Segmentation Of Magnetic Resonance Images Research Articles

310 (PB-126) Poster - Breast tissue segmentation in MR images using deep-learning

310 (PB-126) Poster - Breast tissue segmentation in MR images using deep-learning

Enhanced Detection of White Matter Hyperintensities via Deep Learning-Enabled MR Imaging Segmentation

Enhanced Detection of White Matter Hyperintensities via Deep Learning-Enabled MR Imaging Segmentation

Congenital diaphragmatic hernia: automatic lung and liver MRI segmentation with nnU-Net, reproducibility of pyradiomics features, and a machine learning application for the classification of liver herniation

Prenatal assessment of lung size and liver position is essential to stratify congenital diaphragmatic hernia (CDH) fetuses in risk categories, guiding counseling, and patient management. Manual segmentation on fetal MRI provides a quantitative estimation of total lung volume and liver herniation. However, it is time-consuming and operator-dependent. In this study, we utilized a publicly available deep learning (DL) segmentation system (nnU-Net) to automatically contour CDH-affected fetal lungs and liver on MRI sections. Concordance between automatic and manual segmentation was assessed by calculating the Jaccard coefficient. Pyradiomics standard features were then extracted from both manually and automatically segmented regions. The reproducibility of features between the two groups was evaluated through the Wilcoxon rank-sum test and intraclass correlation coefficients (ICCs). We finally tested the reliability of the automatic-segmentation approach by building a ML classifier system for the prediction of liver herniation based on support vector machines (SVM) and trained on shape features computed both in the manual and nnU-Net-segmented organs. We compared the area under the classifier receiver operating characteristic curve (AUC) in the two cases. Pyradiomics features calculated in the manual ROIs were partly reproducible by the same features calculated in nnU-Net segmented ROIs and, when used in the ML procedure, to predict liver herniation (both AUC around 0.85). Conclusion: Our results suggest that automatic MRI segmentation is feasible, with good reproducibility of pyradiomics features, and that a ML system for liver herniation prediction offers good reliability. Trial registration: https://clinicaltrials.gov/ct2/show/NCT04609163?term=NCT04609163&draw=2&rank=1; Clinical Trial Identification no. NCT04609163.What is Known:• Magnetic resonance imaging (MRI) is crucial for prenatal congenital diaphragmatic hernia (CDH) assessment. It enables the quantification of the total lung volume and the extent of liver herniation, which are essential for stratifying the severity of CDH, guiding counseling, and patient management.• The manual segmentation of MRI scans is a time-consuming process that is heavily reliant upon the skill set of the operator.What is New:• MRI lung and liver automatic segmentation using the deep learning nnU-Net system is feasible, with good Jaccard coefficient values and satisfactory reproducibility of pyradiomics features compared to manual results.• A feasible ML system for predicting liver herniation could improve prenatal assessments and CDH patient management.

Based on neural network cascade abnormal texture information dissemination of classification of patients with schizophrenia and depression

This study used MRI brain image segmentation to identify novel magnetic resonance imaging (MRI) biomarkers to distinguish patients with schizophrenia (SCZ), major depressive disorder (MD), and healthy control (HC). Brain texture measurements, including entropy and contrast, were calculated to capture variability in adjacent MRI voxel intensity. These measures are then applied to group classification in deep learning techniques and combined with hierarchical correlations to locate results. Texture feature maps were extracted from segmented brain MRI scans of 141 patients with schizophrenia (SCZ), 103 patients with major depressive disorder (MD) and 238 healthy controls (HC). Gray scale coassociation matrix (GLCM) is a monomer matrix calculated in a voxel cube. Deep learning methods were evaluated to determine the application capability of texture feature mapping in binary classification (SCZ vs. HC, MD vs. HC, SCZ vs. MD). The method is implemented by repeated nesting and cross-validation for feature selection. Regions that show the highest correlation (positive or negative). In this study, the authors successfully classified SCZ, MD and HC. This suggests that texture analysis can be used as an effective feature extraction method to distinguish different disease states. Compared with other methods, texture analysis can capture richer image information and improve classification accuracy in some cases. The classification accuracy of SCZ and HC, MD and HC, SCZ and MD reached 84.6%, 86.4% and 76.21%, respectively. Among them, SCZ and HC are the most significant features with high sensitivity and specificity.

