Segmentation Of Intervertebral Discs Research Articles

Cervical Intervertebral Disc Segmentation Based on Multi-Scale Information Fusion and Its Application

The cervical intervertebral disc, a cushion-like element between the vertebrae, plays a critical role in spinal health. Investigating how to segment these discs is crucial for identifying abnormalities in cervical conditions. This paper introduces a novel approach for segmenting cervical intervertebral discs, utilizing a framework based on multi-scale information fusion. Central to this approach is the integration of multi-level features, both low and high, through an encoding–decoding process, combined with multi-scale semantic fusion, to progressively refine the extraction of segmentation characteristics. The multi-scale semantic fusion aspect of this framework is divided into two phases: one leveraging convolution for scale interaction and the other utilizing pooling. This dual-phase method markedly improves segmentation accuracy. Facing a shortage of datasets for cervical disc segmentation, we have developed a new dataset tailored for this purpose, which includes interpolation between layers to resolve disparities in pixel spacing along the longitudinal and transverse axes in CT image sequences. This dataset is good for advancing cervical disc segmentation studies. Our experimental findings demonstrate that our network model not only achieves good segmentation accuracy on human cervical intervertebral discs but is also highly effective for three-dimensional reconstruction and printing applications. The dataset will be publicly available soon.

Accurate Intervertebral Disc Segmentation Approach Based on Deep Learning.

Automatically segmenting specific tissues or structures from medical images is a straightforward task for deep learning models. However, identifying a few specific objects from a group of similar targets can be a challenging task. This study focuses on the segmentation of certain specific intervertebral discs from lateral spine images acquired from an MRI scanner. In this research, an approach is proposed that utilizes MultiResUNet models and employs saliency maps for target intervertebral disc segmentation. First, a sub-image cropping method is used to separate the target discs. This method uses MultiResUNet to predict the saliency maps of target discs and crop sub-images for easier segmentation. Then, MultiResUNet is used to segment the target discs in these sub-images. The distance maps of the segmented discs are then calculated and combined with their original image for data augmentation to predict the remaining target discs. The training set and test set use 2674 and 308 MRI images, respectively. Experimental results demonstrate that the proposed method significantly enhances segmentation accuracy to about 98%. The performance of this approach highlights its effectiveness in segmenting specific intervertebral discs from closely similar discs.

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.

An effective U-Net and BiSeNet complementary network for spine segmentation

Spine segmentation with MRI plays an important role in the diagnosis and treatment of various spinal diseases, especially for multi-class segmentation of different vertebrae and intervertebral discs. However, due to the similarity between classes and differences within classes of spinal images, it is still a challenge to realize accurate multi-class fusion segmentation of different vertebrae and intervertebral discs. In this paper, we propose an effective U-Net and BiSeNet complementary network for spine segmentation to fully exploit their advantages in feature extraction. The network consists of a residual U-Net, a spatial feature extractor, and a feature fusion extractor. The residual U-Net selects the U-Net framework based on ResNet34, aiming at fully extracting the features of vertebrae and intervertebral discs in MRI. The spatial feature extractor takes the strip pooling (SP) blocks to replace the spatial extraction path in BiSeNet network, aiming at capturing long-range relations among the vertebrae and intervertebral discs and the interconnections of same class. The feature fusion extractor adopts the attention refinement modules (ARM) to aggregate the features from the residual U-Net and the spatial feature extractor, aiming at guiding the network to learn the distinguishing features between vertebrae and intervertebral discs by attention mechanism and making full use of the complementary features of the two paths. Experiments on MRI of 172 subjects show that our proposed network achieves impressive performance with mean Dice similarity coefficients of 82.802 % in all spinal structures. The proposed method has great value in the diagnosis and treatment of spinal diseases.

Automatic generation of subject-specific finite element models of the spine from magnetic resonance images.

