The value of T1- and FST2-Weighted-based radiomics nomogram in differentiating pleomorphic adenoma and Warthin tumor.

PURPOSE: To establish a radiomics nomogram based on MRI radiomics features combined with clinical characteristics for distinguishing pleomorphic adenoma (PA) from warthin tumor (WT). METHODS: 294 patients with PA (n = 159) and WT (n = 135) confirmed by histopathology were included in this study between July 2017 and June 2023. Clinical factors including clinical data and MRI features were analyzed to establish clinical model. 10 MRI radiomics features were extracted and selected from T1WI and FS-T2WI, used to establish radiomics model and calculate radiomics scores (Rad-scores). Clinical factors and Rad-scores were combined to serve as crucial parameters for combined model. Through Receiver operator characteristics (ROC) curve and decision curve analysis (DCA), the discriminative values of the three models were qualified and compared, the best-performing combined model was visualized in the form of a radiomics nomogram. RESULTS: The combined model demonstrated excellent discriminative performance for PA and WT in the training set (AUC=0.998) and testing set (AUC=0.993) and performed better compared with the clinical model and radiomics model in the training set (AUC=0.996, 0.952) and testing model (AUC=0.954, 0.849). The DCA showed that the combined model provided more overall clinical usefulness in distinguishing parotid PA from WT than another two models. CONCLUSION: An analytical radiomics nomogram based on MRI radiomics features, incorporating clinical factors, can effectively distinguish between PA and WT.

Anatomical study of the relationship between the lumbar intervertebral disc, nerves, and psoas major.

Cadaveric study; To describe the characteristics of the nerve and its relationship with the lumbar intervertebral disc and psoas major muscle. Nerve injury is an understudied complication of extreme lateral interbody fusion. A detailed description of the nerve anatomy would be helpful for surgeons to minimize the risk of this complication. The lumbar plexus and lumbar sympathetic nerve of 10 embalmed male cadavers were dissected, and the distribution, number, and spatial orientation of the nerves on the L1/2 to L4/5 intervertebral discs were examined. Metal wires were applied along nerve paths through the psoas major muscle. The position of the nerves was examined on CT. In zone III at L1/2 and L4/5, no nerves were found. In zone II and zone III at L2/3, no lumbar plexus was found, and only the ramus communicans passed through. At the L1-L5 level, the density of nerves in the posterior half of the psoas major muscle was greater than that in the anterior half. The lumbar plexus was found in all of zone IV. The genitofemoral nerve emerges superficially and anteriorly from the medial border of the psoas major at the L3-4 level, but at the L1/2 level, the sympathetic trunk is located in zone II. The remaining disc-level sympathetic trunks appear in zone I. No nerves were found in zone III of the L1/2 or L4/5 disc. In zones II and III of L2/3, the lumbar plexus appears safe. The genitofemoral nerve travels through zones II and III of L3/4. The distribution density of nerves in the posterior half of the psoas major muscle was greater than that in the anterior half of that muscle at the L1-L5 level.

Super Resolution of Pulmonary Nodules Target Reconstruction Using a Two-Channel GAN Models.

RATIONALE AND OBJECTIVES: To develop a Dual generative-adversarial-network (GAN) Cascaded Network (DGCN) for generating super-resolution computed tomography (SRCT) images from normal-resolution CT (NRCT) images and evaluate the performance of DGCN in multi-center datasets. MATERIALS AND METHODS: This retrospective study included 278 patients with chest CT from two hospitals between January 2020 and June 2023, and each patient had all three NRCT (512×512 matrix CT images with a resolution of 0.70 mm, 0.70 mm,1.0 mm), high-resolution CT (HRCT, 1024×1024 matrix CT images with a resolution of 0.35 mm, 0.35 mm,1.0 mm), and ultra-high-resolution CT (UHRCT, 1024×1024 matrix CT images with a resolution of 0.17 mm, 0.17 mm, 0.5 mm) examinations. Initially, a deep chest CT super-resolution residual network (DCRN) was built to generate HRCT from NRCT. Subsequently, we employed the DCRN as a pre-trained model for the training of DGCN to further enhance resolution along all three axes, ultimately yielding SRCT. PSNR, SSIM, FID, subjective evaluation scores, and objective evaluation parameters related to pulmonary nodule segmentation in the testing set were recorded and analyzed. RESULTS: DCRN obtained a PSNR of 52.16, SSIM of 0.9941, FID of 137.713, and an average diameter difference of 0.0981 mm. DGCN obtained a PSNR of 46.50, SSIM of 0.9990, FID of 166.421, and an average diameter difference of 0.0981 mm on 39 testing cases. There were no significant differences between the SRCT and UHRCT images in subjective evaluation. CONCLUSION: Our model exhibited a significant enhancement in generating HRCT and SRCT images and outperformed established methods regarding image quality and clinical segmentation accuracy across both internal and external testing datasets.