ViT-UperNet: a hybrid vision transformer with unified-perceptual-parsing network for medical image segmentation

The existing image semantic segmentation models have low accuracy in detecting tiny targets or multi-targets at overlapping regions. This work proposes a hybrid vision transformer with unified-perceptual-parsing network (ViT-UperNet) for medical image segmentation. A self-attention mechanism is embedded in a vision transformer to extract multi-level features. The image features are extracted hierarchically from low to high dimensions using 4 groups of Transformer blocks with different numbers. Then, it uses a unified-perceptual-parsing network based on a feature pyramid network (FPN) and a pyramid pooling module (PPM) for the fusion of multi-scale contextual features and semantic segmentation. FPN can naturally use hierarchical features, and generate strong semantic information on all scales. PPM can better use the global prior knowledge to understand complex scenes, and extract features with global context information to improve segmentation results. In the training process, a scalable self-supervised learner named masked autoencoder is used for pre-training, which strengthens the visual representation ability and improves the efficiency of the feature learning. Experiments are conducted on cardiac magnetic resonance image segmentation where the left and right atrium and ventricle are selected for segmentation. The pixels accuracy is 93.85%, the Dice coefficient is 92.61% and Hausdorff distance is 11.16, which are improved compared with the other methods. The results show the superiority of Vit-UperNet in medical images segmentation, especially for the low-recognition and serious-occlusion targets.

Knee cartilage MR images segmentation based on multi-dimensional hybrid convolutional neural network

Accurate segmentation of knee cartilage in MR images is crucial for early diagnosis and treatment of knee conditions. Manual segmentation is time-consuming, leading researchers to explore automatic deep learning methods. However, the choice between 2D and 3D networks for organ segmentation remains debated. In this paper, we propose a hybrid 2D and 3D deep neural network approach, named UVNet, which combines the strengths of both techniques to enhance segmentation performance. Within this network structure, the 3D segmentation network serves as the backbone for feature extraction, while the 2D segmentation network functions as an information supplement network. Local and global MIP images are generated by employing various maximum intensity projection modes of knee MRI volumes as input for the information supplement network. By constructing a local and global MIP feature fusion module, the supplementary information obtained from the 2D segmentation network is fully integrated into the backbone network. We assess the quality of the proposed method using the Osteoarthritis Initiative (OAI) dataset and the 2010 Grand Challenge Knee Image Segmentation (SKI-10) dataset, comparing it to the Baseline Network and other advanced 2D and 3D segmentation methods. The experiments demonstrate that UVNet achieves competitive performance in the aforementioned two cartilage segmentation tasks.

Neuroanatomical comparison of treatment-resistant and treatment-responsive schizophrenia patients using the cloud-based brain magnetic resonance image segmentation and parcellation system: An MRIcloud study

Recent developments in neuroimaging have improved our understanding of the biological mechanisms underlying schizophrenia. However, neuroimaging findings in treatment-resistant schizophrenia (TRS) remain unclear. In the present study, we aimed to explore potential neuroanatomical regions that may be associated with treatment resistance in schizophrenia patients by comparing neuroanatomical regions of TRS and non-TRS patients using the MRICloud method. A total of 33 schizophrenia patients (meeting DSM 5 diagnostic criteria for schizophrenia) were included in the study. Patients were dichotomized into TRS (n = 18) and non-TRS (n = 15) groups, and all patients underwent MRI. Neuroanatomical regions of TRS and non-TRS patients were compared using the MRICloud method. Disease severity was measured using the Positive and Negative Syndrome Scale (PANSS). Interestingly, a statistically significant greater left Corpus Collosum (CC) thickness was found in TRS patients compared to non-TRS patients. It is clear that further studies comparing TRS patients with non-TRS patients are needed, and these studies should focus on the circuits in the corpus callosum that are thought to play a role in treatment resistance. Further longitudinal studies are also needed to complement the cross-sectional studies, using a multimodal imaging approach in the patients with clearly defined TRS criteria.

