3D Image Volume Research Articles

Subject-aware PET Denoising with Contrastive Adversarial Domain Generalization.

Recent advances in deep learning (DL) have greatly improved the performance of positron emission tomography (PET) denoising performance. However, DL model performance can vary a lot across subjects, due to the large variability of the count levels and spatial distributions. A generalizable DL model that mitigates the subject-wise variations is highly expected toward a reliable and trustworthy system for clinical application. In this work, we propose a contrastive adversarial learning framework for subject-wise domain generalization (DG). Specifically, we configure a contrastive discriminator in addition to the UNet-based denoising module to check the subject-related information in the bottleneck feature, while the denoising module is adversarially trained to enforce the extraction of subject-invariant features. The sampled low-count realizations from the list-mode data are used as anchor-positive pairs to be close to each other, while the other subjects are used as negative samples to be distributed far away. We evaluated on 97 18F-MK6240 tau PET studies, each having 20 noise realizations with 25% fractions of events. Training, validation, and testing were implemented using 1400, 120, and 420 pairs of 3D image volumes in a subject-independent manner. The proposed contrastive adversarial DG demonstrated superior denoising performance than conventional UNet without subject-wise DG and cross-entropy-based adversarial DG.

Aberration correction in 3D transthoracic echocardiography

Three-dimensional cardiac imaging has been available in the clinic for more than two decades. Continuous improvement in image quality has occurred in this period due to the development of probe technology and beamforming techniques. The purpose of this article is to quantitatively and qualitatively analyze the effect of a commercially available aberration correction algorithm on clinically acquired 3D transthoracic echocardiography (3D TTE) images. Clinical triplane and 3D volume cineloops of at least one cardiac cycle of pre-beamformed channel data were captured from 50 patients using a GE HealthCare Vivid E95 system with the 4Vc-D matrix array probe. This resulted in a total of 3200 vol and 3136 triplane frames. The data were post-processed with and without aberration correction. Quantitatively, assessed by an image quality parameter based on coherence, all recordings were improved by aberration correction compared to those without aberration correction. Triplane data obtained a larger improvement in image quality than volume data. Qualitatively, as demonstrated by case examples, aberration-corrected images appear sharper, have a brighter tissue signal compared to the cavity, and provide better delineation of cardiac structures. 3D rendering of valves can also be significantly improved. In general, aberration correction provides a systematic improvement in clinical cardiac triplane and 3D volume images.

Three-dimensional imaging of upper tract urothelial carcinoma improves diagnostic yield and accuracy.

Upper tract urothelial carcinoma (UTUC) is a rare form of urothelial cancer with a high incidence of recurrence and a low survival rate. Almost two-thirds of UTUCs are invasive at the time of diagnosis; therefore, improving diagnostic methods is key to increasing survival rates. Histopathological analysis of UTUC is essential for diagnosis and typically requires endoscopy biopsy, tissue sectioning, and labeling. However, endoscopy biopsies are minute, and it is challenging to cut into thin sections for conventional histopathology; this complicates diagnosis. Here, we used volumetric 3-dimensional (3D) imaging to explore the inner landscape of clinical UTUC biopsies, without sectioning, revealing that 3D analysis of phosphorylated ribosomal protein S6 (pS6) could predict tumor grade and prognosis with improved accuracy. By visualizing the tumor vasculature, we discovered that pS6+ cells were localized near blood vessels at significantly higher levels in high-grade tumors than in low-grade tumors. Furthermore, the clustering of pS6+ cells was associated with shorter relapse-free survival. Our results demonstrate that 3D volume imaging of the structural niches of pS6 cells deep inside the UTUC samples improved diagnostic yield, grading, and prognosis prediction.