Anatomical Observation and Clinical Significance of the Medial Branch of the Lumbar Dorsal Rami.

STUDY DESIGN: Anatomical study. OBJECTIVE: This study aimed to elaborate on the anatomical characteristics of the medial branch of the lumbar dorsal rami and to discuss its possible clinical significance. SUMMARY OF BACKGROUND DATA: Radiofrequency ablation targeting the medial branch of the lumbar dorsal rami has been increasingly used in the clinical management of facetogenic low back pain (FLBP). Nonetheless, attention is also being given to complications such as atrophy of the lumbar soft tissues and muscles. Therefore, a more detailed understanding of the innervation pattern on the facet joint may improve the precision of nerve ablation therapy for FLBP. METHODS: An anatomical study of eight human specimens was carried out. The anatomic characteristics of the medial branch were observed and recorded. RESULTS: The medial branch originates from the lumbar dorsal rami, running close to the root of the posterolateral side of the superior articular process of the inferior cone. When passed through the mamillo-accessory ligament, it turns direction to the medial and caudal side, running in the multifidus muscle. In our study, each medial branch sent out two to five branches along the way. All the medial branches in L1-L4 gave off one to two small branches when crossing the facet joint and innervated the joint of the lower segment. Nineteen medial branches (23.75%) gave off recurrent branches to innervate the joint at the upper segment. CONCLUSION: The anatomical features of the medial branch remain similar in each lumbar segment. There are two types of joint branches, including the articular fibers that emanate from the medial branch as it runs along the medial border of the facet joint and the recurrent branch from the medial branch that innervates the upper facet joint. Moreover, an anastomotic branch was found in the medial branches between different segments.

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.

A comparative study of the anatomy and MRI images of the lumbar foraminal ligaments at the L1-L5 levels.

PURPOSE: The purpose of this study was to evaluate the ability of MRI images to reveal foraminal ligaments at levels L1-L5 by comparing the results with those of anatomical studies. METHODS: Eighty lumbar foramina were studied. First, the best MRI scanning parameters were selected, and the transverse and sagittal axes of each lumbar foramina were scanned to identify and record the ligament-like structures in each lumbar foramen. Then, the cadaveric specimens were anatomically studied, and all ligament structures in the lumbar foramina were retained. The number, morphology and distribution of ligaments under anatomical and MRI scanning were observed. Histological staining of the dissected ligament structures was performed to confirm that they were ligamentous tissues. Finally, the accuracy of ligament recognition in MRI images was statistically analyzed. RESULTS: A total of 233 foraminal ligaments were identified in 80 lumbar intervertebral foramina through cadaveric anatomy. The radiating ligaments (176, 75.5%) were found to be attached from the nerve root to the surrounding osseous structures, while the transforaminal ligaments (57, 24.5%) traversed the intervertebral foramina without any connection to the nerve roots. A total of 42 transforaminal ligament signals and 100 radiating ligament signals were detected in the MRI images of the 80 intervertebral foramina. CONCLUSION: The MRI can identify the lumbar foraminal ligament, and the recognition rate of the transforaminal ligament is higher than that of the radiating ligament. This study provides a new method for the clinical diagnosis of the relationship between the lumbar foraminal ligament and radicular pain.

Corrigendum: METTL3 contributes to osteosarcoma progression by increasing DANCR mRNA stability via m6A modification.

[This corrects the article DOI: 10.3389/fcell.2021.784719.].

Automated Rib Fracture Detection on Chest X-Ray Using Contrastive Learning.

