Image Intensity Distribution Research Articles

Laser absorption correction for hydroxyl planar laser induced fluorescence measurements in a centrally staged combustor at elevated pressures

Planar laser-induced fluorescence (PLIF) is a crucial spectroscopic technique for measuring minor species [e.g., hydroxyl (OH), methylene (CH), and nitric oxide (NO) radicals] in combustion research, owing to its non-intrusive nature and high sensitivity. However, laser energy attenuation due to absorption poses significant challenges to its application under high-pressure conditions, which may cause asymmetric image intensity distribution along the light propagation direction. An absorption correction method for OH PLIF based on the concept of maximum number density is proposed in the present study. This method offers several key advantages, including simplicity, high accuracy, and versatility, allowing for correcting both time-averaged and instantaneous OH PLIF images. OH PLIF data obtained from a centrally staged combustor at elevated pressures (i.e., 0.3, 0.6, and 1.0 MPa) are utilized to validate the method. Correction for the time-averaged PLIF images achieves a much more symmetric distribution of OH, revealing the overall flame structures that would not have been completely visualized from the original images. The fronts of the pilot and main stage flames have also been recovered from the corrected instantaneous images. This correction algorithm provides an effective way of enhancing data quality for high-cost OH PLIF measurements at pressurized conditions.

EpidermaQuant: Unsupervised Detection and Quantification of Epidermal Differentiation Markers on H-DAB-Stained Images of Reconstructed Human Epidermis.

The integrity of the reconstructed human epidermis generated in vitro can be assessed using histological analyses combined with immunohistochemical staining of keratinocyte differentiation markers. Technical differences during the preparation and capture of stained images may influence the outcome of computational methods. Due to the specific nature of the analyzed material, no annotated datasets or dedicated methods are publicly available. Using a dataset with 598 unannotated images showing cross-sections of in vitro reconstructed human epidermis stained with DAB-based immunohistochemistry reaction to visualize four different keratinocyte differentiation marker proteins (filaggrin, keratin 10, Ki67, HSPA2) and counterstained with hematoxylin, we developed an unsupervised method for the detection and quantification of immunohistochemical staining. The pipeline consists of the following steps: (i) color normalization; (ii) color deconvolution; (iii) morphological operations; (iv) automatic image rotation; and (v) clustering. The most effective combination of methods includes (i) Reinhard's normalization; (ii) Ruifrok and Johnston color-deconvolution method; (iii) proposed image-rotation method based on boundary distribution of image intensity; and (iv) k-means clustering. The results of the work should enhance the performance of quantitative analyses of protein markers in reconstructed human epidermis samples and enable the comparison of their spatial distribution between different experimental conditions.

Characterizing the internal wave wakes and synthetic aperture radar image features of underwater moving objects

In this study, a refined and improved theoretical model was proposed for calculating the synthetic aperture radar (SAR) images of internal wave wakes. This model was based on an equivalent source model of internal wave wakes and the velocity-bunching principle. Wake field, scattering field, and SAR image characteristics were systematically calculated for multiple scenarios. The model described the transfer and solution processes by inputting the background flow field temperature and salinity profiles to map the radar image intensity distribution. The physical mechanisms of the internal wave wake generation and its capture by SAR were comprehensively explained. The effects of various parameters on the internal wave wake SAR images were analyzed comprehensively. The SAR image features containing internal wave wakes were determined based on the gray-level co-occurrence matrix and image power spectrum, which revealed that the maximum surface current induced by the internal wave modes of the same amplitude was considerably larger than that induced by surface-wave mode. When traveling far from the water surface, the rate of change in the total scattering coefficient because of the Bragg effect was approximately 20 times that of the slope effect. In SAR images, the recognizability of wakes depends primarily on the maximum intensity rather than the average disturbance on the sea surface. Therefore, SAR images exhibit considerable differences during downwind radar observations, with the most prominent contrast differences occurring at the maximum spreading angle of wake scattering and 1500 m behind underwater objects. In the image power spectrum, the frequency range of the first modal internal waves was approximately 10–30 Hz, whereas the higher-order modal internal waves had frequencies lower than 10 Hz. Furthermore, the frequency range of the surface-wave mode was larger than that of internal-wave modes, approximately 50–60 Hz.

