Ana I. L. Namburete

Computational methods for quantifying in vivo muscle fascicle curvature from ultrasound images.

Muscle fascicles curve during contraction, and this has been seen using B-mode ultrasound. Curvature can vary along a fascicle, and amongst the fascicles within a muscle. The purpose of this study was to develop an automated method for quantifying curvature across the entirety of an imaged muscle, to test the accuracy of the method against synthetic images of known curvature and noise, and to test the sensitivity of the method to ultrasound probe placement. Both synthetic and ultrasound images were processed using multiscale vessel enhancement filtering to accentuate the muscle fascicles, wavelet-based methods were used to quantify fascicle orientations and curvature distribution grids were produced by quantifying local curvatures for each point within the image. Ultrasound images of ramped isometric contractions of the human medial gastrocnemius were acquired in a test-retest study. The methods enabled distinct curvatures to be determined in different regions of the muscle. The methods were sensitive to kernel sizes during image processing, noise within the image and the variability of probe placements during retesting. Across the physiological range of curvatures and noise, curvatures calculated from validation grids were quantified with a typical standard error of less than 0.026 m⁻¹, and this is about 1% of the maximum curvatures observed in fascicles of contracting muscle.

Learning-based prediction of gestational age from ultrasound images of the fetal brain

Graphical abstract

Fetal cranial segmentation in 2D ultrasound images using shape properties of pixel clusters

The detection of cranial dysmorphisms during pregnancy is achieved by assessing the cranial shape from 2D ultrasound images of the fetal head. As such, several algorithms have been presented to automate this task due to the fact that segmentation of the fetal cranium from ultrasound images is a central problem in obstetric care which is complicated by fuzzy boundaries and variability in fetal position and head shape. In this paper, we introduce a machine learning framework that employs a novel feature set which incorporates local statistics and shape information about pixel clusters (or superpixels) within an image, and evaluate the performance of the feature set in the task of segmenting the cranial pixels in an ultrasound image using a random forest classifier. Our experiments show that the features derived from the shapes of the pixel groupings outperform powerful features such as Haar features and achieved a 97.22% segmentation accuracy when applied to the task of fetal cranial segmentation in ultrasound images.

Data-driven shape parameterization for segmentation of the right ventricle from 3D+t echocardiography

Model-based segmentation facilitates the accurate measurement of geometric properties of anatomy from ultrasound images. Regularization of the model surface is typically necessary due to the presence of noisy and incomplete boundaries. When simple regularizers are insufficient, linear basis shape models have been shown to be effective. However, for problems such as right ventricle (RV) segmentation from 3D+t echocardiography, where dense consistent landmarks and complete boundaries are absent, acquiring accurate training surfaces in dense correspondence is difficult. As a solution, this paper presents a framework which performs joint segmentation of multiple 3D+t sequences while simultaneously optimizing an underlying linear basis shape model. In particular, the RV is represented as an explicit continuous surface, and segmentation of all frames is formulated as a single continuous energy minimization problem. Shape information is automatically shared between frames, missing boundaries are implicitly handled, and only coarse surface initializations are necessary. The framework is demonstrated to successfully segment both multiple-view and multiple-subject collections of 3D+t echocardiography sequences, and the results confirm that the linear basis shape model is an effective model constraint. Furthermore, the framework is shown to achieve smaller segmentation errors than a state-of-art commercial semi-automatic RV segmentation package.

Regional variations in fascicle curvatures within a muscle belly change during contraction

During muscle contraction, the fascicles curve in response to changes in internal pressures within the muscle. Muscle modelling studies have predicted that fascicles curve to different extents in different regions of the muscle and, as such, curvature is expected to vary along and across the muscle belly. In the present study, the local variations in fascicle curvature within the muscle belly were investigated for a range of contractile conditions. B-mode ultrasound scans of the medial and lateral gastrocnemii muscles were collected at five ankle positions-ranging from dorsiflexion to plantarflexion. An automated algorithm was applied to the images in order to extract the local curvatures from the muscle belly regions. Significant variations in fascicle curvature were seen in the superficial-to-deep direction. Curvatures were positive in the superficial layer, negative in the deep layer, and had intermediate values close to zero in the central muscle region. This is indicative of the fascicles following an S-shaped trajectory across the muscle image. The relation between external pressure and curvature regionalization was also investigated by applying elastic compression bandages on the calf. The application of pressure was associated with greater negative curvatures in the distal and central regions of the middle layer, but appeared to have little effect on the superficial and deep layers. The results from this study showed that (1) fascicle curvature increases with contraction level, (2) there is curvature regionalization within the muscle belly, (3) curvature increases with pressure, and (4) fascicles follow an S-shaped trajectory across the muscle images.

