Three-Dimensional Lumbosacral Reconstruction by An Artificial Intelligence-Based Automated MR Image Segmentation for Selecting the Approach of Percutaneous Endoscopic Lumbar Discectomy.

BACKGROUND: Assessing the 3-dimensional (3D) relationship between critical anatomical structures and the surgical channel can help select percutaneous endoscopic lumbar discectomy (PELD) approaches, especially at the L5/S1 level. However, previous evaluation methods for PELD were mainly assessed using 2-dimensional (2D) medical images, making the understanding of the 3D relationship of lumbosacral structures difficult. Artificial intelligence based on automated magnetic resonance (MR) image segmentation has the benefit of 3D reconstruction of medical images. OBJECTIVES: We developed and validated an artificial intelligence-based MR image segmentation method for constructing a 3D model of lumbosacral structures for selecting the appropriate approach of percutaneous endoscopic lumbar discectomy at the L5/S1 level. STUDY DESIGN: Three-dimensional reconstruction study using artificial intelligence based on MR image segmentation. SETTING: Spine and radiology center of a university hospital. METHODS: Fifty MR data samples were used to develop an artificial intelligence algorithm for automatic segmentation. Manual segmentation and labeling of vertebrae bone (L5 and S1 vertebrae bone), disc, lumbosacral nerve, iliac bone, and skin at the L5/S1 level by 3 experts were used as ground truth. Five-fold cross-validation was performed, and quantitative segmentation metrics were used to evaluate the performance of artificial intelligence based on the MR image segmentation method. The comparison analysis of quantitative measurements between the artificial intelligence-derived 3D (AI-3D) models and the ground truth-derived 3D (GT-3D) models was used to validate the feasibility of 3D lumbosacral structures reconstruction and preoperative assessment of PELD approaches. RESULTS: Artificial intelligence-based automated MR image segmentation achieved high mean Dice Scores of 0.921, 0.924, 0.885, 0.808, 0.886, and 0.816 for L5 vertebrae bone, S1 vertebrae bone, disc, lumbosacral nerves, iliac bone, and skin, respectively. There were no significant differences between AI-3D and GT-3D models in quantitative measurements. Comparative analysis of quantitative measures showed a high correlation and consistency. LIMITATIONS: Our method did not involve vessel segmentation in automated MR image segmentation. Our study's sample size was small, and the findings need to be validated in a prospective study with a large sample size. CONCLUSION: We developed an artificial intelligence-based automated MR image segmentation method, which effectively segmented lumbosacral structures (e.g., L5 vertebrae bone, S1 vertebrae bone, disc, lumbosacral nerve, iliac bone, and skin) simultaneously on MR images, and could be used to construct a 3D model of lumbosacral structures for choosing an appropriate approach of PELD at the L5/S1 level.

Deep learning-based detection and classification of lumbar disc herniation on magnetic resonance images.

Background: The severity assessment of lumbar disc herniation (LDH) on MR images is crucial for selecting suitable surgical candidates. However, the interpretation of MR images is time-consuming and requires repetitive work. This study aims to develop and evaluate a deep learning-based diagnostic model for automated LDH detection and classification on lumbar axial T2-weighted MR images. Methods: A total of 1115 patients were analyzed in this retrospective study; both a development dataset (1015 patients, 15 249 images) and an external test dataset (100 patients, 1273 images) were utilized. According to the Michigan State University (MSU) classification criterion, experts labeled all images with consensus, and the final labeled results were regarded as the reference standard. The automated diagnostic model comprised Faster R-CNN and ResNeXt101 as the detection and classification network, respectively. The deep learning-based diagnostic performance was evaluated by calculating mean intersection over union (IoU), accuracy, precision, sensitivity, specificity, F1 score, the area under the receiver operating characteristics curve (AUC), and intraclass correlation coefficient (ICC) with 95% confidence intervals (CIs). Results: High detection consistency was obtained in the internal test dataset (mean IoU = 0.82, precision = 98.4%, sensitivity = 99.4%) and external test dataset (mean IoU = 0.70, precision = 96.3%, sensitivity = 97.8%). Overall accuracy for LDH classification was 87.70% (95% CI: 86.59%-88.86%) and 74.23% (95% CI: 71.83%-76.75%) in the internal and external test datasets, respectively. For internal testing, the proposed model achieved a high agreement in classification (ICC = 0.87, 95% CI: 0.86-0.88, P < 0.001), which was higher than that of external testing (ICC = 0.79, 95% CI: 0.76-0.81, P < 0.001). The AUC for model classification was 0.965 (95% CI: 0.962-0.968) and 0.916 (95% CI: 0.908-0.925) in the internal and external test datasets, respectively. Conclusions: The automated diagnostic model achieved high performance in detecting and classifying LDH and exhibited considerable consistency with experts' classification.