To develop a deep learning-based model for detecting rib fractures on chest X-Ray and to evaluate its performance based on a multicenter study. Chest digital radiography (DR) images from 18,631 subjects were used for the training, testing, and validation of the deep learning fracture detection model. We first built a pretrained model, a simple framework for contrastive learning of visual representations (simCLR), using contrastive learning with the training set. Then, simCLR was used as the backbone for a fully convolutional one-stage (FCOS) objective detection network to identify rib fractures from chest X-ray images. The detection performance of the network for four different types of rib fractures was evaluated using the testing set. A total of 127 images from Data-CZ and 109 images from Data-CH with the annotations for four types of rib fractures were used for evaluation. The results showed that for Data-CZ, the sensitivities of the detection model with no pretraining, pretrained ImageNet, and pretrained DR were 0.465, 0.735, and 0.822, respectively, and the average number of false positives per scan was five in all cases. For the Data-CH test set, the sensitivities of three different pretraining methods were 0.403, 0.655, and 0.748. In the identification of four fracture types, the detection model achieved the highest performance for displaced fractures, with sensitivities of 0.873 and 0.774 for the Data-CZ and Data-CH test sets, respectively, with 5 false positives per scan, followed by nondisplaced fractures, buckle fractures, and old fractures. A pretrained model can significantly improve the performance of the deep learning-based rib fracture detection based on X-ray images, which can reduce missed diagnoses and improve the diagnostic efficacy.

An AI-Based Image Quality Control Framework for Knee Radiographs.

Image quality control (QC) is crucial for the accurate diagnosis of knee diseases using radiographs. However, the manual QC process is subjective, labor intensive, and time-consuming. In this study, we aimed to develop an artificial intelligence (AI) model to automate the QC procedure typically performed by clinicians. We proposed an AI-based fully automatic QC model for knee radiographs using high-resolution net (HR-Net) to identify predefined key points in images. We then performed geometric calculations to transform the identified key points into three QC criteria, namely, anteroposterior (AP)/lateral (LAT) overlap ratios and LAT flexion angle. The proposed model was trained and validated using 2212 knee plain radiographs from 1208 patients and an additional 1572 knee radiographs from 753 patients collected from six external centers for further external validation. For the internal validation cohort, the proposed AI model and clinicians showed high intraclass consistency coefficients (ICCs) for AP/LAT fibular head overlap and LAT knee flexion angle of 0.952, 0.895, and 0.993, respectively. For the external validation cohort, the ICCs were also high, with values of 0.934, 0.856, and 0.991, respectively. There were no significant differences between the AI model and clinicians in any of the three QC criteria, and the AI model required significantly less measurement time than clinicians. The experimental results demonstrated that the AI model performed comparably to clinicians and required less time. Therefore, the proposed AI-based model has great potential as a convenient tool for clinical practice by automating the QC procedure for knee radiographs.

Anatomic zone division and clinical significance of the lumbar sinuvertebral nerves.

BACKGROUND CONTEXT: Discogenic low-back pain (DLBP) is one of the primary causes of low back pain (LBP) and is associated with internal disc disruptions and is mainly transmitted by the sinuvertebral nerve (SVN). The lack of a universal understanding of the anatomical characteristics of the SVN has compromised surgical treatment for DLPB. PURPOSE: This study aims to elaborate on the anatomical characteristics of the SVN and to discuss their possible clinical significance. STUDY DESIGN: The SVNs were dissected and immunostained in ten human lumbar specimens. METHODS: The SVNs at the segments from L1-L2 to L5-S1 in ten human cadavers were studied, and the number, origin, course, diameter, anastomotic branches, and branching points of the SVNs were documented. Three longitudinal and five transverse zones were defined in the dorsal coronal plane of the vertebral body and disc. The vertebrae were divided longitudinally as follows: the region between the medial edges of the bilateral pedicles is divided into three equal parts, the middle third is zone I and the lateral third on both sides are zones II; the areas lateral to the medial margin of the pedicle were zones III. The transverse zones were designated as follows: (a)superior margin of the vertebral body to superior margin of the pedicle; (b) between superior and inferior margins of the pedicle; (c) inferior margin of the pedicle to inferior margin of the vertebral body; (d) superior margin of the disc to the midline of the disc; and (e) midline of the disc to the inferior margin of the disc. The distribution characteristics of SVNs in various zones were recorded, and tissue sections were immunostained with anti-NF 200 and anti-PGP 9.5. RESULTS: The SVNs are divided into main trunks and deputy branches, with 109 main trunks and 451 deputy branches identified in the 100 lumbar intervertebral foramens (IVFs). The main trunks of the SVN originate from the spinal nerve and/or the communicating branch, but the deputy branch originating from both roots was not observed. All the main trunks and deputy branches of the SVNs originate from the posterolateral disc (III d and III e). The deputy branches of the SVN primarily innervate the posterolateral aspect of the intervertebral disc (III d 46.78%, III e 36.36%) and the subpedicular vertebral body (III c 16.85%). The main trunk of the SVNs passes primarily through the subpedicular vertebral body (III c 96.33%) and divides into ascending, transverse, and descending branches in the IVF: III c (23/101, 22.77%) or spinal canal: II c (73/101, 72.28%), II d (3/101, 2.97%), II b (2/101, 1.98%). The main trunk possesses extensive innervation, and except for the most medial discs (I d and I e), it almost dominates all other zones of the spinal canal. At the segments from L1-L2 to L5-S1, 39 ipsilateral anastomoses connecting the ascending branch to the main trunk or spinal nerve at the upper level were observed, with one contralateral anastomosis observed at L5. CONCLUSION: The zone distribution characteristics of SVNs are similar across all levels. Comparatively, the proportion of double-root origin and the number of insertion points of the SVNs increased at the lower level. The three types of anastomosis offer connections between SVNs at the same level and at different levels. The posteromedial disc is innervated by corresponding and subjacent main trunks, with the posterolateral disc mainly innervated by the deputy branch. CLINICAL SIGNIFICANCE: Detailed information and zone distribution characteristics of the lumbar SVNs can help improve clinicians' understanding of DLBP and improve the effectiveness of treatments targeting the SVNs.

