyright © 2018 World Federation for Ultrasound in Medicine & Biology. All rights reserved.
Printed in the USA. All rights reserved
0301-5629/$ - see front matter
https://doi.org/10.1016/j.ultrasmedbio.2017.09.001
● Original Contribution
Abstract—A new method to address the problem of shadowing in fetal brain ultrasound volumes is presented.
The proposed approach is based on the spatial composition of multiple 3-D fetal head projections using the
weighted Euclidean norm as an operator. A support vector machine, which is trained with optimal textural
features, was used to assign weighting according to the posterior probabilities of brain tissue and shadows. Both
phantom and real fetal head ultrasound volumes were compounded using previously reported operators and
compared with the proposed composition method to validate it. The quantitative evaluations revealed increases
in signal-to-noise ratio ≤35% and in contrast-to-noise ratio ≤135% using real data. Qualitative comparisons
made by obstetricians indicated that this novel method adequately recovers brain tissue and improves the visi-
bility of the main cerebral structures. This may prove useful both for fetal monitoring and in the diagnosis of
brain defects. Overall this new approach outperforms spatial composition methods previously reported.
(E-mail: vera@xanum.uam.mx) © 2018 World Federation for Ultrasound in Medicine & Biology. All rights reserved.
Key Words: Ultrasound shadows, Support vector machine, Image fusion, Speckle reduction, Fetal brain, Spatial
composition.
278
Spatial compounding of 3-D fetal brain US ● J. Perez-Gonzalez et al. 279
causes the images to contain shadows and artifacts, reported by Vogt and Ermert (2008), a combination of high-
especially in the second and third trimesters, as the cranial frequency ultrasound with a mechanical scan and multi-
bones thicken and calcify during the gestation process. angle compounding for skin image acquisition is used.
These changes, in turn, affect the appropriate identifica- Wilhjelm et al. (2004) performed an extensive visual
tion of several fetal structures and the correct measurement and qualitative evaluation of composition operators based
of development indicators such as biparietal diameter, head on mean, geometric and logarithmic mean, median,
circumference and cerebellar volume (Jardim and maximum values and root mean square; they reported that
Figueiredo 2005). the mean is the operator that provided better results re-
To attenuate the ultrasound shadows and artifacts, this garding SNR and CNR improvement when the number of
study focuses on the improvement of fetal head US images projections used in the composition increases. Adam et al.
during the second and third trimesters of gestation. At this (2006) found that the application of non-linear filters, such
age, cranial calcification leads to partial acoustic occlu- as adaptive anisotropic diffusion or Gaussian kernels, after
sions, which make difficult the precise extraction of brain the composition process by coherent averaging, signifi-
indicators and, consequently, may result in an inaccurate cantly reduces the speckle noise; however, this can also
assessment of fetal health. A new spatial composition attenuate edges.
method is proposed that extracts information from several Grau and Noble (2005) proposed a spatial compo-
US fetal brain volumes. It allows characterization of the sition method using multiscale information and phase-
acoustic parameters of brain tissue in areas where cranial based image analysis for US heart compounding, achieving
occlusion is present. This information may then be used speckle noise reduction without a decrease in contrast on
to mitigate the effect of occlusion on image quality. This the main heart features. Rajpoot et al. (2011) presented a
approach is based on the automatic classification and proba- cardiac volume compounding strategy based on a wavelet-
bilistic estimation of brain tissue and shadow areas from fusion approach that improves SNR and CNR. Gooding
multiple US projections. et al. (2010) investigated the benefits of fusing several 4-D
heart US acquisitions, using different operators such as
the mean, median, maximum values, wavelet transform and
Related work mean shift algorithms. They obtained noise reductions and
Numerous physical or computational approaches have contrast increases up to 50% compared with a single scan.
been proposed to improve the quality of US acquisi- Perperidis et al. (2016) employed an anthropomorphic left
tions. The focus of this study is on image compounding ventricle phantom to examine the interslice angular dis-
methods, which combine information of different acqui- placement and 3-D sector angular range on the elevational
sitions to improve image quality and reduce noise. spatial compounding using the mean operator in cardiac
There are two types of compounding methods: fre- ultrasound data.