Deep Learning-Based Automated Magnetic Resonance Image Segmentation of the Lumbar Structure and Its Adjacent Structures at the L4/5 Level.

(1) Background: This study aims to develop a deep learning model based on a 3D Deeplab V3+ network to automatically segment multiple structures from magnetic resonance (MR) images at the L4/5 level. (2) Methods: After data preprocessing, the modified 3D Deeplab V3+ network of the deep learning model was used for the automatic segmentation of multiple structures from MR images at the L4/5 level. We performed five-fold cross-validation to evaluate the performance of the deep learning model. Subsequently, the Dice Similarity Coefficient (DSC), precision, and recall were also used to assess the deep learning model's performance. Pearson's correlation coefficient analysis and the Wilcoxon signed-rank test were employed to compare the morphometric measurements of 3D reconstruction models generated by manual and automatic segmentation. (3) Results: The deep learning model obtained an overall average DSC of 0.886, an average precision of 0.899, and an average recall of 0.881 on the test sets. Furthermore, all morphometry-related measurements of 3D reconstruction models revealed no significant difference between ground truth and automatic segmentation. Strong linear relationships and correlations were also obtained in the morphometry-related measurements of 3D reconstruction models between ground truth and automated segmentation. (4) Conclusions: We found it feasible to perform automated segmentation of multiple structures from MR images, which would facilitate lumbar surgical evaluation by establishing 3D reconstruction models at the L4/5 level.

SpineRegNet: Spine Registration Network for volumetric MR and CT image by the joint estimation of an affine-elastic deformation field.

Spine registration for volumetric magnetic resonance (MR) and computed tomography (CT) images plays a significant role in surgical planning and surgical navigation system for the radiofrequency ablation of spine intervertebral discs. The affine transformation of each vertebra and elastic deformation of the intervertebral disc exist at the same time. This situation is a major challenge in spine registration. Existing spinal image registration methods failed to solve the optimal affine-elastic deformation field (AEDF) simultaneously, only consider the overall rigid or elastic alignment with the help of a manual spine mask, and encounter difficulty in meeting the accuracy requirements of clinical registration application. In this study, we propose a novel affine-elastic registration framework named SpineRegNet. The SpineRegNet consists of a Multiple Affine Matrices Estimation (MAME) Module for multiple vertebrae alignment, an Affine-Elastic Fusion (AEF) Module for joint estimation of the overall AEDF, and a Local Rigidity Constraint (LRC) Module for preserving the rigidity of each vertebra. Experiments on T2-weighted volumetric MR and CT images show that the proposed approach achieves impressive performance with mean Dice similarity coefficients of 91.36%, 81.60%, and 83.08% for the mask of the vertebrae on Datasets A-C, respectively. The proposed technique does not require a mask or manual participation during the tests and provides a useful tool for clinical spinal disease surgical planning and surgical navigation systems.

Comprehensive assessment of osteoporosis in lumbar spine using compositional MR imaging of trabecular bone.

OBJECTIVES: To comprehensively assess osteoporosis in the lumbar spine, a compositional MR imaging technique is proposed to quantify proton fractions for all the water components as well as fat in lumbar vertebrae measured by a combination of a 3D short repetition time adiabatic inversion recovery prepared ultrashort echo time (STAIR-UTE) MRI and IDEAL-IQ. METHODS: A total of 182 participants underwent MRI, quantitative CT, and DXA. Lumbar collagen-bound water proton fraction (CBWPF), free water proton fraction (FWPF), total water proton fraction (TWPF), bone mineral density (BMD), and T-score were calculated in three vertebrae (L2-L4) for each subject. The correlations of the CBWPF, FWPF, and TWPF with BMD and T-score were investigated respectively. A comprehensive diagnostic model combining all the water components and clinical characteristics was established. The performances of all the water components and the comprehensive diagnostic model to discriminate between normal, osteopenia, and osteoporosis cohorts were also evaluated using receiver operator characteristic (ROC). RESULTS: The CBWPF showed strong correlations with BMD (r = 0.85, p < 0.001) and T-score (r = 0.72, p < 0.001), while the FWPF and TWPF showed moderate correlations with BMD (r = 0.65 and 0.68, p < 0.001) and T-score (r = 0.47 and 0.49, p < 0.001). The high area under the curve values obtained from ROC analysis demonstrated that CBWPF, FWPF, and TWPF have the potential to differentiate the normal, osteopenia, and osteoporosis cohorts. At the same time, the comprehensive diagnostic model shows the best performance. CONCLUSIONS: The compositional MRI technique, which quantifies CBWPF, FWPF, and TWPF in trabecular bone, is promising in the assessment of bone quality. KEY POINTS: • Compositional MR imaging technique is able to quantify proton fractions for all the water components (i.e., collagen-bound water proton fraction (CBWPF), free water proton fraction (FWPF), and total water proton fraction (TWPF)) in the human lumbar spine. • The biomarkers derived from the compositional MR imaging technique showed moderate to high correlations with bone mineral density (BMD) and T-score and showed good performance in distinguishing people with different bone mass. • The comprehensive diagnostic model incorporating CBWPF, FWPF, TWPF, and clinical characteristics showed the highest clinical diagnostic capability for the assessment of osteoporosis.