FractalRG: Advanced fractal region growing using Gaussian mixture models for left atrium segmentation

This paper presents an advanced region growing method for precise left atrium (LA) segmentation and estimation of atrial wall thickness in CT/MRI scans. The method leverages a Gaussian mixture model (GMM) and fractal dimension (FD) analysis in a three-step procedure to enhance segmentation accuracy. The first step employs GMM for seed initialization based on the probability distribution of image intensities. The second step utilizes fractal-based texture analysis to capture image self-similarity and texture complexity. An enhanced approach for generating 3D fractal maps is proposed, providing valuable texture information for region growing. In the last step, fractal-guided 3D region growing is applied for segmentation. This process expands seed points iteratively by adding neighboring voxels meeting specific similarity criteria. GMM estimations and fractal maps are used to restrict the region growing process, reducing the search space for global segmentation and enhancing computational efficiency. Experiments on a dataset of 10 CT scans with 3,947 images resulted in a Dice score of 0.85, demonstrating superiority over traditional techniques. In a dataset of 30 MRI scans with 3,600 images, the proposed method achieved a competitive Dice score of 0.89±0.02, comparable to Deep Learning-based models. These results highlight the effectiveness of our approach in accurately delineating the LA region across diverse imaging modalities.

Towards Enhancing Automated Defect Recognition (ADR) in Digital X-ray Radiography Applications: Synthesizing Training Data through X-ray Intensity Distribution Modeling for Deep Learning Algorithms

Industrial radiography is a pivotal non-destructive testing (NDT) method that ensures quality and safety in a wide range of industrial sectors. Conventional human-based approaches, however, are prone to challenges in defect detection accuracy and efficiency, primarily due to the high inspection demand from manufacturing industries with high production throughput. To solve this challenge, numerous computer-based alternatives have been developed, including Automated Defect Recognition (ADR) using deep learning algorithms. At the core of training, these algorithms demand large volumes of data that should be representative of real-world cases. However, the availability of digital X-ray radiography data for open research is limited by non-disclosure contractual terms in the industry. This study presents a pipeline that is capable of modeling synthetic images based on statistical information acquired from X-ray intensity distribution from real digital X-ray radiography images. Through meticulous analysis of the intensity distribution in digital X-ray images, the unique statistical patterns associated with the exposure conditions used during image acquisition, type of component, thickness variations, beam divergence, anode heel effect, etc., are extracted. The realized synthetic images were utilized to train deep learning models, yielding an impressive model performance with a mean intersection over union (IoU) of 0.93 and a mean dice coefficient of 0.96 on real unseen digital X-ray radiography images. This methodology is scalable and adaptable, making it suitable for diverse industrial applications.

A three-dimensional deep learning model for inter-site harmonization of structural MR images of the brain: Extensive validation with a multicenter dataset

In multicenter MRI studies, pooling the imaging data can introduce site-related variabilities and can therefore bias the subsequent analyses. To harmonize the intensity distributions of brain MR images in a multicenter dataset, unsupervised deep learning methods can be employed. Here, we developed a model based on cycle-consistent adversarial networks for the harmonization of T1-weighted brain MR images. In contrast to previous works, it was designed to process three-dimensional whole-brain images in a stable manner while optimizing computation resources. Using six different MRI datasets for healthy adults (n=1525 in total) with different acquisition parameters, we tested the model in (i) three pairwise harmonizations with site effects of various sizes, (ii) an overall harmonization of the six datasets with different age distributions, and (iii) a traveling-subject dataset. Our results for intensity distributions, brain volumes, image quality metrics and radiomic features indicated that the MRI characteristics at the various sites had been effectively homogenized. Next, brain age prediction experiments and the observed correlation between the gray-matter volume and age showed that thanks to an appropriate training strategy and despite biological differences between the dataset populations, the model reinforced biological patterns. Furthermore, radiologic analyses of the harmonized images attested to the conservation of the radiologic information in the original images. The robustness of the harmonization model (as judged with various datasets and metrics) demonstrates its potential for application in retrospective multicenter studies.

Immune Marker Spatial Distribution and Clinical Outcome after PD-1 Blockade in Mismatch Repair-deficient, Advanced Colorectal Carcinomas.