The generation of subject-specific finite element models of the spine is generally a time-consuming process based on computed tomography (CT) images, where scanning exposes subjects to harmful radiation. In this study, a method is presented for the automatic generation of spine finite element models using images from a single magnetic resonance (MR) sequence. The thoracic and lumbar spine of eight adult volunteers was imaged using a 3D multi-echo-gradient-echo sagittal MR sequence. A deep-learning method was used to generate synthetic CT images from the MR images. A pre-trained deep-learning network was used for the automatic segmentation of vertebrae from the synthetic CT images. Another deep-learning network was trained for the automatic segmentation of intervertebral discs from the MR images. The automatic segmentations were validated against manual segmentations for two subjects, one with scoliosis, and another with a spine implant. A template mesh of the spine was registered to the segmentations in three steps using a Bayesian coherent point drift algorithm. First, rigid registration was applied on the complete spine. Second, non-rigid registration was used for the individual discs and vertebrae. Third, the complete spine was non-rigidly registered to the individually registered discs and vertebrae. Comparison of the automatic and manual segmentations led to dice-scores of 0.93-0.96 for all vertebrae and discs. The lowest dice-score was in the disc at the height of the implant where artifacts led to under-segmentation. The mean distance between the morphed meshes and the segmentations was below 1mm. In conclusion, the presented method can be used to automatically generate accurate subject-specific spine models.

MAS-Net:Multi-modal Assistant Segmentation Network For Lumbar Intervertebral Disc.

Objective.Despite advancements in medical imaging technology, the diagnosis and positioning of lumbar disc diseases still heavily rely on the expertise and experience of medical professionals. This process is often time-consuming, labor-intensive, and susceptible to subjective factors. Achieving automatic positioning and segmentation of lumbar intervertebral disc (LID) is the first and critical step in intelligent diagnosis of lumbar disc diseases. However, due to the complexity of the vertebral body and the ambiguity of the soft tissue boundaries of the LID, accurate and intelligent segmentation of LIDs remains challenging. The study aims to accurately and intelligently segment and locate LIDs by fully utilizing multi-modal lumbar magnetic resonance Images (MRIs).Approach.A novel multi-modal assistant segmentation network (MAS-Net) is proposed in this paper. The architecture consists of four key components: the multi-branch fusion encoder (MBFE), the cross-modality correlation evaluation (CMCE), the channel fusion transformer (CFT), and the selective Kernel (SK) based decoder. The MBFE module captures and integrates various modal features, while the CMCE module facilitates the fusion process between the MBFE and decoder. The CFT module selectively guides the flow of information between the MBFE and decoder and effectively utilizes skip connections from multiple layers. The SK module computes the significance of each channel using global pooling operations and applies weights to the input feature maps to improve the models recognition of important features.Main results.The proposed MAS-Net achieved a dice coefficient of 93.08% on IVD3Seg and 93.22% on DualModalDisc dataset, outperforming the current state-of-the-art network, accurately segmenting the LIDs, and generating a 3D model that can precisely display the LIDs.Significance.MAS-Net automates the diagnostics process and addresses challenges faced by doctors. Simplifying and enhancing the clarity of visual representation, multi-modal MRI allows for better information complementation and LIDs segmentation. By successfully integrating data from various modalities, the accuracy of LID segmentation is improved.

MLP-Res-Unet：MLPs and residual blocks-based U-shaped network intervertebral disc segmentation of multi-modal MR spine images.

Intervertebral disc degeneration (IVD) is now the most prevalent disease in the world; thus, precise intervertebral disc segmentation is essential for the assessment and diagnosis of spinal diseases. Multi-modal magnetic resonance (MR) imaging is more multi-dimensional and thorough than unimodal imaging. However, manual segmentation of multi-modal MRI not only imposes a huge burden on physicians but also has a high error rate. In this study, we propose a new method that can efficiently and accurately segment intervertebral discs from multi-modal MR spine images, providing a reproducible usage scheme for the diagnosis of spinal disorders. We suggest a network structure called MLP-Res-Unet that reduces the amount of computational load and the number of parameters while maintaining performance. Our contribution is two-fold. First, a medical image segmentation network that fuses residual blocks and a multilayer perceptron (MLP) is proposed. Secondly, we design a new deep supervised method and pass the features extracted from the encoder to the decoder through the residual path to achieve a new full-scale residual connection. We evaluate the network on the MICCAI-2018 IVD dataset and obtain Dice similarity coefficient equal to 94.77 (%) and Jaccard coefficient equal to 84.74 (%), while we reduce the amount of parameters by a factor of 3.9 and computation by a factor of 2.4 compared to the IVD-Net. Experiments show that MLP-Res-Unet improves segmentation performance and creates a simpler model structure while reducing the number of parameters and computation.

