Development of magnetic resonance imaging of brachial plexus neuralgia.

As the incidence of peripheral neurological diseases increases, the precise display of nerves becomes important in imaging examinations. Among them, the pain caused by brachial plexus neuropathy is very prominent, and the magnetic resonance imaging of nerve is quite complex and messy. This paper will systematically elaborate from the aspects of brachial plexus neuropathy, morphological and functional imaging, and post-processing.

Recent Advances of Magnetic Resonance Neuroimaging in Trigeminal Neuralgia.

Trigeminal neuralgia (TN) is a disease of unclear pathogenesis. It has a low incidence and is not fatal, but it can cause afflicted patients' depression or suicide. In the past, neurovascular compression was considered to be the main cause of TN, but recent studies have found that neurovascular contact is also common in asymptomatic patients and the asymptomatic side in symptomatic patients. This indicates that the neurovascular contact is not, or is only to a lesser extent, a factor in the development of TN. Thus, the study of the peripheral branches of the trigeminal nerve is necessary to understand the etiology of TN. With the development of imaging technology and the emergence of various imaging modalities, it is possible to study the etiology of TN and the pathological changes of related structures by magnetic resonance neuroimaging. This article reviews the recent advances in magnetic resonance neuroimaging of the trigeminal nerve.

Effects of thalamic infarction on the structural and functional connectivity of the ipsilesional primary somatosensory cortex.

OBJECTIVES: To identify regions causally influenced by thalamic stroke by measuring white matter integrity, cortical volume, and functional connectivity (FC) among patients with thalamic infarction (TI) and to determine the association between structural/functional alteration and somatosensory dysfunction. METHODS: Thirty-one cases with TI-induced somatosensory dysfunction and 32 healthy controls underwent magnetic resonance imaging scanning. We reconstructed the ipsilesional central thalamic radiation (CTR) and assessed its integrity using fractional anisotropy (FA), assessed S1 ipsilesional changes with cortical volume, and identified brain regions functionally connected to TI locations and regions without TI to examine the potential effects on somatosensory symptoms. RESULTS: Compared with controls, TI patients showed decreased FA (F = 17.626, p < 0.001) in the ipsilesional CTR. TI patients exhibited significantly decreased cortical volume in the ipsilesional top S1. Both affected CTR (r = 0.460, p = 0.012) and S1 volume (r = 0.375, p = 0.049) were positively correlated with somatosensory impairment in TI patients. In controls, the TI region was highly functionally connected to atrophic top S1 and less connected to the adjacent middle S1 region in FC mapping. However, T1 patients demonstrated significantly increased FC between the ipsilesional thalamus and middle S1 area, which was adjacent to the atrophic S1 region. CONCLUSIONS: TI induces remote changes in the S1, and this network of abnormality underlies the cause of the sensory deficits. However, our other finding that there is stronger connectivity in pathways adjacent to the damaged ones is likely responsible for at least some of the recovery of function. KEY POINTS: • TI led to secondary impairment in the CTR and cortical atrophy in the ipsilesional top of S1. • TI patients exhibited significantly higher functional connectivity with the ipsilateral middle S1 which was mainly located within the non-atrophic area of S1. • Our results provide neuroimaging markers for non-invasive treatment and predict somatosensory recovery.

Computed tomography-guided catheter drainage with ozone in management of pyogenic liver abscess.

PURPOSE: To compare the treatment efficacy of percutaneous catheter drainage alone to catheter drainage combined with ozone in the management of pyogenic liver abscess (PLA). MATERIAL AND METHODS: This prospective study included 85 patients diagnosed with PLA. All patients were randomly divided into two groups: catheter drainage alone (Group I); catheter drainage combined with ozone (Group II). Drainage was considered successful when: 1) the abscess cavities were completely drained, and 2) clinical symptoms were resolved. Kruskall-Wallis nonparametric test was used to compare the success rates, length of stay (LOS), and need of further surgery. A value of p < 0.05 was considered significant for all statistical analyses. RESULTS: In all the patients' percutaneous catheters were placed successfully under the guidance of computed tomography. All of the patients in Group I (43; 50.6%) were treated with percutaneous catheter drainage alone, while the patients in Group II (42; 49.4%) were treated with PCD combined with ozone. The success rates of Group I and II were 81% and 94%, respectively (p < 0.05). The duration of fever as well as LOS was longer for Group I when compared with Group II (p < 0.05). CONCLUSIONS: Catheter drainage combined with ozone is an effective and safe treatment in PLA.

