Treatment of Galen Vein Arteriovenous Malformation with Gamma Knife Surgery.

The vein of Galen arteriovenous malformation is a rare abnormality of the fetal cerebral vascular system. It is caused by the persistence of a cerebral arteriovenous fistula of the median prosencephalic vein. Due to the high mortality rate of the surgical option in its treatment, the approach with embolization and radiosurgery combinations continues to be popular. We present a 3-year-old child patient who was accidentally detected by vein of Galen malformations during a screening for headache complaints with known heart disease. In the treatment of this patient, we performed radiosurgery therapy alone, rather than a combination. Our case is the third case of a and the youngest example child who was treated with only radiosurgery without embolization. Gamma knife therapy, which is a more convenient and effective treatment plan, is a method that can be safely used instead of open surgery with a high mortality rate.

Revisiting the microsurgical anatomy of the sagittal stratum and surgical implications: fiber microdissection and tractography study.

OBJECTIVE: The term "sagittal stratum" was coined by Heinrich Sachs in 1892 to define a parasagittally oriented white matter layer at the temporo-occipital cortex. Although this term has been widely used for more than 100 years, the description, classification, borders, and involved fibers of the structure vary among authors and remain imprecise. Through fiber microdissection and tractography, the authors aimed to define the sagittal stratum and resolve the uncertainty by revealing the relationship of this structure to other cerebral white matter pathways and the orientation of fibers in it. METHODS: Twenty postmortem human cerebral hemispheres were prepared according to Klingler's method. Fiber dissections were performed under a surgical microscope and with microsurgical techniques. The results of dissection at each step were photographed with 2D and 3D imaging techniques, and 3D photogrammetry techniques were used to create a 360° model. Diffusion tensor imaging and 7T high-resolution MRI were used to confirm the findings. RESULTS: This study revisited the 3D organization of white matter tracts in the sagittal stratum through fiber microdissection and tractography. The microneuroanatomical structure of the sagittal stratum and its special organization with fibers from all three fiber systems are demonstrated. The authors' findings revealed that the sagittal stratum has two layers consisting of four different fiber tracts. Its external layer consists of a long association fiber and a commissural fiber, while its internal layer consists of intertwined projection fibers, including temporo-parieto-occipitopontine fibers and the posterior thalamic peduncle. Detailed microdissection also showed the location of the posterior thalamic peduncle in the most medial site of all posterior hemispheric projection fibers. CONCLUSIONS: The structure of the sagittal stratum is distinctive in that it contains all three main fiber systems: association, commissural, and projection. Because of its expansive location in the temporal and occipital lobes, it can be damaged by most neurosurgical pathologies and procedures. The authors emphasize the significance of preserving the sagittal stratum during surgical interventions while also challenging the notion of a "silent" brain, suggesting that the current inability to fully comprehend cerebral function contributes to this misconception. Detailed knowledge of the complex white matter anatomy of the sagittal stratum can guide neurosurgeons in surgical planning and the selection of appropriate surgical approaches with intraoperative orientation for safe surgery and less comorbidity.

The first case of glioma detected by an artificial intelligence algorithm running on real-time data in neurosurgery: illustrative case.

BACKGROUND: The aim of this paper is to report one of the significant applications of artificial intelligence (AI) and how it affects everyday clinical practice in neurosurgery. The authors present a case in which a patient was diagnosed via an AI algorithm during ongoing magnetic resonance imaging (MRI). According to this algorithm, the corresponding physicians were immediately warned, and the patient received prompt appropriate treatment. OBSERVATIONS: A 46-year-old female presenting with nonspecific headache was admitted to undergo MRI. Scanning revealed an intraparenchymal mass that was detected by an AI algorithm running on real-time patient data while the patient was still in the MRI scanner. The day after MRI, a stereotactic biopsy was performed. The pathology report confirmed an isocitrate dehydrogenase wild-type diffuse glioma. The patient was referred to the oncology department for evaluation and immediate treatment. LESSONS: This is the first report of a glioma diagnosed by an AI algorithm and a subsequent prompt operation in the literature-the first of many and an example of how AI will enhance clinical practice.

Neurological recovery after early versus delayed surgical decompression for acute traumatic spinal cord injury.

