BgNet: Classification of benign and malignant tumors with MRI multi-plane attention learning.

Objectives: To propose a deep learning-based classification framework, which can carry out patient-level benign and malignant tumors classification according to the patient's multi-plane images and clinical information. Methods: A total of 430 cases of spinal tumor, including axial and sagittal plane images by MRI, of which 297 cases for training (14072 images), and 133 cases for testing (6161 images) were included. Based on the bipartite graph and attention learning, this study proposed a multi-plane attention learning framework, BgNet, for benign and malignant tumor diagnosis. In a bipartite graph structure, the tumor area in each plane is used as the vertex of the graph, and the matching between different planes is used as the edge of the graph. The tumor areas from different plane images are spliced at the input layer. And based on the convolutional neural network ResNet and visual attention learning model Swin-Transformer, this study proposed a feature fusion model named ResNetST for combining both global and local information to extract the correlation features of multiple planes. The proposed BgNet consists of five modules including a multi-plane fusion module based on the bipartite graph, input layer fusion module, feature layer fusion module, decision layer fusion module, and output module. These modules are respectively used for multi-level fusion of patient multi-plane image data to realize the comprehensive diagnosis of benign and malignant tumors at the patient level. Results: The accuracy (ACC: 79.7%) of the proposed BgNet with multi-plane was higher than that with a single plane, and higher than or equal to the four doctors' ACC (D1: 70.7%, p=0.219; D2: 54.1%, p<0.005; D3: 79.7%, p=0.006; D4: 72.9%, p=0.178). Moreover, the diagnostic accuracy and speed of doctors can be further improved with the aid of BgNet, the ACC of D1, D2, D3, and D4 improved by 4.5%, 21.8%, 0.8%, and 3.8%, respectively. Conclusions: The proposed deep learning framework BgNet can classify benign and malignant tumors effectively, and can help doctors improve their diagnostic efficiency and accuracy. The code is available at https://github.com/research-med/BgNet.

Predicting postoperative recovery in cervical spondylotic myelopathy: construction and interpretation of T2*-weighted radiomic-based extra trees models.

OBJECTIVES: Conventional MRI may not be ideal for predicting cervical spondylotic myelopathy (CSM) prognosis. In this study, we used radiomics in predicting postoperative recovery in CSM. We aimed to develop and validate radiomic feature-based extra trees models. METHODS: There were 151 patients with CSM who underwent preoperative T2-/ T2*-weighted imaging (WI) and surgery. They were divided into good/poor outcome groups based on the recovery rate. Datasets from multiple scanners were randomised into training and internal validation sets, while the dataset from an independent scanner was used for external validation. Radiomic features were extracted from the transverse spinal cord at the maximum compressed level. Threshold selection algorithm, collinearity removal, and tree-based feature selection were applied sequentially in the training set to obtain the optimal radiomic features. The classification of intramedullary increased signal on T2/T2*WI and compression ratio of the spinal cord on T2*WI were selected as the conventional MRI features. Clinical features were age, preoperative mJOA, and symptom duration. Four models were constructed: radiological, radiomic, clinical-radiological, and clinical-radiomic. An AUC significantly > 0.5 was considered meaningful predictive performance based on the DeLong test. The mean decrease in impurity was used to measure feature importance. p < 0.05 was considered statistically significant. RESULTS: On internal and external validations, AUCs of the radiomic and clinical-radiomic models, and radiological and clinical-radiological models ranged from 0.71 to 0.81 (significantly > 0.5) and 0.40 to 0.55, respectively. Wavelet-LL first-order variance was the most important feature in the radiomic model. CONCLUSION: Radiomic features, especially wavelet-LL first-order variance, contribute to meaningful predictive models for CSM prognosis. KEY POINTS: • Conventional MRI features may not be ideal in predicting prognosis. • Radiomics provides greater predictive efficiency in the recovery from cervical spondylotic myelopathy.

Utility of Advanced DWI in the Detection of Spinal Cord Microstructural Alterations and Assessment of Neurologic Function in Cervical Spondylotic Myelopathy Patients.