HSA-net with a novel CAD pipeline boosts both clinical brain tumor MR image classification and segmentation

Brain tumors are among the most prevalent neoplasms in current medical studies. Accurately distinguishing and classifying brain tumor types accurately is crucial for patient treatment and survival in clinical practice. However, existing computer-aided diagnostic pipelines are inadequate for practical medical use due to tumor complexity. In this study, we curated a multi-centre brain tumor dataset that includes various clinical brain tumor data types, including segmentation and classification annotations, surpassing previous efforts. To enhance brain tumor segmentation accuracy, we propose a new segmentation method: HSA-Net. This method utilizes the Shared Weight Dilated Convolution module (SWDC) and Hybrid Dense Dilated Convolution module (HDense) to capture multi-scale information while minimizing parameter count. The Effective Multi-Dimensional Attention (EMA) and Important Feature Attention (IFA) modules effectively aggregate task-related information. We introduce a novel clinical brain tumor computer-aided diagnosis pipeline (CAD) that combines HSA-Net with pipeline modification. This approach not only improves segmentation accuracy but also utilizes the segmentation mask as an additional channel feature to enhance brain tumor classification results. Our experimental evaluation of 3327 real clinical data demonstrates the effectiveness of the proposed method, achieving an average Dice coefficient of 86.85 % for segmentation and a classification accuracy of 95.35 %. We also validated the effectiveness of our proposed method using the publicly available BraTS dataset.

STBI-GAN: An adversarial learning approach for data synthesis on traumatic brain segmentation

Automatic brain segmentation of magnetic resonance images (MRIs) from severe traumatic brain injury (sTBI) patients is critical for brain abnormality assessments and brain network analysis. Construction of sTBI brain segmentation model requires manually annotated MR scans of sTBI patients, which becomes a challenging problem as it is quite impractical to implement sufficient annotations for sTBI images with large deformations and lesion erosion. Data augmentation techniques can be applied to alleviate the issue of limited training samples. However, conventional data augmentation strategies such as spatial and intensity transformation are unable to synthesize the deformation and lesions in traumatic brains, which limits the performance of the subsequent segmentation task. To address these issues, we propose a novel medical image inpainting model named sTBI-GAN to synthesize labeled sTBI MR scans by adversarial inpainting. The main strength of our sTBI-GAN method is that it can generate sTBI images and corresponding labels simultaneously, which has not been achieved in previous inpainting methods for medical images. We first generate the inpainted image under the guidance of edge information following a coarse-to-fine manner, and then the synthesized MR image is used as the prior for label inpainting. Furthermore, we introduce a registration-based template augmentation pipeline to increase the diversity of the synthesized image pairs and enhance the capacity of data augmentation. Experimental results show that the proposed sTBI-GAN method can synthesize high-quality labeled sTBI images, which greatly improves the 2D and 3D traumatic brain segmentation performance compared with the alternatives. Code is available at .

Pregnancy-induced remodeling of the murine reproductive tract: a longitudinal in vivo magnetic resonance imaging study

Mammalian pregnancy requires gradual yet extreme remodeling of the reproductive organs to support the growth of the embryos and their birth. After delivery, the reproductive organs return to their non-pregnant state. As pregnancy has traditionally been understudied, there are many unknowns pertaining to the mechanisms behind this remarkable remodeling and repair process which, when not successful, can lead to pregnancy-related complications such as maternal trauma, pre-term birth, and pelvic floor disorders. This study presents the first longitudinal imaging data that focuses on revealing anatomical alterations of the vagina, cervix, and uterine horns during pregnancy and postpartum using the mouse model. By utilizing advanced magnetic resonance imaging (MRI) technology, T1-weighted and T2-weighted images of the reproductive organs of three mice in their in vivo environment were collected at five time points: non-pregnant, mid-pregnant (gestation day: 9–10), late pregnant (gestation day: 16–17), postpartum (24–72 h after delivery) and three weeks postpartum. Measurements of the vagina, cervix, and uterine horns were taken by analyzing MRI segmentations of these organs. The cross-sectional diameter, length, and volume of the vagina increased in late pregnancy and then returned to non-pregnant values three weeks after delivery. The cross-sectional diameter of the cervix decreased at mid-pregnancy before increasing in late pregnancy. The volume of the cervix peaked at late pregnancy before shortening by 24–72 h postpartum. As expected, the uterus increased in cross-sectional diameter, length, and volume during pregnancy. The uterine horns decreased in size postpartum, ultimately returning to their average non-pregnant size three weeks postpartum. The newly developed methods for acquiring longitudinal in vivo MRI scans of the murine reproductive system can be extended to future studies that evaluate functional and morphological alterations of this system due to pathologies, interventions, and treatments.