The aim of this study was to determine whether early surgical treatment results in better neurological recovery 12 months after injury than late surgical treatment in patients with acute traumatic spinal cord injury (tSCI). Patients with tSCI requiring surgical spinal decompression presenting to 17 centres in Europe were recruited. Depending on the timing of decompression, patients were divided into early (≤ 12 hours after injury) and late (> 12 hours and < 14 days after injury) groups. The American Spinal Injury Association neurological (ASIA) examination was performed at baseline (after injury but before decompression) and at 12 months. The primary endpoint was the change in Lower Extremity Motor Score (LEMS) from baseline to 12 months. The final analyses comprised 159 patients in the early and 135 in the late group. Patients in the early group had significantly more severe neurological impairment before surgical treatment. For unadjusted complete-case analysis, mean change in LEMS was 15.6 (95% confidence interval (CI) 12.1 to 19.0) in the early and 11.3 (95% CI 8.3 to 14.3) in the late group, with a mean between-group difference of 4.3 (95% CI -0.3 to 8.8). Using multiply imputed data adjusting for baseline LEMS, baseline ASIA Impairment Scale (AIS), and propensity score, the mean between-group difference in the change in LEMS decreased to 2.2 (95% CI -1.5 to 5.9). Compared to late surgical decompression, early surgical decompression following acute tSCI did not result in statistically significant or clinically meaningful neurological improvements 12 months after injury. These results, however, do not impact the well-established need for acute, non-surgical tSCI management. This is the first study to highlight that a combination of baseline imbalances, ceiling effects, and loss to follow-up rates may yield an overestimate of the effect of early surgical decompression in unadjusted analyses, which underpins the importance of adjusted statistical analyses in acute tSCI research.

How did intraoperative neuromonitorization prevent tetraplegia?

PURPOSE: Patients with mucopolysaccharidosis type IVA (MPS IVA) have many risk factors for myelopathy and paresis. These are spinal cord compression, bone stenosis, and soft tissue thickening with ligament laxity, deformity, odontoid hypoplasia, and atlantoaxial instability. Although most patients with MPS IVA appear generally healthy at birth, patients often show skeletal deformities within a few years. Surgical indications are difficult to determine. Historically, many physicians have used prophylactic decompression and fusion in young, asymptomatic MPS IVA patients to prevent cord compression. Although spinal cord decompression is usually required at the craniocervical junction in patients with MPS IVA, decompression may be required at other spinal cord levels as well. There is a risk of developing neurological damage during surgery. The most common causes are ischemia secondary to cardiac output deteriorated in the prone position or due to artery damage, and local trauma due to neck movements or traction while bringing the patient to the prone position. Neurophysiological monitoring is very important during surgery to reduce the risk of neurological damage in spinal cord surgery. In this case report, a case with loss of lower extremity neuromonitorization motor evoked potential (MEP) responses in the early period of surgery without any intervention to the craniocervical junction after prone positioning will be presented.

Comparison of the Results of Suture and Resorbable Plate-Screw Fixation in Craniosynostosis.

BACKGROUND: Although many fixation methods are used alone or in combination for craniosynostosis, only few studies have compared the effectiveness and long-term results of these methods. METHOD: In this study, patients in whom suture or resorbable plate-screw system was used for fixation were evaluated in terms of postoperative results and complications. The data of patients who underwent surgery for craniosynostosis between 2002 and 2019 were retrospectively reviewed and evaluated. RESULTS: A total of 70 patients, 41 in the suture group and 29 in the resorbable plate-screw group, were included in the study. Whitaker classification was used for head shape evaluation, and anthropometric head circumference measurements were performed in all patients in the preoperative and postoperative periods. In the postoperative period, all patients were compared in terms of the operation time, transfusion requirement, discharge, follow-up period, and complications according to the chosen fixation method.The mean age, postoperative complication rates, anthropometric head circumference measurements, and Whitaker scores of both groups were found to be statistically similar. Although the resorbable plate-screw group had a longer follow-up period, the operation time was longer in the suture group. Furthermore, the suture group had lower transfusion requirement and earlier discharge from the hospital than the resorbable plate-screw group. CONCLUSIONS: If fixation with suture is chosen in suitable patients, in addition to the low patient cost, this method can be safely applied in centers with limited logistical possibilities, because of the results and complication rates being similar to fixation with resorbable plate-screws.

Sagittal spinopelvic alignment in tethered cord syndrome and split cord malformation.