BACKGROUND: Diffusion-weighted imaging (DWI) can quantify the microstructural changes in the spinal cord. It might be a substitute for T2 increased signal intensity (ISI) for cervical spondylotic myelopathy (CSM) evaluation and prognosis. PURPOSE: The purpose of the study is to investigate the relationship between DWI metrics and neurologic function of patients with CSM. STUDY TYPE: Retrospective. POPULATION: Forty-eight patients with CSM (18.8% females) and 36 healthy controls (HCs, 25.0% females). FIELD STRENGTH/SEQUENCE: 3 T; spin-echo echo-planar imaging-DWI; turbo spin-echo T1/T2; multi-echo gradient echo T2*. ASSESSMENT: For patients, conventional MRI indicators (presence and grades of T2 ISI), DWI indicators (neurite orientation dispersion and density imaging [NODDI]-derived isotropic volume fraction [ISOVF], intracellular volume fraction, and orientation dispersion index [ODI], diffusion tensor imaging [DTI]-derived fractional anisotropy [FA] and mean diffusivity [MD], and diffusion kurtosis imaging [DKI]-derived FA, MD, and mean kurtosis), clinical conditions, and modified Japanese Orthopaedic Association (mJOA) were recorded before the surgery. Neurologic function improvement was measured by the 3-month follow-up recovery rate (RR). For HCs, DWI, and mJOA were measured as baseline comparison. STATISTICAL TESTS: Continuous (categorical) variables were compared between patients and HCs using Student's t-tests or Mann-Whitney U tests (chi-square or Fisher exact tests). The relationships between DWI metrics/conventional MRI findings, and the pre-operative mJOA/RR were assessed using correlation and multivariate analysis. P < 0.05 was considered statistically significant. RESULTS: Among patients, grades of T2 ISI were not correlated with pre-surgical mJOA/RR (P = 0.717  and 0.175, respectively). NODDI ODI correlated with pre-operative mJOA (r = -0.31). DTI FA, DKI FA, and NODDI ISOVF were correlated with the recovery rate (r = 0.31, 0.41, and -0.34, respectively). In multivariate analysis, NODDI ODI (DTI FA, DKI FA, NODDI ISOVF) significantly contributed to the pre-operative mJOA (RR) after adjusting for age. DATA CONCLUSION: DTI FA, DKI FA, and NODDI ISOVF are predictors for prognosis in patients with CSM. NODDI ODI can be used to evaluate CSM severity. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY STAGE: 5.

Optimal machine learning methods for radiomic prediction models: Clinical application for preoperative T2*-weighted images of cervical spondylotic myelopathy.

INTRODUCTION: Predicting the postoperative neurological function of cervical spondylotic myelopathy (CSM) patients is generally based on conventional magnetic resonance imaging (MRI) patterns, but this approach is not completely satisfactory. This study utilized radiomics, which produced advanced objective and quantitative indicators, and machine learning to develop, validate, test, and compare models for predicting the postoperative prognosis of CSM. MATERIALS AND METHODS: In total, 151 CSM patients undergoing surgical treatment and preoperative MRI was retrospectively collected and divided into good/poor outcome groups based on postoperative modified Japanese Orthopedic Association (mJOA) scores. The datasets obtained from several scanners (an independent  scanner) for the training (testing) cohort were used for cross-validation (CV). Radiological models based on the intramedullary hyperintensity and compression ratio were constructed with 14 binary classifiers. Radiomic models based on 237 robust radiomic features were constructed with the same 14 binary classifiers in combination with 7 feature reduction methods, resulting in 98 models. The main outcome measures were the area under the receiver operating characteristic curve (AUROC) and accuracy. RESULTS: Forty-one (11) radiomic models were superior to random guessing during CV (testing), with significant increased AUROC and/or accuracy (P AUROC < .05 and/or P accuracy < .05). One radiological model performed better than random guessing during CV (P accuracy < .05). In the testing cohort, the linear SVM preprocessor + SVM, the best radiomic model (AUROC: 0.74 ± 0.08, accuracy: 0.73 ± 0.07), overperformed the best radiological model (P AUROC = .048). CONCLUSION: Radiomic features can predict postoperative spinal cord function in CSM patients. The linear SVM preprocessor + SVM has great application potential in building radiomic models.

Open-Ring Butenolides from a Marine-Derived Anti-Neuroinflammatory Fungus Aspergillus terreus Y10.