quency and spatially based. Frequency compounding Another compounding operator used is the weighted
combines multiple images of the same object acquired at mean. zu Berge et al. (2014) published results of an
different frequencies, which has been reported to improve orientation-aware compounding using confidence maps
the signal-to-noise ratio (SNR), but affects axial resolu- (Karamalis et al. 2012), which can compensate uncertain-
tion (Erez et al. 2008; Perperidis et al. 2015). In contrast, ty in attenuated regions by estimating a per-voxel
spatial compounding fuses several US images of the same confidence in the information depicted by US volumes fol-
region taken from different angles or transducer posi- lowing a random walk framework. These maps can be used
tions with the purpose of building a new image with as weights to compound several US images. Preliminary
enhanced contours, better SNR and attenuated artifacts, results have been reported on the weighted mean compo-
without negative effects on resolution. According to sition of multiple 2-D simulated brain images contaminated
Contreras Ortiz et al. (2012), if N uncorrelated or partial- by artificial multiplicative noise (Perez-Gonzalez et al.
ly correlated volumes are used in the composition, the 2015).
reduction in speckle is of the order of N using coher- These previous works focus mainly on enhancing
ent averaging. image quality from multiple projections; however, the spe-
Also, several authors have carried out spatial com- cific goal of recovering or estimating missing information
pounding using the mean operator and have reported SNR in occluded areas is only partially solved. This work rep-
and contrast-to-noise ratio (CNR) improvements in US resents a new approach that has as its main aim dealing
volumes of the female breast (Krücker et al. 2000), gall with the problem of acoustic occlusions in US volumes.
bladder of a healthy human (Rohling et al. 1997), athero- The proposed method is based on the spatial composi-
sclerotic plaques (Jespersen et al. 2000; Kofoed et al. 2001) tion of multiple projections accompanied by a suitable
and bovine muscle and epidural space with warping (Groves estimation of the posterior probability of tissue and shadows
and Rohling 2004; Tran et al. 2007). In another approach or artifacts. This method can be useful in building a new
280 Ultrasound in Medicine & Biology Volume 44, Number 1, 2018
US fetal brain volume reducing occlusion artifacts, which classification problem is targeted to discriminate infor-
is important in the assessment of fetal health. mative versus uninformative (e.g., artifact) input voxels.
Effectively, the learning of the weight estimation is achieved
METHODS through feature extraction (Fig. 1C), feature selection
(Fig. 1D), and computation of the probabilities from the
The problem of fusing multiple 3-D ultrasound scans
results of the binary classifier (Fig. 1C). The details of the
taken from different scanning positions into a single volume
steps are described in the following subsections.
is addressed. An overview of the proposed methodology
is illustrated in Figure 1. First, the ultrasound scans are
registered and re-sliced to a global coordinate system Probabilistic spatial compounding
(Fig. 1B). This step can be done by rigid registration of A set of aligned US volumes is designated as
landmark points. Once the scans are registered, the goal Vn ( x, y, z ), with n = 1, 2, … , N being the number of
is to compute for each voxel in the volume the intensity studies in three dimensions and with voxel coordinates (x,
that best represents the underlying anatomy. The main chal- y, z). The information from each acquisition can be com-
lenge here is inherent in ultrasound imaging because the bined using different composition operators; in this work,
same anatomical location is represented by very differ- the Euclidean norm operator of the set of volumes Vn : 3
ent intensity values when imaged from different views. This weighted by Ψ n ∈ 3 → [0, 1] is used. It is defined as:
is due mainly to the differing attenuation paths, but also
N
to shadow artifacts. The fusion is formulated in terms of
probabilistic spatial compounding (Fig. 1F), where the
V ( x, y, z ) = ∑Ψ n ( x, y, z ) ⋅ Vn ( x, y, z ) 2 (1)
n =1
effect of each input scan is modulated by a probabilistic
weight. In this context, the purpose is to learn the esti- where V(x, y, z) is a new volume composed of N US
mation of the weights in a supervised manner from an volumes, and Ψ n ( x, y, z ) are the weighting factors per
annotated data set. Although this is a regression problem, voxel, which aim to give more prevalence to regions with
it is difficult to give an a priori probability value to each fetal brain tissue and lower weight to areas with occlu-
of the input values to be fused. Instead, a simpler binary sion acoustic artifacts (Fig. 1F). Therefore, the question
Fig. 1. Methodology overview. CNR = contrast-to-noise ratio; GLCM = gray-level co-occurrence matrix; PCA = principal com-
ponent analysis; SNR = signal-to-noise ratio; SVM = support vector machine.
