Segmentation Of Magnetic Resonance Images Research Articles

The Quantitative Evaluation of Automatic Segmentation in Lumbar Magnetic Resonance Images.

This study aims to overcome challenges in lumbar spine imaging, particularly lumbar spinal stenosis, by developing an automated segmentation model using advanced techniques. Traditional manual measurement and lesion detection methods are limited by subjectivity and inefficiency. The objective is to create an accurate and automated segmentation model that identifies anatomical structures in lumbar spine magnetic resonance imaging scans. Leveraging a dataset of 539 lumbar spinal stenosis patients, the study utilizes the residual U-Net for semantic segmentation in sagittal and axial lumbar spine magnetic resonance images. The model, trained to recognize specific tissue categories, employs a geometry algorithm for anatomical structure quantification. Validation metrics, like Intersection over Union (IOU) and Dice coefficients, validate the residual U-Net's segmentation accuracy. A novel rotation matrix approach is introduced for detecting bulging discs, assessing dural sac compression, and measuring yellow ligament thickness. The residual U-Net achieves high precision in segmenting lumbar spine structures, with mean IOU values ranging from 0.82 to 0.93 across various tissue categories and views. The automated quantification system provides measurements for intervertebral disc dimensions, dural sac diameter, yellow ligament thickness, and disc hydration. Consistency between training and testing datasets assures the robustness of automated measurements. Automated lumbar spine segmentation with residual U-Net and deep learning exhibits high precision in identifying anatomical structures, facilitating efficient quantification in lumbar spinal stenosis cases. The introduction of a rotation matrix enhances lesion detection, promising improved diagnostic accuracy, and supporting treatment decisions for lumbar spinal stenosis patients.

A geometric approach to robust medical image segmentation

Robustness of deep learning segmentation models is crucial for their safe incorporation into clinical practice. However, these models can falter when faced with distributional changes. This challenge is evident in magnetic resonance imaging (MRI) scans due to the diverse acquisition protocols across various domains, leading to differences in image characteristics such as textural appearances. We posit that the restricted anatomical differences between subjects could be harnessed to refine the latent space into a set of shape components. The learned set then aims to encompass the relevant anatomical shape variation found within the patient population.We explore this by utilising multiple MRI sequences to learn texture invariant and shape equivariant features which are used to construct a shape dictionary using vector quantisation. We investigate shape equivariance to a number of different types of groups. We hypothesise and prove that the greater the group order, i.e., the denser the constraint, the better becomes the model robustness. We achieve shape equivariance either with a contrastive based approach or by imposing equivariant constraints on the convolutional kernels. The resulting shape equivariant dictionary is then sampled to compose the segmentation output. Our method achieves state-of-the-art performance for the task of single domain generalisation for prostate and cardiac MRI segmentation. Code is available at https://github.com/AinkaranSanthi/A_Geometric_Perspective_For_Robust_Segmentation.

Optimizing Performance of Transformer-based Models for Fetal Brain MR Image Segmentation.

Purpose To test the performance of a transformer-based model when manipulating pretraining weights, dataset size, and input size and comparing the best model with the reference standard and state-of-the-art models for a resting-state functional (rs-fMRI) fetal brain extraction task. Materials and Methods An internal retrospective dataset (172 fetuses, 519 images; collected 2018-2022) was used to investigate influence of dataset size, pretraining approaches, and image input size on Swin-U-Net transformer (UNETR) and UNETR models. The internal and external (131 fetuses, 561 images) datasets were used to cross-validate and to assess generalization capability of the best model versus state-of-the-art models on different scanner types and number of gestational weeks (GWs). The Dice similarity coefficient (DSC) and the balanced average Hausdorff distance (BAHD) were used as segmentation performance metrics. Generalized equation estimation multifactorial models were used to assess significant model and interaction effects of interest. Results The Swin-UNETR model was not affected by the pretraining approach and dataset size and performed best with the mean dataset image size, with a mean DSC of 0.92 and BAHD of 0.097. Swin-UNETR was not affected by scanner type. Generalization results on the internal dataset showed that Swin-UNETR had lower performance compared with the reference standard models and comparable performance on the external dataset. Cross-validation on internal and external test sets demonstrated better and comparable performance of Swin-UNETR versus convolutional neural network architectures during the late-fetal period (GWs > 25) but lower performance during the midfetal period (GWs ≤ 25). Conclusion Swin-UNTER showed flexibility in dealing with smaller datasets, regardless of pretraining approaches. For fetal brain extraction from rs-fMR images, Swin-UNTER showed comparable performance with that of reference standard models during the late-fetal period and lower performance during the early GW period. Keywords: Transformers, CNN, Medical Imaging Segmentation, MRI, Dataset Size, Input Size, Transfer Learning Supplemental material is available for this article. © RSNA, 2024.