Targeting the programmed cell death protein 1 (PD-1)/programmed cell death ligand 1 (PD-L1) interaction has led to durable responses in fewer than half of patients with mismatch repair-deficient (MMR-d) advanced colorectal cancers. Immune contexture, including spatial distribution of immune cells in the tumor microenvironment (TME), may predict immunotherapy outcome. Immune contexture and spatial distribution, including cell-to-cell distance measurements, were analyzed by multiplex immunofluorescence (mIF) in primary colorectal cancers with d-MMR (N = 33) from patients treated with anti-PD-1 antibodies. By digital image analysis, density, ratio, intensity, and spatial distribution of PD-L1, PD-1, CD8, CD3, CD68, LAG3, TGFβR2, MHC-I, CD14, B2M, and pan-cytokeratin were computed. Feature selection was performed by regularized Cox regression with LASSO, and a proportional hazards model was fitted to predict progression-free survival (PFS). For predicting survival among patients with MMR-d advanced colorectal cancer receiving PD-1 blockade, cell-to-cell distance measurements, but not cell densities or ratios, achieved statistical significance univariately. By multivariable feature selection, only mean number of PD-1+ cells within 10 μm of a PD-L1+ cell was significantly predictive of PFS. Dichotomization of this variable revealed that those with high versus low values had significantly prolonged PFS [median not reached (>83 months) vs. 8.5 months (95% confidence interval (95% CI), 4.7-NR)] with a median PFS of 28.4 months for all patients [adjusted HR (HRadj) = 0.14; 95% CI, 0.04-0.56; P = 0.005]. Expression of PD-1 was observed on CD8+ T cells; PD-L1 on CD3+ and CD8+ T lymphocytes, macrophages (CD68+), and tumor cells. In d-MMR colorectal cancers, PD-1+ to PD-L1+ receptor to ligand proximity is a potential predictive biomarker for the effectiveness of PD-1 blockade.

A novel intrarenal multimodal 2D/3D registration algorithm and preliminary phantom study.

Retrograde intrarenal surgery (RIRS) is a widely utilized diagnostic and therapeutic tool for multiple upper urinary tract pathologies. The image-guided navigation system can assist the surgeon to perform precise surgery by providing the relative position between the lesion and the instrument after the intraoperative image is registered with the preoperative model. However, due to the structural complexity and diversity of multi-branched organs such as kidneys, bronchi, etc., the consistency of the intensity distribution of virtual and real images will be challenged, which makes the classical pure intensity registration method prone to bias and random results in a wide search domain. In this paper, we propose a structural feature similarity-based method combined with a semantic style transfer network, which significantly improves the registration accuracy when the initial state deviation is obvious. Furthermore, multi-view constraints are introduced to compensate for the collapse of spatial depth information and improve the robustness of the algorithm. Experimental studies were conducted on two models generated from patient data to evaluate the performance of the method and competing algorithms. The proposed method obtains mean target error (mTRE) of 0.971±0.585mm and 1.266±0.416mm respectively, with better accuracy and robustness overall. Experimental results demonstrate that the proposed method has the potential to be applied to RIRS and extended to other organs with similar structures.

Scintillation Characteristics of Gaussian Vortex Beam Propagation in Turbulent Flume

Aiming at the low sensitivity of weak turbulent wake detection of underwater vehicles, studied the laser propagation characteristics in underwater weak turbulence, and then proposed a method based on the statistical characteristics of the scintillation peak of Gaussian vortex beam for detecting the weak turbulence fluctuation. According to the refractive index power spectrum of turbulent flume, the intensity distribution images of Gaussian vortex beam propagating through turbulent flume are simulated by using the random phase screen method, and the scintillation characteristics of Gaussian vortex beam under different conditions are studied. For the simulation results, under the weak turbulence conditions with low refractive index structure coefficient, the average scintillation indexes near the peak value of spot scintillation indexes are obviously higher than those of the whole image. Under the condition that the temperature difference between hot plate and cold plate, between hot plate and water are about 6.4°C and 5.8°C, respectively, the scintillation indexes of the laser propagation intensity image under different temperature gradient (turbulence intensity) are calculated in the experiment. The results show that, the mean values of the scintillation indexes near the spot scintillation peak fluctuate around 1.02 and 1.07, and the mean values in whole image fluctuate around 0.58 and 0.68, respectively, when the temperature gradient is small, which verify the effectiveness of the statistical characteristics of the scintillation peak in detecting weak turbulence.

Rayleigh-based segmentation of ISAR images.

Inverse synthetic aperture radar (ISAR) provides a solution to increase the radar angular resolution by observing a moving target over time. The high-resolution ISAR image should undergo a segmentation step to get the target's point cloud data, which is then used for classification purposes. Existing segmentation algorithms seek an optimal threshold in an iterative manner, which adds to the complexity of ISAR and results in an increase in the processing time. In this paper, we take advantage of the distribution of the ISAR image intensity, which is based on the Rayleigh distribution, and obtain an explicit relationship for the optimal segmentation threshold. The proposed segmentation algorithm alleviates the requirement for iterative optimization and its efficiency is shown using both simulated and experimental ISAR images.