To investigate structurally novel and anti-neuroinflammatory natural compounds from marine-derived microorganisms, the secondary metabolites of Aspergillus terreus Y10, a fungus separated from the sediment of the coast in the South China Sea, were studied. Three new compounds (2⁻4), with novel open-ring butenolide skeletons, were isolated from the ethyl acetate extract of the culture medium. In addition, a typical new butenolide, asperteretal F (1), was found to dose-dependently inhibit tumor necrosis factor (TNF-α) generation with an IC50 of 7.6 µg/mL. The present study shows the existence of open-ring butenolides, and suggests that butenolides such as asperteretal F (1) are a promising new anti-neuroinflammatroy candidate for neurodegenerative diseases.

Epigenetic upregulation of CXCL12 expression mediates antitubulin chemotherapeutics-induced neuropathic pain.

Clinically, Microtubule-targeted agents-induced neuropathic pain hampers chemotherapeutics for patients with cancer. Here, we found that application of paclitaxel or vincristine increased the protein and mRNA expression of CXCL12 and frequency and amplitude of miniature excitatory post synaptic currents (mEPSCs) in spinal dorsal horn neurons. Spinal local application of CXCL12 induced the long-term potentiation of nociceptive synaptic transmission and increased the amplitude of mEPSCs. Inhibition of CXCL12 using the transgenic mice (CXCL12) or neutralizing antibody or siRNA ameliorated the mEPSC's enhancement and mechanical allodynia. In addition, paclitaxel and vincristine both could increase the phosphorylation of signal transducer and activator of transcription 3 (STAT3) and the acetylation of histone H4 in the CXCL12-expressing neurons. Immunoprecipitation and chromatin immunoprecipitation assays demonstrated that antitubulin chemotherapeutics increased the binding of STAT3 to the CXCL12 gene promoter and the interaction between STAT3 and p300, and contributed to the enhanced transcription of CXCL12 by increasing the acetylation of histone H4 in CXCL12 gene promoter. Inhibition of STAT3 by intrathecal injection of adeno-associated virus encoding Cre and green fluorescent protein into STAT3 mice or inhibitor S3I-201 into rats suppressed the CXCL12 upsurge by decreasing the acetylation of histone H4. Finally, blockade of CXCR4 but not CXCR7 ameliorated the paclitaxel- or vincristine-induced mechanical allodynia. Together, these results suggested that enhanced interaction between STAT3 and p300 mediated the epigenetic upregulation of CXCL12 in dorsal horn neurons, which contributed to the antitubulin chemotherapeutics-induced persistent pain.

The inhibition of spinal synaptic plasticity mediated by activation of AMP-activated protein kinase signaling alleviates the acute pain induced by oxaliplatin.

Our recent findings demonstrated that oxaliplatin entering CNS may directly induce spinal central sensitization, and contribute to the rapid development of CNS-related side effects including acute pain during chemotherapy. However, the mechanism is largely unclear. In the current study, we found that the amplitude of C-fiber-evoked field potentials was significantly increased and the expression of phosphorylated mammalian AMP-activated protein kinase α (AMPKα) was markedly decreased following high frequency stimulation (HFS) or single intraperitoneal injection of oxaliplatin (4mg/kg). Spinal local application of AMPK agonist metformin (25µg) prevented the long term potentiation (LTP) induction and the activation of mTOR/p70S6K signal pathway, and significantly attenuated the acute thermal hyperalgesia and mechanical allodynia following single oxaliplatin treatment. Importantly, we found that incubation of low concentration oxaliplatin at dose of 6.6nM (the detected concentration in CSF following a single intraperitoneal injection of oxaliplatin) also significantly inhibited the AMPKα activation and increased the amplitude of sEPSCs, the number of action potential, and the expression of p-mTOR and p-p70S6K in spinal cord slices. Metformin (25µg) or rapamycin (2µg) inhibited the increased excitability of dorsal horn neurons and the decrease of p-AMPKα expression induced by low concentration oxaliplatin incubation. Furthermore, spinal application of AMPK inhibitor compound C (5µg) induced the spinal LTP, thermal hyperalgesia and mechanical allodynia, and rapamycin attenuated the spinal LTP, the thermal hyperalgesia and mechanical allodynia following oxaliplatin treatment (i.p.). Local application of metformin significantly decreased the mTOR and p70S6K activation induced by tetanus stimulation or oxaliplatin (i.p.). These results suggested that the decreased AMPKα activity via negatively regulating mTOR/p70S6K signal pathway enhanced the synaptic plasticity and contributed to acute pain induced by low concentration of oxaliplatin entering CNS.

mir-500-Mediated GAD67 Downregulation Contributes to Neuropathic Pain.