Automated measurement of spine indices on axial MR images for lumbar spinal stenosis diagnosis using segmentation-guided regression network.

PURPOSE: Automated measurement of spine indices on axial magnetic resonance (MR) images plays a significant role in lumbar spinal stenosis diagnosis. Existing direct spine indices measurement approaches fail to explicitly focus on the task-specific region or feature channel with the additional information for guiding. We aim to achieve accurate spine indices measurement by introducing the guidance of the segmentation task. METHODS: In this paper, we propose a segmentation-guided regression network (SGRNet) to achieve automated spine indices measurement. SGRNet consists of a segmentation path for generating the spine segmentation prediction and a regression path for producing spine indices estimation. The segmentation path is a U-Net-like network which includes a segmentation encoder and a decoder which generates multilevel segmentation features and segmentation prediction. The proposed segmentation-guided attention module (SGAM) in the regression encoder extracts the attention-aware regression feature under the guidance of the segmentation feature. Based on the attention-aware regression feature, a fully connected layer is utilized to output the accurate spine indices estimation. RESULTS: Experiments on the open-access Lumbar Spine MRI data set show that SGRNet achieves state-of-the-art performance with a mean absolute error of 0.49 mm and mean Pearson correlation coefficient of 0.956 for four indices estimation. CONCLUSIONS: The proposed SGAM in SGRNet is capable of improving the performance of spine indices measurement by focusing on the task-specific region and feature channel under the guidance of the segmentation task.

Automated Magnetic Resonance Image Segmentation of Spinal Structures at the L4-5 Level with Deep Learning: 3D Reconstruction of Lumbar Intervertebral Foramen.

OBJECTIVE: 3D reconstruction of lumbar intervertebral foramen (LIVF) has been beneficial in evaluating surgical trajectory. Still, the current methods of reconstructing the 3D LIVF model are mainly based on manual segmentation, which is laborious and time-consuming. This study aims to explore the feasibility of automatically segmenting lumbar spinal structures and increasing the speed and accuracy of 3D lumbar intervertebral foramen (LIVF) reconstruction on magnetic resonance image (MRI) at the L4-5 level. METHODS: A total of 100 participants (mean age: 42.2 ± 14.0 years; 52 males and 48 females; mean body mass index, 22.7 ± 3.2 kg/m2 ), were enrolled in this prospective study between March and July 2020. All participants were scanned on L4-5 level with a 3T MR unit using 3D T2-weighted sampling perfection with application-optimized contrast with various flip-angle evolutions (SPACE) sequences. The lumbar spine's vertebra bone structures (VBS) and intervertebral discs (IVD) were manually segmented by skilled surgeons according to their anatomical outlines from MRI. Then all manual segmentation were saved and used for training. An automated segmentation method based on a 3D U-shaped architecture network (3D-UNet) was introduced for the automated segmentation of lumbar spinal structures. A number of quantitative metrics, including dice similarity coefficient (DSC), precision, and recall, were used to evaluate the performance of the automated segmentation method on MRI. Wilcoxon signed-rank test was applied to compare morphometric parameters, including foraminal area, height and width of 3D LIVF models between automatic and manual segmentation. The intra-class correlation coefficient was used to assess the test-retest reliability and inter-observer reliability of multiple measurements for these morphometric parameters of 3D LIVF models. RESULTS: The automatic segmentation performance of all spinal structures (VBS and IVD) was found to be 0.918 (healthy levels: 0.922; unhealthy levels: 0.916) for the mean DSC, 0.922 (healthy levels: 0.927; unhealthy levels: 0.920) for the mean precision, and 0.917 (healthy levels: 0.918; unhealthy levels: 0.917) for the mean recall in the test dataset. It took approximately 2.5 s to achieve each automated segmentation, far less than the 240 min for manual segmentation. Furthermore, no significant differences were observed in the foraminal area, height and width of the 3D LIVF models between manual and automatic segmentation images (P > 0.05). CONCLUSION: A method of automated MRI segmentation based on deep learning algorithms was capable of rapidly generating accurate segmentation of spinal structures and can be used to construct 3D LIVF models from MRI at the L4-5 level.