Bayesian Uncertainty Estimation by Hamiltonian Monte Carlo: Applications to Cardiac MRI Segmentation

Deep learning (DL)-based methods have achieved state-of-the-art performance for many medical image segmentation tasks. Nevertheless, recent studies show that deep neural net- works (DNNs) can be miscalibrated and overconfident, leading to ”silent failures” that are risky for clinical applications. Bayesian DL provides an intuitive approach to DL failure de- tection, based on posterior probability estimation. However, the posterior is intractable for large medical image segmentation DNNs. To tackle this challenge, we propose a Bayesian learning framework using Hamiltonian Monte Carlo (HMC), tempered by cold posterior (CP) to accommodate medical data augmentation, named HMC-CP. For HMC compu- tation, we further propose a cyclical annealing strategy, capturing both local and global geometries of the posterior distribution, enabling highly efficient Bayesian DNN training with the same computational budget as training a single DNN. The resulting Bayesian DNN outputs an ensemble segmentation along with the segmentation uncertainty. We evaluate the proposed HMC-CP extensively on cardiac magnetic resonance image (MRI) segmentation, using in-domain steady-state free precession (SSFP) cine images as well as out-of-domain datasets of quantitative T1 and T2 mapping. Our results show that the proposed method improves both segmentation accuracy and uncertainty estimation for in- and out-of-domain data, compared with well-established baseline methods such as Monte Carlo Dropout and Deep Ensembles. Additionally, we establish a conceptual link between HMC and the commonly known stochastic gradient descent (SGD) and provide general insight into the uncertainty of DL. This uncertainty is implicitly encoded in the training dynamics but often overlooked. With reliable uncertainty estimation, our method provides a promising direction toward trustworthy DL in clinical applications. We release our code in <a href='https://gitlab.tudelft.nl/yidongzhao/hmc_uncertainty'>https://gitlab.tudelft.nl/yidongzhao/hmc_uncertainty</a>

Subject-Specific Probability Maps of Scalp, Skull and Cerebrospinal Fluid for Cranial Bones Segmentation in Neonatal Cerebral MRIs

