Slice Volume Research Articles

Fourier feature network for 3D vessel reconstruction from biplane angiograms

3D reconstruction of biplane cerebral angiograms remains a challenging, unsolved research problem due to the loss of depth information and the unknown pixelwise correlation between input images. The occlusions arising from only two views complicate the reconstruction of fine vessel details and the simultaneous addressing of inherent missing information. In this paper, we take an incremental step toward solving this problem by reconstructing the corresponding 2D slice of the cerebral angiogram using biplane 1D image data. We developed a coordinate-based neural network that encodes the 1D image data along with a deterministic Fourier feature mapping from a given input point, resulting in a slice reconstruction that is more spatially accurate. Using only one 1D row of biplane image data, our Fourier feature network reconstructed the corresponding volume slices with a peak signal-to-noise ratio (PSNR) of 26.32 ± 0.36, a structural similarity index measure (SSIM) of 61.38 ± 1.79, a mean squared error (MSE) of 0.0023 ± 0.0002, and a mean absolute error (MAE) of 0.0364 ± 0.0029. Our research has implications for future work aimed at improving backprojection-based reconstruction by first examining individual slices from 1D information as a prerequisite.

A Novel Liver Tumor segmentation of Adverse Propagation Advanced Swin Transformer Network with Mask region-based convolutional neural networks

The diagnosis and treatment of liver diseases from computed tomography (CT) images is an indispensable task for segmentation of Liver & its tumours. Due to the uneven presence, fuzzy borders, diverse densities, shapes and sizes of lesions segmentation of liver & its tumour is a difficult task. At this point we mainly focused on deep learning algorithms for segmenting liver and its tumour from abdominal CT scan images thereafter minimising the time & energy used for a liver diseases diagnosis This study aims to classify and segment liver tumors using a novel deep learning-based model. A Mask region-based convolutional neural network (Mask R-CNN) model is proposed for multiorgan segmentation to aid esophageal radiation treatment. Due to the fact that organ boundaries may be fuzzy and organ shapes are various, original Mask R-CNN works well on natural image segmentation while leaves something to be desired on the multiorgan segmentation task. Addressing it, the advantages of this method are threefold: (1) a ROI (region of interest) generation method is presented in the RPN (region proposal network) which is able to utilize multiscale semantic features. (2) A prebackground classification subnetwork is integrated to the original mask generation branch to improve the precision of multiorgan segmentation. The segmented image is added to the Adverse Propagation Advanced Swin Transformer Network (APESTNet) to prevent overfitting. The proposed model is based on CT volume slices of patients with liver tumors and evaluated on the public 3D dataset IRCADB01.The proposed model dataset is split into training as 60% and testing as 40 % for classification. The proposed model's accuracy and recall are 99.23 % and 98.24 %, respectively.

Weakly-Supervised Detection of Bone Lesions in CT.

The skeletal region is one of the common sites of metastatic spread of cancer in the breast and prostate. CT is routinely used to measure the size of lesions in the bones. However, they can be difficult to spot due to the wide variations in their sizes, shapes, and appearances. Precise localization of such lesions would enable reliable tracking of interval changes (growth, shrinkage, or unchanged status). To that end, an automated technique to detect bone lesions is highly desirable. In this pilot work, we developed a pipeline to detect bone lesions (lytic, blastic, and mixed) in CT volumes via a proxy segmentation task. First, we used the bone lesions that were prospectively marked by radiologists in a few 2D slices of CT volumes and converted them into weak 3D segmentation masks. Then, we trained a 3D full-resolution nnUNet model using these weak 3D annotations to segment the lesions and thereby detected them. Our automated method detected bone lesions in CT with a precision of 96.7% and recall of 47.3% despite the use of incomplete and partial training data. To the best of our knowledge, we are the first to attempt the direct detection of bone lesions in CT via a proxy segmentation task.

