Probabilistic Learning Coherent Point Drift for 3D Ultrasound Fetal Head Registration.

Quantification of brain growth is crucial for the assessment of fetal well being, for which ultrasound (US) images are the chosen clinical modality. However, they present artefacts, such as acoustic occlusion, especially after the 18th gestational week, when cranial calcification appears. Fetal US volume registration is useful in one or all of the following cases: to monitor the evolution of fetometry indicators, to segment different structures using a fetal brain atlas, and to align and combine multiple fetal brain acquisitions. This paper presents a new approach for automatic registration of real 3D US fetal brain volumes, volumes that contain a considerable degree of occlusion artefacts, noise, and missing data. To achieve this, a novel variant of the coherent point drift method is proposed. This work employs supervised learning to segment and conform a point cloud automatically and to estimate their subsequent weight factors. These factors are obtained by a random forest-based classification and are used to appropriately assign nonuniform membership probability values of a Gaussian mixture model. These characteristics allow for the automatic registration of 3D US fetal brain volumes with occlusions and multiplicative noise, without needing an initial point cloud. Compared to other intensity and geometry-based algorithms, the proposed method achieves an error reduction of 7.4% to 60.7%, with a target registration error of only 6.38 ± 3.24 mm. This makes the herein proposed approach highly suitable for 3D automatic registration of fetal head US volumes, an approach which can be useful to monitor fetal growth, segment several brain structures, or even compound multiple acquisitions taken from different projections.

Prediction of spinal curve progression in Adolescent Idiopathic Scoliosis using Random Forest regression.

BACKGROUND: The progression of the spinal curve represents one of the major concerns in the assessment of Adolescent Idiopathic Scoliosis (AIS). The prediction of the shape of the spine from the first visit could guide the management of AIS and provide the right treatment to prevent curve progression. METHOD: In this work, we propose a novel approach based on a statistical generative model to predict the shape variation of the spinal curve from the first visit. A spinal curve progression approach is learned using 3D spine models generated from retrospective biplanar X-rays. The prediction is performed every three months from the first visit, for a time lapse of one year and a half. An Independent Component Analysis (ICA) was computed to obtain Independent Components (ICs), which are used to describe the main directions of shape variations. A dataset of 3D shapes of 150 patients with AIS was employed to extract the ICs, which were used to train our approach. RESULTS: The approach generated an estimation of the shape of the spine through time. The estimated shape differs from the real curvature by 1.83, 5.18, and 4.79° of Cobb angles in the proximal thoracic, main thoracic, and thoraco-lumbar lumbar sections, respectively. CONCLUSIONS: The results obtained from our approach indicate that predictions based on ICs are very promising. ICA offers the means to identify the variation in the 3D space of the evolution of the shape of the spine. Another advantage of using ICs is that they can be visualized for interpretation.

Dynamic ensemble selection of learner-descriptor classifiers to assess curve types in adolescent idiopathic scoliosis.

While classification is important for assessing adolescent idiopathic scoliosis (AIS), it however suffers from low interobserver and intraobserver reliability. Classification using ensemble methods may contribute to improving reliability using the proper 2D and 3D images of spine curvature features. In this study, we present two new techniques to describe the spine, namely, leave-one-out and fan leave-one-out. Using these techniques, three descriptors are computed from a stereoradiographic 3D reconstruction to describe the relationship between a vertebra and its neighbors. A dynamic ensemble selection method is introduced for automatic spine classification. The performance of the method is evaluated on a dataset containing 962 3D spine models categorized according to three curve types. With a log loss of 0.5623, the dynamic ensemble selection outperforms voting and stacking ensemble learning techniques. This method can improve intraobserver and interobserver reliability, identify the best combination of descriptors for characterizing spine curve types, and provide assistance to clinicians in the form of information to classify borderline curvature types. Graphical abstract ᅟ.

A 3D Hermite-based multiscale local active contour method with elliptical shape constraints for segmentation of cardiac MR and CT volumes.

Analysis of cardiac images is a fundamental task to diagnose heart problems. Left ventricle (LV) is one of the most important heart structures used for cardiac evaluation. In this work, we propose a novel 3D hierarchical multiscale segmentation method based on a local active contour (AC) model and the Hermite transform (HT) for LV analysis in cardiac magnetic resonance (MR) and computed tomography (CT) volumes in short axis view. Features such as directional edges, texture, and intensities are analyzed using the multiscale HT space. A local AC model is configured using the HT coefficients and geometrical constraints. The endocardial and epicardial boundaries are used for evaluation. Segmentation of the endocardium is controlled using elliptical shape constraints. The final endocardial shape is used to define the geometrical constraints for segmentation of the epicardium. We follow the assumption that epicardial and endocardial shapes are similar in volumes with short axis view. An initialization scheme based on a fuzzy C-means algorithm and mathematical morphology was designed. The algorithm performance was evaluated using cardiac MR and CT volumes in short axis view demonstrating the feasibility of the proposed method.