Spatial compounding of 3-D fetal brain US ● J. Perez-Gonzalez et al. 281
is how to assign weighting factors. In this context, this Finally, a principal component analysis (PCA) was
method proposes learning the weights in a supervised implemented to select the most significant features for the
manner from an annotated data set of two classes: brain classification process and to reduce the dimensionality of
tissue and shadowed regions. Feature extraction and se- the input space (264 initially) (Hotelling 1933; Pearson
lection, together with the computation of the posterior 1901). The number of features can be reduced by select-
probabilities from the results of the classifier, were used ing the PCA coefficients with the higher variance. These
to estimate the weighting factors. This methodology is de- components were used to classify fetal brain tissue and
scribed below. areas with shadows (Fig. 1D).
Fig. 2. Truncated cone phantom in axial view. (a) Ultrasound acquisition without occlusions and (b) ultrasound acquisition
obtained by positioning a plastic piece between the transducer and the phantom to generate acoustic shadows. (c) Phantom
designed in lateral and axial views.
σ and C can be optimized by gradually modifying their to contrast probabilistic spatial compounding (PSC) results
values, filling a grid and then choosing the combination using phantom and real data sets, some of the most fre-
that maximizes accuracy. quently used composition operators were tested. The details
Depending on the structures of interest, the training of each data set and their validation are explained in the
data set can be selected from a single US volume by choos- following subsections.
ing representative regions of brain tissue (midline, head
contour, cerebellum, frontal lobe, etc.) with y = +1 and Phantom data set. To validate the implemented al-
shadows or artifacts with y = −1. The remaining acquisi- gorithm, a 3-D truncated conical phantom inside a box was
tions can be used to classify and to estimate the probabilistic built (Fig. 2C). The phantom was prepared with 6 wt%
maps (weighting factors). Thus, new volumes from dif- gelatin gel and 4 wt% agar, which is the standard mate-
ferent transducer positions or subjects do not require re- rial used in US phantom applications. In contrast, the
training the SVM. surrounding tissue-mimicking gel was made with 4 wt%
gelatin and 1.5 wt% agar to ensure good distinction from
Data set and validation the conical shape in US (Dang et al. 2011). We used this
To test the capability of the proposed algorithm to phantom to perform two series of acquisitions. The first
recover brain information, an US phantom was used. consisted on a set of six different volumes acquired from
Several volumes taken from different transducer angles several transducer positions (four orthogonal and two
were generated and processed. To validate this experi- oblique views); Figure 2A is an example image in axial
ment, the SNR, CNR and correlation metrics between a view. For the second series, six volumes were obtained
composed volume and the baseline were computed. Af- at the same previous positions, but this time an acoustic
terward, a set of fetal brain US volumes (acquired from occlusion was artificially created by placing a piece of
axial and coronal projections) was processed; the aim was plastic between the transducer and the phantom; Figure 2B
to build a new fetal brain volume without occlusion arti- is a representative image of an US with such an occlu-
facts. To analyze these results a quantitative validation sion. The occlusion covered 37.5% of the total phantom
(using SNR and CNR) and a qualitative evaluation by en- volume. All acquisitions were performed in B-mode using
gineering and clinical experts were carried out. Additionally, an Ultrasonix Sonix RP system with a motorized curvilinear
Spatial compounding of 3-D fetal brain US ● J. Perez-Gonzalez et al. 283
Fig. 3. Ultrasound fetal brain examples in axial transcerebellar plane. (a) An example with the following structures marked:
head contour (HC), midline (MID), cerebellum (CER), cavum septum pellucidum (CSP), peduncles (PC), cisterna magna (CM)
and nuchal fold (NF). (b) Fetal image with several shadows.