Segmentation and classification of intervertebral disc using capsule stacked autoencoder

Accurate location and segmentation of IVD (intervertebral disc) are important for detecting spinal cord diseases. Despite tremendous advances in medical imaging, IVD localization and segmentation remains a hot research topic. The spine is exposed to various kinds of compression forces, which seriously causes the function of the disc and causes disorders like disc bulging and herniation. This work uses CAD (computer aided design) for IVD localization and segmentation using axial MRI images of the spine. DL (deep learning) models ensure speed and accuracy in diagnosing the process and classifying the spine problem. Hence, this work employs a DL based IVD localization and segmentation. Initially, the image is resized and enhanced by AHE (Adaptive Histogram equalization). Then, the Mask-Region-based Convolutional Neural Network (Mask R-CNN) is used to localize IVD. After localizing, the SegNet (semantic segmentation network) model efficiently carries out disc segmentation. Then the weights of SegNet are optimally fine-tuned by the adaptive rain optimization algorithm (AROA). Finally, the DL model capsule stacked autoencoder (CSAE) is used for classifying the types of diseases in IVD. The overall implementation in the Python platform and analysis in the benchmark dataset Lumbar Spine MRI achieved better accuracy and precision of 98.5% and 97.8%, respectively.

SSCK-Net: Spine segmentation in MRI based on cross attention and key-points recognition-assisted learner

Multiple spine segmentation of vertebrae and intervertebral discs for magnetic resonance images (MRI) plays a significant role in various spinal diseases diagnosis and treatments of spine disorder. However, the inherent complexity and characteristics of the spine pose challenges in balancing the inter-class similarity and intra-class variety of spine, improving generalization ability, learning rate, and accuracy. To address the above issues, a spine segmentation in MRI based on cross attention and key-points recognition-assisted learner (SSCK-Net) is proposed. Firstly, a multi-channel cross attention (MCCA) mechanism is put forward to generate a comprehensive description of the spine by fusing complementary inter-class feature and intra-class feature. Secondly, a key-points recognition-assisted learner (KRAL) is designed, which includes mixed-supervision recognition-assisted label fusion (RALF), to reduce dependence on a single dataset and improve the generalization ability of the network. Subsequently, adaptive transformer (AT) is presented to perform parallel computation through selective kernel fusion, nonlinear activation function with simple inverse and rescaling layer normalization, which reduces training time and prevents performance degradation due to long-term dependence. Finally, a feature enhances unit (FEU) is proposed to fuse the key point features and the segmented features while constraining the key-point features to the fused features again by the refine unit. Our experiments on T2-weighted volumetric MRI show that SSCK-Net achieves impressive performance with a mean Dice similarity coefficient (DSC) 96.12% for 5 vertebral bodies and 95.07% for 5 intervertebral discs on public datasets, outperforming state-of-the-art techniques.

Semi-supervised hybrid spine network for segmentation of spine MR images.

Automatic segmentation of vertebral bodies (VBs) and intervertebral discs (IVDs) in 3D magnetic resonance (MR) images is vital in diagnosing and treating spinal diseases. However, segmenting the VBs and IVDs simultaneously is not trivial. Moreover, problems exist, including blurry segmentation caused by anisotropy resolution, high computational cost, inter-class similarity and intra-class variability, and data imbalances. We proposed a two-stage algorithm, named semi-supervised hybrid spine network (SSHSNet), to address these problems by achieving accurate simultaneous VB and IVD segmentation. In the first stage, we constructed a 2D semi-supervised DeepLabv3+ by using cross pseudo supervision to obtain intra-slice features and coarse segmentation. In the second stage, a 3D full-resolution patch-based DeepLabv3+ was built. This model can be used to extract inter-slice information and combine the coarse segmentation and intra-slice features provided from the first stage. Moreover, a cross tri-attention module was applied to compensate for the loss of inter-slice and intra-slice information separately generated from 2D and 3D networks, thereby improving feature representation ability and achieving satisfactory segmentation results. The proposed SSHSNet was validated on a publicly available spine MR image dataset, and remarkable segmentation performance was achieved. Moreover, results show that the proposed method has great potential in dealing with the data imbalance problem. Based on previous reports, few studies have incorporated a semi-supervised learning strategy with a cross attention mechanism for spine segmentation. Therefore, the proposed method may provide a useful tool for spine segmentation and aid clinically in spinal disease diagnoses and treatments. Codes are publicly available at: https://github.com/Meiyan88/SSHSNet.