A Systematic Review and Meta-Analysis of C-Arm Cone-Beam CT-Guided Percutaneous Transthoracic Needle Biopsy of Lung Nodules.

BACKGROUND: A systematic review and meta-analysis of all available publications was performed to evaluate the diagnostic accuracy of percutaneous transthoracic needle biopsy (PTNB) using a C-Arm Cone-Beam CT (CBCT) system in patients with lung nodules. MATERIAL/METHODS: Thedatabases of PUBMED, OVID, EBSCO, EMBASE, and China National Knowledge Infrastructure (CNKI) were systematically searched for relevant original articles on the diagnostic accuracy of CBCT-guided PTNB for the diagnosis of nodules in the lungs. Diagnostic indices including sensitivity, specificity, positive likelihood ratio (PLR), negative likelihood ratio (NLR), diagnostic odds ratio (DOR) and diagnostic score (DS) were calculated. Moreover,summary receiver operating characteristic curves (SROC) were constructed with Stata (version 13.0), Rev Man (version 5.3), and Meta-disc (version 1.4) software. Other clinical indices such as incidence of complications were also recorded. RESULTS: Eight studies met the inclusion and exclusion criteria for the meta-analysis. The pooled sensitivity, specificity, PLR, NLR, DOR, DS, and SROC with 95% confidence intervals were 0.96 (0.93-0.98), 1.00 (0.91-1.00), 711.15 (9.48-53325.89), 0.04 (0.02-0.07), 16585.29 (284.88-9.7e+05), 9.72 (5.65-13.78), and 0.99 (0.97-0.99), respectively. The incidence of pneumothorax and hemorrhage was 10-29.27% and 1.22-47.25%, respectively. CONCLUSIONS: CBCT-guided PTNB has an acceptable rate of complications and is associated with a reasonable radiation exposure. Moreover, it is a highly accurate and safe technique for the diagnosis of lung nodules and can be recommended to be used in routine clinical practice.

Meta-analysis of quantitative diffusion-weighted MR imaging in differentiating benign and malignant pancreatic masses.

There have been numerous studies done to explore the diagnostic performance of quantitative diffusion-weighted (DW) MR imaging to differentiate between benign and malignant pancreatic masses. However, the results have been inconsistent. We performed a meta-analysis to investigate whether DW-MR imaging can differentiate between these two diseases. Databases including MEDLINE, EMBASE and Cochrane Library were utilized to find relevant articles published between January 2001 and January 2014. A Stata version 12.0 and a Meta-Disc version 1.4 were used to describe primary results. Twelve studies with 594 patients, which fulfilled the inclusion criteria, were enrolled for the analysis. The pooled sensitivity and specificity of DW imaging was 0.91 (95% CI: 0.84, 0.95) and 0.86 (95% CI: 0.76, 0.93) respectively. The area under the curve of the summary receiver operating characteristic was 0.95 (95% CI: 0.93, 0.96). The results indicated that DW imaging might be a valuable tool for differentiating benign and malignant pancreatic masses.

Study on the combined toxicity of DEHP and lead on the blood system of rats.