Application of polarization imaging in counting plywood layers by machine vision

This paper introduces a machine vision system based on polarization imaging, which is applicable for automatically counting the number of internal layers in plywood. Industrial machine vision usually suffers from a low accuracy due to low contrast and high complexity of the images, which could be overcome by the introduction of polarization imaging. A polarization camera was utilized to capture images with polarization angles of 0°, 45°, 90°, and 135°, and then a degree of polarization (DOP) distribution image was obtained by calculating the DOP for each pixel. Compared with the intensity distribution image, the contrast of the DOP distribution image was increased by about 60% and the excessive information in the image including wood’s natural texture, dirty spots, dicing marks, and artifacts was mostly filtered. A gray value difference algorithm was applied to the images to determine the edges of the internal layers of plywood and count them up automatically. The experimental results illustrated that polarization imaging could improve the counting accuracy of the algorithm effectively.

Possibilities of differential diagnostics of livores mortis and bruises at different stages of the time since death using laser polarization methods

One of the urgent problems of forensic medicine remains the detection of hemorrhages in soft tissues during examinations of decayed corpses, because late cadaveric phenomena significantly distort the primary morphological picture, thereby complicating the examination. A change in the color of the skin after a few days or later after death most often makes the macroscopic diagnosis of hemorrhages impossible, in particular, their differentiation with livores mortis.The aim of work. To investigate the possibilities of detecting and differentiating bruises in areas of livores mortis at different stages of the time since death by the Muller matrix analysis of polarization images of optically anisotropic polycrystalline networks of human soft tissues.
 Material and methods. Skin sections with subcutaneous fatty tissue were collected from corpses of persons who died from mechanical injuries. The obtained samples were divided into two groups: intact samples of livores mortis at the stages of hypostasis and imbibition and with existing hemorrhages with a known time since death. Tissue research was carried out using a laser polarimeter of a standard scheme.Results. According to the results of the study, it was established that the values of the statistical moments of the 3rd and 4th orders (S3, S4) of the intensity distributions of laser images of the skin show a statistically significant (р1<0,001) difference between intact areas and when bruises and livores mortis are combined. The values of asymmetry and excess (S3 from 1,23±0,032 to 1,56±0,038; S4 from 1,49±0,024 to 1,94±0,021) for intact samples of livores mortis changed with increasing interval of time since death. Similar changes in S3 and S4 (S3 from 1,54±0,031 to 1,83±0,037; S3from 1,82±0,026 to 2,11±0,023) for skin samples in the areas of localization of livores mortis with existing bruises.Conclusions. Thus, it can be stated that the application of the Mueller matrix analysis method of polarization images of optically anisotropic polycrystalline networks of soft human tissues is effective in detecting and differentiating bruises in the areas of cadaveric spots at different stages of the postmortem interval by conducting a statistical analysis of the values of the statistical moments of 3rd and 4th order.

Non-Destructive Inspection of Twisted Wire in Resin Cover Using Terahertz Wave

We proposed a new method for evaluating the deterioration of messenger wires by using terahertz waves. We use terahertz time-domain spectroscopy to measure several twisted wire samples with different levels of deterioration. We find that each twisted wire sample had a different distribution of reflection intensity which was due to the wires' twist structure. We show that it is possible to assess the degradation from the straight lines present in the reflection intensity distribution image. Furthermore, it was confirmed that our method can be applied to wire covered with resin.

A teacher–student framework with Fourier Transform augmentation for COVID-19 infection segmentation in CT images

Automatic segmentation of infected regions in computed tomography (CT) images is necessary for the initial diagnosis of COVID-19. Deep-learning-based methods have the potential to automate this task but require a large amount of data with pixel-level annotations. Training a deep network with annotated lung cancer CT images, which are easier to obtain, can alleviate this problem to some extent. However, this approach may suffer from a reduction in performance when applied to unseen COVID-19 images during the testing phase, caused by the difference in the image intensity and object region distribution between the training set and test set. In this paper, we proposed a novel unsupervised method for COVID-19 infection segmentation that aims to learn the domain-invariant features from lung cancer and COVID-19 images to improve the generalization ability of the segmentation network for use with COVID-19 CT images. First, to address the intensity difference, we proposed a novel data augmentation module based on Fourier Transform, which transfers the annotated lung cancer data into the style of COVID-19 image. Secondly, to reduce the distribution difference, we designed a teacher–student network to learn rotation-invariant features for segmentation. The experiments demonstrated that even without getting access to the annotations of the COVID-19 CT images during the training phase, the proposed network can achieve a state-of-the-art segmentation performance on COVID-19 infection.

