A potassium-chloride co-transporter with altered genome architecture functions as a suppressor in glioma.

Gliomas, the most lethal tumours in brain, have a poor prognosis despite accepting standard treatment. Limited benefits from current therapies can be attributed to genetic, epigenetic and microenvironmental cues that affect cell programming and drive tumour heterogeneity. Through the analysis of Hi-C data, we identified a potassium-chloride co-transporter SLC12A5 associated with disrupted topologically associating domain which was downregulated in tumour tissues. Multiple independent glioma cohorts were included to analyse the characterization of SLC12A5 and found it was significantly associated with pathological features, prognostic value, genomic alterations, transcriptional landscape and drug response. We constructed two SLC12A5 overexpression cell lines to verify the function of SLC12A5 that suppressed tumour cell proliferation and migration in vitro. In addition, SLC12A5 was also positively associated with GABAA receptor activity and negatively associated with pro-tumour immune signatures and immunotherapy response. Collectively, our study provides a comprehensive characterization of SLC12A5 in glioma and supports SLC12A5 as a potential suppressor of disease progression.

Integration of single-cell regulon atlas and multi-omics data for prognostic stratification and personalized treatment prediction in human lung adenocarcinoma.

Transcriptional programs are often dysregulated in cancers. A comprehensive investigation of potential regulons is critical to the understanding of tumorigeneses. We first constructed the regulatory networks from single-cell RNA sequencing data in human lung adenocarcinoma (LUAD). We next introduce LPRI (Lung Cancer Prognostic Regulon Index), a precision oncology framework to identify new biomarkers associated with prognosis by leveraging the single cell regulon atlas and bulk RNA sequencing or microarray datasets. We confirmed that LPRI could be a robust biomarker to guide prognosis stratification across lung adenocarcinoma cohorts. Finally, a multi-omics data analysis to characterize molecular alterations associated with LPRI was performed from The Cancer Genome Atlas (TCGA) dataset. Our study provides a comprehensive chart of regulons in LUAD. Additionally, LPRI will be used to help prognostic prediction and developing personalized treatment for future studies.

A novel co-targeting strategy of EGFR/SEC61G for multi-modality fluorescence/MR/photoacoustic imaging of glioblastoma.

Surgical resection is often the first choice and cornerstone therapy of glioblastoma; the degree of complete resection, as an important prognostic factor, is directly related to individuals' long-term outcomes. However, current imaging approaches, subjected to its single-function and poor targeting affinity, used to have disappointing performance on preoperative diagnosis and intraoperative positioning. Herein, we have designed a nanoparticle for triple-modality NIF/MR/photoacoustic imaging and brought in a dual-targeting strategy with co-expressed EGFR and SEC61G in glioblastoma. In comparison with the dual-negative nanocarrier, the EGFR/SEC61G biotargeting nanoprobe presented a significantly enhanced contrast and durability in vivo. Furthermore, we have evaluated the safety and biocompatibility using a CCK-8 assay ex vivo, which showed negligible toxicity. Therefore, the dual-target probes hold great potentials for a comprehensive preoperative plan and durable intraoperative navigation in glioblastoma.

Multi-dimensional omics characterization in glioblastoma identifies the purity-associated pattern and prognostic gene signatures.

BACKGROUND: The presence of tumor-associated stroma and tumor-infiltrated immune cells have been largely reported across glioblastomas. Tumor purity, defined as the proportion of tumor cells in the tumor, was associated with the genomic and clinicopathologic features of the tumor and may alter the interpretation of glioblastoma biology. METHODS: We use an integrative approach to infer tumor purity based on multi-omic data and comprehensively evaluate the impact of tumor purity on glioblastoma (GBM) prognosis, genomic profiling, and the immune microenvironment in the Cancer Genome Atlas Consortium (TCGA) cohort. RESULTS: We found that low tumor purity was significantly associated with reduced survival time. Additionally, we established a purity-relevant 5-gene signature that was an independent prognostic biomarker and validated it in the TCGA, CGGA and GSE4412 cohort. Moreover, we correlated tumor purity with genomic characteristics and tumor microenvironment. We identified that gamma delta T cells in glioblastoma microenvironment were positively correlated with purity and served as a marker for favorable prognosis, which was validated in both TCGA and CGGA dataset. CONCLUSIONS: We observe the potential confounding effects of tumor purity on GBM clinical and molecular information interpretation. GBM microenvironment could be purity-dependent, which provides new insights into the clinical implications of glioblastoma.