Deep-learning based 3D birefringence image generation using 2D multi-view holographic images

Refractive index stands as an inherent characteristic of a material, allowing non-invasive exploration of the three-dimensional (3D) interior of the material. Certain materials with different refractive indices produce a birefringence phenomenon in which incident light is split into two polarization components when it passes through the materials. Representative birefringent materials appear in calcite crystals, liquid crystals (LCs), biological tissues, silk fibers, polymer films, etc. If the internal 3D shape of these materials can be visually expressed through a non-invasive method, it can greatly contribute to the semiconductor, display industry, optical components and devices, and biomedical diagnosis. This paper introduces a novel approach employing deep learning to generate 3D birefringence images using multi-viewed holographic interference images. First, we acquired a set of multi-viewed holographic interference pattern images and a 3D volume image of birefringence directly from a polarizing DTT (dielectric tensor tomography)-based microscope system about each LC droplet sample. The proposed model was trained to generate the 3D volume images of birefringence using the two-dimensional (2D) interference pattern image set. Performance evaluations were conducted against the ground truth images obtained directly from the DTT microscopy. Visualization techniques were applied to describe the refractive index distribution in the generated 3D images of birefringence. The results show the proposed method’s efficiency in generating the 3D refractive index distribution from multi-viewed holographic interference images, presenting a novel data-driven alternative to traditional methods from the DTT devices.

Compressive sensing-based multi-focus line-scanning two-photon microscopy for fast 3D imaging

Fast 3D volume imaging methods have been playing increasingly important roles in biological studies. In this article, we present the design and characterization of a multi-focus line-scanning two-photon microscope. Specifically, a digital micromirror device (DMD) is employed to generate a randomly distributed focus array on a plane (i.e., x-z) via binary holography. Next, a galvanometric mirror scans the focus array in a direction normal to the plane (i.e., y-axis) over the imaging volume. For sparse samples, e.g., neural networks in a brain, 1-3 foci are used together with compressive sensing algorithm to achieve a volume imaging rate of 15.5 volumes/sec over 77 × 120 × 40 µm3. High-resolution optical cross-sectional images on selected planes and regions can be generated by sequentially scanning the laser focus generated on the x-z plane with good imaging speeds (e.g., 107 frames/sec over 80 × 120 × 40 µm3). In the experiments, microbeads, pollens, and mouse brain slices have been imaged to characterize the point spread function and volume image rate and quality at different sampling ratios. The results show that the multi-focus line-scanning microscope presents a fast and versatile 3D imaging platform for deep tissue imaging and dynamic live animal studies.

Cross noise level PET denoising with continuous adversarial domain generalization

Objective. Performing positron emission tomography (PET) denoising within the image space proves effective in reducing the variance in PET images. In recent years, deep learning has demonstrated superior denoising performance, but models trained on a specific noise level typically fail to generalize well on different noise levels, due to inherent distribution shifts between inputs. The distribution shift usually results in bias in the denoised images. Our goal is to tackle such a problem using a domain generalization technique. Approach. We propose to utilize the domain generalization technique with a novel feature space continuous discriminator (CD) for adversarial training, using the fraction of events as a continuous domain label. The core idea is to enforce the extraction of noise-level invariant features. Thus minimizing the distribution divergence of latent feature representation for different continuous noise levels, and making the model general for arbitrary noise levels. We created three sets of 10%, 13%–22% (uniformly randomly selected), or 25% fractions of events from 97 18F-MK6240 tau PET studies of 60 subjects. For each set, we generated 20 noise realizations. Training, validation, and testing were implemented using 1400, 120, and 420 pairs of 3D image volumes from the same or different sets. We used 3D UNet as the baseline and implemented CD to the continuous noise level training data of 13%–22% set. Main results. The proposed CD improves the denoising performance of our model trained in a 13%–22% fraction set for testing in both 10% and 25% fraction sets, measured by bias and standard deviation using full-count images as references. In addition, our CD method can improve the SSIM and PSNR consistently for Alzheimer-related regions and the whole brain. Significance. To our knowledge, this is the first attempt to alleviate the performance degradation in cross-noise level denoising from the perspective of domain generalization. Our study is also a pioneer work of continuous domain generalization to utilize continuously changing source domains.