Flows of healthy and hardened RBC suspensions through a micropillar array.

Red blood cell (RBC) deformability is an important haemorheological factor; it is impaired in many pathologies leading to microvascular complications. Several microfluidic platforms have been utilized to examine the role of deformability in RBC flows but their geometries tend to be simplified. In the present study, we extend our previous work on healthy RBC flows in micropillar arrays [1] to probe the effect of impaired RBC deformability on the velocity and haematocrit distributions in microscale RBC flows. Healthy and artificially hardened RBC suspensions at 25% haematocrit were perfused through the micropillar array at various flow rates and imaged. RBC velocities were determined by Particle Image Velocimetry (PIV) and haematocrit distributions were inferred from the image intensity distributions. The pillars divide the flow into two distinct RBC streams separated by a cell-depleted region along the centreline and in the rear/front stagnation points. RBC deformability was not found to significantly affect the velocity distributions; the shape of the velocity profiles in the interstitial space remained the same for healthy and hardened RBCs. Time-averaged and spatiotemporal intensity distributions, however, reveal differences in the dynamics and local distributions of healthy and hardened cells; hardened cells appear to enter the cell-depleted regions more frequently and their interstitial distributions are more uniform. The study highlights the importance of local RBC distributions and the impact of RBC deformability on cell transport in complex microscale flows.

Two‐Dimensional Angular Bandwidth Broadening of Metasurface Grating

Waveguide‐type near‐eye displays (NED) have attracted increasing attention in the market of augmented reality (AR) and virtual reality (VR) devices, thanks to their outstanding performance within ultra‐compact size. The performance of waveguide‐type NED mainly depends on the waveguide coupler that transmits the incident image to the user's eye through the total internal reflection (TIR) inside the waveguide. However, the waveguide couplers, that have been widely used, exhibit nonuniform diffraction efficiency within the transferable angular range, i.e., field of view (FoV) of waveguide‐type NED, so that the image intensity distribution distortion is induced. Thus, it is needed that many researchers focus on broadening angular bandwidth to overcome the non‐uniformity of the diffraction efficiency. Herein, the 2D angular bandwidth broadening metasurface grating that exhibits uniform and high diffraction efficiency for the 2D FoV range is proposed. Specifically, the proposed device is designed specifically, and the diffraction efficiency of this device shows uniform efficiency of about 75% with a variance of 0.25% for the FoV range, and it is demonstrated both numerically and experimentally. Consequently, it is expected that the proposed device can be a game‐changer in the market for waveguide‐type NED for the enhancement of image uniformity.

Detection of early decayed oranges by structured-illumination reflectance imaging coupling with texture feature classification models.

Citrus fruits are susceptible to fungal infection after harvest. To reduce the economic loss, it is necessary to reject the infected citrus fruit before storage and transportation. However, the infected area in the early stage of decay is almost invisible on the fruit surface, so the detection of early decayed citrus is very challenging. In this study, a structured-illumination reflectance imaging (SIRI) system combined with a visible light-emitting diode (LED) lamp and a monochrome camera was developed to detect early fungal infection in oranges. Under sinusoidal modulation illumination with spatial frequencies of 0.05, 0.15, and 0.25 cycles mm–1, three-phase-shifted images with phase offsets of − 2π/3, 0, and 2π/3 were acquired for each spatial frequency. The direct component (DC) and alternating component (AC) images were then recovered by image demodulation using a three-phase-shifting approach. Compared with the DC image, the decayed area can be clearly identified in the AC image and RT image (AC/DC). The optimal spatial frequency was determined by analyzing the AC image and pixel intensity distribution. Based on the texture features extracted from DC, AC, and RT images, four kinds of classification models including partial least square discriminant analysis (PLS-DA), support vector machine (SVM), least squares-support vector machine (LS-SVM), and k-nearest neighbor (KNN) were established to detect the infected oranges, respectively. Model optimization was also performed by extracting important texture features. Compared to all models, the PLS-DA model developed based on eight texture features of RT images achieved the optimal classification accuracy of 96.4%. This study showed for the first time that the proposed SIRI system combined with appropriate texture features and classification model can realize the early detection of decayed oranges.