Anti-Cancer Effect of Cap-Translation Inhibitor 4EGI-1 in Human Glioma U87 Cells: Involvement of Mitochondrial Dysfunction and ER Stress.

BACKGROUND: Cancer cells are frequently addicted to deregulated oncogenic protein translation that usually arises as a consequence of increased signaling flux from eIF4F activation. The small molecule 4EG-I, a potent inhibitor of translation initiation through disrupting eIF4E/eIF4G interaction, has been shown to exert anticancer effects in animal models of human cancers. METHODS: Here, we extensively investigated the anticancer activity of 4EGI-1 in human glioma U87 cells. The anti-cancer effects of 4EGI-1 were measured by cell viability, lactate dehydrogenase (LDH) release, TUNEL staining, flow cytometry and western blot analysis in vitro, and also examined in a U87 xenograft model in vivo. The potential underlying molecular mechanisms were investigated by measuring mitochondrial function and ER stress. RESULTS: We found that 4EGI-1 impaired the assembly of the eIF4F complex and decreased the expression of the eIF4E regulated proteins. The results of TUNEL staining and flow cytometry showed that 4EGI-1 treatment induced apoptotic cell death in a dose-dependent manner. Furthermore, 4EGI-1-induced apoptosis in U87 cells was associated with mitochondrial dysfunction and activation of the intrinsic mitochondrial pathway, which was dependent on the induction of the pro-apoptotic protein Bax. In addition, 4EGI-1 treatment triggered ER stress, which was evidenced by morphological changes of ER lumen and ER calcium release, as well as the dose-dependent increases in the expression of ER stress related proteins. Moreover, knockdown of the ER chaperone GRP-78 through siRNA was shown to partially reverse the 4EGI-1-induced ER stress in U87 cells. In vivo, 4EGI-1 strongly inhibited growth of U87 glioma xenografts without any apparent organ related toxicities. CONCLUSION: These data indicate that the use of inhibitors that directly target the translation initiation complex eIF4F could represent a potential novel approach for human glioma therapy.

[Influence of preventive use of vasopressin tannate on diabetes insipidus and serum sodium at the early postoperation of craniopharyngioma].

OBJECTIVE: To explore the influence of preventive use of vasopressin tannate on diabetes insipidus and serum sodium at the early postoperation of craniopharyngioma.
 Methods: The data of 83 patients, who underwent unilateral sub-frontal approach resection of craniopharyngioma between 2010 and 2014 by the same senior neurosurgeon, were retrospectively analyzed. The patients were divided into a vasopressin tannate group (used group) and a control group. The diabetes insipidus and serum sodium changes were compared between the two groups.
 Results: Compared with the control group, the incidence of diabetes insipidus decreased at the early postoperation in the vasopressin tannate group (P<0.05). There was high incidence of diabetes insipidus in patients with pituitary stalk excision and tumor close adhesion to the third ventricle floor at the early postoperation (P<0.05). Under such conditions, the incidence of diabetes insipidus in the vasopressin tannate group was decreased compared with the control group (P<0.05). Postoperative hypernatremia occurred in 37 patients (44.6%), and hyponatremia occurred in 60 patients (72.3%), the average time of the occurrence of hpernatremia and hyponatremia was 1.4 and 3.7 days after surgery. Postoperative high serum sodium and low serum sodium appeared alternately in 19 patients (22.9%). There was significant difference in the serum sodium distribution in the first day after surgery in both groups (P<0.05), and the percent of hpernatremia in the vasopressin tannate group was significantly less than that in the control group (P<0.05).
 Conclusion: Preventive use of vasopressin tannate can effectively reduce diabetes insipidus and hypernatremia incidence at the early postoperative stage after microsurgery for craniopharyngioma.

A natural compound melatonin enhances the effects of Nimotuzumab via inhibiting EGFR in glioblastoma.

Sleep disorders are prevalent and debilitating symptoms in primary brain tumor patients, notably those receiving radiation therapy. Nevertheless, the relationship between sleep disorders, melatonin - a circadian rhythm regulatory hormone, and gliomas is underexplored. Melatonin exhibits various biological functions, one of them being anti-tumor activity. In the context of gliomas, often overexpressing EGFR, the humanized monoclonal antibody Nimotuzumab targets this marker. Our research discovered that variations in circadian rhythm significantly influence tumor growth in mice through impacting melatonin secretion. Harnessing proteogenomic, we identified that melatonin could inhibit the phosphorylation of EGFR and its downstream effectors, key elements in angiogenesis and tumor progression. Building on structural simulations, we propose that melatonin may amplify Nimotuzumab's anti-glioma efficacy by inhibiting EGFR TK dimerization. This proposition was validated in our in vitro and in vivo studies where melatonin synergistically augmented cytotoxicity and apoptosis in Nimotuzumab-treated glioma cells. Thus, melatonin shows promise as a beneficial addition to Nimotuzumab treatment in glioma patients.