Di(2-ethylhexyl) phthalate (DEHP) is a commonly used phthalate ester compound, while lead is a persistent and bioaccumulative heavy metal. Both can be exposed to the body through a variety of ways, which may have an impact on the blood system. In this study, we examined the impact of co-exposure to DEHP (0, 10, 100 mg/kg) and Pb (0, 5, 50 mg/kg) on the blood system of male SD rats. The study revealed that continuous exposure to DEHP and Pb for 20 days resulted in a decrease in leukocytes and lymphocytes, while an increase in neutrophils and monocytes. Co-exposure led to a significant decrease in the spleen coefficients. Furthermore, the combined exposure could increase the ratio of bone marrow cells in G1 phase, and decrease the ratio of cells in S phase and G2 phase. Cytokine testing showed that combined exposure affects the secretion of hematopoietic factors and may cause bone marrow cell apoptosis. Single or combined exposure to DEHP and Pb can cause oxidative stress in serum and bone marrow. Overall, these results indicate that the co-exposure of DEHP and Pb adversely affected the blood system of rats, mainly due to the induction of oxidative stress and ultimately affects the secretion of cytokines. The combined effect of the two substances is primarily antagonistic. These results have important implications for the risk assessment of combined pollution and provide valuable theoretical guidance.

Magnetic resonance imaging-guided radiofrequency ablation of breast cancer: a current state of the art review.

With a gradual increase in breast cancer incidence and mortality rates and an urgent need to improve patient prognosis and cosmetology, magnetic resonance imaging (MRI)-guided radiofrequency ablation (RFA) therapy has attracted wide attention as a new treatment method for breast cancer. MRI-RFA results in a higher complete ablation rate and extremely low recurrence and complication rates. Thus, it may be used as an independent treatment for breast cancer or adjuvant to breast-conserving surgery to reduce the extent of breast resection. Furthermore, with MRI guidance, accurate control of RFA can be achieved, and breast cancer treatment can enter a new stage of minimally invasive, safe, and comprehensive therapy. With progress in MR thermometry technology, the applications of MRI are expected to broaden.

CT radiomics to differentiate neuroendocrine neoplasm from adenocarcinoma in patients with a peripheral solid pulmonary nodule: a multicenter study.

Purpose: To construct and validate a computed tomography (CT) radiomics model for differentiating lung neuroendocrine neoplasm (LNEN) from lung adenocarcinoma (LADC) manifesting as a peripheral solid nodule (PSN) to aid in early clinical decision-making. Methods: A total of 445 patients with pathologically confirmed LNEN and LADC from June 2016 to July 2023 were retrospectively included from five medical centers. Those patients were split into the training set (n = 316; 158 LNEN) and external test set (n = 129; 43 LNEN), the former including the cross-validation (CV) training set and CV test set using ten-fold CV. The support vector machine (SVM) classifier was used to develop the semantic, radiomics and merged models. The diagnostic performances were evaluated by the area under the receiver operating characteristic curve (AUC) and compared by Delong test. Preoperative neuron-specific enolase (NSE) levels were collected as a clinical predictor. Results: In the training set, the AUCs of the radiomics model (0.878 [95% CI: 0.836, 0.915]) and merged model (0.884 [95% CI: 0.844, 0.919]) significantly outperformed the semantic model (0.718 [95% CI: 0.663, 0.769], p both<.001). In the external test set, the AUCs of the radiomics model (0.787 [95% CI: 0.696, 0.871]), merged model (0.807 [95%CI: 0.720, 0.889]) and semantic model (0.729 [95% CI: 0.631, 0.811]) did not exhibit statistical differences. The radiomics model outperformed NSE in sensitivity in the training set (85.3% vs 20.0%; p <.001) and external test set (88.9% vs 40.7%; p = .002). Conclusion: The CT radiomics model could non-invasively, effectively and sensitively predict LNEN and LADC presenting as a PSN to assist in treatment strategy selection.

The CT-guided percutaneous drainage of pancreatic pseudocyst accompanied by pseudoaneurysm: A case report.