ObjectivesSegmentation of cranial bones in magnetic resonance images (MRIs) is a challenging and indispensable task to study neonatal brain development and injury. This paper presents a new approach for creating subject-specific probability maps of the scalp, skull and cerebrospinal fluid (CSF) from retrospective bimodal (MR and CT) images acquired from neonates in the gestational age range of 39 to 42 weeks. These maps are subsequently employed for the segmentation of cranial bones in cerebral MRIs from neonates in the same age range. Material and methodsRetrospective MR and CT of neonates with normal head in the gestational age range of 39-42 weeks were preprocessed, segmented semi-automatically and employed as atlas data. For an input MR image acquired from a subject under study, a preprocessing stage and three main processing blocks were performed: First, subject-specific head and intracranial templates and CSF probability map were created using retrospective MR atlas data. Second, the CT atlas data were coregistered to MR templates and the resulted deformation matrices were fed to the next block to create subject-specific scalp and skull probability maps. Finally, some novel performance measures were presented to evaluate the performance of subject-specific CSF, scalp and skull probability maps for skull and intracranial segmentation in neonatal MRIs. ResultsThe subject-specific probability maps were employed for brain tissue extraction and compared with two public methods such as Brain Extraction Tool (BET) and Brain Surface Extractor (BSE). They were also applied for cranial bone extraction. Then, the similarity in shape between the frontal and occipital sutures (which had been reconstructed from segmented cranial bones) and the ground truth landmarks was evaluated. For this purpose, modified versions of the Dice similarity coefficient (DSC) were used. Finally, a retrospective bimodal (MR-CT) data acquired from a neonate within a short time interval was used for evaluation. After co-alignment of the two images, the DSC and modified Hausdorff distance (MHD) were used to compare the similarity of cranial bones in the MR and CT images. ConclusionSignificant improvements were achieved compared to conventional methods which rely solely on MR image intensities. These advancements hold promise for enhancing neurodevelopmental studies in neonates. The algorithm for creating subject-specific atlases is publicly accessible through a graphical user interface at medvispy.ee.kntu.ac.ir.

Semi-automated software improves interrater reliability and reduces processing time of magnetic resonance imaging-based exocrine pancreatic assessments in pediatric patients

ObjectivesMagnetic resonance (MR) imaging with secretin stimulation (MR-PFTs) is a non-invasive test for pancreatic exocrine function based on assessing the volume of secreted bowel fluid in vivo. Adoption of this methodology in clinical care and research is largely limited to qualitative assessment of secretion as current methods for secretory response quantification require manual thresholding and segmentation of MR images, which can be time-consuming and prone to interrater variability. We describe novel software (PFTquant) that preprocesses and thresholds MR images, performs heuristic detection of non-bowel fluid objects, and provides the user with intuitive semi-automated tools to segment and quantify bowel fluid in a fast and robust manner. We evaluate the performance of this software on a retrospective set of clinical MRIs.MethodsTwenty MRIs performed in children (< 18 years) were processed independently by two observers using a manual technique and using PFTquant. Interrater agreement in measured secreted fluid volume was compared using intraclass correlation coefficients, Bland-Altman difference analysis, and Dice similarity coefficients.ResultsInterrater reliability of measured bowel fluid secretion using PFTquant was 0.90 (0.76–0.96 95% C.I.) with − 4.5 mL mean difference (-39.4–30.4 mL 95% limits of agreement) compared to 0.69 (0.36–0.86 95% C.I.) with − 0.9 mL mean difference (-77.3–75.5 mL 95% limits of agreement) for manual processing. Dice similarity coefficients were better using PFTquant (0.88 +/- 0.06) compared to manual processing (0.85 +/- 0.10) but not significantly (p = 0.11). Time to process was significantly (p < 0.001) faster using PFTquant (412 +/- 177 s) compared to manual processing (645 +/- 305 s).ConclusionNovel software provides fast, reliable quantification of secreted fluid volume in children undergoing MR-PFTs. Use of the novel software could facilitate wider adoption of quantitative MR-PFTs in clinical care and research.