PURPOSE: Sagittal imbalance is common in degenerative and congenital spinal diseases. Some studies have examined spinal deformities in the spina bifida. However, sagittal spinopelvic parameters in tethered cord syndrome (TCS) and split cord malformation (SCM) have been poorly evaluated in the literature. In this study, we investigated sagittal spinopelvic differences in TCS due to fatty filum terminale and SCM patients. MATERIAL AND METHODS: A total of 78 patients with spina bifida occulta (30 SCM and 48 TCS due to fatty filum terminale) were included in the study. Radiological images of these patients were retrospectively evaluated. We evaluated the pelvic incidence, pelvic tilt, sacral slope, sagittal vertical axis (SVA), T1 pelvic angle, lumbar lordosis (LL), thoracic kyphosis, thoracolumbar alignment, and change in those parameters with age. RESULTS: Correlation coefficients between age and LL, T1 pelvic angle, and the SVA in patients with TCS due to fatty filum terminale were statistically significant. In addition, correlation coefficients between age and LL and the SVA in patients with SCM were statistically significant. Notably, LL was increased at a statistically significant level with age in patients with TCS and SCM. CONCLUSION: Improved knowledge of spinal balance parameters in patients with TCS and SCM may be helpful in understanding the clinical course of these pathologies, and provide information regarding the success of surgery at the follow-up period.

Utilizing Deep Convolutional Generative Adversarial Networks for Automatic Segmentation of Gliomas: An Artificial Intelligence Study.

AIM: To describe a deep convolutional generative adversarial networks (DCGAN) model which learns normal brain MRI from normal subjects than finds distortions such as a glioma from a test subject while performing a segmentation at the same time. MATERIAL AND METHODS: MRIs of 300 healthy subjects were employed as training set. Additionally, test data were consisting anonymized T2-weigted MRIs of 27 healthy subjects and 27 HGG patients. Consecutive axial T2-weigted MRI slices of every subject were extracted and resized to 364x448 pixel resolution. The generative model produced random normal synthetic images and used these images for calculating residual loss to measure visual similarity between input MRIs and generated MRIs. RESULTS: The model correctly detected anomalies on 24 of 27 HGG patients? MRIs and marked them as abnormal. Besides, 25 of 27 healthy subjects? MRIs in the test dataset detected correctly as healthy MRI. The accuracy, precision, recall, and AUC were 0.907, 0.892, 0.923, and 0.907, respectively. CONCLUSION: Our proposed model demonstrates acceptable results can be achieved only by training with normal subject MRIs via using DCGAN model. This model is unique because it learns only from normal MRIs and it is able to find any abnormality which is different than the normal pattern.

Stereotactic radiosurgery for cerebral cavernous malformation: comparison of hemorrhage rates before and after stereotactic radiosurgery.

OBJECTIVE: Cerebral cavernous malformation (CM) is an angiographically occult vascular pathology. Although microsurgery is the gold standard treatment to control the symptoms of CM, resection carries high risk in some situations, especially eloquent areas. The objective was to evaluate annual hemorrhage rates (AHRs) before and after stereotactic radiosurgery (SRS) treatment of cerebral CM in different locations. METHODS: A total of 195 patients (119 women and 76 men) with CM treated at the Gazi University Gamma Knife Center between April 2005 and June 2017 were analyzed. The mean ± SD follow-up period was 67.4 ± 31.1 months (range 12 days to 170 months). AHR before SRS, AHR after SRS, morbidity associated with radiation, seizure control rate after SRS, lesion volume, coexistence with developmental venous anomaly, and SRS treatment parameters were analyzed, with evaluation of radiological data and clinical charts performed retrospectively. The seizure control rate was assessed using the Engel outcome scale. RESULTS: The AHR before SRS was 15.3%. Application of SRS to these patients significantly reduced the AHR rates to 2.6% during the first 2 years after treatment and to 1.4% thereafter. Favorable seizure control (Engel class I and II) after radiosurgery was achieved in 23 patients (88.5%) with epilepsy. Radiation-related temporary complications occurred in 15.4% of patients, and permanent morbidity occurred in 4.6%. CONCLUSIONS: SRS is a safe and effective treatment modality for reducing the hemorrhage risk of CM. The authors suggest that SRS should be considered for the treatment of patients with CM, high surgical risks, and hemorrhage history, instead of a using a wait-and-see policy.