Transmit beam design for tissue harmonic volume imaging of muscular tissues with a row-column array

Row-Column-addressed Arrays (RCAs), which have recently become commercially available, transmit along the rows and receive along columns of a 2D array in order to produce 3D volume images with low channel count. Imaging of the inherently three-dimensional, layered, and fibrous structure of muscular tissues in 3D using an RCA can improve evaluations of muscle function and disease compared to conventional 2D cross-sectional imaging, but volume images obtained using an RCA suffer from low lateral spatial resolution, low contrast, and grating lobe artifacts. Tissue harmonic imaging (THI) employs nonlinear acoustic effects to image at twice the transmit frequency, and can yield increased spatial resolution, increased contrast, and decreased artifacts from grating lobes. Here we investigate transmission considerations for THI in muscular tissues using a commercially available RCA (Vermon RC6gV). The parameter space is explored efficiently with frequency domain simulations of the 3D Westervelt equation. Pulse inversion imaging is applied experimentally using both steered plane wave and focused transmits to evaluate THI with an RCA in tissue phantoms and in muscular tissue. Pulse inversion volume images are compared to conventional images in terms of signal-to-noise, contrast, and ability to identify layers and fibrous structures in muscle in 3D. [Work supported by NIH HEAL Initiative R61AT012282.]

Four-dimensional (4D) Ultrasound Shear Wave Elastography Using Sequential Excitation.

Current shear wave elastography methods primarily focus on 2D imaging. To explore mechanical properties of biological tissues in 3D, a four-dimensional (4D, x, y, z, t) ultrasound shear wave elastography is required. However, 4D ultrasound shear wave elastography is still challenging due to the limitation of the hardware of standard ultrasound acquisition systems. In this study, we introduce a novel method to achieve 4D shear wave elastography, named sequential-based excitation shear wave elastography (SE-SWE). This method can achieve 4D elastography implemented by a 1024-element 2D array with a standard ultrasound 256-channel system. The SE-SWE method employs sequential excitation to generate shear waves, and utilizes a 2D array, dividing it into four sub-sections, to capture shear waves across multiple planes. This process involves sequentially exciting each sub-section to capture shear waves, followed by compounding the acquired data from these subsections. The phantom studies showed strong concordance between the shear wave speeds (SWS) measured by SE-SWE and expected values, confirming the accuracy of this method and potential to differentiate tissues by stiffness. In ex vivo chicken breast experiments, SE-SWE effectively distinguished between orientations relative to muscle fibers, highlighting its ability to capture the anisotropic properties of tissues. The SE-SWE method advances shear wave elastography significantly by using a 2D array divided into four subsections and sequential excitation, achieving high-resolution volumetric imaging at 1.6mm resolution. The SE-SWE method offers a straightforward and effective approach for 3D shear volume imaging of tissue biological properties.

Three-Dimensional Magneto-Acousto-Electrical Computed Tomography (3D MAE-CT): A Preliminary Study Using Ultrasound Linear Array Transducer.

Magneto-acousto-electrical tomography (MAET) is a hybrid imaging method that combines the high spatial resolution of ultrasonography with the high contrast of electrical impedance tomography (EIT). While most previous studies on MAET have focused on two-dimensional imaging, our recent research proposed a novel three-dimensional (3D) MAET method using B-mode and translational scanning. This method has been the first to reconstruct a 3D volume image of conductivity interfaces. However, this method has its limitations in mapping irregular shapes of conductivity. To address this challenge, we propose a 3D magneto-acousto-electrical computed tomography (3D MAE-CT) method utilizing an ultrasound linear array transducer in this work. Both phantom and in vitro experiments were conducted to validate our proposed method. The results from the phantom experiments demonstrate that our method can map the 3D volume conductivity with high spatial resolution. The oblique angles extracted from the 3D image closely match practical value, with the relative error ranging between -2.80% and 4.07%. Furthermore, the in vitro experiment successfully obtained a 3D image of a chicken heart, marking the first MAET 3D conductivity image of a tissue sample to date.

Membrane contact site detection (MCS-DETECT) reveals dual control of rough mitochondria-ER contacts.