IMG-02. USING MRI RADIOMICS AND MACHINE LEARNING TO PREDICT OVERALL SURVIVAL FOR PEDIATRIC DIFFUSE MIDLINE GLIOMAS

Abstract BACKGROUND Pediatric diffuse midline gliomas (DMG) are aggressive central nervous system tumors with a median overall survival (OS) of less than one year from diagnosis. There is no curative therapy for DMG, and radiation therapy (RT) is the standard treatment. Magnetic resonance imaging (MRI) is the common noninvasive tool for DMG diagnosis and monitoring of tumor response to therapy. We developed an automatic pipeline to segment subregions of DMG and select MRI features that predict patient OS. METHODS We acquired diagnostic and post-RT multisequence MRI (T1, T1ce, T2, T2 FLAIR) and manual segmentations of pediatric DMG patients from two centers: 53 from Children’s National Hospital (internal) and 16 from Children’s Hospital of Philadelphia (external). We pretrained a deep learning model on a public adult brain tumor dataset, and finetuned the model to segment tumor core (TC) and whole tumor (WT) of DMG. We used PyRadiomics and sequential feature selection to select discriminative features based on the segmented volumes. Two machine learning models were trained on our internal cohort to predict patient 1-year survival from diagnosis. One model used only diagnostic tumor features and the other used both diagnostic and post-RT features. RESULTS For segmentation, Dice score (mean [median]±SD) was 0.91 (0.94)±0.12 and 0.74 (0.83)±0.32 for TC, and 0.88 (0.91)±0.07 and 0.86 (0.89)±0.06 for WT for internal and external cohorts, respectively. For OS prediction, accuracy was 77% and 81% at time of diagnosis, and 85% and 78% post-RT for internal and external cohorts, respectively. Heterogeneous WT intensity in baseline T2 FLAIR and smaller post-RT TC/WT volume ratio indicate longer OS. CONCLUSIONS Our method accurately predict OS for DMG patients and can be extended to other rare pediatric brain tumors. With automated and standardized analysis, early prognostication of OS can guide patient risk stratification and clinical decisions.

A Semi-Automatic Magnetic Resonance Imaging Annotation Algorithm Based on Semi-Weakly Supervised Learning.

The annotation of magnetic resonance imaging (MRI) images plays an important role in deep learning-based MRI segmentation tasks. Semi-automatic annotation algorithms are helpful for improving the efficiency and reducing the difficulty of MRI image annotation. However, the existing semi-automatic annotation algorithms based on deep learning have poor pre-annotation performance in the case of insufficient segmentation labels. In this paper, we propose a semi-automatic MRI annotation algorithm based on semi-weakly supervised learning. In order to achieve a better pre-annotation performance in the case of insufficient segmentation labels, semi-supervised and weakly supervised learning were introduced, and a semi-weakly supervised learning segmentation algorithm based on sparse labels was proposed. In addition, in order to improve the contribution rate of a single segmentation label to the performance of the pre-annotation model, an iterative annotation strategy based on active learning was designed. The experimental results on public MRI datasets show that the proposed algorithm achieved an equivalent pre-annotation performance when the number of segmentation labels was much less than that of the fully supervised learning algorithm, which proves the effectiveness of the proposed algorithm.

Unveiling interactions between intervertebral disc morphologies and mechanical behavior through personalized finite element modeling.

Introduction: Intervertebral Disc (IVD) Degeneration (IDD) is a significant health concern, potentially influenced by mechanotransduction. However, the relationship between the IVD phenotypes and mechanical behavior has not been thoroughly explored in local morphologies where IDD originates. This work unveils the interplays among morphological and mechanical features potentially relevant to IDD through Abaqus UMAT simulations. Methods: A groundbreaking automated method is introduced to transform a calibrated, structured IVD finite element (FE) model into 169 patient-personalized (PP) models through a mesh morphing process. Our approach accurately replicates the real shapes of the patient's Annulus Fibrosus (AF) and Nucleus Pulposus (NP) while maintaining the same topology for all models. Using segmented magnetic resonance images from the former project MySpine, 169 models with structured hexahedral meshes were created employing the Bayesian Coherent Point Drift++ technique, generating a unique cohort of PP FE models under the Disc4All initiative. Machine learning methods, including Linear Regression, Support Vector Regression, and eXtreme Gradient Boosting Regression, were used to explore correlations between IVD morphology and mechanics. Results: We achieved PP models with AF and NP similarity scores of 92.06\% and 92.10\% compared to the segmented images. The models maintained good quality and integrity of the mesh. The cartilage endplate (CEP) shape was represented at the IVD-vertebra interfaces, ensuring personalized meshes. Validation of the constitutive model against literature data showed a minor relative error of 5.20%. Discussion: Analysis revealed the influential impact of local morphologies on indirect mechanotransduction responses, highlighting the roles of heights, sagittal areas, and volumes. While the maximum principal stress was influenced by morphologies such as heights, the disc's ellipticity influenced the minimum principal stress. Results suggest the CEPs are not influenced by their local morphologies but by those of the AF and NP. The generated free-access repository of individual disc characteristics is anticipated to be a valuable resource for the scientific community with a broad application spectrum.

