SDS-Net: A lightweight 3D convolutional neural network with multi-branch attention for multimodal brain tumor accurate segmentation.

The accurate and fast segmentation method of tumor regions in brain Magnetic Resonance Imaging (MRI) is significant for clinical diagnosis, treatment and monitoring, given the aggressive and high mortality rate of brain tumors. However, due to the limitation of computational complexity, convolutional neural networks (CNNs) face challenges in being efficiently deployed on resource-limited devices, which restricts their popularity in practical medical applications. To address this issue, we propose a lightweight and efficient 3D convolutional neural network SDS-Net for multimodal brain tumor MRI image segmentation. SDS-Net combines depthwise separable convolution and traditional convolution to construct the 3D lightweight backbone blocks, lightweight feature extraction (LFE) and lightweight feature fusion (LFF) modules, which effectively utilizes the rich local features in multimodal images and enhances the segmentation performance of sub-tumor regions. In addition, 3D shuffle attention (SA) and 3D self-ensemble (SE) modules are incorporated into the encoder and decoder of the network. The SA helps to capture high-quality spatial and channel features from the modalities, and the SE acquires more refined edge features by gathering information from each layer. The proposed SDS-Net was validated on the BRATS datasets. The Dice coefficients were achieved 92.7, 80.0 and 88.9% for whole tumor (WT), enhancing tumor (ET) and tumor core (TC), respectively, on the BRTAS 2020 dataset. On the BRTAS 2021 dataset, the Dice coefficients were 91.8, 82.5 and 86.8% for WT, ET and TC, respectively. Compared with other state-of-the-art methods, SDS-Net achieved superior segmentation performance with fewer parameters and less computational cost, under the condition of 2.52 M counts and 68.18 G FLOPs.

Methods for the Analysis of 26 Million VOC Area Measurements during the Deepwater Horizon Oil Spill Clean-up.

The NIEHS GuLF STUDY is an epidemiologic study of the health of workers who participated in the 2010 Deepwater Horizon oil spill response and clean-up effort. Even with a large database of approximately 28 000 personal samples that were analyzed for total hydrocarbons (THCs) and other oil-related chemicals, resulting in nearly 160 000 full-shift personal measurements, there were still exposure scenarios where the number of measurements was too limited to rigorously assess exposures. Also available were over 26 million volatile organic compounds (VOCs) area air measurements of approximately 1-min duration, collected from direct-reading instruments on 38 large vessels generally located near the leaking well. This paper presents a strategy for converting the VOC database into hourly average air concentrations by vessel as the first step of a larger process designed to use these data to supplement full-shift THC personal exposure measurements. We applied a Bayesian method to account for measurements with values below the analytic instrument's limit of detection while processing the large database into average instrument-hour concentrations and then hourly concentrations across instruments on each day of measurement on each of the vessels. To illustrate this process, we present results on the drilling rig ship, the Discoverer Enterprise. The methods reduced the 26 million measurements to 21 900 hourly averages, which later contributed to the development of additional full-shift THC observations. The approach used here can be applied by occupational health professionals with large datasets of direct-reading instruments to better understand workplace exposures.

A direct slicing technique for the 3D printing of implicitly represented medical models.

In conventional medical image printing methods, volumetric medical data needs to be conversed into STereo Lithography (STL) format, the most commonly used format for representing geometric models for 3D printing. However, this STL conversion process is not only time consuming, but more importantly, it often leads to the loss of accuracy. It has become a critical factor hindering the printing efficiency and precision of organ models. By examining the key characteristics of discrete medical volume data, this paper proposes a direct slicing technique for printing implicitly represented 3D medical models. The proposed method mainly consists of three algorithms: (1) A layer-based contour extraction algorithm for discrete volume data; (2) An inner shell construction algorithm based on discrete point differential indentation; (3) An infill generation algorithm based on the constructed virtual contour and scan lines. The proposed method has been applied to the slicing of several organ models for experiments, and the ratios of time cost and memory cost between the conventional method and the proposed method are about 4-100 and 1.1 to 1.4 respectively, which demonstrate that the proposed method has a great improvement in both time and space performance when compared with the conventional STL-based method. Our technique extends the direct input format of geometric models for additive manufacturing. That is, discrete volume data can be used as a direct input for additive manufacturing without conversion to STL format.

Direct 3D model extraction method for color volume images.

BACKGROUND: There is a great demand for the extraction of organ models from three-dimensional (3D) medical images in clinical medicine diagnosis and treatment. OBJECTIVE: We aimed to aid doctors in seeing the real shape of human organs more clearly and vividly. METHODS: The method uses the minimum eigenvectors of Laplacian matrix to automatically calculate a group of basic matting components that can properly define the volume image. These matting components can then be used to build foreground images with the help of a few user marks. RESULTS: We propose a direct 3D model segmentation method for volume images. This is a process of extracting foreground objects from volume images and estimating the opacity of the voxels covered by the objects. CONCLUSIONS: The results of segmentation experiments on different parts of human body prove the applicability of this method.