Voxel-based diktiometry: Combining convolutional neural networks with voxel-based analysis and its application in diffusion tensor imaging for Parkinson's disease.

Extracting population‐wise information from medical images, specifically in the neurological domain, is crucial to better understanding disease processes and progression. This is frequently done in a whole‐brain voxel‐wise manner, in which a population of patients and healthy controls are registered to a common co‐ordinate space and a statistical test is performed on the distribution of image intensities for each location. Although this method has yielded a number of scientific insights, it is further from clinical applicability as the differences are often small and altogether do not permit for a high‐performing classifier. In this article, we take the opposite approach of using a high‐performing classifier, specifically a traditional convolutional neural network, and then extracting insights from it which can be applied in a population‐wise manner, a method we call voxel‐based diktiometry. We have applied this method to diffusion tensor imaging (DTI) analysis for Parkinson's disease (PD), using the Parkinson's Progression Markers Initiative database. By using the network sensitivity information, we can decompose what elements of the DTI contribute the most to the network's performance, drawing conclusions about diffusion biomarkers for PD that are based on metrics which are not readily expressed in the voxel‐wise approach.

Hyalite Sol-Gel Amoeba: A Physiology-Based Biophysical Model for Segmentation and Biotransformation of Medical Images To 3D Solid-State Characterizing Native Tissue Properties for Patient-Specific and Patient-Appropriate Analysis for Surgical Applications

Introduction: The endeavour to improve medical image segmentation techniques for higher analysis in surgical planning and medical therapeutics is far from becoming a standard of care in clinical practice. Hyalite Sol-Gel Amoeba model based on biophysical sciences apart from performing image segmentation is designed to extract real-world tissue densities for patient-specific and patient-appropriate analysis. Objectives: Amoeba Proteus is a unicellular independent entity, with a nucleus and sol-gel protoplasm enclosed in a membrane. The study presents versatile restructuring anatomy and physiology of the Amoeba Proteus for segmentation of 2D, and 3D medical images based on well-established principles of energy minimization and active contour. It demonstrates how the animalcule glides and advances by throwing pseudopodia driven by phenomenal actin-myosin activity that can segment a region-of-interest, and finally, at the time of apoptosis, its protoplasm and organelles acquire distribution of original image intensities to characterize tissue densities. Methods: This seminal study following a brief review of computer vision science discusses the relationship between optical density and tissue density, and the theory of sol-gel fluid mechanics. The framework of the HSG-Amoeba is described with the segmentation of various skeletal components of the thoracic cage. Results: This being a foundational study to describe the concept of the HSG-Amoeba model it requires the development of a mathematical algorithm to demonstrate its worthiness as a tool for surgical applications. Conclusion: The focus of the study is to present the design and framework of the newly conceived HSG-Amoeba model to segment a medical image and extract tissue densities without altering the original image intensities.

Automated cervical tumor segmentation on MR images using multi-view feature attention network

Precise cervical cancer treatment highly relies on accurate segmentation of cervical tumors from magnetic resonance (MR) images. However, this task is challenged by the inhomogeneous intensity distributions in MR images and the large variations in tumor shapes and locations. The large slice thickness further results in limited inter-slice correlations and 3D contextual information can be utilized, which influences the segmentation performance greatly. To tackle the above challenges and make full use of the 3D contextual information, a multi-view feature attention-based segmentation network (MVFA-Net) is proposed in this study. Toward the weak correlations among adjacent MR slices, features from different views of the volumetric MR images are extracted and treated individually and then fused by a channel-wise attention model. A cervical MR data set collected from 160 cervical cancer patients was employed to evaluate the performance of the proposed MVFA-Net. In comparison experiments, the proposed MVFA-Net outperforms the other eight medical image segmentation networks 2.6%-11.1% and 0.39 mm-0.97 mm on Dice similarity coefficient (DSC) and Average surface distance (ASD), respectively. Extensive ablation studies demonstrate the effectiveness of the proposed multi-view attention block and MVFA-Net. Additionally, with the trained segmentation network, no more than 6 s will be taken to segment one unseen patient, which is highly efficient for clinical practice. The presented segmentation network might be useful for cervical cancer treatment routine to improve the segmentation accuracy, consistency, and efficiency. The code is publicly available at: https://github.com/xyndameinv/MVFA-Net.