Pan-cancer evaluation of regulated cell death to predict overall survival and immune checkpoint inhibitor response.

Regulated cell death (RCD) plays a pivotal role in various biological processes, including development, tissue homeostasis, and immune response. However, a comprehensive assessment of RCD status and its associated features at the pan-cancer level remains unexplored. Furthermore, despite significant advancements in immune checkpoint inhibitors (ICI), only a fraction of cancer patients currently benefit from treatments. Given the emerging evidence linking RCD and ICI efficacy, we hypothesize that the RCD status could serve as a promising biomarker for predicting the ICI response and overall survival (OS) in patients with malignant tumors. We defined the RCD levels as the RCD score, allowing us to delineate the RCD landscape across 30 cancer types, 29 normal tissues in bulk, and 2,573,921 cells from 82 scRNA-Seq datasets. By leveraging large-scale datasets, we aimed to establish the positive association of RCD with immunity and identify the RCD signature. Utilizing 7 machine-learning algorithms and 18 ICI cohorts, we developed an RCD signature (RCD.Sig) for predicting ICI response. Additionally, we employed 101 combinations of 10 machine-learning algorithms to construct a novel RCD survival-related signature (RCD.Sur.Sig) for predicting OS. Furthermore, we obtained CRISPR data to identify potential therapeutic targets. Our study presents an integrative framework for assessing RCD status and reveals a strong connection between RCD status and ICI effectiveness. Moreover, we establish two clinically applicable signatures and identify promising potential therapeutic targets for patients with tumors.

Mime: A flexible machine-learning framework to construct and visualize models for clinical characteristics prediction and feature selection.

The widespread use of high-throughput sequencing technologies has revolutionized the understanding of biology and cancer heterogeneity. Recently, several machine-learning models based on transcriptional data have been developed to accurately predict patients' outcome and clinical response. However, an open-source R package covering state-of-the-art machine-learning algorithms for user-friendly access has yet to be developed. Thus, we proposed a flexible computational framework to construct a machine learning-based integration model with elegant performance (Mime). Mime streamlines the process of developing predictive models with high accuracy, leveraging complex datasets to identify critical genes associated with prognosis. An in silico combined model based on de novo PIEZO1-associated signatures constructed by Mime demonstrated high accuracy in predicting the outcomes of patients compared with other published models. Furthermore, the PIEZO1-associated signatures could also precisely infer immunotherapy response by applying different algorithms in Mime. Finally, SDC1 selected from the PIEZO1-associated signatures demonstrated high potential as a glioma target. Taken together, our package provides a user-friendly solution for constructing machine learning-based integration models and will be greatly expanded to provide valuable insights into current fields. The Mime package is available on GitHub (https://github.com/l-magnificence/Mime).

Mood swings are causally associated with intracranial aneurysm subarachnoid hemorrhage: A Mendelian randomization study.

BACKGROUND: Mood swings have been observed in patients with intracranial aneurysm (IA), but it is still unknown whether mood swings can affect IA. AIM: To explore the causal association between mood swings or experiencing mood swings and IA through a two-sample Mendelian randomization (MR) study. METHODS: Summary-level statistics of mood swings, experiencing mood swings, IA, aneurysm-associated subarachnoid hemorrhage (aSAH), and non-ruptured IA (uIA) were collected from the genome-wide association study. Two-sample MR and various sensitivity analyses were employed to explore the causal association between mood swings or experiencing mood swings and IA, or aSAH, or uIA. The inverse-variance weighted method was used as the primary method. RESULTS: Genetically determined mood swings (odds ratio [OR] = 5.23, 95% confidence interval (95%CI): 1.65-16.64, p = .005) and experiencing mood swings (OR = 2.50, 95%CI: 1.37-4.57, p = .003) were causally associated with an increased risk of IA. Mood swings (OR = 5.67, 95%CI: 1.40-23.04, p = .015) and experiencing mood swings were causally associated with the risk of aSAH (OR = 2.91, 95%CI: 1.47-5.75, p = .002). Neither mood swings (OR = 1.95, 95%CI: .31-12.29, p = .478) nor experiencing mood swings (OR = 1.20, 95%CI: .48-3.03, p = .693) were associated with uIA. CONCLUSIONS: Mood swings and experiencing mood swings increased the risk of IA and aSAH incidence. These results suggest that alleviating mood swings may reduce IA rupture incidence and aSAH incidence.