Identification and morphological analysis of mitochondria-ER contacts (MERCs) by fluorescent microscopy is limited by subpixel resolution interorganelle distances. Here, the membrane contact site (MCS) detection algorithm, MCS-DETECT, reconstructs subpixel resolution MERCs from 3D super-resolution image volumes. MCS-DETECT shows that elongated ribosome-studded riboMERCs, present in HT-1080 but not COS-7 cells, are morphologically distinct from smaller smooth contacts and larger contacts induced by mitochondria-ER linker expression in COS-7 cells. RiboMERC formation is associated with increased mitochondrial potential, reduced in Gp78 knockout HT-1080 cells and induced by Gp78 ubiquitin ligase activity in COS-7 and HeLa cells. Knockdown of riboMERC tether RRBP1 eliminates riboMERCs in both wild-type and Gp78 knockout HT-1080 cells. By MCS-DETECT, Gp78-dependent riboMERCs present complex tubular shapes that intercalate between and contact multiple mitochondria. MCS-DETECT of 3D whole-cell super-resolution image volumes, therefore, identifies novel dual control of tubular riboMERCs, whose formation is dependent on RRBP1 and size modulated by Gp78 E3 ubiquitin ligase activity.

Astrocyte ensheathment of calyx-forming axons of the auditory brainstem precedes accelerated expression of myelin genes and myelination by oligodendrocytes.

Early postnatal brain development involves complex interactions among maturing neurons and glial cells that drive tissue organization. We previously analyzed gene expression in tissue from the mouse medial nucleus of the trapezoid body (MNTB) during the first postnatal week to study changes that surround rapid growth of the large calyx of Held (CH) nerve terminal. Here, we present genes that show significant changes in gene expression level during the second postnatal week, a developmental timeframe that brackets the onset of airborne sound stimulation and the early stages of myelination. Gene Ontology analysis revealed that many of these genes are related to the myelination process. Further investigation of these genes using a previously published cell type-specific bulk RNA-Seq data set in cortex and our own single-cell RNA-Seq data set in the MNTB revealed enrichment of these genes in the oligodendrocyte lineage (OL) cells. Combining the postnatal day (P)6-P14 microarray gene expression data with the previously published P0-P6 data provided fine temporal resolution to investigate the initiation and subsequent waves of gene expression related to OL cell maturation and the process of myelination. Many genes showed increasing expression levels between P2 and P6 in patterns that reflect OL cell maturation. Correspondingly, the first myelin proteins were detected by P4. Using a complementary, developmental series of electron microscopy 3D image volumes, we analyzed the temporal progression of axon wrapping and myelination in the MNTB. By employing a combination of established ultrastructural criteria to classify reconstructed early postnatal glial cells in the 3D volumes, we demonstrated for the first time that astrocytes within the mouse MNTB extensively wrap the axons of the growing CH terminal prior to OL cell wrapping and compaction of myelin. Our data revealed significant expression of several myelin genes and enrichment of multiple genes associated with lipid metabolism in astrocytes, which may subserve axon wrapping in addition to myelin formation. The transition from axon wrapping by astrocytes to OL cells occurs rapidly between P4 and P9 and identifies a potential new role of astrocytes in priming calyceal axons for subsequent myelination.

Left atrium 4D-flow segmentation with high-resolution contrast-enhanced magnetic resonance angiography.

Atrial fibrillation (AF) leads to intracardiac thrombus and an associated risk of stroke. Phase-contrast cardiovascular magnetic resonance (CMR) with flow-encoding in all three spatial directions (4D-flow) provides a time-resolved 3D volume image with 3D blood velocity, which brings individual hemodynamic information affecting thrombus formation. As the resolution and contrast of 4D-flow are limited, we proposed a semi-automated 4D-flow segmentation method for the left atrium (LA) using a standard-of-care contrast-enhanced magnetic resonance angiography (CE-MRA) and registration technique. LA of 54 patients with AF were segmented from 4D-flow taken in sinus rhythm using two segmentation methods. (1) Phase-contrast magnetic resonance angiography (PC-MRA) was calculated from 4D-flow, and LA was segmented slice-by-slice manually. (2) LA and other structures were segmented from CE-MRA and transformed into 4D-flow coordinates by registration with the mutual information method. Overlap of volume was tested by the Dice similarity coefficient (DSC) and the average symmetric surface distance (ASSD). Mean velocity and stasis were calculated to compare the functional property of LA from two segmentation methods. LA volumes from segmentation on CE-MRA were strongly correlated with PC-MRA volume, although mean CE-MRA volumes were about 10% larger. The proposed registration scheme resulted in visually successful registration in 76% of cases after two rounds of registration. The mean of DSC of the registered cases was 0.770 ± 0.045, and the mean of ASSD was 2.704 mm ± 0.668 mm. Mean velocity had no significant difference between the two segmentation methods, and mean stasis had a 3.3% difference. The proposed CE-MRA segmentation and registration method can generate segmentation for 4D-flow images. This method will facilitate 4D-flow analysis for AF patients by making segmentation easier and overcoming the limit of resolution.