Deep learning automatic semantic segmentation of glioblastoma multiforme regions on multimodal magnetic resonance images.

In patients having naïve glioblastoma multiforme (GBM), this study aims to assess the efficacy of Deep Learning algorithms in automating the segmentation of brain magnetic resonance (MR) images to accurately determine 3D masks for 4 distinct regions: enhanced tumor, peritumoral edema, non-enhanced/necrotic tumor, and total tumor. A 3D U-Net neural network algorithm was developed for semantic segmentation of GBM. The training dataset was manually delineated by a group of expert neuroradiologists on MR images from the Brain Tumor Segmentation Challenge 2021 (BraTS2021) image repository, as ground truth labels for diverse glioma (GBM and low-grade glioma) subregions across four MR sequences (T1w, T1w-contrast enhanced, T2w, and FLAIR) in 1251 patients. The in-house test was performed on 50GBM patients from our cohort (PerProGlio project). By exploring various hyperparameters, the network's performance was optimized, and the most optimal parameter configuration was identified. The assessment of the optimized network's performance utilized Dice scores, precision, and sensitivity metrics. Our adaptation of the 3D U-net with additional residual blocks demonstrated reliable performance on both the BraTS2021 dataset and the in-house PerProGlio cohort, employing only T1w-ce sequences for enhancement and non-enhanced/necrotic tumor models and T1w-ce + T2w + FLAIR for peritumoral edema and total tumor. The mean Dice scores (training and test) were 0.89 and 0.75; 0.75 and 0.64; 0.79 and 0.71; and 0.60 and 0.55, for total tumor, edema, enhanced tumor, and non-enhanced/necrotic tumor, respectively. The results underscore the high precision with which our network can effectively segment GBM tumors and their distinct subregions. The level of accuracy achieved agrees with the coefficients recorded in previous GBM studies. In particular, our approach allows model specialization for each of the different tumor subregions employing only those MR sequences that provide value for segmentation.

Development of a software system for surgical robots based on multimodal image fusion: study protocol.

Surgical robots are gaining increasing popularity because of their capability to improve the precision of pedicle screw placement. However, current surgical robots rely on unimodal computed tomography (CT) images as baseline images, limiting their visualization to vertebral bone structures and excluding soft tissue structures such as intervertebral discs and nerves. This inherent limitation significantly restricts the applicability of surgical robots. To address this issue and further enhance the safety and accuracy of robot-assisted pedicle screw placement, this study will develop a software system for surgical robots based on multimodal image fusion. Such a system can extend the application range of surgical robots, such as surgical channel establishment, nerve decompression, and other related operations. Initially, imaging data of the patients included in the study are collected. Professional workstations are employed to establish, train, validate, and optimize algorithms for vertebral bone segmentation in CT and magnetic resonance (MR) images, intervertebral disc segmentation in MR images, nerve segmentation in MR images, and registration fusion of CT and MR images. Subsequently, a spine application model containing independent modules for vertebrae, intervertebral discs, and nerves is constructed, and a software system for surgical robots based on multimodal image fusion is designed. Finally, the software system is clinically validated. We will develop a software system based on multimodal image fusion for surgical robots, which can be applied to surgical access establishment, nerve decompression, and other operations not only for robot-assisted nail placement. The development of this software system is important. First, it can improve the accuracy of pedicle screw placement, percutaneous vertebroplasty, percutaneous kyphoplasty, and other surgeries. Second, it can reduce the number of fluoroscopies, shorten the operation time, and reduce surgical complications. In addition, it would be helpful to expand the application range of surgical robots by providing key imaging data for surgical robots to realize surgical channel establishment, nerve decompression, and other operations.