3D Imaging of PEMFC Electrode Microstructure by Electron Tomography and 3D FIB/SEM

Scanning and transmission electron microscopies (SEM and TEM) are two imaging techniques widely used in the study of PEMFC electrode microstructure. They have played a significant role in the improvement of electrode components and the understanding of their main degradation mechanisms. However, the currently available description of the electrode microstructure does not allow yet to unambiguously identify the key microstructural factors that limit gas and proton transport within the electrode. These factors are crucial as they control the performance of the PEMFC, especially at high current density, and are therefore the subject of numerous studies, using either fine electrochemical measurements or modeling approaches.The objective of our work is to provide an improved description of the electrode microstructure by giving quantitative information on its porosity at different scales as well as on the ionomer distribution. For this purpose, we develop 3D characterization techniques applied to the PEMFC electrodes such as electron tomography and 3D FIB/SEM.The studied cathode electrode was prepared using TEC10E50E catalyst from Tanaka that is 50 wt % loading of Pt deposited on high-specific area carbon (HSAC), and Nafion D2020. The Pt loading of the electrode is 0.2 mgPtcm-2 and the ionomer/carbon ratio is 0.8.As a first step, electron tomography analyses were performed on the Pt/HSAC powder to determine the distribution of Pt nanoparticles (NPs) which can be located either on the carbon surface (outer NPs) or inside the carbon porosity (inner NPs)[1-3]. Our strategy is to record tilt image series by using two annular detectors: i) a high angle annular detector avoiding Pt NP diffraction contrast for the 3D image reconstruction of Pt NPs (without diffraction artifact) and ii) a lower angle annular detector that enhances carbon contrast for the 3D image reconstruction of the carbon phase. These two segmented images were then combined (Figure 1), allowing the calculation of the NP size histogram but also of the volume and the surface area of the two NP populations (inner and outer NPs).On the second step, the porosity of the electrode was analyzed by 3D FIB/SEM. A volume of around 10 X 10 x 5 μm3 was imaged with a cubic voxel size of 5 × 5 × 5 nm3. The solid phase (carbon, Pt NPs and ionomer) segmentation was based on a composite image created from two electron detectors (secondary and backscattered electrons) and using a machine learning software. Quantitative data such as the total porosity, the pore size distribution or the agglomerate size distribution of the solid phase were extracted from this volume. Figure 2a shows a 2D slice of this segmented volume where the solid phase is in black and the porosity in white.In order to analyze the electrode porosity with a higher spatial resolution, electron tomography experiment was also performed on a 150 nm thick slice of the electrode cut by ultramicrotomy after being embedded in an epoxy resin. The tilt image series were recorded with a pixel size of 0.5 nm and a field of view of 2 x 2 µm2. The 2D slice of the reconstructed volume (Figure 2b) shows that the largest solid agglomerates detected on the 3D FIB/SEM image can be identified as an agglomeration of numerous carbon particles. The challenge now is to quantify the porosity created between these carbon particles and to determine how many Pt NPs are located in these large agglomerates.Finally, the distribution of the ionomer was analyzed within the electrode similarly to [4]. For this analysis, a 150 nm slice of the electrode was cut by cryo-ultramicrotomy without embedding in epoxy resin as described in [5]. TEM images show that the ionomer is not homogeneously distributed on the surface of the entire carbon particles but is often observed in the concave surface created between the carbon particles (Figure 3). These observations suggest a ionomer distribution in agreement with the heterogeneous ionomer coating model proposed by Inoue et al. [6]. We also suggest that a part of the ionomer could be localized in the small pores located inside the large carbon agglomerates described in the previous paragraph. This could explain why the ionomer is so difficult to detect on TEM images. This work has been done in the frame of the FURTHER-FC project. This project has received funding from the Fuel Cells and Hydrogen 2 Joint Undertaking (now Clean Hydrogen Partnership) under Grant Agreement No 875025. This Joint Undertaking receives support from the European Union’s Horizon 2020 Research and Innovation program, Hydrogen Europe and Hydrogen Europe Research. Figure 1