Automatic Grading of Disc Herniation, Central Canal Stenosis and Nerve Roots Compression in Lumbar Magnetic Resonance Image Diagnosis.

Aim: Accurate severity grading of lumbar spine disease by magnetic resonance images (MRIs) plays an important role in selecting appropriate treatment for the disease. However, interpreting these complex MRIs is a repetitive and time-consuming workload for clinicians, especially radiologists. Here, we aim to develop a multi-task classification model based on artificial intelligence for automated grading of lumbar disc herniation (LDH), lumbar central canal stenosis (LCCS) and lumbar nerve roots compression (LNRC) at lumbar axial MRIs. Methods: Total 15254 lumbar axial T2W MRIs as the internal dataset obtained from the Fifth Affiliated Hospital of Sun Yat-sen University from January 2015 to May 2019 and 1273 axial T2W MRIs as the external test dataset obtained from the Third Affiliated Hospital of Southern Medical University from June 2016 to December 2017 were analyzed in this retrospective study. Two clinicians annotated and graded all MRIs using the three international classification systems. In agreement, these results served as the reference standard; In disagreement, outcomes were adjudicated by an expert surgeon to establish the reference standard. The internal dataset was randomly split into an internal training set (70%), validation set (15%) and test set (15%). The multi-task classification model based on ResNet-50 consists of a backbone network for feature extraction and three fully-connected (FC) networks for classification and performs the classification tasks of LDH, LCCS, and LNRC at lumbar MRIs. Precision, accuracy, sensitivity, specificity, F1 scores, confusion matrices, receiver-operating characteristics and interrater agreement (Gwet k) were utilized to assess the model's performance on the internal test dataset and external test datasets. Results: A total of 1115 patients, including 1015 patients from the internal dataset and 100 patients from the external test dataset [mean age, 49 years ± 15 (standard deviation); 543 women], were evaluated in this study. The overall accuracies of grading for LDH, LCCS and LNRC were 84.17% (74.16%), 86.99% (79.65%) and 81.21% (74.16%) respectively on the internal (external) test dataset. Internal and external testing of three spinal diseases showed substantial to the almost perfect agreement (k, 0.67 - 0.85) for the multi-task classification model. Conclusion: The multi-task classification model has achieved promising performance in the automated grading of LDH, LCCS and LNRC at lumbar axial T2W MRIs.

Assessment of Osteoporosis in Lumbar Spine: In Vivo Quantitative MR Imaging of Collagen Bound Water in Trabecular Bone.

AIM: Bone collagen matrix makes a crucial contribution to the mechanical properties of bone by imparting tensile strength and elasticity. The collagen content of bone is accessible via quantification of collagen bound water (CBW) indirectly. We prospectively study the performance of the CBW proton density (CBWPD) measured by a 3D short repetition time adiabatic inversion recovery prepared ultrashort echo time (STAIR-UTE) magnetic resonance imaging (MRI) sequence in the diagnosis of osteoporosis in human lumbar spine. METHODS: A total of 189 participants with a mean age of 56 (ranged from 50 to 86) years old were underwent MRI, quantitative computed tomography (QCT), and dual-energy X-ray absorptiometry (DXA) in lumbar spine. Major fracture risk was also evaluated for all participants using Fracture Risk Assessment Tool (FRAX). Lumbar CBWPD, bone marrow fat fraction (BMFF), bone mineral density (BMD) and T score values were calculated in three vertebrae (L2-L4) for each subject. Both the CBWPD and BMFF were correlated with BMD, T score, and FRAX score for comparison. The abilities of the CBWPD and BMFF to discriminate between three different cohorts, which included normal subjects, patients with osteopenia, and patients with osteoporosis, were also evaluated and compared using receiver operator characteristic (ROC) analysis. RESULTS: The CBWPD showed strong correlation with standard BMD (R2 = 0.75, P < 0.001) and T score (R2 = 0.59, P < 0.001), as well as a moderate correlation with FRAX score (R2 = 0.48, P < 0.001). High area under the curve (AUC) values (≥ 0.84 using QCT as reference; ≥ 0.76 using DXA as reference) obtained from ROC analysis demonstrated that the CBWPD was capable of well differentiating between the three different subject cohorts. Moreover, the CBWPD had better correlations with BMD, T score, and FRAX score than BMFF, and also performed better in cohort discrimination. CONCLUSION: The STAIR-UTE-measured CBWPD is a promising biomarker in the assessment of bone quality and fracture risk.

Three-dimensional reconstruction of Kambin's triangle based on automated magnetic resonance image segmentation.