RATIONALE: This case report discusses the CT-guided percutaneous drainage of a pancreatic pseudocyst accompanied by a pseudoaneurysm. Pancreatic pseudocysts can erode the peripancreatic artery and produce pseudoaneurysms. This is rare, but it can be life-threatening. PATIENT CONCERNS: The case presented involves a 58-year-old female who was diagnosed with pancreatic cancer and underwent surgical treatment. She presented with hematochezia, dizziness, and hypodynamic findings with no obvious cause. Imaging revealed a pancreatic pseudocyst and small arterial aneurysms. To reduce the risk of aneurysm rupture, the patient underwent transcatheter arterial coil embolization. Three days later, CT-guided catheter drainage was performed to reduce the erosion of the arterial wall caused by pancreatic fluid. DIAGNOSES: The contrast-enhanced-CT imaging showed a round, slightly high-density lesion in the cyst, suggesting the presence of a pseudoaneurysm. INTERVENTIONS: The patient was sent for another transcatheter arterial embolization with coils and n-butyl-2-cyanoacrylate. OUTCOMES: After receiving the transcatheter arterial embolization, the patient had no serious bleeding or other complications. LESSONS: Early detection and accurate assessment of pseudoaneurysms are essential for appropriate management. This case shows that contrast-enhanced CT is necessary before CT-guided percutaneous drainage of pancreatic pseudocysts. It also shows that, due to the many complications that pancreatic pseudocysts may cause, appropriate treatment of pseudocysts complicated with pseudoaneurysm has important clinical significance.

Nano-enzyme functionalized hydrogels promote diabetic wound healing through immune microenvironment modulation.

Non-healing diabetic wounds often culminate in amputation and mortality. The main pathophysiological features in diabetic wounds involve the accumulation of M1-type macrophages and excessive oxidative stress. In this study, we engineered a nano-enzyme functionalized hydrogel by incorporating a magnesium ion-doped molybdenum-based polymetallic oxide (Mg-POM), a novel bioactive nano-enzyme, into a GelMA hydrogel, to obtain the GelMA@Mg-POM system to enhance diabetic wound healing. GelMA@Mg-POM was crosslinked using UV light, yielding a hydrogel with a uniformly porous three-dimensional mesh structure. In vitro experiments showed that GelMA@Mg-POM extraction significantly enhanced human umbilical vein endothelial cell (HUVEC) migration, scavenged ROS, improved the inflammatory microenvironment, induced macrophage reprogramming towards M2, and promoted HUVEC regeneration of CD31 and fibroblast regeneration of type I collagen. In in vivo experiments, diabetic rat wounds treated with GelMA@Mg-POM displayed enhanced granulation tissue genesis and collagen production, as evidenced by HE and Masson staining. Immunohistochemistry demonstrated the ability of GelMA@Mg-POM to mitigate macrophage-associated inflammatory responses and promote angiogenesis. Overall, these findings suggest that GelMA@Mg-POM holds significant promise as a biomaterial for treating diabetic wounds.

Advances in antitumor application of ROS enzyme-mimetic catalysts.

The rapid growth of research on enzyme-mimetic catalysts (Enz-Cats) is expected to promote further advances in nanomedicine for biological detection, diagnosis and treatment of disease, especially tumors. ROS-based nanomedicines present fascinating potential in antitumor therapy owing to the rapid development of nanotechnology. In this review, we focus on the applications of Enz-Cats based on ROS in antitumor therapy. Firstly, the definition and category of ROS are introduced, and the key factors enhancing ROS levels are carefully elucidated. Then, the rationally engineered Enz-Cats via different synthetic approaches with high ROS-producing efficiencies are comprehensively discussed. Subsequently, oncotherapy application of Enz-Cats is comprehensively discussed, which integrates diverse synergistic treatment modalities and exhibits high efficiency in ROS generation. Finally, the challenges and future research direction of this field are presented. This review is dedicated to unraveling the enigmas surrounding the interplay of nanomedicine and organisms.

The white matter characteristic of the genu of corpus callosum coupled with pain intensity and negative emotion scores in patients with trigeminal neuralgia: a multivariate analysis.