Stereotactic Radiosurgery after Subtotal Resection of Critically-Located Grade I Meningioma: A Single-Center Experience and Review of Literature.

AIM: To analyze the results of stereotactic radiosurgery in 295 patients with residual Grade I meningiomas located at parasellar region, petroclival region, cerebellopontine angle and parasagittal region. MATERIAL AND METHODS: A total of 295 patients with Grade 1 residual Meningiomas (197 women, 98 men), who were treated by adjuvant radiosurgery in Gazi University Gamma Knife Center between 2004-2015 were analyzed. WHO Grade 2 and 3 meningiomas were not included in our study. Minimum radiological follow-up was 24 months. The median follow-up was 54 months. The tumor volume, location, treatment dose, morbidity, progression free survival and tumor control rate were analyzed. RESULTS: The median tumor volume was 5.2 cm3 (0.04-39.7), median age was 50 (20-80), median dose was 14 Gy and tumor control rate was 94.5% (stationary in 85.0%, volume reduction in 9.5%). Increase in tumor volume was seen in 16 patients (5.5%) and re-operation was performed in 5 of them (1.6%). Stereotactic radiosurgery was performed again for 8 patients (2.7%).The location of the tumors was as follows: 39.3% parasellar region, 20% cerebellopontine angle, 13.6% petroclival and 27.1% was parasagittal, falcine or convexity. Major morbidities were detected in 6 (2%) patients. Minor morbidities were detected in 18 (6.1%) patients. CONCLUSION: Stereotactic radiosurgery is an effective and safe treatment modality for residual Grade I meningiomas.

Intraventricular treatment of paediatric meningitis due to extensively drug-resistant Gram-negative bacteria: two case reports and review of the literature.

Nosocomial meningitis caused by Gram-negative bacteria is associated with increasingly common neurosurgical procedures in children, with an increase in incidence recently reported. These infections are associated with an increased risk of mortality, prolonged hospitalisation, and increased costs. In this report, we describe two paediatric cases with central nervous system infections caused by extensively drug-resistant Gram-negative bacteria that were successfully treated with intraventricular colistin. To the best of our knowledge, this is the first comprehensive review and discussion of intraventricular antimicrobial therapy in a paediatric population. Based on our comprehensive review of the relevant literature, it appears that intraventricular administration of colistin may be a promising and effective option in the treatment of central nervous system infections in children who do not respond to other treatment options.

Reduced field of view under the surgical microscope due to personal protective equipment: lessons learned during the COVID-19 pandemic.

OBJECTIVE: During the coronavirus disease 2019 (COVID-19) pandemic, neurosurgeons all around the globe continue to operate in emergency cases using new self-protective measures. Personal protective equipment (PPE) use is recommended in all surgeries. The authors have experienced varying degrees of field of view (FOV) loss under the surgical microscope with different PPE. Herein, they aimed to investigate the effects of different PPE on FOV while using the surgical microscope. METHODS: Fifteen neurosurgeons and neurosurgery residents participated in this study. Three kinds of PPE (safety spectacles, blast goggles, and face shields) were tested while using a surgical microscope. FOV was measured using a 12 × 12-cm checkered sheet of paper on which every square had an area of 25 mm2 under the microscope. The surgical microscope was positioned perpendicular to the test paper, and the zoom was fixed. Each participant marked on the test sheet the peripheral borders of their FOV while using different PPE and without wearing any PPE. A one-way repeated-measures ANOVA was performed to determine if there was a significant difference in FOV values with the different PPE. RESULTS: FOV was significantly different between each PPE (F[3, 42] = 6339.845, p < 0.0005). Post hoc analysis revealed a significant decrease in the FOV from the naked eye (9305.33 ± 406.1 mm2) to blast goggles (2501.91 ± 176.5 mm2) and face shields (92.33 ± 6.4 mm2). There were no significant FOV changes with the safety spectacles (9267.45 ± 410.5 mm2). CONCLUSIONS: While operating under a surgical microscope safety spectacles provide favorable FOVs. Face shields increase the eye piece-pupil distance, which causes a severe reduction in FOV.

