Creating a neuroanatomy education model with augmented reality and virtual reality simulations of white matter tracts

OBJECTIVE

The utilization of digital technologies has experienced a notable surge, particularly in cases where access to cadavers is constrained, within the context of practical neuroanatomy training. This study evaluates augmented reality (AR)- and virtual reality (VR)-based educational models for neuroanatomy education.

METHODS

Three-dimensional models were created using advanced photogrammetry. VR- and AR-based educational models were developed by arranging these 3D models to align with the learning objectives of neurosurgery residents and second-year medical students whose cadaveric training was disrupted due to an earthquake in Turkey. Participants engaged with and evaluated the VR- and AR-based educational models, followed by the completion of a 20-item graded user experience survey. A 10-question mini-test was given to assess the baseline knowledge level prior to training and to measure the achievement of learning objectives after training.

RESULTS

Forty neurosurgery residents were trained with a VR-based educational model using VR headsets. An AR-based educational model was provided online to 200 second-year medical students for their practical neuroanatomy lesson. The average correct answer rates before the training were 7.5/10 for residents and 4.8/10 for students. These rates were significantly improved after the training to 9.7/10 for residents and to 8.7/10 for students (p < 0.001). Feedback from the users concurred that VR- and AR-based training could significantly enhance the learning experience in the field of neuroanatomy.

CONCLUSIONS

VR/AR-based educational models have the potential to improve education. VR/AR-based training systems can serve as an auxiliary tool in neuroanatomy training, offering a realistic alternative to traditional learning tools.

Machine learning applications in craniosynostosis diagnosis and treatment prediction: a systematic review

Craniosynostosis refers to the premature fusion of one or more of the fibrous cranial sutures connecting the bones of the skull. Machine learning (ML) is an emerging technology and its application to craniosynostosis detection and management is underexplored. This systematic review aims to evaluate the application of ML techniques in the diagnosis, severity assessment, and predictive modeling of craniosynostosis. A comprehensive search was conducted on the PubMed and Google Scholar databases using predefined keywords related to craniosynostosis and ML. Inclusion criteria encompassed peer-reviewed studies in English that investigated ML algorithms in craniosynostosis diagnosis, severity assessment, or treatment outcome prediction. Three independent reviewers screened the search results, performed full-text assessments, and extracted data from selected studies using a standardized form. Thirteen studies met the inclusion criteria and were included in the review. Of the thirteen papers examined on the application of ML to the identification and treatment of craniosynostosis, two papers were dedicated to sagittal craniosynostosis, five papers utilized several different types of craniosynostosis in the training and testing of their ML models, and six papers were dedicated to metopic craniosynostosis. ML models demonstrated high accuracy in identifying different types of craniosynostosis and objectively quantifying severity using innovative metrics such as metopic severity score and cranial morphology deviation. The findings highlight the significant strides made in utilizing ML techniques for craniosynostosis diagnosis, severity assessment, and predictive modeling. Predictive modeling of treatment outcomes following surgical interventions showed promising results, aiding in personalized treatment strategies. Despite methodological diversities among studies, the collective evidence underscores ML's transformative potential in revolutionizing craniosynostosis management.

Comparative analysis of bevacizumab and LITT for treating radiation necrosis in previously radiated CNS neoplasms: a systematic review and meta-analysis

PURPOSE

Radiation necrosis (RN) is a local inflammatory reaction that arises in response to radiation injury and may cause significant morbidity. This study aims to evaluate and compare the efficacy of bevacizumab and laser interstitial thermal therapy (LITT) in treating RN in patients with previously radiated central nervous system (CNS) neoplasms.

METHODS

PubMed, Cochrane, Scopus, and EMBASE databases were screened. Studies of patients with radiation necrosis from primary or secondary brain tumors were included. Indirect meta-analysis with random-effect modeling was performed to compare clinical and radiological outcomes.

RESULTS

Twenty-four studies were included with 210 patients in the bevacizumab group and 337 patients in the LITT group. Bevacizumab demonstrated symptomatic improvement/stability in 87.7% of cases, radiological improvement/stability in 86.2%, and steroid wean-off in 45%. LITT exhibited symptomatic improvement/stability in 71.2%, radiological improvement/stability in 64.7%, and steroid wean-off in 62.4%. Comparative analysis revealed statistically significant differences favoring bevacizumab in symptomatic improvement/stability (p = 0.02), while no significant differences were observed in radiological improvement/stability (p = 0.27) or steroid wean-off (p = 0.90). The rates of adverse reactions were 11.2% for bevacizumab and 14.9% for LITT (p = 0.66), with the majority being grade 2 or lower (72.2% for bevacizumab and 62.5% for LITT).