Background: Trigeminal neuralgia (TN) is a chronic neuropathic pain disorder that not only causes intense pain but also affects the psychological health of patients. Since TN pain intensity and negative emotion may be grounded in our own pain experiences, they exhibit huge inter-individual differences. This study investigates the effect of inter-individual differences in pain intensity and negative emotion on brain structure in patients with TN and the possible pathophysiology mechanism underlying this disease. Methods: T1 weighted magnetic resonance imaging and diffusion tensor imaging scans were obtained in 46 patients with TN and 35 healthy controls. All patients with TN underwent pain-related and emotion-related questionnaires. Voxel-based morphometry and regional white matter diffusion property analysis were used to investigate whole brain grey and white matter quantitatively. Innovatively employing partial least squares correlation analysis to explore the relationship among pain intensity, negative emotion and brain microstructure in patients with TN. Results: Significant difference in white matter integrity were identified in patients with TN compared to the healthy controls group; The most correlation brain region in the partial least squares correlation analysis was the genus of the corpus callosum, which was negatively associated with both pain intensity and negative emotion. Conclusion: The genu of corpus callosum plays an important role in the cognition of pain perception, the generation and conduction of negative emotions in patients with TN. These findings may deepen our understanding of the pathophysiology of TN.

Radiomics nomogram based on MRI water imaging identifying symptomatic nerves of patients with primary trigeminal neuralgia: A preliminary study.

The study proposes a combined nomogram based on radiomics features from magnetic resonance neurohydrography and clinical features to identify symptomatic nerves in patients with primary trigeminal neuralgia. We retrospectively analyzed 140 patients with clinically confirmed trigeminal neuralgia. Out of these, 24 patients constituted the external validation set, while the remaining 116 patients contributed a total of 231 nerves, comprising 118 symptomatic nerves, and 113 normal nerves. Radiomics features were extracted from the MRI water imaging (t2-mix3d-tra-spair). Radiomics feature selection was performed using L1 regularization-based regression, while clinical feature selection utilized univariate analysis and multivariate logistic regression. Subsequently, radiomics, clinical, and combined models were developed by using multivariate logistic regression, and a nomogram of the combined model was drawn. The performance of nomogram in discriminating symptomatic nerves was assessed through the area under the curve (AUC) of receiver operating characteristics, accuracy, and calibration curves. Clinical applications of the nomogram were further evaluated using decision curve analysis. Five clinical factors and 13 radiomics signatures were ultimately selected to establish predictive models. The AUCs in the training and validation cohorts were 0.77 (0.70-0.84) and 0.82 (0.72-0.92) with the radiomics model, 0.69 (0.61-0.77) and 0.66 (0.53-0.79) with the clinical model, 0.80 (0.74-0.87), and 0.85 (0.76-0.94) with the combined model, respectively. In the external validation set, the AUCs for the clinical, radiomics, and combined models were 0.70 (0.60-0.79), 0.78 (0.65-0.91), and 0.81 (0.70-0.93), respectively. The calibration curve demonstrated that the nomogram exhibited good predictive ability. Moreover, The decision curve analysis curve indicated shows that the combined model holds high clinical application value. The integrated model, combines radiomics features from magnetic resonance neurohydrography with clinical factors, proves to be effective in identify symptomatic nerves in trigeminal neuralgia. The diagnostic efficacy of the combined model was notably superior to that of the model constructed solely from conventional clinical features.

Magnetic resonance imaging for prostate cancer clinical application.

As prostate cancer is a biologically heterogeneous disease for which a variety of treatment options are available, the major objective of prostate cancer imaging is to achieve more precise disease characterization. In clinical practice, magnetic resonance imaging (MRI) is one of the imaging tools for the evaluation of prostate cancer, the fusion of MRI or dynamic contrast-enhanced MRI (DCE-MRI) with magnetic resonance spectroscopic imaging (MRSI) is improving the evaluation of cancer location, size, and extent, while providing an indication of tumor aggressiveness. This review summarizes the role of MRI in the application of prostate cancer and describes molecular MRI techniques (including MRSI and DCE-MRI) for aiding prostate cancer management.

Establishment of a rabbit liver metastasis model by percutaneous puncture of the spleen and implantation of the VX2 tumor strain under CT guidance.