ICUnet++: an Inception-CBAM network based on Unet++ for MR spine image segmentation.

In recent years, more attention paid to the spine caused by related diseases, spinal parsing (the multi-class segmentation of vertebrae and intervertebral disc) is an important part of the diagnosis and treatment of various spinal diseases. The more accurate the segmentation of medical images, the more convenient and quick the clinicians can evaluate and diagnose spinal diseases. Traditional medical image segmentation is often time consuming and energy consuming. In this paper, an efficient and novel automatic segmentation network model for MR spine images is designed. The proposed Inception-CBAM Unet++ (ICUnet++) model replaces the initial module with the Inception structure in the encoder-decoder stage base on Unet++ , which uses the parallel connection of multiple convolution kernels to obtain the features of different receptive fields during in the feature extraction. According to the characteristics of the attention mechanism, Attention Gate module and CBAM module are used in the network to make the attention coefficient highlight the characteristics of the local area. To evaluate the segmentation performance of network model, four evaluation metrics, namely intersection over union (IoU), dice similarity coefficient(DSC), true positive rate(TPR), positive predictive value(PPV) are used in the study. The published SpineSagT2Wdataset3 spinal MRI dataset is used during the experiments. In the experiment results, IoU reaches 83.16%, DSC is 90.32%, TPR is 90.40%, and PPV is 90.52%. It can be seen that the segmentation indicators have been significantly improved, which reflects the effectiveness of the model.

Lumbar intervertebral disc segmentation for computer modeling and simulation

Background and objectiveThe present work had as its main objective the development of a method for localizing and automatically segmenting lumbar intervertebral discs (IVD) in 3D from magnetic resonance imaging (MRI), with the goal of supporting the generation of finite element (FE) models from actual lumbar spine anatomy, by providing accurate and personalized information on the shape of the patient's IVD. The extension of the method to allow performing separate segmentations of the IVD's two main structures – annulus fibrosus (AF) and nucleus pulposus (NP) – as well as automatically detecting degenerated IVD where this distinction is no longer possible was also an objective of the work. MethodsThe method presented here evolves from 2D segmentations in the sagittal profile using Gabor filters towards 3D segmentations. It works by detecting the spine curves and intensity regions corresponding to IVD. As so, the 2D method from Zhu et al. (2013) was partially implemented, modified and adapted to 3D use, and then tested with eight spines from two separated online datasets. The 3D adaptation was achieved by using vertebral body segmentation masks to approximate the shape of the vertebrae and to adjust the spine curves accordingly. ResultsThe method showed average values of 85%, 83% and 96% for the Dice coefficient, sensitivity and specificity, respectively. The method correctly identified 65 of 68 (96%) IVD as either healthy or degenerated. The method's Dice coefficient is within the range of existing 3D IVD segmentation methods in the literature (81–92%). The method took on average 6–7 s to perform a full 3D segmentation, which is well within the range of the existing methods (2 s – 19 min). ConclusionsThe developed method can be used to generate accurate 3D models of the IVD based on MRI, with AF/NP distinction and detection of marked degeneration by comparing each IVD with the remaining spine levels. Further work shall improve the method towards distinguishing between specific levels of degeneration for clinically oriented FE modeling.

Grayscale self-adjusting network with weak feature enhancement for 3D lumbar anatomy segmentation.

The automatic segmentation of lumbar anatomy is a fundamental problem for the diagnosis and treatment of lumbar disease. The recent development of deep learning techniques has led to remarkable progress in this task, including the possible segmentation of nerve roots, intervertebral discs, and dural sac in a single step. Despite these advances, lumbar anatomy segmentation remains a challenging problem due to the weak contrast and noise of input images, as well as the variability of intensities and size in lumbar structures across different subjects. To overcome these challenges, we propose a coarse-to-fine deep neural network framework for lumbar anatomy segmentation, which obtains a more accurate segmentation using two strategies. First, a progressive refinement process is employed to correct low-confidence regions by enhancing the feature representation in these regions. Second, a grayscale self-adjusting network (GSA-Net) is proposed to optimize the distribution of intensities dynamically. Experiments on datasets comprised of 3D computed tomography (CT) and magnetic resonance (MR) images show the advantage of our method over current segmentation approaches and its potential for diagnosing and lumbar disease treatment.