Predicting Pixel Defect Rates Based on Image Sensor Parameters

Experimental measurements have shown that image sensors are continuously subject to the development of in-field permanent defects in the form of hot pixels. Based on measurements of defect rates in 23 DSLRs, 4 point and shoot cameras, and 11 cell phone cameras, we show that the rate of these defects depends on the technology (APS or CCD) and on design parameters the like of imager area, pixel size, and gain (ISO). Increasing the image sensitivity (ISO) (from 400 up to 25,600 ISO range) causes the defects to be more noticeable, with some going into saturation, and at the same time increases the number of defects. Partially stuck hot pixels, which have an offset independent of exposure time, make up more than 40% of the defects and are particularly affected by ISO changes. Comparing different sensor sizes has shown that if the pixel size is nearly constant, the defect rate scales linearly with sensor area, suggesting a measurement metric of defects/year/sq mm. Plotting this rate for different pixel and sensor sizes (from 7.5 down to 1.5 microns) shows that defect rates grow rapidly as the pixel size shrinks. Curve fitting shows an empirical power law with defect rate proportional to the pixel size to the power of-2.5. However, separating the pixel types shows that CCDs scale more slowly, with a power of-2, which translates into the pixel area. CMOS sensors, on the other hand, scale more rapidly with the pixel size to the power of-3.3. The result is that for 6-7 micron pixels the CCD defect rate is ~2.5 greater than the CMOS, but for 2 micron pixels the defect rates are both much higher and about equal. This paper presents a formula for predicting the expected rate of defect development for a given set of sensor parameters. This formula can be used by sensor designers when determining the imager parameters, taking into account the length of time the imager is expected to be in service.

Fully-automated alignment of 3D fetal brain ultrasound to a canonical reference space using multi-task learning.

HIGHLIGHTSWe propose a FCN to automatically co‐align 3D fetal neurosonography images.The multi‐task FCN predicts skull boundaries, eye location, and 3D brain orientation.Our proposed brain alignment method is invariant to fetal size and gestational age.Structural and anatomical correspondence was achieved in 88% of 140 tested volumes. ABSTRACT Methods for aligning 3D fetal neurosonography images must be robust to (i) intensity variations, (ii) anatomical and age‐specific differences within the fetal population, and (iii) the variations in fetal position. To this end, we propose a multi‐task fully convolutional neural network (FCN) architecture to address the problem of 3D fetal brain localization, structural segmentation, and alignment to a referential coordinate system. Instead of treating these tasks as independent problems, we optimize the network by simultaneously learning features shared within the input data pertaining to the correlated tasks, and later branching out into task‐specific output streams. Brain alignment is achieved by defining a parametric coordinate system based on skull boundaries, location of the eye sockets, and head pose, as predicted from intracranial structures. This information is used to estimate an affine transformation to align a volumetric image to the skull‐based coordinate system. Co‐alignment of 140 fetal ultrasound volumes (age range: 26.0±4.4 weeks) was achieved with high brain overlap and low eye localization error, regardless of gestational age or head size. The automatically co‐aligned volumes show good structural correspondence between fetal anatomies.

Robust Regression of Brain Maturation from 3D Fetal Neurosonography Using CRNs

We propose a fully three-dimensional Convolutional Regression Network (CRN) for the task of predicting fetal brain maturation from 3D ultrasound (US) data. Anatomical development is modelled as the sonographic patterns visible in the brain at a given gestational age, which are aggregated by the model into a single value: the brain maturation (BM) score. These patterns are learned from 589 3D fetal volumes, and the model is applied to 3D US images of 146 fetal subjects acquired at multiple, ethnically diverse sites, spanning an age range of 18 to 36 gestational weeks. Achieving a mean error of 7.7 days between ground-truth and estimated maturational scores, our method outperforms the current state-of-art for automated BM estimation from 3D US images.

Predicting Fetal Neurodevelopmental Age from Ultrasound Images

We propose an automated framework for predicting age and neurodevelopmental maturation of a fetus based on 3D ultrasound (US) brain image appearance. A topology-preserving manifold representation of the fetal skull enabled design of bespoke scale-invariant image features. Our regression forest model used these features to learn a mapping from age-related sonographic image patterns to fetal age and development. The Sylvian Fissure was identified as a critical region for accurate age estimation, and restricting the search space to this anatomy improved prediction accuracy on a set of 130 healthy fetuses (error ± 3.8 days; r = 0.98 performing the best current clinical method. Our framework remained robust when applied to a routine clinical population.

Projecting the rate of in-field pixel defects based on pixel size, sensor area, and ISO

Image sensors continuously develop in-field permanent hot pixel defects over time. Experimental measurements of DSLR, point and shoot, and cell phone cameras, show that the rate of these defects depends on the technology (APS or CCD) and on design parameters like imager area, pixel size, and gain (ISO). Increased image sensitivity (ISO) enhances defects appearance and sometimes results in saturation. 40% of defects are partially stuck hot pixels, with an offset independent of exposure time, and are particularly affected by ISO changes. Comparing different sensor sizes with similar pixel sizes showed that defect rates scale linearly with sensor area, suggesting the metric of defects/year/sq mm. Plotting this rate for different pixel sizes (7.5 down to 1.5 microns) shows that defect rates grow rapidly as pixel size shrinks. Curve fitting shows an empirical power law with defect rates proportional to the pixel size to the power of -2.1 for CCD and to the power of -3.6 for CMOS. At 7um pixels, the CCD defect rate is ~2.5 greater than for CMOS, but for 2.4um pixels the rates are equal. Extending our empirical formula to include ISO allows us to predict the expected defect development rate for a wide set of sensor parameters.