Functional characterization of TSPAN7 as a novel indicator for immunotherapy in glioma.

Glioma is the most common primary malignant tumor of the central nervous system in clinical practice. Most adult diffuse gliomas have poor efficacy after standard treatment, especially glioblastoma. With the in-depth understanding of brain immune microenvironment, immunotherapy as a new treatment has attracted much attention. In this study, through analyzing a large number of glioma cohorts, we reported that TSPAN7, a member of the tetraspanin family, decreased in high-grade gliomas and low expression was associated with poor prognosis in glioma patients. Meanwhile, the expression pattern of TSPAN7 was verified in glioma clinical samples and glioma cell lines by qPCR, Western Blotting and immunofluorescence. In addition, functional enrichment analysis showed that cell proliferation, EMT, angiogenesis, DNA repair and MAPK signaling pathways were activated in the TSPAN7 lower expression subgroup. Lentiviral plasmids were used to overexpress TSPAN7 in U87 and LN229 glioma cell lines to explore the anti-tumor role of TSPAN7 in glioma. Moreover, by analyzing the relationship between TSPAN7 expression and immune cell infiltration in multiple datasets, we found that TSPAN7 was significantly negatively correlated with the immune infiltration of tumor-related macrophages, especially M2-type macrophages. Further analysis of immune checkpoints showed that, the expression level of TSPAN7 was negatively correlated with the expression of PD-1, PD-L1 and CTLA-4. Using an independent anti-PD-1 immunotherapy cohorts of GBM, we demonstrated that TSPAN7 expression may had a synergistic effect with PD-L1 on the response to immunotherapy. Based on the above findings, we speculate that TSPAN7 can serve as a biomarker for prognosis and a potential immunotherapy target in glioma patients.

Transcription factor ZBTB42 is a novel prognostic factor associated with immune cell infiltration in glioma.

Background: ZBTB42 is a transcription factor that belongs to the ZBTB transcript factor family and plays an important role in skeletal muscle development. Dysregulation of ZBTB42 expression can lead to a variety of diseases. However, the function of ZBTB42 in glioma development has not been studied by now. Methods: We analyzed the expression of ZBTB42 in LGG and GBM via the The Cancer Genome Atlas CGA and Chinese Glioma Genome Atlas database. Gene Ontology, KEGG, and GSVA analyses were performed to illustrate ZBTB42-related pathways. ESTIMATE and CIBERSORT were applied to calculate the immune score and immune cell proportion in glioma. One-class logistic regression OCLR algorithm was used to study the stemness of glioma. Multivariate Cox analysis was employed to detect the prognostic value of five ZBTB42-related genes. Results: Our results show that ZBTB42 is highly expressed in glioma and may be a promising prognostic factor for Low Grade Glioma and GBM. In addition, ZBTB42 is related to immune cell infiltration and may play a role in the immune suppression microenvironment. What's more, ZBTB42 is correlated with stem cell markers and positively associated with glioma stemness. Finally, a five genes nomogram based on ZBTB42 was constructed and has an effective prognosis prediction ability. Conclusion: We identify that ZBTB42 is a prognostic biomarker for Low Grade Glioma and GBM and its function is related to the suppressive tumor microenvironment and stemness of glioma.

ESRG is critical to maintain the cell survival and self-renewal/pluripotency of hPSCs by collaborating with MCM2 to suppress p53 pathway.

The mechanisms of self-renewal and pluripotency maintenance of human pluripotent stem cells (hPSCs) have not been fully elucidated, especially for the role of those poorly characterized long noncoding RNAs (lncRNAs). ESRG is a lncRNA highly expressed in hPSCs, and its functional roles are being extensively explored in the field. Here, we identified that the transcription of ESRG can be directly regulated by OCT4, a key self-renewal factor in hPSCs. Knockdown of ESRG induces hPSC differentiation, cell cycle arrest, and apoptosis. ESRG binds to MCM2, a replication-licensing factor, to sustain its steady-state level and nuclear location, safeguarding error-free DNA replication. Further study showed that ESRG knockdown leads to MCM2 abnormalities, resulting in DNA damage and activation of the p53 pathway, ultimately impairs hPSC self-renewal and pluripotency, and induces cell apoptosis. In summary, our study suggests that ESRG, as a novel target of OCT4, plays an essential role in maintaining the cell survival and self-renewal/pluripotency of hPSCs in collaboration with MCM2 to suppress p53 signaling. These findings provide critical insights into the mechanisms underlying the maintenance of self-renewal and pluripotency in hPSCs by lncRNAs.