Residual-atrous attention network for lumbosacral plexus segmentation with MR image

Accurate segmentation of the lumbosacral plexus is a crucial step for diagnosis and analysis of nerve damage in clinical. Due to the extremely low contrast and complicated structure around the lumbosacral plexus, it has been remaining a challenging task to effectively segment the lumbosacral plexus from spinal MR images. Even though several deep learning methods for spine segmentation have been developed, most of them only pay attention to the segmentation of vertebral bodies and intervertebral discs rather than nerves. To solve these problems, in this paper, we propose a residual-atrous attention network (RA2-Net) for lumbosacral plexus segmentation with MR images. Specifically, the RA2-Net consists of three main parts, (1) the atrous encoder module is employed to learn multi-scale contextual features from MR images in the encoder, (2) the residual skip connection operation is used to integrate the features with high-resolution spatial details in the encoder and the high-level contextual features in the decoder, and (3) the scale attention block is proposed for fusing the multi-scale high-level features in the decoder. We perform our proposed RA2-Net for the lumbosacral plexus segmentation on the collected spinal MRI dataset with 10 patients (a total of 236 MRI scans). Extensive experiments demonstrate that our RA2-Net achieves better performance in lumbosacral plexus segmentation with MR images when compared with several state-of-the-art methods.

Spine Segmentation with Multi-view GCN and Boundary Constraint.

Multi-class segmentation of vertebrae and inter-vertebral discs (IVDs) is crucial for the diagnosis and treatment of spinal diseases. However, it is still a challenge due to similarities between neighboring vertebrae of a subject and differences among the IVDs from different subjects. In this paper, we propose a novel spine segmentation framework to achieve automatic segmentation of vertebrae and IVDs in MR images. The core component of the new framework is a Multi-View GCN (MVGCN), which utilizes multi-view features and graph convolutional network (GCN) to reason about the relations of vertebrae and IVDs. We additionally use a boundary constraint for better segmentation of the boundary between vertebrae and IVDs. We test our method on a public spine dataset of 172 MR volumetric images for the vertebrae and IVDs segmentation. The experimental results demonstrate the efficacy of our method. Code and models of our method will be available in the future.

Multi-scanner and multi-modal lumbar vertebral body and intervertebral disc segmentation database

Magnetic resonance imaging (MRI) is widely utilized for diagnosing and monitoring of spinal disorders. For a number of applications, particularly those related to quantitative MRI, an essential step towards achieving reliable and objective measurements is the segmentation of the examined structures. Performed manually, such process is time-consuming and prone to errors, posing a bottleneck to its clinical applicability. A more efficient analysis would be achieved by automating a segmentation process. However, routine spine MRI acquisitions pose several challenges for achieving robust and accurate segmentations, due to varying MRI acquisition characteristics occurring in data acquired from different sites. Moreover, heterogeneous annotated datasets, collected from multiple scanners with different pulse sequence protocols, are limited. Thus, we present a manually segmented lumbar spine MRI database containing a wide range of data obtained from multiple scanners and pulse sequences, with segmentations of lumbar vertebral bodies and intervertebral discs. The database is intended for the use in developing and testing of automated lumbar spine segmentation algorithms in multi-domain scenarios.

Automatic semantic segmentation and detection of vertebras and intervertebral discs by neural networks

Objective: To realize a tool for automatic segmentation and detection of lumbar disc degenerative disease and fractures in MRI images using convolutional neural networks. Material and methods: We developed, on one hand, a Picture Archiving and Communication System (PACS) with a DICOM viewer (Digital Imaging and Communications in Medicine) to extract training data and implement 2 CNN networks dedicated to the segmentation task and on the other hand, the analysis of simple lumbar pathologies on the other hand.Two hundred forty-four MRI scans T2 weighted sagittal were selected at the university hospital Pasteur 2 of Nice - France.After accomplishing segmentation and classification task for all structures of interest, we trained two neural networks (U-Net++ and Yolov5x) to segment and detect discs and vertebras. Results: Neural networks allowed semantic segmentations with a good accuracy of the order of 0.96 and 0.93 DICE index for intervertebral discs and vertebral bodies respectively.They are less effective in detecting of common pathologies (degenerative disc disease, disc herniation, vertebral fractures) with an area under the precision-recall curve of 0.88 for fractures and 0.76 for degenerative disc disease. Conclusion: Our work has shown good efficiency for the segmentation of vertebral bodies and intervertebral discs, but progress remains to be made in the detection of degenerative discopathy and vertebral fractures.On this last point, we believe that the lower performance can be attributed to a lack of training images and that better performances will be achieved with the increase of the training data set on our home made PACS. We will also provide other regions of interest and conditions.

