Search

We have applied a deep learning framework, trained on mouse embryo images acquired with a 40 MHz annular array, to volumetric data acquired with a VisualSonics Vevo 3100 commercial scanner using a 40-MHz linear array. The deep learning framework was robust enough to accurately segment out the body and the brain ventricle from the 3D data generated by the commercial scanner. These results show that there is no need to retrain the algorithm with hundreds of new manually segmented datasets.

The segmentation of the brain ventricle (BV) and body in embryonic mice high-frequency ultrasound (HFU) volumes can provide useful information for biological researchers. However, manual segmentation of the BV and body requires substantial time and expertise. This work proposes a novel deep learning based end-to-end auto-context refinement framework, consisting of two stages. The first stage produces a low resolution segmentation of the BV and body simultaneously. The resulting probability map for each object (BV or body) is then used to crop a region of interest (ROI) around the target object in both the original image and the probability map to provide context to the refinement segmentation network. Joint training of the two stages provides significant improvement in Dice Similarity Coefficient (DSC) over using only the first stage (0.818 to 0.906 for the BV, and 0.919 to 0.934 for the body). The proposed method significantly reduces the inference time (102.36 to 0.09 s/volume ≈1000x faster) while slightly improves the segmentation accuracy over the previous methods using slide-window approaches.

Volumetric analysis of brain ventricles (BVs) is important to the study of normal and abnormal development of the central nervous system of mouse embryos. High-frequency ultrasound (HFU) is frequently used to image embryos because it is real-time, non-invasive, and provides fine-resolution images. However, manual segmentation of BVs from 3D HFU volumes remains challenging and time consuming. Therefore, automatic segmentation, staging, and mutant detection algorithms are needed for studies with large embryo counts. An accurate and automatic method to segment BVs from high-frequency ultrasound images has been stated in a prior work. This paper presents novel algorithms for deriving the Y-skeleton of a BV region and decomposing the BV region into five components (fourth ventricle, aqueduct, third ventricle and two lateral ventricles). Embryo staging and mutant detection are accomplished by analyzing the volume profile along the BV skeleton and the volumes of the five BV components.

Volumetric analysis of brain ventricles is important to the study of normal and abnormal development of the central nervous system of mouse embryos. High-frequency ultrasound (HFU) is frequently used to image embryos because HFU is real-time, non-invasive, and provides fine-resolution images. However, manual segmentation of ventricles from 3D HFU volumes remains challenging and time consuming. In this study, in utero and in vivo volumetric ultrasound data were acquired from pregnant mice using a 5-element, 40-MHz annular array. An automatic segmentation algorithm based on active shape model (ASM) was developed to segment the brain ventricles of the embryos; ASM allows us to efficiently “learn” from training data (i.e., manually segmented data). The algorithm was further enhanced by using detail-preserving reference shapes (also learned from training data) and region growing constrained by the reference shape. The hybrid algorithm was applied to three 12.5-day-old embryos. Results were qualitatively analyzed and compared with manual segmentation results in regions typically difficult to segment (e.g., thin brain ventricle connections). In addition, quantitative analysis using the Dice similarity coefficient (DSC) was used to compare the automatic segmentation results with manual segmentation. We obtained average DSC values of 0.848±0.015 for the brain ventricles and our method produced morphologically accurate results. Therefore, our method could streamline current HFU longitudinal studies of brain development that require manual segmentation.

Computer assisted medical image processing can extract vital information that may be elusive to human eyes. In this paper, an algorithm is proposed to automatically estimate the position of the actual midline from the brain CT scans using multiple regions shape matching. The method matches feature points identified from a set of ventricle templates, extracted from MRI, with the corresponding feature points in the segmented ventricles from CT images. Then based on the matched feature points, the position of the actual midline is estimated. The proposed multiple regions shape matching algorithm addresses the deformation problem arising from the intrinsic multiple regions nature of the brain ventricles. Experiments on the CT scans from patients with traumatic brain injuries (TBI) show promising results, particularly the proposed algorithm proves to be quite robust.

One of the hallmarks of Alzheimer's disease (AD) is the loss of neurons in the brain. In many cases, the medical experts use MR (magnetic resonance) images to qualitatively measure the neuronal loss by the shrinkage (atrophy) of the structures-of-interest, or sometimes more easily by the enlargement of the fluid-filled structures, such as the ventricles. For quantitative analysis, volume is the common choice. Volume, or area in 2D, is a gross measure and it cannot capture shape differences that can improve the diagnostic accuracy. Because most existing methods use complex and difficult- to-reproduce shape descriptors, the experts prefer more easily and robustly extractable area and volume in their diagnosis. In this paper, we introduce several novel and easily-extractable 2D shape descriptors for brain ventricle, and show that they and some of the well-known simple shape descriptors, such as perimeter, are better descriptors in the classification of AD patients and healthy controls.

In this paper, an algorithm that can define the threshold value automatically in region growing is proposed in order to detect a brain ventricle using a wavelet transform in MRI brain images. After the wavelet transform, edge sharpness, which means the average magnitude of detail signals on the contour of the object, was computed by using the magnitude of horizontal and vertical detail signals. The contours of a brain ventricle were detected by increasing the threshold value repeatedly and computing edge sharpness. When the edge sharpness became maximal, the optimal threshold was determined, and the detection of a brain ventricle was accomplished finally. This paper suggests an algorithm that can detect a brain ventricle; compares that algorithm with the geodesic active contour model numerically and visually by applying real MRI brain images; and verifies the efficiency of the proposed algorithm.

We use point distribution models (PDMs) to investigate lateral asymmetries in the shape of brain ventricles between control subjects and people with schizophrenia. Ventricle surfaces were extracted from T2-weighted MR images and PDMs generated using structural correspondences on the individual surfaces. Using paired linear discriminant analysis we calculate the vector in shape space that maximally separates the shapes of right and left ventricles in the group. The magnitude of the asymmetry is quantified by projection of the individual ventricle shapes onto this vector. We observe significant differences in the magnitude of the asymmetry in both schizophrenia and control groups. There is also a clear difference in the pattern of asymmetry. Male and female subgroups show different magnitudes and patterns of asymmetry, in both groups.