Fig. 4. Truncated cone phantom compounding results in axial view (a circular shape should be observed). (a) Baseline. (b–f)
Compounding using the (b) mean, (c) weighted mean by confidence map, (d) maximum values, (e) root mean square and (f)
probabilistic spatial compounding.
operators’ performance when the number of acquisitions On the other hand, an increase in SNR and CNR can
with shadows is increased from 1 to 6 in the composi- be observed (Fig. 5) when six volumes are considered for
tion process. In the top row of Figure 5A and B, the the composition. the PSC method presents considerable
behavior of SNR and CNR is illustrated. It can be seen improvements compared with the MEAN (49.6% and
that as the number of volumes used for the composition 145.9%), WMCM (26.1% and 113.4%), MAX (9.1% and
increases, SNR and CNR improve considerably, which is 489.7%) and RMS (21% and 272.1%) methods. The MAX
consistent with previous work (Jespersen et al. 2000). An and RMS methods exhibit good performance on the SNR,
exception is when the fourth volume is added, because it but affect image contrast, and the MEAN and WMCM
has a higher content of occlusion artifacts, thus provok- methods present a better balance between SNR and
ing a decrease in SNR and/or CNR; this behavior is CNR; however, the phantom shape is altered by occlu-
observed only for the MEAN, WMCM, MAX and RMS sion artifacts.
methods. For PSC, these parameters remain stable, pos- When these indices were computed for the baseline
sibly because of the method’s ability to select and weight image, an SNR of 6.32 and a CNR of 4.54 were ob-
information in the composition process. tained, which represent increments of 16.7% and 92.8%
286 Ultrasound in Medicine & Biology Volume 44, Number 1, 2018
Fig. 5. Quantitative assessment of phantom compounding using the MEAN, weighted mean by confidence map (WMCM),
maximum values (MAX), root mean square (RMS) and probabilistic spatial compounding (PSC) approaches. The horizontal
axis indicates the number of volumes used to generate the compounded volume. (a) Signal-to-noise ratio (SNR). (b) Contrast-
to-noise ratio (CNR). (c) Cross correlation (CC). (d) Normalized mutual information (NMI).
respectively, compared with the values obtained for the two different volumes, and therefore, they provide an es-
proposed PSC method; it must be recalled that the base- timation of the capacity of each method to recover
line image was composed of non-occluded projections. information preserving the phantom shape from differ-
Also, the behavior of CC and NMI indices was ob- ent projections, compared with the baseline image. In this
served for MEAN, WMCM, MAX, RMS and PSC sense, the results indicate that the proposed PSC method
composition results, compared with the baseline image perform better than the MEAN, WMCM, MAX and RMS
(Fig. 5C, D). It can be observed that all five methods pro- methods. However, it must be remarked that all methods
vided substantially better results when the number of are dependent on the quantity of information provided by
volumes considered for the composition was increased. each volume used in the composition process. If they
However, the best performance was obtained using PSC contain minimal information or are completely oc-
with CC = 0.63 and NMI = 0.42. These values represent cluded, the resulting composed image will be very poor.
enhancements of 20% and 28.3%, respectively, with respect
to the MEAN method, and enhancements of 15.8% and Fetal brain US compounding
17.9% compared with the WMCM method. In contrast, The second series of experiments consisted of quan-
the MAX and RMS approaches obtained the worst results titative and qualitative evaluations on the fetal brain US
as revealed by CC and NMI metrics. These two param- volumes composed using the PSC algorithm and other
eters indicate the similarity of information contained in methods. The first test consisted of evaluating the
Spatial compounding of 3-D fetal brain US ● J. Perez-Gonzalez et al. 287
Fig. 6. Ultrasound fetal brain results in axial transcerebellar plane. (a) Single ultrasound acquisition. (b–f) Compounding using
the (b) mean, (c) weighted mean by confidence map, (d) maximum values, (e) root mean square and (f) probabilistic spatial
compounding.
compounding volume quality measured by the SNR and method (CNR = 12.13). In the second column of Table 1
CNR indices. Afterward, two qualitative tests were carried it can be seen that the proposed methodology yields the
out: general evaluation by acquisition and processing US best result (with increases of 3.5% to 135%), withstatistical
image experts, and fetal brain structure evaluation by ob- differences versus SA and all the other methods tested.
stetrician experts. These results reveal that the best balance of SNR and CNR
In Figure 6 is an example of compounding results with corresponds to PSC followed by the WMCM and MEAN
two projections using the MEAN, WMCM, MAX, RMS, methods. This suggests that the proposed approach con-
PSC and SA. It can be appreciated that in all cases the siderably improves the quality of US volumes by enhancing
composition process helps to recover occluded areas com- information, reducing multiplicative noise and mitigat-
pared with SA. Such is the case for the MAX method ing shadowed regions.
