Pathologic aspects of skull base tumors

Clinical situations for which 3D printing is considered an appropriate representation or extension of data contained in a medical imaging examination: neurosurgical and otolaryngologic conditions

BACKGROUND

Medical three dimensional (3D) printing is performed for neurosurgical and otolaryngologic conditions, but without evidence-based guidance on clinical appropriateness. A writing group composed of the Radiological Society of North America (RSNA) Special Interest Group on 3D Printing (SIG) provides appropriateness recommendations for neurologic 3D printing conditions.

METHODS

A structured literature search was conducted to identify all relevant articles using 3D printing technology associated with neurologic and otolaryngologic conditions. Each study was vetted by the authors and strength of evidence was assessed according to published guidelines.

RESULTS

Evidence-based recommendations for when 3D printing is appropriate are provided for diseases of the calvaria and skull base, brain tumors and cerebrovascular disease. Recommendations are provided in accordance with strength of evidence of publications corresponding to each neurologic condition combined with expert opinion from members of the 3D printing SIG.

CONCLUSIONS

This consensus guidance document, created by the members of the 3D printing SIG, provides a reference for clinical standards of 3D printing for neurologic conditions.

Predictive Factors for Pediatric Craniopharyngioma Recurrence: An Extensive Narrative Review

Despite being classified as benign tumors, craniopharyngiomas (CPs) are associated with significant morbidity and mortality due to their location, growth pattern, and tendency to recur. Two types can be identified depending on age distribution, morphology, and growth pattern, adamantinomatous and papillary. The adamantinomatous CP is one of the most frequently encountered central nervous system tumors in childhood. Our aim was to review the relevant literature to identify clinical, morphological, and immunohistochemical prognostic factors that have been implicated in childhood-onset CP recurrence. Lack of radical surgical removal of the primary tumor by an experienced neurosurgical team and radiotherapy after a subtotal excision has been proven to significantly increase the recurrence rate of CP. Other risk factors that have been consistently recognized in the literature include younger age at diagnosis (especially <5 years), larger tumor size at presentation, cystic appearance, difficult tumor location, and tight adherence to surrounding structures, as well as the histological presence of whorl-like arrays. In addition, several other risk factors have been studied, albeit with conflicting results, especially in the pediatric population. Identifying risk factors for CP recurrence is of utmost importance for the successful management of these patients in order to ultimately ensure the best prognosis.

Tumor type detection in brain MR images of the deep model developed using hypercolumn technique, attention modules, and residual blocks

Brain cancer is a disease caused by the growth of abnormal aggressive cells in the brain outside of normal cells. Symptoms and diagnosis of brain cancer cases are producing more accurate results day by day in parallel with the development of technological opportunities. In this study, a deep learning model called BrainMRNet which is developed for mass detection in open-source brain magnetic resonance images was used. The BrainMRNet model includes three processing steps: attention modules, the hypercolumn technique, and residual blocks. To demonstrate the accuracy of the proposed model, three types of tumor data leading to brain cancer were examined in this study: glioma, meningioma, and pituitary. In addition, a segmentation method was proposed, which additionally determines in which lobe area of the brain the two classes of tumors that cause brain cancer are more concentrated. The classification accuracy rates were performed in the study; it was 98.18% in glioma tumor, 96.73% in meningioma tumor, and 98.18% in pituitary tumor. At the end of the experiment, using the subset of glioma and meningioma tumor images, it was determined which at brain lobe the tumor region was seen, and 100% success was achieved in the analysis of this determination. In this study, a hybrid deep learning model is presented to determine the detection of the brain tumor. In addition, open-source software was proposed, which statistically found in which lobe region of the human brain the brain tumor occurred. The methods applied and tested in the experiments have shown promising results with a high level of accuracy, precision, and specificity. These results demonstrate the availability of the proposed approach in clinical settings to support the medical decision regarding brain tumor detection.

Tumor type detection in brain MR images of the deep model developed using hypercolumn technique, attention modules, and residual blocks

Brain cancer is a disease caused by the growth of abnormal aggressive cells in the brain outside of normal cells. Symptoms and diagnosis of brain cancer cases are producing more accurate results day by day in parallel with the development of technological opportunities. In this study, a deep learning model called BrainMRNet which is developed for mass detection in open-source brain magnetic resonance images was used. The BrainMRNet model includes three processing steps: attention modules, the hypercolumn technique, and residual blocks. To demonstrate the accuracy of the proposed model, three types of tumor data leading to brain cancer were examined in this study: glioma, meningioma, and pituitary. In addition, a segmentation method was proposed, which additionally determines in which lobe area of the brain the two classes of tumors that cause brain cancer are more concentrated. The classification accuracy rates were performed in the study; it was 98.18% in glioma tumor, 96.73% in meningioma tumor, and 98.18% in pituitary tumor. At the end of the experiment, using the subset of glioma and meningioma tumor images, it was determined which at brain lobe the tumor region was seen, and 100% success was achieved in the analysis of this determination. In this study, a hybrid deep learning model is presented to determine the detection of the brain tumor. In addition, open-source software was proposed, which statistically found in which lobe region of the human brain the brain tumor occurred. The methods applied and tested in the experiments have shown promising results with a high level of accuracy, precision, and specificity. These results demonstrate the availability of the proposed approach in clinical settings to support the medical decision regarding brain tumor detection.