Mechanical nanosurgery of chemoresistant glioblastoma using magnetically controlled carbon nanotubes.

Glioblastoma (GBM) is the most common and aggressive primary brain cancer. Despite multimodal treatment including surgery, radiotherapy, and chemotherapy, median patient survival has remained at ~15 months for decades. This situation demands an outside-the-box treatment approach. Using magnetic carbon nanotubes (mCNTs) and precision magnetic field control, we report a mechanical approach to treat chemoresistant GBM. We show that GBM cells internalize mCNTs, the mobilization of which by rotating magnetic field results in cell death. Spatiotemporally controlled mobilization of intratumorally delivered mCNTs suppresses GBM growth in vivo. Functionalization of mCNTs with anti-CD44 antibody, which recognizes GBM cell surface-enriched antigen CD44, increases mCNT recognition of cancer cells, prolongs mCNT enrichment within the tumor, and enhances therapeutic efficacy. Using mouse models of GBM with upfront or therapy-induced resistance to temozolomide, we show that mCNT treatment is effective in treating chemoresistant GBM. Together, we establish mCNT-based mechanical nanosurgery as a treatment option for GBM.

A designer peptide against the EAG2-Kvß2 potassium channel targets the interaction of cancer cells and neurons to treat glioblastoma.

Glioblastoma (GBM) is an incurable brain cancer that lacks effective therapies. Here we show that EAG2 and Kvß2, which are predominantly expressed by GBM cells at the tumor-brain interface, physically interact to form a potassium channel complex due to a GBM-enriched Kvß2 isoform. In GBM cells, EAG2 localizes at neuron-contacting regions in a Kvß2-dependent manner. Genetic knockdown of the EAG2-Kvß2 complex decreases calcium transients of GBM cells, suppresses tumor growth and invasion and extends the survival of tumor-bearing mice. We engineered a designer peptide to disrupt EAG2-Kvß2 interaction, thereby mitigating tumor growth in patient-derived xenograft and syngeneic mouse models across GBM subtypes without overt toxicity. Neurons upregulate chemoresistant genes in GBM cells in an EAG2-Kvß2-dependent manner. The designer peptide targets neuron-associated GBM cells and possesses robust efficacy in treating temozolomide-resistant GBM. Our findings may lead to the next-generation therapeutic agent to benefit patients with GBM.

Mechanosensitive brain tumor cells construct blood-tumor barrier to mask chemosensitivity.

Major obstacles in brain cancer treatment include the blood-tumor barrier (BTB), which limits the access of most therapeutic agents, and quiescent tumor cells, which resist conventional chemotherapy. Here, we show that Sox2+ tumor cells project cellular processes to ensheathe capillaries in mouse medulloblastoma (MB), a process that depends on the mechanosensitive ion channel Piezo2. MB develops a tissue stiffness gradient as a function of distance to capillaries. Sox2+ tumor cells perceive substrate stiffness to sustain local intracellular calcium, actomyosin tension, and adhesion to promote cellular process growth and cell surface sequestration of ß-catenin. Piezo2 knockout reverses WNT/ß-catenin signaling states between Sox2+ tumor cells and endothelial cells, compromises the BTB, reduces the quiescence of Sox2+ tumor cells, and markedly enhances the MB response to chemotherapy. Our study reveals that mechanosensitive tumor cells construct the BTB to mask tumor chemosensitivity. Targeting Piezo2 addresses the BTB and tumor quiescence properties that underlie treatment failures in brain cancer.

A neurodevelopmental epigenetic programme mediated by SMARCD3-DAB1-Reelin signalling is hijacked to promote medulloblastoma metastasis.

