Early Experience With Artificial Intelligence Software to Detect Intracranial Occlusive Stroke in Trauma Patients.

Objective Identifying ischemic stroke is a diagnostic challenge in the trauma subpopulation. We describe our early experience with artificial intelligence-assisted image analysis software for automatically identifying acute ischemic stroke in trauma patients.  Methods Patients were retrospectively screened for (i) admission to the trauma service at a level one trauma center between 2020 and 2022, (ii) radiologist-confirmed intracranial occlusion, (iii) occlusion identified on computed tomography angiography performed within 24 hours of admission, (iv) no intracranial hemorrhage, and (v) contemporaneous analysis with the large vessel occlusion (LVO) detection program. Baseline characteristics, stroke detection, response-activation, and outcome data were summarized.  Results Of 9893 trauma patients admitted, 88 (0.89%) patients had a cerebral stroke diagnosis, of which 10 patients (10/88; 11.4%) met inclusion criteria. Most patients were admitted following a fall (8/10; 80%). Six (6/10; 60.0%) patients had LVOs. The program correctly detected 83.3% (5/6) of patients, and these patients were triaged in less than one hour from arrival on average. The program did not falsely identify non-LVOs as LVOs for any patients. Conclusions Identifying adjunct tools to aid timely identification and treatment of ischemic stroke in trauma patients is necessary to increase the chances for meaningful neurological recovery. Our early experience exhibited potential for using automated software to aid occlusion identification and subsequent stroke team mobilization. Future studies in larger cohorts will expand upon these preliminary findings to establish the accuracy and clinical benefit of automated stroke detection tool integration for the trauma population.

Correlating Age and Hematoma Volume with Extent of Midline Shift in Acute Subdural Hematoma Patients: Validation of an Artificial Intelligence Tool for Volumetric Analysis.

OBJECTIVE: Decision for intervention in acute subdural hematoma patients is based on a combination of clinical and radiographic factors. Age has been suggested as a factor to be strongly considered when interpreting midline shift (MLS) and hematoma volume data for assessing critical clinical severity during operative intervention decisions for acute subdural hematoma patients. The objective of this study was to demonstrate the use of an automated volumetric analysis tool to measure hematoma volume and MLS and quantify their relationship with age. METHODS: A total of 1789 acute subdural hematoma patients were analyzed using qER-Quant software (Qure.ai, Mumbai, India) for MLS and hematoma volume measurements. Univariable and multivariable regressions analyzed association between MLS, hematoma volume, age, and MLS:hematoma volume ratio. RESULTS: In comparison to young patients (≤ 70 years), old patients (>70 years) had significantly higher average hematoma volume (old: 62.2 mL vs. young 46.8 mL, P < 0.0001), lower average MLS (old: 6.6 mm vs. young: 7.4 mm, P = 0.025), and lower average MLS:hematoma volume ratio (old: 0.11 mm/mL vs. young 0.15 mm/mL, P < 0.0001). Young patients had an average of 1.5 mm greater MLS for a given hematoma volume in comparison to old patients. With increasing age, the ratio between MLS and hematoma volume significantly decreases (P = 0.0002). CONCLUSIONS: Commercially available, automated, artificial intelligence (AI)-based tools may be used for obtaining quantitative radiographic measurement data in patients with acute subdural hematoma. Our quantitative results are consistent with the qualitative relationship previously established between age, hematoma volume, and MLS, which supports the validity of using AI-based tools for acute subdural hematoma volume estimation.

Novel use of an image-guided supraorbital craniotomy via an eyebrow approach for the repair of a delayed traumatic orbital encephalocele: illustrative cases.

BACKGROUND: Traumatic orbital encephaloceles are rare but severe complications of orbital fractures. These encephaloceles can present months to years after the initial injury. OBSERVATIONS: The authors present two cases of traumatic orbital encephalocele in young males struck by motor vehicles. LESSONS: The exact traumatic mechanism of these encephaloceles is unknown, and diagnosis can be confounded by concomitant injuries. The use of a minimally invasive supraorbital keyhole craniotomy has the potential to change how this disease process is managed and has not been previously documented in this setting.