VASCO: Volume and Surface Co-Decomposition for Hybrid Manufacturing

Additive and subtractive hybrid manufacturing (ASHM) involves the alternating use of additive and subtractive manufacturing techniques, which provides unique advantages for fabricating complex geometries with otherwise inaccessible surfaces. However, a significant challenge lies in ensuring tool accessibility during both fabrication procedures, as the object shape may change dramatically, and different parts of the shape are interdependent. In this study, we propose a computational framework to optimize the planning of additive and subtractive sequences while ensuring tool accessibility. Our goal is to minimize the switching between additive and subtractive processes to achieve efficient fabrication while maintaining product quality. We approach the problem by formulating it as a Volume-And-Surface-CO-decomposition (VASCO) problem. First, we slice volumes into slabs and build a dynamic-directed graph to encode manufacturing constraints, with each node representing a slab and direction reflecting operation order. We introduce a novel geometry property called hybrid-fabricability for a pair of additive and subtractive procedures. Then, we propose a beam-guided top-down block decomposition algorithm to solve the VASCO problem. We apply our solution to a 5-axis hybrid manufacturing platform and evaluate various 3D shapes. Finally, we assess the performance of our approach through both physical and simulated manufacturing evaluations.

Synthetic 3D Spinal Vertebrae Reconstruction from Biplanar X-rays Utilizing Generative Adversarial Networks.

Computed tomography (CT) offers detailed insights into the internal anatomy of patients, particularly for spinal vertebrae examination. However, CT scans are associated with higher radiation exposure and cost compared to conventional X-ray imaging. In this study, we applied a Generative Adversarial Network (GAN) framework to reconstruct 3D spinal vertebrae structures from synthetic biplanar X-ray images, specifically focusing on anterior and lateral views. The synthetic X-ray images were generated using the DRRGenerator module in 3D Slicer by incorporating segmentations of spinal vertebrae in CT scans for the region of interest. This approach leverages a novel feature fusion technique based on X2CT-GAN to combine information from both views and employs a combination of mean squared error (MSE) loss and adversarial loss to train the generator, resulting in high-quality synthetic 3D spinal vertebrae CTs. A total of n = 440 CT data were processed. We evaluated the performance of our model using multiple metrics, including mean absolute error (MAE) (for each slice of the 3D volume (MAE0) and for the entire 3D volume (MAE)), cosine similarity, peak signal-to-noise ratio (PSNR), 3D peak signal-to-noise ratio (PSNR-3D), and structural similarity index (SSIM). The average PSNR was 28.394 dB, PSNR-3D was 27.432, SSIM was 0.468, cosine similarity was 0.484, MAE0 was 0.034, and MAE was 85.359. The results demonstrated the effectiveness of this approach in reconstructing 3D spinal vertebrae structures from biplanar X-rays, although some limitations in accurately capturing the fine bone structures and maintaining the precise morphology of the vertebrae were present. This technique has the potential to enhance the diagnostic capabilities of low-cost X-ray machines while reducing radiation exposure and cost associated with CT scans, paving the way for future applications in spinal imaging and diagnosis.

CAT-Seg: cascaded medical assistive tool integrating residual attention mechanisms and Squeeze-Net for 3D MRI biventricular segmentation