This study aimed to compare the feasibility, success rate, and safety of establishing a rabbit VX2 liver metastasis model by percutaneous splenic implantation under CT guidance and open splenic implantation of the VX2 tumor strain. Fifty-two New Zealand white rabbits were randomly divided into group A (the percutaneous puncture group) (n = 26) and group B (the laparotomy group) (n = 26). In group A, 26 New Zealand white rabbits were implanted with tumor strains by percutaneous splenic puncture under CT guidance. In group B, 26 New Zealand white rabbits were implanted with tumor strains in the spleen by laparotomy. After 2-3 weeks of implantation, both group A and group B underwent MRI to confirm tumor growth in the spleen and metastasis to the liver. Two experimental rabbits randomly selected from groups A and B were killed for pathological examination. The success rate, complication rate, and operation time in groups A and B were compared and analyzed. A total of 23 rabbits in group A were successfully induced, and the success rate was 88.5% (23/26). The average time of operation was 14.42 ± 3.26 min. A total of 22 rabbits in group B were successfully induced, and the success rate was 84.6% (22/26). The average time of operation in group B was 23.69 ± 5.27 min. There was no significant difference in the success rate of induction between the two groups (P > 0.05). The MRI manifestations of liver metastases were multiple nodular and punctate abnormal signal shadows in the liver. Hematoxylin-eosin (HE) staining showed a large number of tumor cells in the tumor area. CT-guided percutaneous splenic implantation of the VX2 tumor strain to establish a rabbit liver metastasis model is a minimally invasive and feasible inducing method. The success rate of this technique is not lower than that of open splenic implantation, with low incidence of complications, and short operation time.

Asymmetry of brain development in adolescent rats studied by 3.0 T magnetic resonance imaging.

To study the developmental patterns of brain structure in adolescent rats based on the registration with the SIGMA template by 3.0T MRI. Forty male Sprague-Dawley rats (180-220 g) were randomly divided into four groups. Rats in the four groups underwent 3.0 T MRI head scans at 7, 11, 15, and 19 weeks of age, respectively. The voxel-based morphological analysis of the rat brain was performed by coregistration with the SIGMA rat brain template. 3.0 T MRI can be used to study the anatomical structure of the rat brain by registration with the SIGMA template The gray matter volume of the bilateral hippocampus and bilateral entorhinal cortex increased significantly in the development of the rat from 7 to 19 weeks of age. In this period, the subtle structure of the rat brain is asymmetrically developed. The rat aged 7-19 weeks has asymmetrical gray matter volume development in the bilateral entorhinal cortex and hippocampus.

Establishment of a Rat Model of Infraorbital Neuroinflammation Under CT Guidance.

INTRODUCTION: The aim is to establish a rat model of infraorbital neuroinflammation with less trauma, stable pain, and a long duration of pain. The pathogenesis of TN is not fully clear. There are various models of TN in rats with different disadvantages, such as damaging the surrounding structures and inaccuracy of location for infraorbital nerve (ION). We aim to establish a rat model of infraorbital neuroinflammation with minimal trauma, a simple operation, and accurate positioning under CT guidance to help us study the pathogenesis of trigeminal neuralgia. METHODS: Thirty-six adult male Sprague Dawley rats (180-220 g) were randomly divided into 2 groups and injected with talc suspension or saline through the infraorbital foramen (IOF) under CT guidance. Mechanical thresholds were measured in the right ION innervation region of 24 rats over 12 postoperative weeks. At 4 weeks, 8 weeks, and 12 weeks after the operation, the inflammatory involvement of the surgical area was evaluated by MRI, and neuropathy was observed using a transmission electron microscope (TEM). RESULTS: The talc group had a significant decrease in the mechanical threshold at 3 days after surgery that continued until 12 weeks post-operation, and the talc group had a significantly lower mechanical threshold than the saline group 10 weeks post-operation. The talc group had significantly impaired trigeminal nerve (TGN) myelin after 8 weeks post-operation. CONCLUSION: The rat model of infraorbital neuroinflammation established by CT-guided injection of talc into the IOF is a simple operation that results in less trauma, stable pain, and a long duration of pain. Moreover, infraorbital neuroinflammation in peripheral branches of the TGN can cause demyelination of the TGN in the intracranial segment.