UNLABELLED: Neuropathic pain is a common neurobiological disease involving multifaceted maladaptations ranging from gene modulation to synaptic dysfunction, but the interactions between synaptic dysfunction and the genes that are involved in persistent pain remain elusive. In the present study, we found that neuropathic pain induced by the chemotherapeutic drug paclitaxel or L5 ventral root transection significantly impaired the function of GABAergic synapses of spinal dorsal horn neurons via the reduction of the GAD67 expression. We also found that mir-500 expression was significantly increased and involved in the modulation of GAD67 expression via targeting the specific site of Gad1 gene in the dorsal horn. In addition, knock-out of mir-500 or using mir-500 antagomir rescued the GABAergic synapses in the spinal dorsal horn neurons and attenuated the sensitized pain behavior in the rats with neuropathic pain. To our knowledge, this is the first study to investigate the function significance and the underlying molecular mechanisms of mir-500 in the process of neuropathic pain, which sheds light on the development of novel therapeutic options for neuropathic pain. SIGNIFICANCE STATEMENT: Neuropathic pain is a common neurobiological disease involving multifaceted maladaptations ranging from gene modulation to synaptic dysfunction, but the underlying molecular mechanisms remain elusive. The present study illustrates for the first time a mir-500-mediated mechanism underlying spinal GABAergic dysfunction and sensitized pain behavior in neuropathic pain induced by the chemotherapeutic drug paclitaxel or L5 ventral root transection, which sheds light on the development of novel therapeutic options for neuropathic pain.

Cerebrospinal Fluid Oxaliplatin Contributes to the Acute Pain Induced by Systemic Administration of Oxaliplatin.

BACKGROUND: Systemic administration of oxaliplatin has no effect on the tumors in the central nervous system (CNS) due to the limited concentration of oxaliplatin in the cerebrospinal fluid (CSF), while it was clinically reported that oxaliplatin can induce acute encephalopathy. Currently, the impairment of neuronal functions in the CNS after systemic administration of oxaliplatin remains uninvestigated. METHODS: The von Frey test and the plantar test were performed to evaluate neuropathic pain behavior after a single intraperitoneal administration of oxaliplatin (4 mg/kg) in rats. Inductively coupled plasma-mass spectrometry, electrophysiologic recording, real-time quantitative reverse transcription polymerase chain reaction, chromatin immunoprecipitation, Western blot, immunohistochemistry, and small interfering RNA were applied to understand the mechanisms. RESULTS: Concentration of oxaliplatin in CSF showed a time-dependent increase after a single administration of oxaliplatin. Spinal application of oxaliplatin at the detected concentration (6.6 nM) significantly increased the field potentials in the dorsal horn, induced acute mechanical allodynia (n = 12 each) and thermal hyperalgesia (n = 12 each), and enhanced the evoked excitatory postsynaptic currents and spontaneous excitatory postsynaptic currents in the projection neurokinin 1 receptor-expressing lamina I to II neurons. The authors further found that oxaliplatin significantly increased the nuclear factor-κB p65 binding and histone H4 acetylation in cx3cl1 promoter region. Thus, the upregulated spinal CX3CL1 markedly mediated the induction of central sensitization and acute pain behavior after oxaliplatin administration. CONCLUSIONS: The findings of this study suggested that oxaliplatin in CSF may directly impair the normal function of central neurons and contribute to the rapid development of CNS-related side effects during chemotherapy. This provides novel targets to prevent oxaliplatin-induced acute painful neuropathy and encephalopathy.

Inhibition of the STAT3 signaling pathway is involved in the antitumor activity of cepharanthine in SaOS2 cells.