How abnormal neurodevelopment relates to the tumour aggressiveness of medulloblastoma (MB), the most common type of embryonal tumour, remains elusive. Here we uncover a neurodevelopmental epigenomic programme that is hijacked to induce MB metastatic dissemination. Unsupervised analyses of integrated publicly available datasets with our newly generated data reveal that SMARCD3 (also known as BAF60C) regulates Disabled 1 (DAB1)-mediated Reelin signalling in Purkinje cell migration and MB metastasis by orchestrating cis-regulatory elements at the DAB1 locus. We further identify that a core set of transcription factors, enhancer of zeste homologue 2 (EZH2) and nuclear factor I X (NFIX), coordinates with the cis-regulatory elements at the SMARCD3 locus to form a chromatin hub to control SMARCD3 expression in the developing cerebellum and in metastatic MB. Increased SMARCD3 expression activates Reelin-DAB1-mediated Src kinase signalling, which results in a MB response to Src inhibition. These data deepen our understanding of how neurodevelopmental programming influences disease progression and provide a potential therapeutic option for patients with MB.

HESRG: a novel biomarker for intracranial germinoma and embryonal carcinoma.

The novel stem cell-related gene, HESRG, was first identified by our group, and its expression pattern in human tumors remains unknown. In this study, we used RT-PCR to systematically investigate the expression of HESRG in various types of intracranial tumors and found that HESRG was expressed only in germinoma and embryonal carcinoma, but hardly at all in other types of brain tumors. Real-time PCR results further confirmed this expression pattern. Subsequently, we tested 134 intracranial non-germ cell tumors and 64 intracranial germ cell tumors by immunohistochemistry. Our results showed that HESRG was expressed strongly and diffusively in the nuclei of tumor cells in intracranial germinoma and embryonal carcinoma as well as in human embryonic stem cells. No positive staining signal was observed in any other type of intracranial tumors. In germinomas, 25 of 31 showed intensive (3+) expression, four cases showed moderate (2+) immunostaining and the remaining 2 cases showed weak (1+) immunostaining. In embryonal carcinoma, 6 of 9 showed intensive (3+) immunostaining and 3 of 9 showed moderate (2+) immunostaining. These results suggest that HESRG is a novel, sensitive and specific biomarker for intracranial germinoma and embryonal carcinoma.

Prognostic value of OCT4 in primary intracranial germinoma: a single institute analysis of 31 cases.

OCT4 expresses variably in primary intracranial germinomas. In this study, we tested our hypothesis that such variation of OCT4 is predictive of outcome in primary intracranial germinomas. Thirty-one histologically identified CNS germinoma patients were enrolled in our study. We collected medical data, immunohistochemically evaluated the OCT4 expression level, and followed up all patients from April 2001 to May 2010. We found that 7 of the 31 patients expressed OCT4 weakly, 11 expressed OCT4 moderately, and 13 expressed OCT4 strongly. No significant correlation between the OCT4 expression level and clinicopathological characteristics was observed. WV-CS combined treatment modality showed a better 5-year progression-free survival (PFS) rate than other treatment modalities and a low expression level of OCT4 showed a significantly better 5-year PFS. In both the WV-CS combined treatment modality and other treatments modality group, patients received a better 5-year PFS and had a lower level of OCT4 expression. As a result, we suggest OCT4 as a probable prognostic marker for intracranial germinoma.

Deep Learning Model for Intracranial Hemangiopericytoma and Meningioma Classification.

Background: Intracranial hemangiopericytoma/solitary fibrous tumor (SFT/HPC) is a rare type of neoplasm containing malignancies of infiltration, peritumoral edema, bleeding, or bone destruction. However, SFT/HPC has similar radiological characteristics as meningioma, which had different clinical managements and outcomes. This study aims to discriminate SFT/HPC and meningioma via deep learning approaches based on routine preoperative MRI. Methods: We enrolled 236 patients with histopathological diagnosis of SFT/HPC (n = 144) and meningioma (n = 122) from 2010 to 2020 in Xiangya Hospital. Radiological features were extracted manually, and a radiological diagnostic model was applied for classification. And a deep learning pretrained model ResNet-50 was adapted to train T1-contrast images for predicting tumor class. Deep learning model attention mechanism was visualized by class activation maps. Results: Our study reports that SFT/HPC was found to have more invasion to venous sinus (p = 0.001), more cystic components (p < 0.001), and more heterogeneous enhancement patterns (p < 0.001). Deep learning model achieved a high classification accuracy of 0.889 with receiver-operating characteristic curve area under the curve (AUC) of 0.91 in the validation set. Feature maps showed distinct clustering of SFT/HPC and meningioma in the training and test cohorts, respectively. And the attention of the deep learning model mainly focused on the tumor bulks that represented the solid texture features of both tumors for discrimination.