The three-dimensional (3D) anatomy of Kambin's triangle is crucial for surgical planning in minimally invasive spine surgery via the transforaminal approach. Few pieces of research have, however, used image segmentation to explore the 3D reconstruction of Kambin's triangle. This study aimed to develop a new method of 3D reconstruction of Kambin's triangle based on automated magnetic resonance image (MRI) segmentation of the lumbar spinal structures. An experienced (>5 years) "ground truth" spinal pain physician meticulously segmented and labeled spinal structures (e.g., bones, dura mater, discs, and nerve roots) on MRI. Subsequently, a 3D U-Net algorithm was developed for automatically segmenting lumbar spinal structures for the 3D reconstruction of Kambin's triangle. The Dice similarity coefficient (DSC), precision, recall, and the area of Kambin's triangle were used to assess anatomical performance. The automatic segmentation of all spinal structures at the L4/L5 levels and L5/S1 levels resulted in good performance: DSC = 0.878/0.883, precision = 0.889/0.890, recall = 0.873/0.882. Furthermore, the area measurements of Kambin's triangle revealed no significant difference between ground truth and automatic segmentation (p = 0.333 at the L4/L5 level, p = 0.302 at the L5/S1 level). The 3D U-Net model used in this study performed well in terms of simultaneous segmentation of multi-class spinal structures (including bones, dura mater, discs, and nerve roots) on MRI, allowing for accurate 3D reconstruction of Kambin's triangle.

Indole-3-Acetic Acid Alters Intestinal Microbiota and Alleviates Ankylosing Spondylitis in Mice.

Ankylosing spondylitis (AS) is a systemic, chronic, and inflammatory autoimmune disease associated with the disorder of intestinal microbiota. Unfortunately, effective therapies for AS are lacking. Recent evidence has indicated that indole-3-acetic acid (IAA), an important microbial tryptophan metabolite, can modulate intestinal homeostasis and suppress inflammatory responses. However, reports have not examined the in vivo protective effects of IAA against AS. In this study, we investigated the protective effects and underlying mechanisms through which IAA acts against AS. We constructed a proteoglycan (PG)-induced AS mouse model and administered IAA (50 mg/kg body weight) by intraperitoneal injection daily for 4 weeks. The effects of IAA on AS mice were evaluated by examining disease severity, intestinal barrier function, aryl hydrocarbon receptor (AhR) pathway, T-helper 17 (Th17)/T regulatory (Treg) balance, and inflammatory cytokine levels. The intestinal microbiota compositions were profiled through whole-genome sequencing. We observed that IAA decreased the incidence and severity of AS in mice, inhibited the production of pro-inflammatory cytokines (tumor necrosis factor α [TNF-α], interleukin [IL]-6, IL-17A, and IL-23), promoted the production of the anti-inflammatory cytokine IL-10, and reduced the ratios of pro-/anti- inflammatory cytokines. IAA ameliorated pathological changes in the ileum and improved intestinal mucosal barrier function. IAA also activated the AhR pathway, upregulated the transcription factor forehead box protein P3 (FoxP3) and increased Treg cells, and downregulated the transcription factors retinoic acid receptor-related orphan receptor gamma t (RORγt) and signal transducer and activator of transcription 3 (STAT3) and decreased Th17 cells. Furthermore, IAA altered the composition of the intestinal microbiota composition by increasing Bacteroides and decreasing Proteobacteria and Firmicutes, in addition to increasing the abundances of Bifidobacterium pseudolongum and Mucispirillum schaedleri. In conclusion, IAA exerted several protective effects against PG-induced AS in mice, which was mediated by the restoration of balance among the intestinal microbial community, activating the AhR pathway, and inhibiting inflammation. IAA might represent a novel therapeutic approach for AS.

Computerized Characterization of Spinal Structures on MRI and Clinical Significance of 3D Reconstruction of Lumbosacral Intervertebral Foramen.