Cardiac image segmentation is a critical step in the early detection of cardiovascular disease. The segmentation of the biventricular is a prerequisite for evaluating cardiac function in cardiac magnetic resonance imaging (CMRI). In this paper, a cascaded model CAT-Seg is proposed for segmentation of 3D-CMRI volumes. CAT-Seg addresses the problem of biventricular confusion with other regions and localized the region of interest (ROI) to reduce the scope of processing. A modified DeepLabv3+ variant integrating SqueezeNet (SqueezeDeepLabv3+) is proposed as a part of CAT-Seg. SqueezeDeepLabv3+ handles the different shapes of the biventricular through the different cardiac phases, as the biventricular only accounts for small portion of the volume slices. Also, CAT-Seg presents a segmentation approach that integrates attention mechanisms into 3D Residual UNet architecture (3D-ResUNet) called 3D-ARU to improve the segmentation results of the three major structures (left ventricle (LV), Myocardium (Myo), and right ventricle (RV)). The integration of the spatial attention mechanism into ResUNet handles the fuzzy edges of the three structures. The proposed model achieves promising results in training and testing with the Automatic Cardiac Diagnosis Challenge (ACDC 2017) dataset and the external validation using MyoPs. CAT-Seg demonstrates competitive performance with state-of-the-art models. On ACDC 2017, CAT-Seg is able to segment LV, Myo, and RV with an average minimum dice symmetry coefficient (DSC) performance gap of 1.165%, 4.36%, and 3.115% respectively. The average maximum improvement in terms of DSC in segmenting LV, Myo and RV is 4.395%, 6.84% and 7.315% respectively. On MyoPs external validation, CAT-Seg outperformed the state-of-the-art in segmenting LV, Myo, and RV with an average minimum performance gap of 6.13%, 5.44%, and 2.912% respectively.

Breast density analysis of digital breast tomosynthesis

Mammography shifted to digital breast tomosynthesis (DBT) in the US. An automated percentage of breast density (PD) technique designed for two-dimensional (2D) applications was evaluated with DBT using several breast cancer risk prediction measures: normalized-volumetric; dense volume; applied to the volume slices and averaged (slice-mean); and applied to synthetic 2D images. Volumetric measures were derived theoretically. PD was modeled as a function of compressed breast thickness (CBT). The mean and standard deviation of the pixel values were investigated. A matched case–control (CC) study (n = 426 pairs) was evaluated. Odd ratios (ORs) were estimated with 95% confidence intervals. ORs were significant for PD: identical for volumetric and slice-mean measures [OR = 1.43 (1.18, 1.72)] and [OR = 1.44 (1.18, 1.75)] for synthetic images. A 2nd degree polynomial (concave-down) was used to model PD as a function of CBT: location of the maximum PD value was similar across CCs, occurring at 0.41 × CBT, and PD was significant [OR = 1.47 (1.21, 1.78)]. The means from the volume and synthetic images were also significant [ORs ~ 1.31 (1.09, 1.57)]. An alternative standardized 2D synthetic image was constructed, where each pixel value represents the percentage of breast density above its location. Several measures were significant and an alternative method for constructing a standardized 2D synthetic image was produced.

Evaluation of Image Quality for High Heart Rates for Coronary Computed Tomographic Angiography with Advancement in CT Technology: The CONVERGE Registry.

This study aims to evaluate image quality in patients with heart rates above or equal to 70 beats per minute (bpm), performed on a 16 cm scanner (256-slice General Electric Revolution) in comparison to a CT scanner with only 4 cm of coverage (64 slice Volume CT). Recent advancements in image acquisition, such as whole-heart coverage in a single rotation and post-processing methods in coronary computed tomographic angiography (CCTA), include motion-correction algorithms, such as SnapShot Freeze (SSF), which improve temporal resolution and allow for the assessment of coronary artery disease (CAD) with lower motion scores and better image qualities. Studies from the comprehensive evaluation of high temporal- and spatial-resolution cardiac CT using a wide coverage system (CONVERGE) registry (a multicenter registry at four centers) have shown the 16 cm CT scanner having a better image quality in comparison to the 4 cm scanner. However, these studies failed to include patients with undesirable or high heart rates due to well-documented poor image acquisition on prior generations of CCTA scanners. A prospective, observational, multicenter cohort study comparing image quality, quantitively and qualitatively, on scans performed on a 16 cm CCTA in comparison to a cohort of images captured on a 4 cm CCTA at four centers. Participants were recruited based on broad inclusion criteria, and each patient in the 16 cm CCTA arm of the study received a CCTA scan using a 256-slice, whole-heart, single-beat scanner. These patients were then matched by age, gender, and heart rate to patients who underwent CCTA scans on a 4 cm CT scanner. Image quality was graded based on the signal-to-noise ratio, contrast-to-noise ratio, and on a Likert scale of 0-4: 0, very poor-4, excellent. 104 patients were evaluated for this study. The mean heart rate was 75 ± 7 in the 4 cm scanner and 75 ± 7 in the 16 cm one (p = 0.426). The signal-to-noise and contrast-to-noise ratios were higher in the 16 cm scanner (p = 0.0001). In addition, more scans were evaluated as having an excellent quality on the 16 cm scanner than on the 4 cm scanner (p < 0.0001) based on a 4-point Likert scale. The 16 cm scanner has a superior image quality for fast heart rates compared to the 4 cm scanner. This study shows that there is a significantly higher frequency of excellent and good studies showing better contrast-to-noise and signal-to-noise ratios with the 16 cm scanner compared to the 4 cm scanner.