Joined fragment segmentation for fractured bones using GPU-accelerated shape-preserving erosion and dilation.

Joined fragment segmentation for fractured bones segmented from CT (computed tomography) images is a time-consuming task and calls for lots of interactions. To alleviate segmentation burdens of radiologists, we propose a graphics processing unit (GPU)-accelerated 3D segmentation framework requiring less interactions and lower time cost compared with existing methods. We first leverage the normal-based erosion method to separate joined bone fragments. After labeling the separated fragments via CCL (connected component labeling) algorithm, the record-based dilation method is eventually employed to restore bone's original shape. Besides, we introduce an additional random walk algorithm to tackle the special case where fragments are strongly joined. For efficient fragment segmentation, the framework is carried out in parallel with GPU-acceleration technology. Experiments on realistic CT volumes demonstrate that our framework can attain accurate fragment segmentations with dice scores over 99% and averagely takes 3.47 s to complete the segmentation task for a fractured bone volume of 512 × 512 × 425 voxels. We propose a GPU accelerated segmentation framework, which mainly consists of normal-based erosion and record-based dilation, to automatically segment joined fragments for most cases. For the remaining cases, we introduce a random walk algorithm for segmentation with a few interactions.

Automatic gallbladder segmentation using combined 2D and 3D shape features to perform volumetric analysis in native and secretin-enhanced MRCP sequences.

OBJECTIVES: We aimed to develop the first fully automated 3D gallbladder segmentation approach to perform volumetric analysis in volume data of magnetic resonance (MR) cholangiopancreatography (MRCP) sequences. Volumetric gallbladder analysis is performed for non-contrast-enhanced and secretin-enhanced MRCP sequences. MATERIALS AND METHODS: Native and secretin-enhanced MRCP volume data were produced with a 1.5-T MR system. Images of coronal maximum intensity projections (MIP) are used to automatically compute 2D characteristic shape features of the gallbladder in the MIP images. A gallbladder shape space is generated to derive 3D gallbladder shape features, which are then combined with 2D gallbladder shape features in a support vector machine approach to detect gallbladder regions in MRCP volume data. A region-based level set approach is used for fine segmentation. Volumetric analysis is performed for both sequences to calculate gallbladder volume differences between both sequences. RESULTS: The approach presented achieves segmentation results with mean Dice coefficients of 0.917 in non-contrast-enhanced sequences and 0.904 in secretin-enhanced sequences. CONCLUSION: This is the first approach developed to detect and segment gallbladders in MR-based volume data automatically in both sequences. It can be used to perform gallbladder volume determination in epidemiological studies and to detect abnormal gallbladder volumes or shapes. The positive volume differences between both sequences may indicate the quantity of the pancreatobiliary reflux.

On the utility of 3D hand cursors to explore medical volume datasets with a touchless interface.

Analyzing medical volume datasets requires interactive visualization so that users can extract anatomo-physiological information in real-time. Conventional volume rendering systems rely on 2D input devices, such as mice and keyboards, which are known to hamper 3D analysis as users often struggle to obtain the desired orientation that is only achieved after several attempts. In this paper, we address which 3D analysis tools are better performed with 3D hand cursors operating on a touchless interface comparatively to a 2D input devices running on a conventional WIMP interface. The main goals of this paper are to explore the capabilities of (simple) hand gestures to facilitate sterile manipulation of 3D medical data on a touchless interface, without resorting on wearables, and to evaluate the surgical feasibility of the proposed interface next to senior surgeons (N=5) and interns (N=2). To this end, we developed a touchless interface controlled via hand gestures and body postures to rapidly rotate and position medical volume images in three-dimensions, where each hand acts as an interactive 3D cursor. User studies were conducted with laypeople, while informal evaluation sessions were carried with senior surgeons, radiologists and professional biomedical engineers. Results demonstrate its usability as the proposed touchless interface improves spatial awareness and a more fluent interaction with the 3D volume than with traditional 2D input devices, as it requires lesser number of attempts to achieve the desired orientation by avoiding the composition of several cumulative rotations, which is typically necessary in WIMP interfaces. However, tasks requiring precision such as clipping plane visualization and tagging are best performed with mouse-based systems due to noise, incorrect gestures detection and problems in skeleton tracking that need to be addressed before tests in real medical environments might be performed.

FluoRender: joint freehand segmentation and visualization for many-channel fluorescence data analysis.