BACKGROUND: Segmentation of spinal structures is important in medical imaging analysis, which facilitates surgeons to plan a preoperative trajectory for the transforaminal approach. However, manual segmentation of spinal structures is time-consuming, and studies have not explored automatic segmentation of spinal structures at the L5/S1 level. OBJECTIVES: This study sought to develop a new method based on a deep learning algorithm for automatic segmentation of spinal structures. The resulting algorithm may be used to rapidly generate a precise 3D lumbosacral intervertebral foramen model to assist physicians in planning an ideal trajectory in L5/S1 lumbar transforaminal radiofrequency ablation (LTRFA). STUDY DESIGN: This was an observational study for developing a new technique on spinal structures segmentation. STUDY SITE: The study was carried out at the department of radiology and spine surgery at our hospital. METHODS: A total of 100 L5/S1 level data samples from 100 study patients were used in this study. Masks of vertebral bone structures (VBSs) and intervertebral discs (IVDs) for all data samples were segmented manually by a skilled surgeon and served as the "ground truth." After data preprocessing, a 3D-UNet model based on deep learning was used for automated segmentation of lumbar spine structures at L5/S1 level magnetic resonance imaging (MRI). Segmentation performances and morphometric measurement were used for 3D lumbosacral intervertebral foramen (LIVF) reconstruction  generated by either manual segmentation and automatic segmentation. RESULTS: The 3D-UNet model showed high performance in automatic segmentation of lumbar spinal structures (VBSs and IVDs). The corresponding mean Dice similarity coefficient (DSC) of 5-fold cross-validation scores for L5 vertebrae, IVDs, S1 vertebrae, and all L5/S1 level spinal structures were 93.46 ± 2.93%, 90.39 ± 6.22%, 93.32 ± 1.51%, and 92.39 ± 2.82%, respectively. Notably, the analysis showed no associated difference in morphometric measurements between the manual and automatic segmentation at the L5/S1 level. LIMITATIONS: Semantic segmentation of multiple spinal structures (such as VBSs, IVDs, blood vessels, muscles, and ligaments) was simultaneously not integrated into the deep-learning method in this study. In addition, large clinical experiments are needed to evaluate the clinical efficacy of the model. CONCLUSION: The 3D-UNet model developed in this study based on deep learning can effectively and simultaneously segment VBSs and IVDs at L5/S1 level formMR images, thereby enabling rapid and accurate 3D reconstruction of LIVF models. The method can be used to segment VBSs and IVDs of spinal structures on MR images within near-human expert performance; therefore, it is reliable for reconstructing LIVF for L5/S1 LTRFA.

DGMSNet: Spine segmentation for MR image by a detection-guided mixed-supervised segmentation network.

Spine segmentation for magnetic resonance (MR) images is important for various spinal diseases diagnosis and treatment, yet is still a challenge due to the inter-class similarity, i.e., shape and appearance similarities appear in neighboring spinal structures. To reduce inter-class similarity, existing approaches focus on enhancing the semantic information of spinal structures in the supervised segmentation network, whose generalization is limited by the size of pixel-level annotated dataset. In this paper, we propose a novel detection-guided mixed-supervised segmentation network (DGMSNet) to achieve automated spine segmentation. DGMSNet consists of a segmentation path for generating the spine segmentation prediction and a detection path (i.e., regression network) for producing heatmaps prediction of keypoints. A detection-guided learner in the detection path is introduced to generate a dynamic parameter, which is employed to produce a semantic feature map for segmentation path by adaptive convolution. A mixed-supervised loss comprised of a weighted combination of segmentation loss and detection loss is utilized to train DGMSNet with a pixel-level annotated dataset and a keypoints-detection annotated dataset. During training, a series of models are trained with various loss weights. In inference, a detection-guided label fusion approach is proposed to integrate the segmentation predictions generated by those trained models according to the consistency of predictions from the segmentation path and detection path. Experiments on T2-weighted MR images show that DGMSNet achieves the state-of-the-art performance with mean Dice similarity coefficients of 94.39% and 87.21% for segmentations of 5 vertebral bodies and 5 intervertebral discs on the in-house and public datasets respectively.

Quantifying Axial Spine Images Using Object-Specific Bi-Path Network.

Automatic estimation of indices from medical images is the main goal of computer-aided quantification (CADq), which speeds up diagnosis and lightens the workload of radiologists. Deep learning technique is a good choice for implementing CADq. Usually, to acquire high-accuracy quantification, specific network architecture needs to be designed for a given CADq task. In this study, considering that the target organs are the intervertebral disc and the dural sac, we propose an object-specific bi-path network (OSBP-Net) for axial spine image quantification. Each path of the OSBP-Net comprises a shallow feature extraction layer (SFE) and a deep feature extraction sub-network (DFE). The SFEs use different convolution strides because the two target organs have different anatomical sizes. The DFEs use average pooling for downsampling based on the observation that the target organs have lower intensity than the background. In addition, an inter-path dissimilarity constraint is proposed and applied to the output of the SFEs, taking into account that the activated regions in the feature maps of two paths should be different theoretically. An inter-index correlation regularization is introduced and applied to the output of the DFEs based on the observation that the diameter and area of the same object express an approximately linear relation. The prediction results of OSBP-Net are compared to several state-of-the-art machine learning-based CADq methods. The comparison reveals that the proposed methods precede other competing methods extensively, indicating its great potential for spine CADq.

SpineParseNet: Spine Parsing for Volumetric MR Image by a Two-Stage Segmentation Framework With Semantic Image Representation.