The validity and reliability of computed tomography orbital volume measurements.

PURPOSE: Orbital volume calculations allow surgeons to design patient-specific implants to correct volume deficits. It is estimated that changes as small as 1 ml in orbital volume can lead to enophthalmos. Awareness of the limitations of orbital volume computed tomography (CT) measurements is critical to differentiate between true volume differences and measurement error. The aim of this study is to analyze the validity and reliability of CT orbital volume measurements. MATERIALS AND METHODS: A total of 12 cadaver orbits were scanned using a standard CT maxillofacial protocol. Each orbit was dissected to isolate the extraocular muscles, fatty tissue, and globe. The empty bony orbital cavity was then filled with sculpting clay. The volumes of the muscle, fat, globe, and clay (i.e., bony orbital cavity) were then individually measured via water displacement. The CT-derived volumes, measured by manual segmentation, were compared to the direct measurements to determine validity. RESULTS AND CONCLUSIONS: The difference between CT orbital volume measurements and physically measured volumes is not negligible. Globe volumes have the highest agreement with 95% of differences between -0.5 and 0.5 ml, bony volumes are more likely to be overestimated with 95% of differences between -1.8 and 2.6 ml, whereas extraocular muscle volumes have poor validity and should be interpreted with caution.

The "Crumple Zone" hypothesis: Association of frontal sinus volume and cerebral injury after craniofacial trauma.

PURPOSE: The paranasal sinuses are complex anatomical structures of unknown significance. One hypothesis theorizes that the sinuses, in the event of a traumatic injury, function as a crumple zone to distribute and absorb energy to protect the brain and other critical structures. The current study investigates the association between frontal sinus (FS) volume and the severity of cerebral insults following craniofacial trauma. METHODS: All patients with FS fracture admitted to a level 1 trauma center from 2011 to 2014 were retrospectively reviewed. FS volumes were measured from computed tomography (CT) on admission using a proprietary region growing segmentation tool. Head injuries were classified based on the presence of specific types of intracranial pathology and their corresponding Marshall Score. RESULTS: FS fracture was identified on the admission CT in 165 patients. Male patients had significantly larger FS volume compared to females (8.4 ± 6.3 vs. 4.0 ± 2.9 cm3, p < 0.001). Smaller FS volume was significantly associated with a worse Marshall Score (p = 0.041) and a higher incidence of cerebral contusion (p = 0.016) independent of age, gender, mechanism, ISS, and admission GCS. The inverse correlation between FS volume and the Marshall Score was also statistically significant (Spearman correlation coefficient r = -0.19, p = 0.015). Smaller FS volume was observed in patients who suffered intracranial insults, underwent neurosurgical interventions, and had worse clinical outcomes and trended towards significance with respect to an association with subarachnoid hemorrhage (p = 0.074) and subdural hematoma (p = 0.080), and had a statistically significant association with longer length of stay (p < 0.001). CONCLUSION: FS volume is inversely correlated with the severity of intracranial pathology following craniofacial trauma. Our findings are consistent with the "crumple zone" hypothesis and suggest that the FS likely plays a role in mitigating intracranial injury. Furthermore, FS volume is significantly different between male and female patients. This is a novel finding that warrants further validation.

Surgical management of civilian gunshot wounds to the head.