(Fig. 6D), where more brain tissue can be observed, but To evaluate the overall quality of a new compounded
with a granulated aspect and multiplicative noise, espe- volume a qualitative assessment was carried out by experts
cially in the cerebellum and peduncle regions. On the other in US fetal image acquisition and processing. Table 2 out-
hand, in Figure 6F, the results obtained using PSC illus- lines the results of three evaluated parameters: head contour
trate that this method achieves a reduction of shadowed definition, visible brain tissue and general quality. For each
regions and improves image quality without altering the item a comparison between the PSC method and all other
morphology of the fetal brain structures.
In Table 1, a SNR and CNR evaluation of single ac-
quisition and compounding approaches is outlined. It can Table 1. Quantitative evaluation (µ ± σ) of
be seen that all methodologies exhibit considerably better compounding methods in fetal volumes*
results compared with SA. This reveals that the compo- Method SNR CNR
sition of several acquisitions can improve US image quality,
SA 7.83 ± 2.8†
5.15 ± 1.9‡
which agrees with previously reported research (Wilhjelm MEAN 10.27 ± 1.2† 11.44 ± 2.7‡
et al. 2004). On the other hand, to measure statistical dif- WMCM 10.34 ± 1.9 11.71 ± 1.8‡
ferences, a Friedman test, followed by a Wilcoxon test with MAX 10.55 ± 3.6 7.34 ± 3.9‡
RMS 10.33 ± 2.6 10.41 ± 2.5‡
Bonferroni post hoc correction, was carried out. In this PSC 10.53 ± 2.7 12.13 ± 2.3
analysis only the significant differences between PSC and
all other results are presented. With respect to the SNR, CNR = contrast-to-noise ratio; MAX = maximum values; PSC = proba-
bilistic spatial compounding; RMS = root mean square; SA = single-view
PSC exhibits statistical differences in comparison to the acquisition; SNR = signal-to-noise ratio; WMCM = weighted mean by con-
SA and MEAN methods and a slight increase compared fidence map.
with the WMCM and RMS approaches. However, MAX * Comparisons using the Friedman test and Wilcoxon test with Bonferroni
correction statistical tests at significance level (p < 0.05).
has the best performance (SNR = 10.55), although it has †
Indicates significant difference in SNR compared with PSC.
a poorer result for CNR (7.34) compared with the PSC ‡
Indicates significant difference in CNR compared with PSC.
288 Ultrasound in Medicine & Biology Volume 44, Number 1, 2018
Table 2. General qualitative assessment of ultrasound Finally, a thorough validation was carried out for
fetal brain data* the assessment of the most important brain structures
Comparison Very bad Bad Similar Good Excellent considered in the clinical diagnosis of several patholo-
gies. For this purpose, pairs of images were compared
Head contour quality between the proposed method (PSC) and SA, MEAN,
PSC vs. SA 3 10 13 33 41
PSC vs. MEAN 1 17 19 38 25 WMCM, MAX and RMS results, assigning a qualitative
PSC vs. WMCM 4 10 22 37 27 score: very bad, bad, similar, good or excellent. Previ-
PSC vs. MAX 2 8 21 40 29 ously, an expert obstetrician (who did not participate in
PSC vs. RMS 3 16 19 36 26
Visible brain tissue the evaluation) selected the images presented for com-
PSC vs. SA 4 7 20 33 36 parison, in an axial view of transcerebellar and
PSC vs. MEAN 2 12 12 44 30 transventricular planes. Figure 7 summarizes the evalua-
PSC vs. WMCM 0 11 23 36 30
PSC vs. MAX 15 20 24 26 15 tions carried out by three obstetricians on brain structures
PSC vs. RMS 1 12 27 35 25 and common aspects for the images presented on a given
General quality of the volume pair. In Figure 7A, the overall comparison of US volumes’
PSC vs. SA 1 17 12 32 38
PSC vs. MEAN 8 17 12 37 26 general quality can be observed, where the good catego-
PSC vs. WMCM 6 19 13 39 23 ry votes vary between 50% and 83%. These results concur
PSC vs. MAX 0 5 12 38 45 with those obtained for the SNR and CNR evaluations
PSC vs. RMS 10 14 12 33 31
and with the other qualitative evaluation made by experts
CNR = contrast-to-noise ratio; MAX = maximum values; PSC = proba- on US fetal image acquisition and processing discussed
bilistic spatial compounding; RMS = root mean square; SA = single-view
acquisition; SNR = signal-to-noise ratio; WMCM = weighted mean by con-
in the previous section.