Preoperative Radiomics Nomogram Based on CT Image Predicts Recurrence-Free Survival After Surgical Resection of Hepatocellular Carcinoma.

RATIONALE AND OBJECTIVES: To construct preoperative models based on CT radiomics, radiologic and clinical features to predict recurrence-free survival (RFS) after liver resection (LR) of BCLC 0 to B stage hepatocellular carcinoma (HCC) and to classify the prognosis. MATERIALS AND METHODS: This study retrospectively analyzed 161 HCC patients who underwent radical LR. Two methods, the least absolute shrinkage and selection operator and random survival forest analysis, were performed for radiomics signature (RS) construction. Univariate and multivariate stepwise Cox regression analyses were performed to establish a combined nomogram (RCN) of RS and clinical parameters and a clinical nomogram (CN). The performance of the models was assessed comprehensively using Harrell's concordance index (C-index), the calibration curve, and decision curve analysis. The discrimination accuracy of the models was compared using integrated discrimination improvement index (IDI). The risk stratification effect was assessed with Kaplan-Meier survival analysis and subgroup analysis. RESULTS: The RCN achieved a C-index of 0.792/0.758 in the training/validation set, which was higher than the CN, RS, and BCLC stage system. The discriminatory accuracy of the RCN was improved when compared to the CN, RS, and BCLC staging systems (IDI > 0). Decision curve analysis reflected the clinical net benefit of the RCN. The RCN allows risk stratification of patients in different clinical subgroups. CONCLUSION: The integrated model combining RS and clinical factors can more effectively predict RFS after LR of BCLC 0 to B stage HCC patients and can effectively stratify the prognostic risk.

Deep learning-driven MRI trigeminal nerve segmentation with SEVB-net.

Purpose: Trigeminal neuralgia (TN) poses significant challenges in its diagnosis and treatment due to its extreme pain. Magnetic resonance imaging (MRI) plays a crucial role in diagnosing TN and understanding its pathogenesis. Manual delineation of the trigeminal nerve in volumetric images is time-consuming and subjective. This study introduces a Squeeze and Excitation with BottleNeck V-Net (SEVB-Net), a novel approach for the automatic segmentation of the trigeminal nerve in three-dimensional T2 MRI volumes. Methods: We enrolled 88 patients with trigeminal neuralgia and 99 healthy volunteers, dividing them into training and testing groups. The SEVB-Net was designed for end-to-end training, taking three-dimensional T2 images as input and producing a segmentation volume of the same size. We assessed the performance of the basic V-Net, nnUNet, and SEVB-Net models by calculating the Dice similarity coefficient (DSC), sensitivity, precision, and network complexity. Additionally, we used the Mann-Whitney U test to compare the time required for manual segmentation and automatic segmentation with manual modification. Results: In the testing group, the experimental results demonstrated that the proposed method achieved state-of-the-art performance. SEVB-Net combined with the ωDoubleLoss loss function achieved a DSC ranging from 0.6070 to 0.7923. SEVB-Net combined with the ωDoubleLoss method and nnUNet combined with the DoubleLoss method, achieved DSC, sensitivity, and precision values exceeding 0.7. However, SEVB-Net significantly reduced the number of parameters (2.20 M), memory consumption (11.41 MB), and model size (17.02 MB), resulting in improved computation and forward time compared with nnUNet. The difference in average time between manual segmentation and automatic segmentation with manual modification for both radiologists was statistically significant (p < 0.001). Conclusion: The experimental results demonstrate that the proposed method can automatically segment the root and three main branches of the trigeminal nerve in three-dimensional T2 images. SEVB-Net, compared with the basic V-Net model, showed improved segmentation performance and achieved a level similar to nnUNet. The segmentation volumes of both SEVB-Net and nnUNet aligned with expert annotations but SEVB-Net displayed a more lightweight feature.