Each year close to 20000 Americans are involved in gunshot wounds to the head (GSWH). Over 90% of the victims of GSWH eventually fail to survive and only a meager 5% of the patients have a chance to continue with a useful life. One of the fundamental jobs of providers is to realize who the best candidate for the best possible management is. Recent evidence indicates that a good Glasgow Coma Scale (GCS) score at the time of admission puts such patients at high priority for management. Lack of abnormal pupillary response to light, trajectory of slug away for central gray, and visibility of basal cisterns upgrade the need for utmost care for such a victim. Surgical management is careful attention to involvement of air sinuses and repair of base dura. Patients with diffuse injury should have intraventricular intracranial pressure (ICP) monitoring and if needed a timely decompressive craniectomy. Since close to 2% of patients with penetrating brain injury may harbor a vascular injury, subjects with injuries close to the Sylvian fissure and those with the fragment crossing two dural compartments should have computed tomography angiography and if needed digital subtraction angiography to rule out traumatic intracranial aneurysms. In case of a positive study, these patients should have endovascular management of their vascular injuries in order to prevent catastrophic intracerebral hematomas and permanent deficit. Although supported by class III data, subjects of GSWH need to be on broad spectrum antibiotics for a period of 3-5 days. If cerebrospinal fluid (CSF) fistulas are observed at any time during the patient's hospital course, they should be taken very seriously and appropriate management is needed to prevent deep intracranial infections.

Early decompressive craniectomy for severe penetrating and closed head injury during wartime.

OBJECT: Decompressive craniectomy has defined this era of damage-control wartime neurosurgery. Injuries that in previous conflicts were treated in an expectant manner are now aggressively decompressed at the far-forward Combat Support Hospital and transferred to Walter Reed Army Medical Center (WRAMC) and National Naval Medical Center (NNMC) in Bethesda for definitive care. The purpose of this paper is to examine the baseline characteristics of those injured warriors who received decompressive craniectomies. The importance of this procedure will be emphasized and guidance provided to current and future neurosurgeons deployed in theater. METHODS: The authors retrospectively searched a database for all soldiers injured in Operations Iraqi Freedom and Enduring Freedom between April 2003 and October 2008 at WRAMC and NNMC. Criteria for inclusion in this study included either a closed or penetrating head injury suffered during combat operations in either Iraq or Afghanistan with subsequent neurosurgical evaluation at NNMC or WRAMC. Exclusion criteria included all cases in which primary demographic data could not be verified. Primary outcome data included the type and mechanism of injury, Glasgow Coma Scale (GCS) score and injury severity score (ISS) at admission, and Glasgow Outcome Scale (GOS) score at discharge, 6 months, and 1-2 years. RESULTS: Four hundred eight patients presented with head injury during the study period. In this population, a total of 188 decompressive craniectomies were performed (154 for penetrating head injury, 22 for closed head injury, and 12 for unknown injury mechanism). Patients who underwent decompressive craniectomies in the combat theater had significantly lower initial GCS scores (7.7 +/- 4.2 vs 10.8 +/- 4.0, p < 0.05) and higher ISSs (32.5 +/- 9.4 vs 26.8 +/- 11.8, p < 0.05) than those who did not. When comparing the GOS scores at hospital discharge, 6 months, and 1-2 years after discharge, those receiving decompressive craniectomies had significantly lower scores (3.0 +/- 0.9 vs 3.7 +/- 0.9, 3.5 +/- 1.2 vs 4.0 +/- 1.0, and 3.7 +/- 1.2 vs 4.4 +/- 0.9, respectively) than those who did not undergo decompressive craniectomies. That said, intragroup analysis indicated consistent improvement for those with craniectomy with time, allowing them, on average, to participate in and improve from rehabilitation (p < 0.05). Overall, 83% of those for whom follow-up data are available achieved a 1-year GOS score of greater than 3. CONCLUSIONS: This study of the provision of early decompressive craniectomy in a military population that sustained severe penetrating and closed head injuries represents one of the largest to date in both the civilian and military literature. The findings suggest that patients who undergo decompressive craniectomy had worse injuries than those receiving craniotomy and, while not achieving the same outcomes as those with a lesser injury, did improve with time. The authors recommend hemicraniectomy for damage control to protect patients from the effects of brain swelling during the long overseas transport to their definitive care, and it should be conducted with foresight concerning future complications and reconstructive surgical procedures.