CONCLUSION

Both bevacizumab and LITT exhibited favorable clinical and radiological outcomes in managing RN. Bevacizumab was found to be associated with better symptomatic control compared to LITT. Patient-, diagnosis- and lesion-related factors should be considered when choosing the ideal treatment modality for RN to enhance overall patient outcomes.

Chat-GPT on brain tumors: An examination of Artificial Intelligence/Machine Learning's ability to provide diagnoses and treatment plans for example neuro-oncology cases

OBJECTIVE

Assess the capabilities of ChatGPT-3.5 and 4 to provide accurate diagnoses, treatment options, and treatment plans for brain tumors in example neuro-oncology cases.

METHODS

ChatGPT-3.5 and 4 were provided with twenty example neuro-oncology cases of brain tumors, all selected from medical textbooks. The artificial intelligence programs were asked to give a diagnosis, treatment option, and treatment plan for each of these twenty example cases. Team members first determined in which cases ChatGPT-3.5 and 4 provided the correct diagnosis or treatment plan. Twenty neurosurgeons from the researchers' institution then independently rated the diagnoses, treatment options, and treatment plans provided by both artificial intelligence programs for each of the twenty example cases, on a scale of one to ten, with ten being the highest score. To determine whether the difference between the scores of ChatGPT-3.5 and 4 was statistically significant, a paired t-test was conducted for the average scores given to the programs for each example case.

RESULTS

In the initial analysis of correct responses, ChatGPT-4 had an accuracy of 85% for its diagnoses of example brain tumors and an accuracy of 75% for its provided treatment plans, while ChatGPT-3.5 only had an accuracy of 65% and 10%, respectively. The average scores given by the twenty independent neurosurgeons to ChatGPT-4 for its accuracy of diagnosis, provided treatment options, and provided treatment plan were 8.3, 8.4, and 8.5 out of 10, respectively, while ChatGPT-3.5's average scores for these categories of assessment were 5.9, 5.7, and 5.7. These differences in average score are statistically significant on a paired t-test, with a p-value of less than 0.001 for each difference.

CONCLUSIONS

ChatGPT-4 demonstrates great promise as a diagnostic tool for brain tumors in neuro-oncology, as attested to by the program's performance in this study and its assessment by surveyed neurosurgeon reviewers.

Duraplasty with autologous cervical fascia in pediatric posterior fossa tumor surgery: a single-center experience with 214 cases

PURPOSE

Posterior fossa surgeries for pediatric tumors pose challenges in achieving optimal dural repair and duraplasty is usually required. Autografts, allografts, xenografts, and synthetic substitutes can be used for duraplasty. Autologous cervical fascia can be a safe and reliable graft option for duraplasty after posterior fossa surgeries. This study aims to investigate the outcomes of duraplasty with autologous cervical fascial graft in children after posterior fossa surgery for pediatric brain tumors.

METHODS

Pediatric patients with posterior fossa tumor who underwent surgery between March 2001 and August 2022 were retrospectively reviewed. Data on demographics, preoperative symptoms, diagnosis, tumor characteristics, hydrocephalus history, and postoperative complications, including cerebrospinal fluid (CSF) leakage, pseudomeningocele, and meningitis were collected. Logistic regression analysis was performed to explore risk factors for postoperative complications.

RESULTS

Patient cohort included 214 patients. Autologous cervical fascia was used in all patients for duraplasty. Mean age was 7.9 ± 5.3 years. Fifty-seven patients (26.6%) had preoperative hydrocephalus and 14 patients (6.5%) received VPS or EVD perioperatively. Postoperative hydrocephalus was present in 31 patients (14.5%). Rates of CSF leak, pseudomeningocele, and meningitis were 4.2%, 2.8%, and 4.2% respectively. Logistic regression analysis revealed that postoperative EVD and VPS placement were the factors associated with postoperative complications.

CONCLUSION

Autologous cervical fascia is a safe and reliable option for duraplasty with minimal risk of postoperative complications. The straightforward surgical technique and with no additional cost for harvesting the graft renders autologous cervical fascia a favorable alternative for resource-limited countries or surgical settings.

Extraosseous Ewing sarcoma of the pancreas: a case report

Extraosseous Ewing sarcoma is a rare and aggressive malignancy belonging to the Ewing sarcoma family of tumors, primarily affecting soft tissues such as the pelvis, retroperitoneum, and chest wall. Although it predominantly involves these soft tissues, extraosseous Ewing sarcoma can also occur in solid organs, including the pancreas. Here, we present a rare case of a 4-year-old girl diagnosed with primary extraosseous Ewing sarcoma of the pancreas.