AIM: To investigate the molecular mechanisms underlying the antitumor activity of cepharanthine (CEP), an alkaloid extracted from Stephania cepharantha Hayata. METHODS: Human osteosarcoma cell line SaOS2 was used. MTT assay, Hoechst 33342 nuclear staining, flow cytometry, Western blotting and nude mouse xenografts of SaOS2 cells were applied to examine the antitumor activity of CEP in vitro and in vivo. The expression levels of STAT3 and its downstream signaling molecules were measured with Western blotting and immunochemistry analysis. The activity of STAT3 was detected based on the phosphorylation level of STAT3, luciferase gene reporter assay and translocation of STAT3 to the nucleus. RESULTS: Treatment of SaOS2 cells with CEP (2.5-20 µmol/L) inhibited the cell growth in a concentration- and time-dependent manner. CEP (10 µmol/L) caused cell cycle arrest at G(1) phase and induced apoptosis of SaOS2 cells. CEP (10 and 15 µmol/L) significantly decreased the expression of STAT3 in SaOS2 cells. Furthermore, CEP (5 and 10 µmol/L) significantly inhibited the expression of target genes of STAT3, including the anti-apoptotic gene Bcl-xL and the cell cycle regulators c-Myc and cyclin D1. In nude mouse xenografts of SaOS2 cells, CEP (20 mg·kg(-1)·d(-1), ip for 19 d) significantly reduced the volume and weight of the tumor. CONCLUSION: Our findings suggest that inhibition of STAT3 signaling pathway is involved in the anti-tumor activity of CEP.

[Effects of intrathecal ouabain and tizanidine injection for treatment of neuropathic pain in rats].

OBJECTIVE: To investigate the effects of intrathecal ouabain and tizanidine injection for treatment of neuropathic pain in rats. METHODS: Male SD rats weighing 250-300 g were randomly divided into 5 groups (n = 6), namely the control group, ouabain group, tizanidine group, combined ouabain and tizanidine injection group, and the antagonist group. Intrathecal catheter was implanted 7 days before spinal nerve ligation to establish the neuropathic pain model. Mechanical withdrawal threshold (MWT) before and after intrathecal administration of the agents was recorded in the rats. Isobolographic analysis was performed to evaluate the interactions between the agents. RESULTS: Intrathecal injection of ouabain (0.25-5 microg) or tizanidine (0.5-5 microg) alone produced dose-dependent analgesic effect against the neuropathic pain (P < 0.05). Isobolographic analysis revealed a synergistic interaction between ouabain and tizanidine. Intrathecal pretreatment with atropine (5 microg) or yohimbine (20 microg) antagonized the effects of ouabain and tizanidine administered alone or in combination (P < 0.05). CONCLUSION: Intathecal injection of ouabain or tizanidine produces dose-dependent analgesic effects against neuropathic pain, and their synergistic effect after combined injection probably involves the cholinergic transmission and alpha2 receptor.

[Prospective comparison of ultrasonography, helical computed tomography, magnetic resonance imaging, and endoscopic ultrasonography in assessing locoregional invasion of primary pancreatic carcinoma].

OBJECTIVE: To evaluate prospectively the efficacy and clinical significance of ultrasonography (US), helical computed tomography (HCT), endoscopic ultrasonography (EUS) and magnetic resonance imaging (MRI) in assessing locoregional invasion to the surrounding tissue or organs of primary pancreatic carcinoma. METHODS: Sixty-eight consecutive patients with pancreatic carcinoma underwent US, HCT, EUS and MRI examinations before surgical exploration. All imaging results in terms of tumor size and locoregional invasion were assessed separately by two diagnostic radiologists and compared with the surgical and pathological findings. RESULTS: Among the HCT, US, EUS and MRI examinations, EUS had the highest accuracy in assessing tumor size with a regression coefficient for the maximal and minimal diameter of 1.0250 (P = 0.0426) and 0.9873 (P < 0.0001), respectively. In the assessment of locoregional invasion to the surrounding tissue or organs, EUS also had the highest accuracy (75.8%) and sensitivity (80.0%), but MRI had the highest positive predicting value (97.4%). None of these four imaging techniques was significantly correlated with the surgical findings when analyzed by univariate logistic regression. CONCLUSION: Endoscopic ultrasonography may be the most useful imaging technique in assessing tumor size, but for assessing loco-regional invasion of primary pancreatic carcinoma, combination of more than one imaging techniques may be necessary.