Iron homeostasis is altered in response to hypoxia and hypothermic preconditioning in brain glial cells

Background/aim: Altered iron metabolism is one of the pathophysiological mechanisms occurring during hypoxic injuries in the central nervous system. Proper homeostasis of cellular iron is regulated by iron import, storage, and export proteins that prevent excess iron overload or iron starvation in cells. Therapeutic hypothermia is an approved treatment for hypoxic ischemia in newborns, but the underlying molecular mechanism is still unknown. We studied the effects of hypoxia, preceded with preconditioning, on the iron homeostasis of glial cells, known as a major actor in the inflammatory process during perinatal brain injury. Materials and methods: Primary microglia and astrocytes in culture were exposed to 12 h of hypoxia with or without mild hypothermic preconditioning. The mRNA expression was assessed using qPCR. Iron accumulation was visualized via modified Perl's histochemistry. Cytokine levels in cell cultures were measured using ELISA. Results: Hypothermic preconditioning enhanced microglial viability, which previously was decreased in both cell types due to hypoxia. Hypoxia increased iron accumulation in the mixed glial cells and in ferritin expression in both microglia and astrocytes. Hypotermic preconditioning decreased the elevated ferritin-light chain expression significantly in microglia. Iron importer proteins, DMT1 and TfR1, both increased their mRNA expression after hypoxia, and hypothermic preconditioning continued to support the elevation of DMT1 in both glial cell types. Ferroportin expression increased as a survival factor of the glial cell following hypoxia. Hypothermic preconditioning supported this increase in both cell types and was especially significant in astrocytes. IL-10 levels were prominently increased in cell culture after hypothermic preconditioning. Conclusion: The data suggest that hypothermic preconditioning affects cellular iron homeostasis by regulating the storage and transfer proteins of iron. Regulation of the cellular iron traffic may prevent glial cells from experiencing the detrimental effects of hypoxia-related inflammation.

First report of tethered cord syndrome in a patient with Sotos syndrome.

BACKGROUND: Sotos syndrome is caused by a gene deletion with an autosomal dominant pattern of inheritance. The Sotos syndrome was first described by Juan Sotos. Cole and Hughes identified the clinical characteristics of this syndrome. This syndrome is characterized by macrocephaly, frontal bossing, ocular hypertelorism, overgrowth, subdural hygroma, ventricular dilatation, agenesis of the corpus callosum. This syndrome is associated with mutations in NSD 1 (nuclear receptor SET domain-containing protein 1) gene, protein insufficiency, and a 5q35 microdeletion. Sotos syndrome is reported to occur in approximately 1/10,000-15,000 births. CASE PRESENTATION: We present a patient with Sotos syndrome who is harboring a sacral lipoma and tethered cord syndrome and she had growth retardation, frontal bossing and hypertelorism. After a standard approach for tethered cord syndrome, the patient was discharged 3 days after without any additional neurodeficits. CONCLUSION: In the literature, sacral lipoma and tethered cord syndrome with Sotos syndrome have not been published yet.

Cerebral cavernous malformation presenting in childhood: a single-centered surgical experience of 29 cases.

OBJECTIVES: Cerebral cavernous malformations (CMs) are benign vascular hamartomas of central nervous system. Although they are mostly asymptomatic, they may occasionally result in life-threatening complications leading to surgical treatment. The main goal is to evaluate the surgical outcomes of operated pediatric cerebral CMs in our clinic and compare our results with the literature. PATIENTS AND METHODS: The data of 29 pediatric patients who were operated for cerebral CMs in our clinic between 2007 and 2016 were collected. RESULTS: Of 29 patients, 13 were girls and 16 were boys, and the mean age at operation was 11.4 years (range from 2 to 17 years). Main symptoms at presentation were seizures (15 patients, 51.7 %), headache (12 patients, 41.3 %), and focal neurological deficits (4 patients, 13.7 %). The frequency of hemorrhage in CMs was significantly higher in younger patients (p = 0.019). Total excision was achieved in all patients. The mean follow-up period was 27.3 months (range from 12 to 97 months). New neurological deficit following surgery occurred in 1 patient (3.4 %) who completely recovered after 3 months. After surgery, 1 patient (3.4 %) has become free of preoperative deficit; while the rest (27 patients) remained in preoperative neurological status. Of 15 patients presented with seizures preoperatively, 10 patients (66.6 %) were seizure free (Engel Class 1), 4 (26.6 %) were "almost seizure free" (Engel Class 2) and one (6.6 %) experienced "worthwhile improvement" (Engel Class 3) at the last follow up visit. There was no mortality in our series. CONCLUSION: Although management of cerebral CMs in childhood is controversial, total resection ensures good clinical outcome and seizure control. In addition, age can be a predisposing factor for hemorrhage.