BACKGROUND: Image segmentation and registration techniques have enabled biologists to place large amounts of volume data from fluorescence microscopy, morphed three-dimensionally, onto a common spatial frame. Existing tools built on volume visualization pipelines for single channel or red-green-blue (RGB) channels have become inadequate for the new challenges of fluorescence microscopy. For a three-dimensional atlas of the insect nervous system, hundreds of volume channels are rendered simultaneously, whereas fluorescence intensity values from each channel need to be preserved for versatile adjustment and analysis. Although several existing tools have incorporated support of multichannel data using various strategies, the lack of a flexible design has made true many-channel visualization and analysis unavailable. The most common practice for many-channel volume data presentation is still converting and rendering pseudosurfaces, which are inaccurate for both qualitative and quantitative evaluations. RESULTS: Here, we present an alternative design strategy that accommodates the visualization and analysis of about 100 volume channels, each of which can be interactively adjusted, selected, and segmented using freehand tools. Our multichannel visualization includes a multilevel streaming pipeline plus a triple-buffer compositing technique. Our method also preserves original fluorescence intensity values on graphics hardware, a crucial feature that allows graphics-processing-unit (GPU)-based processing for interactive data analysis, such as freehand segmentation. We have implemented the design strategies as a thorough restructuring of our original tool, FluoRender. CONCLUSION: The redesign of FluoRender not only maintains the existing multichannel capabilities for a greatly extended number of volume channels, but also enables new analysis functions for many-channel data from emerging biomedical-imaging techniques.

Output-Sensitive Filtering of Streaming Volume Data.

Real-time volume data acquisition poses substantial challenges for the traditional visualization pipeline where data enhancement is typically seen as a pre-processing step. In the case of 4D ultrasound data, for instance, costly processing operations to reduce noise and to remove artefacts need to be executed for every frame. To enable the use of high-quality filtering operations in such scenarios, we propose an output-sensitive approach to the visualization of streaming volume data. Our method evaluates the potential contribution of all voxels to the final image, allowing us to skip expensive processing operations that have little or no effect on the visualization. As filtering operations modify the data values which may affect the visibility, our main contribution is a fast scheme to predict their maximum effect on the final image. Our approach prioritizes filtering of voxels with high contribution to the final visualization based on a maximal permissible error per pixel. With zero permissible error, the optimized filtering will yield a result that is identical to filtering of the entire volume. We provide a thorough technical evaluation of the approach and demonstrate it on several typical scenarios that require on-the-fly processing.

A fast 3D adaptive bilateral filter for ultrasound volume visualization.

BACKGROUND AND OBJECTIVE: This paper introduces an effective noise removal method for medical ultrasound volume data. Ultrasound data usually need to be filtered because they contain significant noise. Conventional two-dimensional (2D) filtering methods cannot use the implicit information between adjacent layers, and existing 3D filtering methods are slow because of complicated filter kernels. Even though one filter method utilizes simple filters for speed, it is inefficient at removing noise and does not take into account the characteristics of ultrasound sampling. To solve this problem, we introduce a fast filtering method using parallel bilateral filtering and adjust the filter window size proportionally according to its position. METHODS: We devised a parallel bilateral filtering by obtaining a 3D summed area table of a quantized spatial filter. The filtering method is made adaptive by changing the kernel window size according to the distance from the ultrasound signal transmission point. RESULTS: Experiments were performed to compare the noise removal and loss of original data of the anisotropic diffusion filtering, bilateral filtering, and adaptive bilateral filtering of ultrasound volume-rendered images. The results show that the adaptive filter correctly takes into account the sampling characteristics of the ultrasound volumes. CONCLUSIONS: The proposed method can more efficiently remove noise and minimize distortion from ultrasound data than existing simple or non-adaptive filtering methods.

Chemometric Multivariate Tools for Candidate Biomarker Identification: LDA, PLS-DA, SIMCA, Ranking-PCA.

2-D gel electrophoresis usually provides complex maps characterized by a low reproducibility: this hampers the use of spot volume data for the identification of reliable biomarkers. Under these circumstances, effective and robust methods for the comparison and classification of 2-D maps are fundamental for the identification of an exhaustive panel of candidate biomarkers. Multivariate methods are the most suitable since they take into consideration the relationships between the variables, i.e., effects of synergy and antagonism between the spots. Here the most common multivariate methods used in spot volume datasets analysis are presented. The methods are applied on a sample dataset to prove their effectiveness.

Denoising of 3D magnetic resonance images by using higher-order singular value decomposition.