Automatic segmentation of MRI in prospective breast volume evaluation: Comparison of different assessments for immediate breast reconstruction

Assessment of breast volume is essential in preoperative planning of immediate breast reconstruction (IBR) surgery to achieve satisfactory cosmetic outcome. This study introduced a breast volume measurement tool that can be used to perform automatic segmentation of magnetic resonance images (MRI) and calculation of breast volume. We compared the accuracy and reliability of this measurement method with four other conventional modalities. Patients who were scheduled to undergo mastectomy with IBR between 2016 and 2021 were enrolled in the study. Five different breast volume assessments, including automatic segmentation of MRI, manual segmentation of MRI, 3D surface imaging, mammography, and the BREAST-V formula, were used to evaluate different breast volumes. The results were validated using water displacement volumes of the mastectomy specimens. In this pilot study, a total of 50 female patients met the inclusion criteria and contributed 54 breast specimens to the volumetric analysis. There was a strong linear association between the MRI and water displacement methods (automatic segmentation: r=0.911, p<0.001; manual segmentation: r=0.924, p<0.001), followed by 3D surface imaging (r=0.858, p<0.001), mammography (r=0.841, p<0.001), and Breast-V formula (r=0.838, p<0.001). Breast volumes measured using automatic and manual segmentation of MRI had lower mean relative errors (30.3%±22.0% and 28.9%±19.8, respectively) than 3D surface imaging (38.9%±31.2), Breast-V formula (44.8%±25.8), and mammography (60.3%±37.6). Breast volume assessment using the MRI methods had better accuracy and reliability than the other methods used in our study. Breast volume measurement using automatic segmentation of MRI could be more efficient compared to the conventional methods.

Positional contrastive learning for improved thigh muscle segmentation in MR images.

The accurate segmentation of individual muscles is essential for quantitative MRI analysis of thigh images. Deep learning methods have achieved state-of-the-art results in segmentation, but they require large numbers of labeled data to perform well. However, labeling individual thigh muscles slice by slice for numerous volumes is a laborious and time-consuming task, which limits the availability of annotated datasets. To address this challenge, self-supervised learning (SSL) emerges as a promising technique to enhance model performance by pretraining the model on unlabeled data. A recent approach, called positional contrastive learning, exploits the information given by the axial position of the slices to learn features transferable on the segmentation task. The aim of this work was to propose positional contrastive SSL for the segmentation of individual thigh muscles from MRI acquisitions in a population of elderly healthy subjects and to evaluate it on different levels of limited annotated data. An unlabeled dataset of 72 T1w MRI thigh acquisitions was available for SSL pretraining, while a labeled dataset of 52 volumes was employed for the final segmentation task, split into training and test sets. The effectiveness of SSL pretraining to fine-tune a U-Net architecture for thigh muscle segmentation was compared with that of a randomly initialized model (RND), considering an increasing number of annotated volumes (S= 1, 2, 5, 10, 20, 30, 40). Our results demonstrated that SSL yields substantial improvements in Dice similarity coefficient (DSC) when using a very limited number of labeled volumes (e.g., for = 1, DSC 0.631 versus 0.530 for SSL and RND, respectively). Moreover, enhancements are achievable even when utilizing the full number of labeled subjects, with DSC = 0.927 for SSL and 0.924 for RND. In conclusion, positional contrastive SSL was effective in obtaining more accurate thigh muscle segmentation, even with a very low number of labeled data, with a potential impact of speeding up the annotation process in clinics.

Microscope-Based Augmented Reality: A New Approach in Intraoperative 3D Visualization in Microvascular Decompression?