Efficient Brain Age Prediction from 3D MRI Volumes Using 2D Projections.

Using 3D CNNs on high-resolution medical volumes is very computationally demanding, especially for large datasets like UK Biobank, which aims to scan 100,000 subjects. Here, we demonstrate that using 2D CNNs on a few 2D projections (representing mean and standard deviation across axial, sagittal and coronal slices) of 3D volumes leads to reasonable test accuracy (mean absolute error of about 3.5 years) when predicting age from brain volumes. Using our approach, one training epoch with 20,324 subjects takes 20-50 s using a single GPU, which is two orders of magnitude faster than a small 3D CNN. This speedup is explained by the fact that 3D brain volumes contain a lot of redundant information, which can be efficiently compressed using 2D projections. These results are important for researchers who do not have access to expensive GPU hardware for 3D CNNs.

An integrated network based on 2D/3D feature correlations for benign-malignant tumor classification and uncertainty estimation in digital breast tomosynthesis

Objective. Classification of benign and malignant tumors is important for the early diagnosis of breast cancer. Over the last decade, digital breast tomosynthesis (DBT) has gradually become an effective imaging modality for breast cancer diagnosis due to its ability to generate three-dimensional (3D) visualizations. However, computer-aided diagnosis (CAD) systems based on 3D images require high computational costs and time. Furthermore, there is considerable redundant information in 3D images. Most CAD systems are designed based on 2D images, which may lose the spatial depth information of tumors. In this study, we propose a 2D/3D integrated network for the diagnosis of benign and malignant breast tumors. Approach. We introduce a correlation strategy to describe feature correlations between slices in 3D volumes, corresponding to the tissue relationship and spatial depth features of tumors. The correlation strategy can be used to extract spatial features with little computational cost. In the prediction stage, 3D spatial correlation features and 2D features are both used for classification. Main results. Experimental results demonstrate that our proposed framework achieves higher accuracy and reliability than pure 2D or 3D models. Our framework has a high area under the curve of 0.88 and accuracy of 0.82. The parameter size of the feature extractor in our framework is only 35% of that of the 3D models. In reliability evaluations, our proposed model is more reliable than pure 2D or 3D models because of its effective and nonredundant features. Significance. This study successfully combines 3D spatial correlation features and 2D features for the diagnosis of benign and malignant breast tumors in DBT. In addition to high accuracy and low computational cost, our model is more reliable and can output uncertainty value. From this point of view, the proposed method has the potential to be applied in clinic.

SUVR quantification using attention-based 3D CNN with longitudinal Florbetapir PET images in Alzheimer’s disease