Position of lumbar plexus nerves in the psoas major: Application to transpsoas approaches to the lumbar spine.

Far lateral interbody fusion is a minimally invasive operating technique. However, the incidence of postoperative neurological complications is high, and some scholars question its safety. This study describes the neuroanatomical features and spatial orientation within the psoas major. Ten embalmed male cadavers were selected and the left psoas major was dissected. Subsequently, the area between the anterior and the posterior edges of the vertebral body was divided into three equal zones. The nerves' distribution, number, and spatial orientation of the L1/2 to L4/5 intervertebral discs were examined. A caliper was used to measure the diameter of the nerve. The safety zone of the L1/2 intervertebral disc level is located in zone I and II, the relative safe zones of the L2/3 and L4/5 intervertebral discs are located in zone II, and the safety zone of the L3/4 intervertebral disc level is located in the caudal side of zone II. The genitofemoral nerve exits the psoas major in a co-trunk or two-branch pattern, and its exit point was distributed between the L3 and L4 vertebral bodies, mainly at the L3/4 intervertebral disc level. The sympathetic ganglia in the psoas major appeared only in zone I at the L2/3 intervertebral disc level. This is a systematic anatomical study that describes the nerves of the psoas major. Spine surgeons can use this study-which consists of important clinical implications-for preoperative planning, and thus, reduce the risk of nerve injury during surgery.

Superhydrophilic and topography-regulatable surface grafting on PEEK to improve cellular affinity.

Polyetheretherketone (PEEK) has been widely used in the preparation of orthopedic implants due to its biological inertness and similar mechanical modulus to natural bone. However, the affinity between biological tissue (bone and soft tissue) and PEEK surface is weak, leading to low osseointegration and an increased risk of inflammation. The situation could be improved by modifying PEEK surface. Surfaces with good hydrophilicity and proper microtopography would promote cellular adhesion and proliferation. This work presented a two-step surface modification method to achieve the effect. Polyacrylic acid (PAA) chains were grafted on PEEK surface by UV irradiation. Then, ethylenediamine (EDA) was added to introduce amino groups and promote the cross-linking of PAA chains. Furthermore, a mathematical model was built to describe and regulate the surface topography growth process semi-quantitatively. The model fits experimental data quite well (adjusted R2 = 0.779). Results showed that the modified PEEK surface obtained superhydrophilicity. It significantly improved the adhesion and proliferation of BMSCs and MFBs by activating the FAK pathway and Rho family GTPase. The cellular affinity performed better when the surface topography was in network structure with holes in about 25 µm depth and 20-50 µm diameter. Good hydrophilicity seems necessary for the FAK pathway activation, but simply improving surface hydrophilicity might not be enough for cellular affinity improvement. Surface topography at micron scale should be a more important cue. This simple surface modification method could be contributed to further study of cell-microtopography interaction and have potential applications in clinical PEEK orthopedic implants.