Neurovascular compression (NVC) syndromes such as trigeminal neuralgia (TN) are causally treated with microvascular decompression (MVD). Semiautomatic segmentation of high-resolution magnetic resonance imaging (MRI) data and constructive interference in steady state (CISS)/time-of-flight (TOF) sequences are utilized for the three-dimensional (3D) visualization of underlying causative vessels at the root entry zones of the relevant cranial nerves. Augmented reality (AR) of neurovascular structures was introduced especially in the resection of brain tumors or aneurysmatic operations. In this report, the potential feasibility of the implementation of microscope-based AR into the intraoperative microsurgical set-up of MVD was investigated. This article recommends the preoperative evaluation of 3D visualization besides the microscopical view of the surgeon. The implementation of multiple imaging data by AR into the operating microscope may afflict the experienced surgeon's view, which should be examined prospectively.

Evaluating the Efficacy of the 3D U-Net Architecture For Glioblastoma Multiforme Tumor Segmentation

Glioblastoma is the deadliest form of brain cancer which begins as a congregation of cancerous cells within the brain but then progresses into invading and destroying healthy brain tissue. Radiation therapy, the most popular treatment option, is where neuro-oncologists apply intense radiation energy beams directly on the tumor region to kill the cancerous cells. However, for radiation therapy to be effective, the segmented magnetic resonance image (MRI) in which the oncologists base where to apply the radiation must be segmented nearly 100% accurately, or else the energy beams will mistakenly damage healthy brain tissue. Additionally, radiation therapy will be futile if the MRI segmentation is not complete in time for the therapy appointment. My research problem is evaluating the performance of notable segmentation models for accurate and immediate 3D segmentation of glioblastoma multiforme brain tumors from MRIs while focusing on one particular architecture, the 3D U-Net. Each of the models was given 850 MRIs from the same dataset called BraTS, which is an annual competition hosted by the University of Pennsylvania. My 3D U-Net model ended up having the highest training (0.9928), validation (0.968) and testing (0.9867) accuracies of all the models and took approximately 55 seconds to predict segmentations of the tumor region. The results reveal that the 3D U-Net model is capable of automating glioblastoma tumor segmentation in significantly fewer hours than a human oncologist would take, all while maintaining similar or higher accuracy, where even a minor difference can mean the distinction between life and death.

CBAR-UNet: A novel methodology for segmentation of cardiac magnetic resonance images using block attention-based deep residual neural network

CBAR-UNet: A novel methodology for segmentation of cardiac magnetic resonance images using block attention-based deep residual neural network

Deep Learning for Nasopharyngeal Carcinoma Segmentation in Magnetic Resonance Imaging: A Systematic Review and Meta-Analysis

Nasopharyngeal carcinoma is a significant health challenge that is particularly prevalent in Southeast Asia and North Africa. MRI is the preferred diagnostic tool for NPC due to its superior soft tissue contrast. The accurate segmentation of NPC in MRI is crucial for effective treatment planning and prognosis. We conducted a search across PubMed, Embase, and Web of Science from inception up to 20 March 2024, adhering to the PRISMA 2020 guidelines. Eligibility criteria focused on studies utilizing DL for NPC segmentation in adults via MRI. Data extraction and meta-analysis were conducted to evaluate the performance of DL models, primarily measured by Dice scores. We assessed methodological quality using the CLAIM and QUADAS-2 tools, and statistical analysis was performed using random effects models. The analysis incorporated 17 studies, demonstrating a pooled Dice score of 78% for DL models (95% confidence interval: 74% to 83%), indicating a moderate to high segmentation accuracy by DL models. Significant heterogeneity and publication bias were observed among the included studies. Our findings reveal that DL models, particularly convolutional neural networks, offer moderately accurate NPC segmentation in MRI. This advancement holds the potential for enhancing NPC management, necessitating further research toward integration into clinical practice.

Automated Scoring of Alzheimer's Disease Atrophy Scale with Subtype Classification Using Deep Learning-Based T1-Weighted Magnetic Resonance Image Segmentation.