A radiomics-incorporated deep ensemble learning model for multi-parametric MRI-based glioma segmentation

Objective. To develop a deep ensemble learning (DEL) model with radiomics spatial encoding execution for improved glioma segmentation accuracy using multi-parametric magnetic resonance imaging (mp-MRI). Approach. This model was developed using 369 glioma patients with a four-modality mp-MRI protocol: T1, contrast-enhanced T1 (T1-Ce), T2, and FLAIR. In each modality volume, a 3D sliding kernel was implemented across the brain to capture image heterogeneity: 56 radiomic features were extracted within the kernel, resulting in a fourth-order tensor. Each radiomic feature can then be encoded as a 3D image volume, namely a radiomic feature map (RFM). For each patient, all RFMs extracted from all four modalities were processed using principal component analysis for dimension reduction, and the first four principal components (PCs) were selected. Next, a DEL model comprised of four U-Net sub-models was trained for the segmentation of a region-of-interest: each sub-model utilizes the mp-MRI and one of the four PCs as a five-channel input for 2D execution. Last, four softmax probability results given by the DEL model were superimposed and binarized using Otsu’s method as the segmentation results. Three DEL models were trained to segment the enhancing tumor (ET), tumor core (TC), and whole tumor (WT), respectively. The segmentation results given by the proposed ensemble were compared to the mp-MRI-only U-Net results. Main Results. All three radiomics-incorporated DEL models were successfully implemented: compared to the mp-MRI-only U-net results, the dice coefficients of ET (0.777 → 0.817), TC (0.742 → 0.757), and WT (0.823 → 0.854) demonstrated improvement. The accuracy, sensitivity, and specificity results demonstrated similar patterns. Significance. The adopted radiomics spatial encoding execution enriches the image heterogeneity information that leads to the successful demonstration of the proposed DEL model, which offers a new tool for mp-MRI-based medical image segmentation.

Deep self-learning enables fast, high-fidelity isotropic resolution restoration for volumetric fluorescence microscopy

One intrinsic yet critical issue that troubles the field of fluorescence microscopy ever since its introduction is the unmatched resolution in the lateral and axial directions (i.e., resolution anisotropy), which severely deteriorates the quality, reconstruction, and analysis of 3D volume images. By leveraging the natural anisotropy, we present a deep self-learning method termed Self-Net that significantly improves the resolution of axial images by using the lateral images from the same raw dataset as rational targets. By incorporating unsupervised learning for realistic anisotropic degradation and supervised learning for high-fidelity isotropic recovery, our method can effectively suppress the hallucination with substantially enhanced image quality compared to previously reported methods. In the experiments, we show that Self-Net can reconstruct high-fidelity isotropic 3D images from organelle to tissue levels via raw images from various microscopy platforms, e.g., wide-field, laser-scanning, or super-resolution microscopy. For the first time, Self-Net enables isotropic whole-brain imaging at a voxel resolution of 0.2 × 0.2 × 0.2 μm3, which addresses the last-mile problem of data quality in single-neuron morphology visualization and reconstruction with minimal effort and cost. Overall, Self-Net is a promising approach to overcoming the inherent resolution anisotropy for all classes of 3D fluorescence microscopy.