SALW-Net: a lightweight convolutional neural network based on self-adjusting loss function for spine MR image segmentation.

Segmentation of intervertebral discs and vertebrae from spine magnetic resonance (MR) images is essential to aid diagnosis algorithms for lumbar disc herniation. Convolutional neural networks (CNN) are effective methods, but often require high computational costs. Designing a lightweight CNN is more suitable for medical sites lacking high-computing power devices, yet due to the unbalanced pixel distribution in spine MR images, the segmentation is often sub-optimal. To address this issue, a lightweight spine segmentation CNN based on a self-adjusting loss function, which is named SALW-Net, is proposed in this study. For SALW-Net, the self-adjusting loss function could dynamically adjust the loss weights of the two branches according to the differences in segmentation results and labels during the training; thus, the ability for learning unbalanced pixels is enhanced. Two separate datasets are used to evaluate the proposed SALW-Net. Specifically, the proposed SALW-Net has fewer parameter numbers than U-net (only 2%) but achieves higher evaluation scores than that of U-net (the average DSC score of SALW-Net is 0.8781, and that of U-net is 0.8482). In addition, the practicality validation for SALW-Net is also proceeding, including deploying the model on a lightweight device and producing an aid diagnosis algorithm based on segmentation results. This means our SALW-Net has clinical application potential for assisted diagnosis in low computational power scenarios.

Automatic lung segmentation of magnetic resonance images: A new approach applied to healthy volunteers undergoing enhanced Deep-Inspiration-Breath-Hold for motion-mitigated 4D proton therapy of lung tumors

Background and purposeRespiratory suppression techniques represent an effective motion mitigation strategy for 4D-irradiation of lung tumors with protons. A magnetic resonance imaging (MRI)-based study applied and analyzed methods for this purpose, including enhanced Deep-Inspiration-Breath-Hold (eDIBH). Twenty-one healthy volunteers (41–58 years) underwent thoracic MR scans in four imaging sessions containing two eDIBH-guided MRIs per session to simulate motion-dependent irradiation conditions. The automated MRI segmentation algorithm presented here was critical in determining the lung volumes (LVs) achieved during eDIBH. Materials and methodsThe study included 168 MRIs acquired under eDIBH conditions. The lung segmentation algorithm consisted of four analysis steps: (i) image preprocessing, (ii) MRI histogram analysis with thresholding, (iii) automatic segmentation, (iv) 3D-clustering. To validate the algorithm, 46 eDIBH-MRIs were manually contoured. Sørensen-Dice similarity coefficients (DSCs) and relative deviations of LVs were determined as similarity measures. Assessment of intrasessional and intersessional LV variations and their differences provided estimates of statistical and systematic errors. ResultsLung segmentation time for 100 2D-MRI planes was ∼ 10 s. Compared to manual lung contouring, the median DSC was 0.94 with a lower 95 % confidence level (CL) of 0.92. The relative volume deviations yielded a median value of 0.059 and 95 % CLs of −0.013 and 0.13. Artifact-based volume errors, mainly of the trachea, were estimated. Estimated statistical and systematic errors ranged between 6 and 8 %. ConclusionsThe presented analytical algorithm is fast, precise, and readily available. The results are comparable to time-consuming, manual segmentations and other automatic segmentation approaches. Post-processing to remove image artifacts is under development.