Application of visual scoring scales for regional atrophy in Alzheimer's disease (AD) in clinical settings is limited by their high time cost and low intra/inter-rater agreement. To provide automated atrophy scoring using objective volume driven from deep-learning segmentation methods for AD subtype classification using magnetic resonance imaging (MRI). We enrolled 3,959 participants (1,732 cognitively normal [CN], 1594 with mild cognitive impairment [MCI], and 633 with AD). The occupancy indices for each regional volume were calculated by dividing each volume by the size of the lateral and inferior ventricular volumes. MR images from 355 participants (119 CN, 119 MCI, and 117 AD) from three different centers were used for validation. Two neuroradiologists performed visual assessments of the medial temporal, posterior, and global cortical atrophy scores in the frontal lobe using T1-weighted MR images. Images were also analyzed using the deep learning-based segmentation software, Neurophet AQUA. Cutoff values for the three scores were determined using the data distribution according to age. The scoring results were compared for consistency and reliability. Four volumetric-driven scoring results showed a high correlation with the visual scoring results for AD, MCI, and CN. The overall agreement with human raters was weak-to-moderate for atrophy scoring in CN participants, and good-to-almost perfect in AD and MCI participants. AD subtyping by automated scores also showed usefulness as a research tool. Determining AD subtypes using automated atrophy scoring for late-MCI and AD could be useful in clinical settings or multicenter studies with large datasets.

SARFNet: Selective Layer and Axial Receptive Field Network for Multimodal Brain Tumor Segmentation

Efficient magnetic resonance imaging (MRI) segmentation, which is helpful for treatment planning, is essential for identifying brain tumors from detailed images. In recent years, various convolutional neural network (CNN) structures have been introduced for brain tumor segmentation tasks and have performed well. However, the downsampling blocks of most existing methods are typically used only for processing the variation in image sizes and lack sufficient capacity for further extraction features. We, therefore, propose SARFNet, a method based on UNet architecture, which consists of the proposed SLiRF module and advanced AAM module. The SLiRF downsampling module can extract feature information and prevent the loss of important information while reducing the image size. The AAM block, incorporated into the bottleneck layer, captures more contextual information. The Channel Attention Module (CAM) is introduced into skip connections to enhance the connections between channel features to improve accuracy and produce better feature expression. Ultimately, deep supervision is utilized in the decoder layer to avoid vanishing gradients and generate better feature representations. Many experiments were performed to validate the effectiveness of our model on the BraTS2018 dataset. SARFNet achieved Dice coefficient scores of 90.40, 85.54, and 82.15 for the whole tumor (WT), tumor core (TC), and enhancing tumor (ET), respectively. The results show that the proposed model achieves state-of-the-art performance compared with twelve or more benchmarks.

Magnetic Resonance Images Segmentation of Multifidus based on Dense-unet and Superpixel.

Lumbar disc herniation (LDH) is a common clinical condition causing lower back and leg pain. Accurate segmentation of the lumbar discs is crucial for assessing and diagnosing LDH. Magnetic resonance imaging (MRI) can reveal the condition of articular cartilage. However, manual segmentation of MRI images is burdensome for physicians and needs to be more efficient. In this study, we propose a method that combines UNet and superpixel segmentation to address the problem of loss of detailed information in the feature extraction phase, leading to poor segmentation results at object edges. The aim is to provide a reproducible solution for diagnosing patients with lumbar disc herniation. We suggest using the network structure of UNet. Firstly, dense blocks are inserted into the UNet network, and training is performed using the Swish activation function. The Dense-UNet model extracts semantic features from the images and obtains rough semantic segmentation results. Then, an adaptive-scale superpixel segmentation algorithm is applied to segment the input images into superpixel images. Finally, high-level abstract semantic features are fused with the detailed information of the superpixels to obtain edge-optimized semantic segmentation results. Evaluation of a private dataset of multifidus muscles in magnetic resonance images demonstrates that compared to other segmentation algorithms, this algorithm exhibits better semantic segmentation performance in detailed areas such as object edges. Compared to UNet, it achieves a 9.5% improvement in the Dice Similarity Coefficient (DSC) and an 11.3% improvement in the Jaccard Index (JAC). The experimental results indicate that this algorithm improves segmentation performance while reducing computational complexity.