Sagittal balance and intervertebral disc composition in patients with low back pain.

The aim of this study was to verify the relationship between quantitative T2 relaxation measurements of lumbar intervertebral discs (IVDs) and spinopelvic parameters in patients with chronic low back pain. The study was approved by the Clinical Hospital of the Ribeirao Preto Medical School (USP) Ethics Committee, and written consent was obtained from all patients. A total of 455 IVDs from 91 consecutive patients with chronic low back pain were included in this prospective study. All subjects were assessed using the Oswestry Disability Index and visual analogue scale questionnaires and were confirmed to have no other spine diseases except disc degeneration. Spinopelvic parameters including the pelvic incidence (PI), pelvic tilt (PT), sacral slope (SS), sagittal vertical axis (SVA), global tilt (GT), T1 pelvic angle (TPA), lumbar lordosis (LL), thoracic kyphosis (TK), pelvic incidence minus lumbar lordosis mismatch (PI-LL), and lack of lumbar lordosis (LLL) were measured. The study group was categorized according to the Roussouly classification. Sagittal T2 maps were acquired to extract the IVD relaxation times, and the complete manual segmentation of IVDs at all levels was performed using Display® software. Lumbar IVD T2 relaxation times showed significant correlation with PT (P<0.01), GT (P<0.01), TPA (P<0.01), PI-LL (P=0.01), and LLL (P=0.01). No difference was noted between Roussouly subtypes regarding T2 relaxation times at any disc level. Data from questionnaires showed no correlation with T2 relaxation times. Global tilt and T1 pelvic angle were correlated with IVD composition changes (T2 relaxometry). There was no correlation between clinical symptoms and IVD T2 relaxation times.

ECSU-Net: An Embedded Clustering Sliced U-Net Coupled With Fusing Strategy for Efficient Intervertebral Disc Segmentation and Classification.

Automatic vertebra segmentation from computed tomography (CT) image is the very first and a decisive stage in vertebra analysis for computer-based spinal diagnosis and therapy support system. However, automatic segmentation of vertebra remains challenging due to several reasons, including anatomic complexity of spine, unclear boundaries of the vertebrae associated with spongy and soft bones. Based on 2D U-Net, we have proposed an Embedded Clustering Sliced U-Net (ECSU-Net). ECSU-Net comprises of three modules named segmentation, intervertebral disc extraction (IDE) and fusion. The segmentation module follows an instance embedding clustering approach, where our three sliced sub-nets use axis of CT images to generate a coarse 2D segmentation along with embedding space with the same size of the input slices. Our IDE module is designed to classify vertebra and find the inter-space between two slices of segmented spine. Our fusion module takes the coarse segmentation (2D) and outputs the refined 3D results of vertebra. A novel adaptive discriminative loss (ADL) function is introduced to train the embedding space for clustering. In the fusion strategy, three modules are integrated via a learnable weight control component, which adaptively sets their contribution. We have evaluated classical and deep learning methods on Spineweb dataset-2. ECSU-Net has provided comparable performance to previous neural network based algorithms achieving the best segmentation dice score of 95.60% and classification accuracy of 96.20%, while taking less time and computation resources.

Automatic Segmentation of Specific Intervertebral Discs through a Two-Stage MultiResUNet Model.

The automatic segmentation of intervertebral discs from medical images is an important task for an intelligent clinical system. In this study, a deep learning model based on the MultiResUNet model for the automatic segmentation of specific intervertebral discs is presented. MultiResUNet can easily segment all intervertebral discs in MRI images; however, when only certain specific intervertebral discs need to be segmented, problems with segmentation errors, misalignment, and noise occur. In order to solve these problems, a two-stage MultiResUNet model is proposed. Connected-component labeling, automatic cropping, and distance transform are used in the proposed method. The experimental results show that the segmentation errors and misalignments of specific intervertebral discs are greatly reduced, and the segmentation accuracy is increased to about 94%. The performance of the proposed method proves its usefulness for the automatic segmentation of specific intervertebral discs over other deep learning models, such as the U-Net, CNN-based, Attention U-Net, and MultiResUNet models.