VisioRenalNet: Spatial Vision Transformer UNet for enhanced T2-Weighted Kidney MRI Segmentation

Chronic Kidney Disease (CKD) afflicts approximately 20% of the global population, underscoring the pressing need for precise detection and diagnosis. Accurate kidney segmentation in medical imaging is pivotal for capturing intricate details, facilitating effective evaluation and treatment planning. This work consists implementation of U-Net Variants along with enhanced variant for kidney segmentation in Magnetic Resonance Images (MRI). We systematically assess the performance of various U-Net variants, including U-Net, VGGUNet, DenseUNet, ResUNet, U-Net++, and AttentionUNet, utilizing a publicly available dataset of T2-weighted abdomen MRI scans from 100 subjects. Subsequently, we propose an enhanced U-Net framework that seamlessly integrates transformer blocks, spatial Attention Mechanism, and swish activation to enhance performance and robustness. Enhanced UNet provides improved feature learning, enhanced contextual information, selective focus and improved performance metrices for Kidney Segmentation. This significant advancement in medical image segmentation can contribute to enhanced diagnosis, more effective treatment planning, and improved disease management for individuals suffering from kidney diseases. Notably, our enhanced U-Net variant, after 50 epochs, achieved an average Dice coefficient of 89.1%, a Jaccard score of 80.4%, and an impressive accuracy of 96.2%, surpassing all baseline U-Net variants in all evaluation metrics, thereby affirming its superiority in kidney segmentation.

Multi-Source Data Integration for Segmentation of Unannotated MRI Images.

Automatic semantic segmentation of magnetic resonance imaging (MRI) images using deep neural networks greatly assists in evaluating and planning treatments for various clinical applications. However, training these models is conditioned on the availability of abundant annotated data. Even if we annotate enough data, MRI images display considerable variability due to factors such as differences among patients, MRI scanners, and imaging protocols. This variability necessitates retraining neural networks for each specific application domain, which, in turn requires manual annotation by expert radiologists for all new domains. To relax the need for persistent data annotation, we develop a method for unsupervised federated domain adaptation using multiple annotated source domains. Our approach enables the transfer of knowledge from several annotated source domains for use in an unannotated target domain. Initially, we ensure that the target domain data shares similar representations with each source domain in a latent embedding space by minimizing the pair-wise distances between the distributions for the target and the source domains. We then employ an ensemble approach to leverage the knowledge obtained from all domains to build an integrated outcome. We perform experiments on two datasets to demonstrate our method is effective. Our implementation code is publicly available: https://github.com/navapatn/Unsupervised -Federated-Domain-Adaptation-for-Image-Segmentation new.

Integrated Brain Tumor Detection: PSO-Guided Segmentation with U-Net and CNN Classification

Segmentation of tissues in magnetic resonance (MR) images is vital for effective analysis of brain pathology. However, existing approaches for brain MR image segmentation and feature extraction have limitations such as high computational costs and lower accuracy. To overcome these challenges, this paper presents an integrated approach, termed PSO-Guided Segmentation with U-Net and CNN Classification, for the detection and quantification of brain pathology in MR images. The proposed algorithm combines Particle Swarm Optimization (PSO) for enhanced feature extraction, for the classification CNN while segmentation can be done through U-Net. Numerous tests show that the suggested algorithm performs more effectively and accurately than existing techniques in terms of sensitivity and accuracy. By utilizing cutting-edge technologies like Convolutional Neural Networks (CNN), Particle Swarm Optimization (PSO), and U-Net, significant progress has been made in enhancing the accuracy of MR image segmentation and tumor detection. Compared to traditional methods, our proposed methodology outperforms, enhancing accuracy and sensitivity by approximately 0.44%, significantly decreasing computational expenses while maintaining high precision. However, due to the dynamic nature of technology advancements, it remains imperative to continually explore and develop novel frameworks and algorithms to further improve accuracy and achieve the highest level of performance.

