The role of imaging in the development of neurosurgery

Kirkman, Matthew A.

doi:10.1016/j.jocn.2014.05.024

Cited by 27 publications

(15 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various studies have shown the utility of CNNs, a form of deep learning, for vessel segmentation, in particular for retinal imaging (20). Another study showed that a single CNN architecture could learn to segment different tissue types using MR brain, MR breast, and cardiac CTA, but did not target the cerebral vasculature (25). Livne et al demonstrated CNNbased cerebral vascular segmentation using MRAs from 66 adults with cerebrovascular disease.…”

Section: Discussionmentioning

confidence: 99%

Deep Learning for Automated Delineation of Pediatric Cerebral Arteries on Pre-operative Brain Magnetic Resonance Imaging

et al. 2020

View full text Add to dashboard Cite

Introduction: Surgical resection of brain tumors is often limited by adjacent critical structures such as blood vessels. Current intraoperative navigations systems are limited; most are based on two-dimensional (2D) guidance systems that require manual segmentation of any regions of interest (ROI; eloquent structures to avoid or tumor to resect). They additionally require time-and labor-intensive processing for any reconstruction steps. We aimed to develop a deep learning model for real-time fully automated segmentation of the intracranial vessels on preoperative non-angiogram imaging sequences. Methods: We identified 48 pediatric patients (10-months to 22-years old) with high resolution (0.5-1 mm axial thickness) isovolumetric, pre-operative T2 magnetic resonance images (MRIs). Twenty-eight patients had anatomically normal brains, and 20 patients had tumors or other lesions near the skull base. Manually segmented intracranial vessels (internal carotid, middle cerebral, anterior cerebral, posterior cerebral, and basilar arteries) served as ground truth labels. Patients were divided into 80/5/15% training/validation/testing sets. A modified 2-D Unet convolutional neural network (CNN) architecture implemented with 5 layers was trained to maximize the Dice coefficient, a measure of the correct overlap between the predicted vessels and ground truth labels. Results: The model was able to delineate the intracranial vessels in a held-out test set of normal and tumor MRIs with an overall Dice coefficient of 0.75. While manual segmentation took 1-2 h per patient, model prediction took, on average, 8.3 s per patient. Conclusions: We present a deep learning model that can rapidly and automatically identify the intracranial vessels on pre-operative MRIs in patients with normal vascular anatomy and in patients with intracranial lesions. The methodology developed can be translated to other critical brain structures. This study will serve as a foundation for automated high-resolution ROI segmentation for three-dimensional (3D) modeling and integration into an augmented reality navigation platform.

show abstract

Section: Discussionmentioning

confidence: 99%

Deep Learning for Automated Delineation of Pediatric Cerebral Arteries on Pre-operative Brain Magnetic Resonance Imaging

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Advances in imaging technologies over the last few decades have not only played a crucial role in improving diagnosis and staging, but they have also enhanced the capacity for better neurosurgery and improved the overall management of CNS cancers [19-21]. Specifically, advances include a wide range of computed tomography and magnetic resonance imaging (MRI) techniques.…”

Section: Discussionmentioning

confidence: 99%

Premature Mortality Due to Malignancies of the Central Nervous System in Canada, 1980–2010

et al. 2018

View full text Add to dashboard Cite

Background: In this study, we investigated whether there has been an improvement in premature mortality due to central nervous system (CNS) cancers among the Canadian population from 1980 through 2010. Methods: Mortality data for CNS cancers were obtained from World Health Organization mortality database. Years of life lost (YLL) was estimated using Canadian life tables. Average lifespan shortened (ALSS) was calculated and defined as the ratio of YLL relative to the expected lifespan. Results: Over this study period, we observed decreases in age standardized rates to the World Standard Population for mortality due to CNS cancers from 5.3 to 4.1 per 100,000 men, and from 3.6 to 2.9 per 100,000 women. Average YLL decreased from 23.6 to 21.5 years of life among men, and from 27.0 to 23.1 years among women in 1980 and 2010, respectively. The ALSS showed that men with CNS cancers lost 30.1% of their life span and women lost 32.5% in 1980, whereas they lost 25.8 and 26.6% in 2010, respectively. Conclusion: Our study shows that Canadian people with CNS cancers have had their lives prolonged at the end of the study period.

show abstract

“…2). 12,20 Dandy had concerns about the risk of herniation in patients with increased intracranial pressure and thus tended to prefer ventriculography for his patients. 12 The use of PEG nevertheless increased as Dandy's work was replicated and implemented in other hospitals, particularly by a contemporary German internist at the City Hospital of Brunswick, Adolf Bingel.…”

Section: History Of Pneumoencephalographymentioning

confidence: 99%

“…12 By some neurosurgeons' accounts, mortality was reported to be as high as 30%. 20 PEG additionally suffered from low resolution and relatively nonspecific findings. Consistency in interpretation and standardized reporting of studies was challenging, particularly due to the lack of a robust control group, as the procedure was too invasive and risky to obtain images in healthy patients.…”

Section: History Of Pneumoencephalographymentioning

confidence: 99%

Pneumoencephalography in the workup of neuropsychiatric illnesses: a historical perspective

Ishaque¹,

Wallace

Grandhi

2017

Neurosurgical Focus

View full text Add to dashboard Cite

Throughout history, neurosurgical procedures have been fundamental in advancing neuroscience; however, this has not always been without deleterious side effects or harmful consequences. While critical to the progression of clinical neuroscience during the early 20th century, yet, at the same time, poorly tolerated by patients, pneumoencephalography is one such procedure that exemplifies this juxtaposition. Presented herein are historical perspectives and reflections on the role of the pneumoencephalography in the diagnosis and treatment of neuropsychiatric illnesses.

show abstract

The role of imaging in the development of neurosurgery

Cited by 27 publications

References 52 publications

Deep Learning for Automated Delineation of Pediatric Cerebral Arteries on Pre-operative Brain Magnetic Resonance Imaging

Deep Learning for Automated Delineation of Pediatric Cerebral Arteries on Pre-operative Brain Magnetic Resonance Imaging

Premature Mortality Due to Malignancies of the Central Nervous System in Canada, 1980–2010

Pneumoencephalography in the workup of neuropsychiatric illnesses: a historical perspective

Contact Info

Product

Resources

About