Transcranial Doppler ultrasonography identifies symptomatic cavum septum pellucidum cyst: case report.

OBJECTIVE: Cavum Septum Pellucidum (CSP) cysts are considered normal anatomic variants, comprising as many as 15% of the adult and 85% of pediatric populations. On rare occasions, the cavum can obstruct CSF outflow from the lateral ventricles causing elevated intracranial pressure (ICP) and headaches. The purpose of this paper is to present a challenging case of new onset symptomatic CSP in a previously healthy adult male without papilledema and elevated ICP detected by transcranial Doppler (TCD) ultrasonography. CLINICAL PRESENTATION: A previously healthy 44 year-old man presented to the neurology service with debilitating positional headaches that were mitigated solely by recumbent positioning. A magnetic resonance imaging scan (MRI) of the brain revealed a cavum septum pellucidum. A lumbar puncture was performed and revealed normal ICP. No papilledema was evident on fundoscopic examination. A CSF flow study revealed normal dye opacification pattern without evidence of CSF leak. INTERVENTION: Without other clinical indicators of high ICP, but a history suspicious for symptomatic CSP, TCD study was performed and revealed abnormally low cerebral blood flow velocities (CBFV's) and significantly elevated pulsatility indices (PI's) for patient's age indicative of high ICP. Endoscopic fenestration of the septum pellucidum was performed improving the patient's headaches and normalization of the PI's and CBFV's to normal (p<0.01). CONCLUSIONS: Symptomatic CSP is a difficult diagnosis to make based on existing diagnostic paradigm. TCD in the absence of other objective confirmatory studies, can aid in the diagnosis and provide information about the success of fenestration of the cavum septum.

Military traumatic brain and spinal column injury: a 5-year study of the impact blast and other military grade weaponry on the central nervous system.

BACKGROUND: During the past 5 years of Operation Iraqi Freedom (OIF), a significant majority of the severe closed and penetrating head trauma has presented for definitive care at the National Naval Medical Center (NNMC) in Bethesda, MD, and at the Walter Reed Army Medical Center (WRAMC) in Washington, DC. The purpose of this article is to review our experience with this population of patients. MATERIALS: A retrospective review of all inpatient admissions from OIF was performed during a 5-year period (April 2003 to April 2008). Criteria for inclusion in this study included either a closed or penetrating head trauma suffered during combat operations in Iraq who subsequently received a neurosurgical evaluation at NNMC or WRAMC. Exclusion criteria included all patients for whom primary demographic data could not be verified. Primary outcome data included the type and mechanism of injury, Glasgow coma scale (GCS) and injury severity score at admission, and Glasgow outcome scale (GOS) at discharge, 6 months, and 1 to 2 years. RESULTS: Five hundred thirteen consultations were performed by the neurosurgery service on the aforementioned population. Four hundred eight patients met the inclusion criteria for this study (401:7, male: female; 228 penetrating brain injury, 139 closed head injury, 41 not specified). Explosive blast injury (229 patients; 56%) constituted the predominant mechanism of injury. The rates of pulmonary embolism (7%), cerebrospinal fluid leak (8.6%), meningitis (9.1%), spinal cord or column injury (9.8%), and cerebrovascular injury (27%) were characterized. Cerebrospinal fluid leak, vasospasm, penetrating head injury, and lower presenting GCS were statistically associated with longer intensive care unit stays and higher presenting injury severity scores (p < 0.05). While presenting GCS 3-5 correlated with worsened short-term and long-term GOS scores (p < 0.001), almost half of these patients achieved GOS >or=3 at 1- to 2-year follow-up. Total mortality after reaching NNMC/WRAMC was 4.4%. CONCLUSIONS: OIF has resulted in the highest concentration of severe closed and penetrating head trauma to return to NNMC and WRAMC since the Vietnam Conflict. Management scenarios were complex, incorporating principles designed to maximize outcomes in all body systems. Meaningful survival can potentially be achieved in a subset of patients with presenting GCS