FCTformer: Fusing Convolutional Operations and Transformer for 3D Rectal Tumor Segmentation in MR Images

FCTformer: Fusing Convolutional Operations and Transformer for 3D Rectal Tumor Segmentation in MR Images

Deep learning-based brain tumor detection: An MRI segmentation approach

The detection and segmentation of brain tumors from magnetic resonance imaging (MRI) scans are crucial for diagnosing, planning treatments, and monitoring patients with neurological disorders. This abstract provides a comprehensive overview of deep learning-based methods for detecting brain tumors, focusing on techniques for segmenting MRI images. Deep learning models, particularly convolutional neural networks (CNNs), have achieved impressive results in accurately segmenting brain tumors by learning distinctive features directly from the image data. Various CNN architectures, such as U-Net, DeepMedic, and 3D convolutional networks, have been specifically designed to address the challenges of brain tumor segmentation, including tumor heterogeneity, irregular shapes, and varying sizes. Additionally, the integration of multimodal MRI data, such as T1-weighted, T2-weighted, and FLAIR images, has enhanced the robustness and accuracy of deep learning models for brain tumor detection. This abstract discusses the significant advancements, challenges, and future directions in deep learning-based brain tumor detection, emphasizing the potential of MRI segmentation techniques to support clinicians in early diagnosis and personalized treatment planning for patients with brain tumors.

Fuzzy C Means Clustering Coupled with Firefly Optimization Algorithm for the Segmentation of Neurodisorder Magnetic Resonance Images

Medical image segmentation is a critical task in medical image analysis, and clustering algorithms can be utilized to achieve this goal. This research work focuses on the segmentation of neuro disorder magnetic resonance images using Otsu, K-means, and FCM coupled with the firefly optimization algorithm. Otsu is a classical thresholding algorithm that relies on a single threshold value to segment the images. K-Means is one of the simplest and most widely used clustering algorithms. It aims to partition data into K clusters, where each data point belongs to the cluster with the nearest mean. Fuzzy C-Means is an extension of K-Means, allowing data points to belong to multiple clusters with varying degrees of membership. In medical image segmentation, FCM was used to classify pixels or voxels into different tissue classes with soft boundaries, accounting for partial volume effects. Firefly Optimization helps in improving the convergence speed of the FCM algorithm. Firefly optimization is good at exploring the solution space and finding global optima. The combination of FCM and Firefly Optimization leads to more accurate clustering results. The performance evaluation was done by Renyi entropy and Shannon entropy, FCM coupled with the firefly optimization was found to exhibit superior results when compared with the Otsu and K-means clustering algorithms.

Segmentation of abdominal CT and cardiac MR images with multi scale visual attention

Segmentation of abdominal CT and cardiac MR images with multi scale visual attention

DAFNet: A dual attention-guided fuzzy network for cardiac MRI segmentation

<abstract> <sec><title>Background</title><p>In clinical diagnostics, magnetic resonance imaging (MRI) technology plays a crucial role in the recognition of cardiac regions, serving as a pivotal tool to assist physicians in diagnosing cardiac diseases. Despite the notable success of convolutional neural networks (CNNs) in cardiac MRI segmentation, it remains a challenge to use existing CNNs-based methods to deal with fuzzy information in cardiac MRI. Therefore, we proposed a novel network architecture named DAFNet to comprehensively address these challenges.</p> </sec> <sec><title>Methods</title><p>The proposed method was used to design a fuzzy convolutional module, which could improve the feature extraction performance of the network by utilizing fuzzy information that was easily ignored in medical images while retaining the advantage of attention mechanism. Then, a multi-scale feature refinement structure was designed in the decoder portion to solve the problem that the decoder structure of the existing network had poor results in obtaining the final segmentation mask. This structure further improved the performance of the network by aggregating segmentation results from multi-scale feature maps. Additionally, we introduced the dynamic convolution theory, which could further increase the pixel segmentation accuracy of the network.</p> </sec> <sec><title>Result</title><p>The effectiveness of DAFNet was extensively validated for three datasets. The results demonstrated that the proposed method achieved DSC metrics of 0.942 and 0.885, and HD metricd of 2.50mm and 3.79mm on the first and second dataset, respectively. The recognition accuracy of left ventricular end-diastolic diameter recognition on the third dataset was 98.42%.</p> </sec> <sec><title>Conclusion</title><p>Compared with the existing CNNs-based methods, the DAFNet achieved state-of-the-art segmentation performance and verified its effectiveness in clinical diagnosis.</p> </sec> </abstract>