PurposeFlorbetapir PET images provide valuable information about the amount of amyloid deposition in the brain due to neurodegenerative diseases, which helps in the prognosis of patients. The purpose of this study is to develop a system that helps in the automatic amyloid quantification of the standard uptake value ratio so that drug treatments could be effectively determined. Methods2647 Florbetapir PET images obtained from multiple centres of Alzheimer Disease Neuroimaging Initiative (ADNI) and an external dataset of 1413 scans from the Anti-Amyloid Treatment in Asymptomatic Alzheimer’s study are used to design and test the proposed 3D CNN attention-based model to quantify the amyloid deposits. Only 80% of scans from the ADNI dataset are used to train the model. The remaining 20% of scans from ADNI and the external dataset are used for testing the trained model. ResultsThe proposed model achieves a root mean square error of 0.0362 and a mean absolute error of 0.026 on separate hold-out test data from ADNI and a root mean square error of 0.058 and a mean absolute error of 0.044 Anti-Amyloid Treatment in Asymptomatic Alzheimer’s study dataset. A graphical user interface is developed for the proposed model which will display a slice of the Florbetapir PET volume and its predicted standard uptake value ratio. Conclusion3D CNN architecture with both spatial and channel attention provided better results when compared to models without attention. The proposed model proves to be an efficient tool in the automatic amyloid standard uptake value ratio quantification.

Generation of synthetic intermediate slices in 3D OCT cubes for improving pathology detection and monitoring

OCT is a non-invasive imaging technique commonly used to obtain 3D volumes of the ocular structure. These volumes allow the monitoring of ocular and systemic diseases through the observation of subtle changes in the different structures present in the eye. In order to observe these changes it is essential that the OCT volumes have a high resolution in all axes, but unfortunately there is an inverse relationship between the quality of the OCT images and the number of slices of the cube. This results in routine clinical examinations using cubes that generally contain high-resolution images with few slices. This lack of slices complicates the monitoring of changes in the retina hindering the diagnostic process and reducing the effectiveness of 3D visualizations. Therefore, increasing the cross-sectional resolution of OCT cubes would improve the visualization of these changes aiding the clinician in the diagnostic process. In this work we present a novel fully automatic methodology to perform the synthesis of intermediate slices of OCT image volumes in an unsupervised manner. To perform this synthesis, we propose a fully convolutional neural network architecture that uses information from two adjacent slices to generate the intermediate synthetic slice. We also propose a training methodology, where we use three adjacent slices to train the network by contrastive learning and image reconstruction. We test our methodology with three different types of OCT volumes commonly used in the clinical setting and validate the quality of the synthetic slices created with several medical experts and using an expert system.

Complexity equals anything II

We expand on our results in [1] to present a broad new class of gravitational observables in asymptotically Anti-de Sitter space living on general codimension-zero regions of the bulk spacetime. By taking distinct limits, these observables can reduce to well-studied holographic complexity proposals, e.g., the volume of the maximal slice and the action or spacetime volume of the Wheeler-DeWitt patch. As with the codimension-one family found in [1], these new observables display two key universal features for the thermofield double state: they grow linearly in time at late times and reproduce the switchback effect. Hence we argue that any member of this new class of observables is an equally viable candidate as a gravitational dual of complexity. Moreover, using the Peierls construction, we show that variations of the codimension-zero and codimension-one observables are encoded in the gravitational symplectic form on the semi-classical phase-space, which can then be mapped to the CFT.

An unsupervised deep learning-based image translation method for retrospective motion correction of high resolution kidney MRI

A primary challenge for in vivo kidney magnetic resonance imaging (MRI) is the presence of different types of involuntary physiological motion, affecting the diagnostic utility of acquired images due to severe motion artifacts. Existing prospective and retrospective motion correction methods remain ineffective when dealing with complex large amplitude nonrigid motion artifacts. Here, we introduce an unsupervised deep learning-based image to image translation method between motion-affected and motion-free image domains, for correction of rigid-body, respiratory and nonrigid motion artifacts in vivo kidney MRI.High resolution (i.e., 156 × 156 × 370 μm) ex vivo 3 Tesla MRI scans of 13 porcine kidneys (because of their anatomical homology to human kidney) were conducted using a 3D T2-weighted turbo spin echo sequence. Rigid-body, respiratory and nonrigid motion-affected images were then simulated using the magnitude-only ex vivo motion-free image set. Each 2D coronal slice of motion-affected and motion-free image volume was then divided into patches of 128 × 128 for training the model. We proposed to add normalised cross-correlation loss to cycle consistency generative adversarial network structure (NCC-CycleGAN), to enforce edge alignment between motion-corrected and motion-free image domains.Our NCC-CycleGAN motion correction model demonstrated high performance with an in-tissue structural similarity index measure of 0.77 ± 0.08, peak signal-to-noise ratio of 26.67 ± 3.44 and learned perceptual image patch similarity of 0.173 ± 0.05 between the reconstructed motion-corrected and ground truth motion-free images. This corresponds to a significant respective average improvement of 34%, 23% and 39% (p < 0.05; paired t-test) for the three metrics to correct the three different types of simulated motion artifacts.We demonstrated the feasibility of developing an unsupervised deep learning-based method for efficient automated retrospective kidney MRI motion correction, while preserving microscopic tissue structures in high resolution imaging.