Spine parsing (i.e., multi-class segmentation of vertebrae and intervertebral discs (IVDs)) for volumetric magnetic resonance (MR) image plays a significant role in various spinal disease diagnoses and treatments of spine disorders, yet is still a challenge due to the inter-class similarity and intra-class variation of spine images. Existing fully convolutional network based methods failed to explicitly exploit the dependencies between different spinal structures. In this article, we propose a novel two-stage framework named SpineParseNet to achieve automated spine parsing for volumetric MR images. The SpineParseNet consists of a 3D graph convolutional segmentation network (GCSN) for 3D coarse segmentation and a 2D residual U-Net (ResUNet) for 2D segmentation refinement. In 3D GCSN, region pooling is employed to project the image representation to graph representation, in which each node representation denotes a specific spinal structure. The adjacency matrix of the graph is designed according to the connection of spinal structures. The graph representation is evolved by graph convolutions. Subsequently, the proposed region unpooling module re-projects the evolved graph representation to a semantic image representation, which facilitates the 3D GCSN to generate reliable coarse segmentation. Finally, the 2D ResUNet refines the segmentation. Experiments on T2-weighted volumetric MR images of 215 subjects show that SpineParseNet achieves impressive performance with mean Dice similarity coefficients of 87.32 ± 4.75%, 87.78 ± 4.64%, and 87.49 ± 3.81% for the segmentations of 10 vertebrae, 9 IVDs, and all 19 spinal structures respectively. The proposed method has great potential in clinical spinal disease diagnoses and treatments.

Multiple Axial Spine Indices Estimation via Dense Enhancing Network With Cross-Space Distance-Preserving Regularization.

Automatic estimation of axial spine indices is clinically desired for various spine computer aided procedures, such as disease diagnosis, therapeutic evaluation, pathophysiological understanding, risk assessment, and biomechanical modeling. Currently, the spine indices are manually measured by physicians, which is time-consuming and laborious. Even worse, the tedious manual procedure might result in inaccurate measurement. To deal with this problem, in this paper, we aim at developing an automatic method to estimate multiple indices from axial spine images. Inspired by the success of deep learning for regression problems and the densely connected network for image classification, we propose a dense enhancing network (DE-Net) which uses the dense enhancing blocks (DEBs) as its main body, where a feature enhancing layer is added to each of the bypass in a dense block. The DEB is designed to enhance discriminative feature embedding from the intervertebral disc and the dural sac areas. In addition, the cross-space distance-preserving regularization (CSDPR), which enforces consistent inter-sample distances between the output and the label spaces, is proposed to regularize the loss function of the DE-Net. To train and validate the proposed method, we collected 895 axial spine MRI images from 143 subjects and manually measured the indices as the ground truth. The results show that all deep learning models obtain very small prediction errors, and the proposed DE-Net with CSDPR acquires the smallest error among all methods, indicating that our method has great potential for spine computer aided procedures.

Species Identification of Oaks (Quercus L., Fagaceae) from Gene to Genome.

Species identification of oaks (Quercus) is always a challenge because many species exhibit variable phenotypes that overlap with other species. Oaks are notorious for interspecific hybridization and introgression, and complex speciation patterns involving incomplete lineage sorting. Therefore, accurately identifying Quercus species barcodes has been unsuccessful. In this study, we used chloroplast genome sequence data to identify molecular markers for oak species identification. Using next generation sequencing methods, we sequenced 14 chloroplast genomes of Quercus species in this study and added 10 additional chloroplast genome sequences from GenBank to develop a DNA barcode for oaks. Chloroplast genome sequence divergence was low. We identified four mutation hotspots as candidate Quercus DNA barcodes; two intergenic regions (matK-trnK-rps16 and trnR-atpA) were located in the large single copy region, and two coding regions (ndhF and ycf1b) were located in the small single copy region. The standard plant DNA barcode (rbcL and matK) had lower variability than that of the newly identified markers. Our data provide complete chloroplast genome sequences that improve the phylogenetic resolution and species level discrimination of Quercus. This study demonstrates that the complete chloroplast genome can substantially increase species discriminatory power and resolve phylogenetic relationships in plants.

Anti-TNF-α therapy alters the gut microbiota in proteoglycan-induced ankylosing spondylitis in mice.