fidence map. Head contour is one of the most important anatom-
Values in bold represent the highest number of votes for each comparison. ical structures in clinical practice, because it serves as the
* Fetal image processing experts’ comparisons of three different aspects;
all comparisons were carried out between the PSC and the SA, MEAN,
basis for estimation of several other biomarkers, such as
WMCM, MAX or RMS approach. Values correspond to the number of votes biparietal and fronto-occipital diameters, cranial circum-
assigned to one of the five categories (columns 2–6). N = 100. ference and gestational age (Monteagudo and Timor-Tritsch
2009). The percentages of votes obtained when compar-
approaches, as well as an SA, was performed. It can be ing head contours in all images pairs are illustrated in
seen that in comparison to SA, PSC received most of the Figure 7B. Note that PSC is clearly superior to SA, with
votes in the excellent category with 41% for head contour most of the votes in the good and excellent categories.
quality, 36% for visible brain tissue and 38% for general Because the head is one of the structures that is less af-
quality; this is evidence that the composition using proba- fected by acoustic occlusion (in fact, shadows are generated
bilistic maps can improve image aspects such as quality mainly by the skull itself), several composition scores are
and capability to recover missing information, con- similar, which is reflected in evaluations comparing PSC
trasted with a single US volume. Regarding head contour with all other methods. Specifically, some enhancement
quality, PSC is mainly in the good category (between 36% was observed in images composed using WMCM; this can
and 40%). In the case of visible brain tissue, it can be ap- be explained by the intensity homogenization of regions
preciated that the majority of the votes were assigned to around the fetal skull, caused by the use of confidence
the good category when comparing PSC with all other com- maps, inherent to this method.
pounding methods. Nevertheless, if we focus only on the Other important structures used in fetal brain assess-
comparison between PCS and MAX, similar numbers of ment are the midline and CSP; these serve as elementary
votes were obtained in all categories; this is due to the fact references for plane realignment or detection of brain dis-
that MAX always provides composed volumes with orders associated with midline deviation, among others
maximal information, but, as mentioned before, it alters (Monteagudo and Timor-Tritsch 2009). In Figure 7C and
edges, has poor contrast and can modify the morphology D are the results obtained when comparing these struc-
of several fetal brain structures. Finally, for general quality tures; it can be observed that PSC was evaluated as better
evaluation, the PSC comparisons present positive results than the other methods, with 50%–83% of votes in the good
with scores between 33% and 39% in the good category, category, for both midline and CSP.
when contrasting PSC with MEAN, WMCM and RMS; An important aspect of assessment in this work was
in the case of PSC versus MAX, a total of 45% votes in the overall quality of visible brain tissue after the PSC pro-
the excellent category were obtained. These results reaf- cedure was applied for image compounding. The results
firm that the proposed method has a better capability to obtained are illustrated in Figure 7E, where it can be seen
improve quality, and at the same time it minimizes oc- that PSC performs better than SA, MEAN and RMS, with
cluded areas by recovering information from the volumes most of the votes in the good and excellent categories; the
used for the composition. comparison of PSC with WMCM yields 66% good votes.
Spatial compounding of 3-D fetal brain US ● J. Perez-Gonzalez et al. 289
Fig. 7. Evaluation of the main fetal brain structures and quality aspects in ultrasound volumes. Three obstetrician experts com-
pared five different parameters (a–e) of the results obtained with probabilistic spatial compounding (PSC) versus the single-
view acquisition (SA), MEAN, weighted mean by confidence map (WMCM), maximal values (MAX) and root mean square
(RMS) approaches. In each panel are 100% stacked bar charts of the votes obtained for each comparison performed.