A New Approach for Estimation of Physical Properties of Irregular Shape Fruit

Dimensions, volume, and mass of agricultural goods are essential physical features to build sizing, grading, and packaging systems. Manual property measurements are time-consuming, costly, and labor-intensive due to traditional technologies while various devices need to be installed to adapt process requirements. Furthermore, it is very challenging to accurately measure product with irregular or specific shapes, such as starfruit (Averrhoa carambola). Recently, there have been several research results on estimating features of the irregularly shaped object, they are either get inaccurate results or need repeated captures, computational resources, and time to rebuild the three-dimensional representation of the goods. The starfruit has not been studied completely in this size and weight measurements. This paper focuses on new techniques which exhibit simple installation to generate multiple functions for estimating the dimensions, volume, and mass with high accuracy. In this proposed method, we separated the process into two main phases. In the first phase, a camera is used to capture a top-view image of a starfruit, then image processing and machine vision techniques are applied to process the acquisition image before the process slices numerically the starfruit into several pieces along the longitudinal axis and estimates the physical attributes of each pieces using disc method and conical frustum method. Its volume is the summation of the volume of each partial slice. In the next phase, the density is used to estimate the mass of starfruit since the correlation coefficient (R-squared) between the volume and mass of starfruit is nearly linear with 0.9205. The validated results are highly competitive with accuracy of about 99% for the volume and mass in 300 testing samples.

A Deep Learning Approach for Liver and Tumor Segmentation in CT Images Using ResUNet.

According to the most recent estimates from global cancer statistics for 2020, liver cancer is the ninth most common cancer in women. Segmenting the liver is difficult, and segmenting the tumor from the liver adds some difficulty. After a sample of liver tissue is taken, imaging tests, such as magnetic resonance imaging (MRI), computer tomography (CT), and ultrasound (US), are used to segment the liver and liver tumor. Due to overlapping intensity and variability in the position and shape of soft tissues, segmentation of the liver and tumor from computed abdominal tomography images based on shade gray or shapes is undesirable. This study proposed a more efficient method for segmenting liver and tumors from CT image volumes using a hybrid ResUNet model, combining the ResNet and UNet models to address this gap. The two overlapping models were primarily used in this study to segment the liver and for region of interest (ROI) assessment. Segmentation of the liver is done to examine the liver with an abdominal CT image volume. The proposed model is based on CT volume slices of patients with liver tumors and evaluated on the public 3D dataset IRCADB01. Based on the experimental analysis, the true value accuracy for liver segmentation was found to be approximately 99.55%, 97.85%, and 98.16%. The authentication rate of the dice coefficient also increased, indicating that the experiment went well and that the model is ready to use for the detection of liver tumors.