Ankylosing spondylitis is a chronic, progressive disease, and its treatment is relevant to the gut microbiota. Anti-tumor necrosis factor-alpha (anti-TNF-α) therapy alters the gut microbiota in many diseases, including inflammatory bowel disease. However, little is known about the effect of TNF-α blocker treatment on the gut microbiota in ankylosing spondylitis. Herein, the effect of a TNF-α blocker on the gut microbiota in proteoglycan-induced arthritis was investigated. Proteoglycan-induced mice were treated with an rhTNFR:Fc solution of etanercept (5 µg/g) for 4 weeks. rhTNFR:Fc treatment attenuated the arthritis incidence and severity of arthritis in the proteoglycan-induced mice and decreased inflammation in the ankle joints and ameliorated ileal tissue destruction. Moreover, high gut permeability occurred, and zonula occludens-1 and occludin protein levels were reduced in proteoglycan-induced mice. These levels were significantly restored by the administration of rhTNFR:Fc. The serum TNF-α and IL-17 levels were also decreased. In addition, flora analysis via 16S rDNA high-throughput sequencing revealed that rhTNFR:Fc treatment restored the gut microbiota composition to a composition similar to that in control mice. In conclusion, anti-TNF-α therapy attenuated proteoglycan-induced arthritis progression and modulated the gut microbiota and intestinal barrier function. These results provide new insights for anti-TNF-α therapy strategies via regulating the gut microbiota in ankylosing spondylitis.

Genome Comparison Reveals Mutation Hotspots in the Chloroplast Genome and Phylogenetic Relationships of Ormosia Species.

The papilionoid legume genus Ormosia comprises approximately 130 species, which are distributed mostly in the Neotropics, with some species in eastern Asia and northeastern Australia. The taxonomy and evolutionary history remain unclear due to the lack of a robust species-level phylogeny. Chloroplast genomes can provide important information for phylogenetic and population genetic studies. In this study, we determined the complete chloroplast genome sequences of five Ormosia species by Illumina sequencing. The Ormosia chloroplast genomes displayed the typical quadripartite structure of angiosperms, which consisted of a pair of inverted regions separated by a large single-copy region and a small single-copy region. The location and distribution of repeat sequences and microsatellites were determined. Comparative analyses highlighted a wide spectrum of variation, with trnK-rbcL, atpE-trnS-rps4, trnC-petN, trnS-psbZ-trnG, trnP-psaJ-rpl33, and clpP intron being the most variable regions. Phylogenetic analysis revealed that Ormosia is in the Papilionoideae clade and is sister to the Lupinus clade. Overall, this study, which provides Ormosia chloroplast genomic resources and a comparative analysis of Ormosia chloroplast genomes, will be beneficial for the evolutionary study and phylogenetic reconstruction of the genus Ormosia and molecular barcoding in population genetics and will provide insight into the chloroplast genome evolution of legumes.

Clinical Anatomy and Possible Clinical Significance of the Intervertebral Vein in the Lumbar Intervertebral Foramina.

BACKGROUND: The detailed structure of the lumbar intervertebral foramina has been well-studied. Nevertheless, detailed descriptions of branches of the intervertebral vein (IV) through the lumbar intervertebral foramina are lacking. OBJECTIVES: This study aimed to provide an anatomical basis for invasive treatment targeting the branches of the IV using an approach through the lumbar intervertebral foramina, particularly for the purposes of transforaminal epidural steroid injection. STUDY DESIGN: This research involved a dissection-based study of 10 embalmed human cadavers. SETTING: The research took place at The Third Affiliated Hospital of Southern Medical University. METHODS: One hundred lumbar intervertebral foramina from 10 embalmed cadavers were studied. Branches of the IV in the intervertebral foramina were observed. The length and diameter of the veins were measured using a Vernier caliper. RESULTS: At a rate of 100%, branches of the IV were observed in the 100 lumbar foramina examined in our study. The following 4 types of branches of the IV were routinely found: Type I in 27 (27%) of the IV foramina, in which a superior branch of the IV ran along the inferior margin of the vertebral pedicle; Type II in 18 (18%) of the intervertebral foramina, in which an inferior branch of the IV ran along the superior margin of the inferior vertebral pedicle; Type III in 41 (41%) of the intervertebral foramina, in which the IV was divided into a superior and inferior branch; and Type IV in 14 (14%) of the intervertebral foramina, in which the IV was divided into 2 superior branches and an inferior branch. LIMITATIONS: The greatest weakness of this study is that it lacks actual clinical verification. Future clinical trials are expected to contribute more objective data concerning the IV branches. Due to the relative changes in vascular position during dissection, the relevant data warrant improvement. CONCLUSIONS: The lumbar IVs are an important part of the anatomical structure of the intervertebral foramina. Adequate knowledge of the IV may be of clinical importance to physicians performing transforaminal epidural steroid injection. KEY WORDS: Clinical anatomy, intervertebral veins, lumbar vertebra, Kambin's triangle, safe triangle, intervertebral foramina, vertebral venous system, inadvertent injection, transforaminal epidural steroid injection.