Contemporary sequential segmental approach to congenital heart disease using four-dimensional magnetic resonance imaging with ferumoxytol: an illustrated editorial.

The ferumoxytol-enhanced 4D MR angiography with MUSIC (Multiphase Steady State Imaging with Contrast) technique provides a single data set that captures dynamic cardiovascular anatomy and ventricular function at the same time. Homogeneous opacification of all cardiovascular structures within the imaging volume allows full sequential segmental approach to the congenital heart diseases without any blind spots. The complex systemic and pulmonary venous anatomy is particularly well captured in the MUSIC. Cinematographic display of multiplanar sectional and 3D volume images is helpful in the morphological identification of the cardiac chambers, the assessment of the dynamic nature of the ventricular outflow tracts, and the assessment of the coronary arterial origins and courses.

A Graph Theory Study of Resting-State Functional MRI Connectivity in Children With Carbon Monoxide Poisoning.

The effect of carbon monoxide (CO) poisoning on the topology of brain functional networks is unclear, especially in children whose brains are still developing. To investigate the topological alterations of the whole-brain functional connectome in children with CO poisoning and characterize its relationship with disease severity. Cross-sectional and prospective study. A total of 26 patients with CO poisoning and 26 healthy controls. A 3.0 T MRI system/echo planar imaging (EPI) and 3D brain volume imaging (BRAVO) sequences. We used the network-based statistics (NBS) method to explore between-group differences in functional connectivity strength and a graph-theoretical-based analytic method to explore the topology of brain networks. Student's t-test, chi-square test, NBS, Pearson correlation coefficient, and false discovery rate correction. The statistical significance threshold was set at P < 0.05. The case group's brain functional network topology was impaired in comparison to the control group (reduced global efficiency and small-worldness, increased characteristic path length). According to node and edge analyses, the case group showed topologically damaged regions in the frontal lobe and basal ganglia, as well as neuronal circuits with weaker connections. Also, there was a significant correlation between the patients' coma time and the degree (r = -0.4564), efficiency (r = -0.4625), and characteristic path length (r = 0.4383) of the nodes in the left orbital inferior frontal gyrus. Carbon monoxide hemoglobin content (COHb) concentration and right rolandic operculum node characteristic path length (r = -0.3894) were significantly correlated. The node efficiency and node degree of the right middle frontal gyrus (r = 0.4447 and 0.4539) and right pallidum (r = 0.4136 and 0.4501) significantly correlated with the MMSE score. The brain network topology of CO poisoned children is damaged, which is manifested by reduced network integration and may lead to a series of clinical symptoms in patients. 2. Stage 2.

Deep learning based registration for head motion correction in positron emission tomography as a strategy for improved image quantification

Objectives: Positron emission tomography (PET) is affected by various kinds of patient movement during a scan. Frame-by-frame image registration is one of the most practiced motion correction techniques. In recent years, deep learning has shown a remarkable ability to quickly and accurately register images once trained. This paper studies the feasibility of using a deep learning framework to correct 3D positron emission tomography image volumes for head motion in routine positron emission tomography imaging to improve quantification in motion impacted data.Materials and Methods: A neural network was trained with 3D positron emission tomography image volumes in an unsupervised manner to predict transformation parameters required to perform image registration. A multi-step convolutional neural network (CNN) was combined with a spatial transform layer. Pairs of target and source images were used as input to the network. To prepare the training dataset, a previously published TOF-PEPT algorithm was applied to automatically detect static frames where the patient remained in a relatively steady position and transitional frames where they underwent abrupt motion. A single image volume was reconstructed for each static frame. The image reconstructed from the first static frame served as the target image with images from subsequent static frames being used as source images. The trained neural network predicted transformation parameters that could be used to perform frame-by-frame image-based motion correction but also enabled raw listmode positron emission tomography data correction where individual line-of-responses were repositioned. Line profiles and ROIs were drawn across the reconstructed image volumes to compare performance and quantitative results between standard registration tools and the deep learning technique. Corrected volumes were further compared to motion free images quantitatively using Dice indices.Results: In total, one hundred 3D positron emission tomography image volumes were used to train the network. Cross-validation was carried out using a 4:1 ratio for the training and test data. A conventional algorithm for affine registration from the Advanced Normalization Tools (ANTs) software package served as a baseline. To evaluate the correction performance, the mean Dice index and standardized uptake value (SUV) were used. Application of the algorithm to clinical data showed good performance with respect to registration accuracy as well as processing time. The neural network yielded a mean Dice index of ∼0.87 which was similar to the advanced Normalization Tools algorithm and did so ∼3x faster using a multi-core CPU and ∼20x faster with a GPU. Standardized uptake value analysis showed that quantitative results were 30%–60% higher in the motion-corrected images, and the neural network performed better than or close to the advanced Normalization Tools.Conclusion: The aim of this work was to study the quantitative impact of using a data-driven deep learning motion correction technique for positron emission tomography data and assess its performance. The results showed the technique is capable of producing high quality registrations that compensate for patient motion that occurs during a scan and improve quantitative accuracy.