Spatial Compounding of 3-D Fetal Brain Ultrasound Using Probabilistic Maps.

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 visibility 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.

Left ventricle segmentation in fetal echocardiography using a multi-texture active appearance model based on the steered Hermite transform.

OBJECTIVE: Fetal echocardiographic analysis is essential for detecting cardiac defects at early gestational ages. Fetal cardiac function can be assessed by performing some measurements regarding the dimension and shape of the heart cavities. In this work we propose an automatic segmentation method applied to the analysis of the left ventricle in fetal echocardiography. METHODS: For segmentation of the left ventricle, we designed a novel multi-texture active appearance model (AAM) based on the Hermite transform (HT). Local orientation analysis is addressed by steering the coefficients obtained with the HT. The method basically consists of an AAM-based scheme which uses the steered HT to efficiently code texture patterns of the input image. A wider and detailed description of the image features can be obtained with this method. Compared with classic AAM methods, the segmentation performance is substantially improved with the proposed scheme. Since AAM-based approaches process local information, an automatic method is also proposed to initialize the multi-texture AAM. For this purpose, a database of pre-segmented images was built. Then, techniques such as thresholding, mathematical morphology and correlation are combined to identify the position and orientation of the left ventricle. Typical issues found in fetal cardiac ultrasound images such as different orientations and shape variations of the heart cavities can be easily handled with the designed method. RESULTS: Several images of fetal echocardiography were used to evaluate the proposed segmentation method. The algorithm performance was validated using different metrics. We used a database of 143 real images of fetal hearts acquired for different phases of the cardiac cycle. We obtained an average Dice coefficient of 0.8631 and a point-to-curve distance of 2.027 pixels. The proposed algorithm was also validated by comparing it with other segmentation methods. CONCLUSIONS: We have designed an automatic algorithm for left ventricle segmentation in fetal echocardiography. The reported results demonstrate that the proposed approach can achieve an efficient segmentation of the left ventricular cavity. Typical problems found in images of fetal echocardiography are satisfactorily handled with the proposed multi-texture AAM scheme.

Automatic segmentation of the fetal cerebellum on ultrasound volumes, using a 3D statistical shape model.

Previous work has shown that the segmentation of anatomical structures on 3D ultrasound data sets provides an important tool for the assessment of the fetal health. In this work, we present an algorithm based on a 3D statistical shape model to segment the fetal cerebellum on 3D ultrasound volumes. This model is adjusted using an ad hoc objective function which is in turn optimized using the Nelder-Mead simplex algorithm. Our algorithm was tested on ultrasound volumes of the fetal brain taken from 20 pregnant women, between 18 and 24 gestational weeks. An intraclass correlation coefficient of 0.8528 and a mean Dice coefficient of 0.8 between cerebellar volumes measured using manual techniques and the volumes calculated using our algorithm were obtained. As far as we know, this is the first effort to automatically segment fetal intracranial structures on 3D ultrasound data.

Automatic segmentation of the cerebellum of fetuses on 3D ultrasound images, using a 3D Point Distribution Model.

Analysis of fetal biometric parameters on ultrasound images is widely performed and it is essential to estimate the gestational age, as well as the fetal growth pattern. The use of three dimensional ultrasound (3D US) is preferred over other tomographic modalities such as CT or MRI, due to its inherent safety and availability. However, the image quality of 3D US is not as good as MRI and therefore there is little work on the automatic segmentation of anatomic structures in 3D US of fetal brains. In this work we present preliminary results of the development of a 3D Point Distribution Model (PDM), for automatic segmentation, of the cerebellum in 3D US of the fetal brain. The model is adjusted to a fetal 3D ultrasound, using a genetic algorithm which optimizes a model fitting function. Preliminary results show that the approach reported is able to automatically segment the cerebellum in 3D ultrasounds of fetal brains.

Computer assisted biopsy of breast tumors.

In this paper we report our preliminary results of the development of a computer assisted system for breast biopsy. The system is based on tracked ultrasound images of the breast. A three dimensional ultrasound volume is constructed from a set of tracked B-scan images acquired with a calibrated probe. The system has been designed to assist a radiologist during breast biopsy, and also as a training system for radiology residents. A semiautomatic classification algorithm was implemented to assist the user with the annotation of the tumor on an ultrasound volume. We report the development of the system prototype, tested on a physical phantom of a breast with a tumor, made of polivinil alcohol.