Puffing characteristics of berry slice under continuous microwave puffing conditions

To elucidate the puffing characteristics of the berry slice under continuous microwave conditions, heat and mass transfer and deformation of slices were investigated based on the models of coupled multi-physics fields involving electromagnetic heating, heat and mass transfer and solid mechanics. The results indicated that transmission mode of microwaves in a microwave cavity determined the electric field distribution inside slices with interior focusing phenomenon described by higher temperature and lower moisture content at the central region of slices than that of edge. The berry slice volume showed a “invisible-rapid-maintained” deformation under the synergistic effects of temperature, moisture and internal pressure with sample movement. This study may provide guidance for the elucidation of microwave puffing process of the moving slice and the underlying applications such as technology optimization and quality control of slices like berry. Novelty impact statement This work investigates the puffing characteristics of the moving berry slices under a continuous microwave dryer, and elucidates the heat and mass transfer and deformation process of berry slices by means of experiment and simulation. The distribution of alternating electric field profiles with high and low levels determine the absorption of microwave energy, heat and mass transfer in berry slices to induce the volume deformation and uneven distribution. The volume of berry slices laid on moving conveyor belt under continuous microwave puffing undergoes three deformation trends as invisible change followed by rapid expansion till desired shape.

Research on Gas Extraction and Cut Flow Technology for Lower Slice Pressure Relief Gas under Slice Mining of Extra-thick Coal Seam.

For extra-thick coal seams, slice mining is a safer mining method than top coal mining, which can effectively reduce the strong mine pressure behavior caused by mining. However, in the slice mining of high-gas and extra-thick coal seams, the gas in the lower slice flows into the goaf, which increases the gas control difficulty on the upper slice working face. It is easy to cause the gas transfinite at the upper corner in the upper slice and reduce the mining efficiency. Therefore, it is of a great significance to carry out the research on gas control technology in slice mining of the extra-thick coal seam. There are some problems in the gas control of slice mining, such as a single gas control method, low control efficiency, and unclear gas migration law. Therefore, it is necessary to study the gas migration law and propose a targeted prevention and control the technical scheme. In order to improve the gas control efficiency of the extra-thick coal seam, the evolution law of permeability of the lower slice is obtained under mining through experimental research. The liquid–solid coupling seepage-flow model for gas migration is established in the lower slice. Comsol Multiphysics software is used to study the migration law of pressure relief gas in the lower slice. Based on the gas migration law, the gas extraction and cut flow technology for the lower slice long borehole is proposed. Through this technology, the amount of gas flowing into the upper slice goaf and the gas content of the lower slice are reduced, and the drilling horizon is optimized. The research results show that the determination of the optimal drilling horizon of the lower slice needs to balance the amount of gas flowing into the goaf and the total amount of gas extraction. The range of 3–7 m horizon in the lower slice is appropriate to the boreholes arranged. When the borehole is located in the lower slice −3 m horizon, the 360 day gas emission quantity of goaf can be reduced to 51.2% of the nondrilled emission quantity, and the total extraction amount is 1143 m3. When the borehole is located in the lower slice −7 m horizon, the 360 day gas emission quantity of goaf can be reduced to 95.31% of the nondrilled emission quantity, and the total extraction amount is 1461 m3. Considering the gas emission capacity of the upper slice and ensuring that the total extraction volume of the lower slice is maximized and the boreholes in the lower slice are not damaged, the boreholes are located in the −6 m horizon of the lower slice.

Sinogram interpretability based CT artefact reduction for multi-material workpieces

ABSTRACT Computed tomography (CT) is a technology for the simultaneous inspection of internal and external features of workpieces. However, beam hardening and scattered radiation artefacts caused by the different material densities and atomic numbers commonly confound CT measurements of multi-material workpieces. Multispectral CT (MSP CT) measurements reduce artefacts by combining multiple CT volumes performed with different x-ray spectra. However, all known simulation-based CT parameter optimisation approaches for industrial applications consider only the single-spectrum case. This paper investigates the CT radon space, focusing on sinogram interpretability. Multispectral CT x-ray spectra can be determined by defining and analysing sinogram areas corresponding to equivalent volume slice artefacts. Validation indicates that the two MSP CT spectra recommended via a proposed CT simulation considering critical sinogram areas cause an artefact reduction. Results are quantified by a standard deviation reduction of measured geometrical features.