A dataset of rodent cerebrovasculature from in vivo multiphoton fluorescence microscopy imaging

We present MiniVess, the first annotated dataset of rodent cerebrovasculature, acquired using two-photon fluorescence microscopy. MiniVess consists of 70 3D image volumes with segmented ground truths. Segmentations were created using traditional image processing operations, a U-Net, and manual proofreading. Code for image preprocessing steps and the U-Net are provided. Supervised machine learning methods have been widely used for automated image processing of biomedical images. While much emphasis has been placed on the development of new network architectures and loss functions, there has been an increased emphasis on the need for publicly available annotated, or segmented, datasets. Annotated datasets are necessary during model training and validation. In particular, datasets that are collected from different labs are necessary to test the generalizability of models. We hope this dataset will be helpful in testing the reliability of machine learning tools for analyzing biomedical images.

Sex differences in fetal intracranial volumes assessed by in utero MR imaging

BackgroundThe primary aim of the study is to test the null hypothesis that there are no statistically significant differences in intracranial volumes between male and female fetuses. Furthermore, we have studied the symmetry of the cerebral hemispheres in the cohort of low-risk fetuses.Methods200 normal fetuses between 18 and 37 gestational weeks (gw) were included in the cohort and all had in utero MR, consisting of routine and 3D-volume imaging. The surfaces of the cerebral ventricles, brain and internal table of the skull were outlined manually and volume measurements were obtained of ventricles (VV), brain parenchyma (BPV), extraaxial CSF spaces (EAV) and the total intracranial volume (TICV). The changes in those values were studied over the gestational range, along with potential gender differences and asymmetries of the cerebral hemispheres.ResultsBPV and VV increased steadily from 18 to 37 gestational weeks, and as a result TICV also increased steadily over that period. TICV and BPV increased at a statistically significantly greater rate in male relative to female fetuses after 24gw. The greater VV in male fetuses was apparent earlier, but the rate of increase was similar for male and female fetuses. There was no difference between the genders in the left and right hemispherical volumes, and they remained symmetrical over the age range measured.ConclusionsWe have described the growth of the major intracranial compartments in fetuses between 18 and 37gw. We have shown a number of statistically different features between male and female fetuses, but we have not detected any asymmetry in volumes of the fetal cerebral hemispheres.

Rapid and fully automated blood vasculature analysis in 3D light-sheet image volumes of different organs

Light-sheet fluorescence microscopy (LSFM) can produce high-resolution tomograms of tissue vasculature with high accuracy. However, data processing and analysis is laborious due to the size of the datasets. Here,we introduce VesselExpress, an automated software that reliably analyzes six characteristic vascular network parameters including vessel diameter in LSFM data on average computing hardware. VesselExpress is ∼100 times faster than other existing vessel analysis tools, requires no user interaction, and integrates batch processing and parallelization. Employing an innovative dual Frangi filter approach, we show that obesity induces a large-scale modulation of brain vasculature in mice and that seven other major organs differ strongly in their 3D vascular makeup. Hence, VesselExpress transforms LSFM from an observational to an analytical working tool.