The denoising of magnetic resonance (MR) images is important to improve the inspection quality and reliability of quantitative image analysis. Nonlocal filters by exploiting similarity and/or sparseness among patches or cubes achieve excellent performance in denoising MR images. Recently, higher-order singular value decomposition (HOSVD) has been demonstrated to be a simple and effective method for exploiting redundancy in the 3D stack of similar patches during denoising 2D natural image. This work aims to investigate the application and improvement of HOSVD to denoising MR volume data. The wiener-augmented HOSVD method achieves comparable performance to that of BM4D. For further improvement, we propose to augment the standard HOSVD stage by a second recursive stage, which is a repeated HOSVD filtering of the weighted summation of the residual and denoised image in the first stage. The appropriate weights have been investigated by experiments with different image types and noise levels. Experimental results over synthetic and real 3D MR data demonstrate that the proposed method outperforms current state-of-the-art denoising methods.

Alternative automatic alignment method for specimen tilt-series images based on back-projected volume data cross-correlations.

We devised a new automatic image alignment method for a specimen tilt series; this method is based on the volume data cross-correlation among 3-D cross-sections reconstructed from different sets of projection images (including a single image) for tilt-series alignment or tilt-axis search purposes. This method requires neither markers nor image feature points traceable through the tilt series, and it was examined through simulations and applied to biological thin sections. The method automatically aligned tilt series centred at the correctly detected tilt axis with a precision sufficient for practical applications.

Reproducible surveillance breast ultrasound using an image fusion technique in a short-interval follow-up for BI-RADS 3 lesions: a pilot study.

The aim of our study was to verify the utility of surveillance ultrasound (US) using real-time virtual sonography (RVS)--to coordinate present US images with past US images reconstructed from previously acquired US volume data using an image fusion technique--for short-interval follow-up of Breast Imaging-Reporting and Data System (BI-RADS) category 3 mass lesions. We enrolled 20 women (23 lesions) with more than 24 mo of follow-up after classification as BI-RADS category 3 during initial US. US surveillance was scheduled at 6, 12 and 24 mo. Measurement of the target lesion diameter was performed after the probe was adjusted to include the maximum diameter of a past US image at each visit. RVS was technically successful in 100% of patients. All target lesions were detected, including two iso-echoic lesions. The mean target lesion diameters at baseline and at 6, 12 and 24 mo were 8.2 ± 4.2, 8.4 ± 4.5, 8.1 ± 4.5 and 8.3 ± 5.0 mm, respectively (p = 0.785). Our results suggest that RVS is a reproducible, operator-independent technique for comparison of US images of BI-RADS category 3 mass lesions obtained at different time points.

3D defect segmentation on CT volume data using morphology and resample techniques.

Segmentation of CT volume data is important and useful in non-destructive testing and evaluating. To eliminate the artifacts influence, we propose a new approach of 3D defect segmentation using two steps. First of all, an initial segmentation using 3D morphological method is performed. The initial segmentation results include false defects. Secondly, resample in polar coordinates method is performed. The experimental results prove that our method is effective to correctly segment 3D defects and eliminate false segmentation. Some experiments on CT volume data with noise are made, the results show that our method is also useful.

A novel method for 3D crack edge extraction in CT volume data.

To reduce time cost and improve the performance of edge extraction in CT volume data which is often in large size, we propose a novel method of 3D crack edge extraction using two fusion steps, one is fusion on Finite Line Integral Transform (FLIT) values in spatial directions called SD-FLIT and another is fusion on Local Binary Pattern (LBP) values on spatial planes called SP-LBP. By analyzing the S function of LBP operator, we find that value "0" of this function can describe the change between two equivalence planes. However, this property is sensitive to point difference, thus SD-FLIT is introduced to smooth noises and artifacts before the application of SP-LBP to extract 3D edge on binary volume data. Besides, fusions on directions and planes are aimed at extracting enough spatial information. Experimental results show that, owing to the sufficiency of information extraction and the simplicity of computation, our method can get continuous, thin and occlusive 3D edge, including the crack tip. Furthermore, it can be used to complicate volume data. Compared with 3D wavelet and Facet model, our method cost less time, saving at least 89% of that.

3D Reconstruction of High-resolution Volume Data Based on Surface Points / 航天医学与医学工程

Objective: To develop a way of high-quality real-time three dimension surface reconstruction for high-resolution volume data.Method 3D surface point sets of single organ were using a method of binding the threshold and morphological operations.The normal vector of every surface point was calculated.According to the gray gradients of volume data,the triangle face was replaced by surface points to describe the organ surface,and the surface was displayed with OpenGL interface of display card after defining the color and transparent of the organ surface.Result Based on hardware platform of personal computer,the reconstruction of skeleton and skin for the digitized virtual Chinese man No.1(VCH-M1) from CT database was constructed,the rendering speed was faster than 25 F/s.Conclusion The algorithm is capable of realizing a real-time rendering for 512?512?1720 high resolution volume data.