Women in Neurosurgery: Gender Differences in Authorship in High-Impact Neurosurgery Journals through the Last Two Decades.

OBJECTIVE: Despite common gender disparities in authorship across the vast majority of specialties, the presence of a similar lack of equality in neurosurgery literature is not published yet. Therefore the authors examined the changes in representation of women among the first and senior (last) authors of original articles in high-impact neurosurgical journals between 2003 and 2018. METHODS: Data regarding women proportions among the first and senior authors were collected from the issues of Neurosurgery and Journal of Neurosurgery published in 2003, 2008, 2013, and 2018. RESULTS: According to the analysis of 3247 original articles, compared with male authors, female authors have published fewer articles as the first (518 of women, 2729 of men) and senior authors (352 of women, 2884 of men). Nonetheless, the proportion of women in the first authorship represented a significant increase from 2003 to 2018 (from 12% to 16.5%, respectively; P < 0.01), but not in senior authorship (11.7% in 2003 vs. 10.5% in 2018; P > 0.05). Overall, women wrote more research articles than case reports as both first and senior authors (451 and 301 vs. 67 and 51, respectively). In addition, women demonstrated a higher percentage of first authors on female senior author articles (30.4%) than male senior author articles (14.1%). CONCLUSIONS: Although a rising trend in female authorship of neurosurgical literature has been going on through the last 2 decades, this advancement could not be regarded as satisfactory, as the gender gap in authorship is still excessive. Strikingly, female first authors had a tendency of coauthoring with female senior authors.

Posterior fossa horns; a new calvarial finding of mucopolysaccharidoses with well-known cranial MRI features

Background/aim: Mucopolysaccharidoses (MPS) are a group of hereditary metabolic diseases. The aim of this study was to share the previously unreported calvarial finding of internal hypertrophy of the occipitomastoid sutures (IHOMS) together with some other well-known cranial MRI findings in this patient series. Materials and methods: A retrospective evaluation was conducted of 80 cranial MRIs of patients who had been diagnosed and followed up with MPS from 2008 to 2019 in our center. Of these patients, 11 had Hurler, 14 had Hunter, 24 had Sanfilippo, 15 had Morquio, 14 had Maroteaux­Lamy, and 2 had Sly disease. The cranial MRIs were assessed in two main groups as parenchymal intradural cranial MRI findings and extradural calvarial findings. Results: The most common parenchymal intradural cranial MRI findings were white matter signal alterations (n = 51, 63%) and perivascular space enlargements (n = 39, 48%). The most common extradural calvarial findings were J-shaped sella (n = 45, 56%) and tympanic effusion (n = 44, 55%). Although IHOMS was defined in a relatively small number of the patients (n = 12, 15%), the prevalence rate was high in MPS type I (n = 6, 54%). Conclusion: The abnormal cranial MRI findings of the MPS patients, including the newly identified IHOMS, may provide diagnostic clues to differentiate the type of the disease in radiological imaging.

A Novel Deep Learning Algorithm for the Automatic Detection of High-Grade Gliomas on T2-Weighted Magnetic Resonance Images: A Preliminary Machine Learning Study.

AIM: To propose a convolutional neural network (CNN) for the automatic detection of high-grade gliomas (HGGs) on T2-weighted magnetic resonance imaging (MRI) scans. MATERIAL AND METHODS: A total of 3580 images obtained from 179 individuals were used for training and validation. After random rotation and vertical flip, training data was augmented by factor of 10 in each iteration. In order to increase data processing time, every single image converted into a Jpeg image which has a resolution of 320x320. Accuracy, precision and recall rates were calculated after training of the algorithm. RESULTS: Following training, CNN achieved acceptable performance ratios of 0.854 to 0.944 for accuracy, 0.812 to 0.980 for precision and 0.738 to 0.907 for recall. Also, CNN was able to detect HGG cases even though there is no apparent mass lesion in the given image. CONCLUSION: Our preliminary findings demonstrate; currently proposed CNN model achieves acceptable performance results for the automatic detection of HGGs on T2-weighted images.