On the contrary, results obtained between PSC and MAX structures, with 66% good votes when comparing PSC with
are more balanced, with 50% of the votes falling in the SA, MEAN, WMCM, MAX and RMS. The cerebellum
similar category. This is in agreement with results re- was one of the best qualified structures with all votes falling
ported in the previous sections, where it was remarked that in the good and excellent categories, whereas the tha-
composition using MAX always provides volumes with lamic region received 46% of similar and bad scores and
higher-intensity values, thus mitigating shadowed regions, only 54% of good votes.
but also altering borders and structure shape and reduc- These comparisons reveal that PSC composition
ing CNR. allows a general enhancement of volume quality and, more
Other structures analyzed were the thalamus in the specifically, of those brain structures most frequently used
transventricular axial plane and the peduncles, cerebel- for fetal brain evaluation; this can lead to better quanti-
lum, nuchal fold and cisterna magna in the transcerebellar fication and segmentation processes and, therefore, to
axial plane. Results are similar to those obtained for other adequate clinical diagnostics.
290 Ultrasound in Medicine & Biology Volume 44, Number 1, 2018
Processing and Analysis (SIPAM 2015). Proc SPIE 9681; 2015. http:// 2007: Ultrasonic Imaging and Signal Processing. Proc SPIE; 2007;
dx.doi.org/10.1117/12.2207958. 6513:65130W.
Perperidis A, Cusack D, White A, McDicken N, MacGillivray T, Anderson Tsantis S, Cavouras D, Kalatzis I, Piliouras N, Dimitropoulos N,
T. Temporal compounding: A novel implementation and its impact Nikiforidis G. Development of a support vector machine-based image
on quality and diagnostic value in echocardiography. Ultrasound Med analysis system for assessing the thyroid nodule malignancy risk on
Biol 2015;41:1749–1765. ultrasound. Ultrasound Med Biol 2005;31:1451–1459.
Perperidis A, McDicken N, MacGillivray T, Anderson T. Elevational Vapnik VN. The nature of statistical learning theory, 2nd ed. New York:
spatial compounding for enhancing image quality in echocardiography. Springer; 2000.
Ultrasound 2016;24:74–85. Vogt M, Ermert H. Limited-angle spatial compound imaging of skin with
Platt J. Probabilistic outputs for support vector machines and compari- high-frequency ultrasound (20 MHz). IEEE Trans Ultrason Ferroelect
sons to regularized likelihood methods: Advances in large margin Freq Control 2008;55:1975–1983.
classifiers, vol. 10. Cambridge: MIT Press; 1999. p. 61–74. Wang S. Texture feature extraction of hyper-spectral image with three-
Rajpoot K, Grau V, Noble JA, Szmigielski C, Becher H. Multiview fusion dimensional gray-level co-occurrence. J Inform Comput Sci 2015;
3-D echocardiography: Improving the information and quality of real- 12:1439–1448.
time 3-D echocardiography. Ultrasound Med Biol 2011;37:1056– Wilhjelm J, Jensen M, Jespersen S, Sahl B, Falk E. Visual and quanti-
1072. tative evaluation of selected image combination schemes in ultrasound
Rodrigues R, Braz R, Pereira M, Moutinho J, Pinheiro AM. A two- spatial compound scanning. IEEE Trans Med Imaging 2004;23:181–
step segmentation method for breast ultrasound masses based on multi- 190.
resolution analysis. Ultrasound Med Biol 2015;41:1737–1748. zu Berge CS, Kapoor A, Navab N. Orientation-driven ultrasound com-
Rohling R, Gee A, Berman L. Three-dimensional spatial compounding pounding using uncertainty information. Lect Notes Comput Sci 2014;
of ultrasound images. Med Image Anal 1997;1:177–193. 236–245.
Timor-Trisch I, Monteagudo A, Cohen H. Neuroecografia Prenatal y Neo- Zettinig O, Fuerst B, Kojcev R, Esposito M, Salehi M, Wein W,
natal, vol. 1. Madrid: Marban Libros; 2004. Rackerseder J, Frisch B, Navab N. Toward real–time 3D ultra-
Tran D, Kamani A, Lessoway V, Rohling RN. Adaptive spatial com- sound registration-based visual servoing for interventional navigation.
pounding for improving ultrasound images of the epidural space. In: In: Proceedings, IEEE International Conference on Robotics and Au-
Emelianov SY, McAleavey SA, eds. Proceedings, Medical Imaging tomation, Stockholm, Sweden. New York: IEEE, 2016.