Intracranial hemorrhage is a medical emergency that requires urgent diagnosis and immediate treatment to improve patient outcome. Machine learning algorithms can be used to perform medical image classification and assist clinicians in diagnosing radiological scans. In this paper, we apply 3-dimensional convolutional neural networks (3D CNN) to classify computed tomography (CT) brain scans into normal scans (N) and abnormal scans containing subarachnoid hemorrhage (SAH), intraparenchymal hemorrhage (IPH), acute subdural hemorrhage (ASDH) and brain polytrauma hemorrhage (BPH). The dataset used consists of 399 volumetric CT brain images representing approximately 12,000 images from the National Neuroscience Institute, Singapore. We used a 3D CNN to perform both 2-class (normal versus a specific abnormal class) and 4-class classification (between normal, SAH, IPH, ASDH). We apply image thresholding at the image pre-processing step, that improves 3D CNN classification accuracy and performance by accentuating the pixel intensities that contribute most to feature discrimination. For 2-class classification, the F1 scores for various pairs of medical diagnoses ranged from 0.706 to 0.902 without thresholding. With thresholding implemented, the F1 scores improved and ranged from 0.919 to 0.952. Our results are comparable to, and in some cases, exceed the results published in other work applying 3D CNN to CT or magnetic resonance imaging (MRI) brain scan classification. This work represents a direct application of a 3D CNN to a real hospital scenario involving a medically emergent CT brain diagnosis.
Covid-19 vaccine associated cerebral venous thrombosis (CVT) are rare adverse events and can be considered as black swan events."Black swan events", originally described by Nassim N. Taleb in economic theory, are rare, unexpected events whose potential to occur only becomes apparent after they have happened, where they are neither predicted nor anticipated, and only on retrospect, a clear basis is found for their occurrence that justifies their apparent randomness. The modified Adenovirus vector Covid-19 vaccines (ChAdOx1 nCoV-19 (Oxford-AstraZeneca) and Ad26.COV2.S (Johnson & Johnson/Janssen)) and mRNA based Covid-19 vaccines (BNT162b2 mRNA CORRESPONDENCE E357 CORRESPONDENCE E359
Object. The choice of programmable or nonprogrammable shunts for the management of hydrocephalus after aneurysmal subarachnoid hemorrhage (SAH) remains undefined. Variable intracranial pressures make optimal management difficult. Programmable shunts have been shown to reduce problems with drainage, but at 3 times the cost of nonprogrammable shunts.Methods. All patients who underwent insertion of a ventriculoperitoneal shunt for hydrocephalus after aneurysmal SAH between 2006 and 2012 were included. Patients were divided into those in whom nonprogrammable shunts and those in whom programmable shunts were inserted. The rates of shunt revisions, the reasons for adjustments of shunt settings in patients with programmable devices, and the effectiveness of the adjustments were analyzed. A cost-benefit analysis was also conducted to determine if the overall cost for programmable shunts was more than for nonprogrammable shunts.Results. Ninety-four patients underwent insertion of shunts for hydrocephalus secondary to SAH. In 37 of these patients, nonprogrammable shunts were inserted, whereas in 57 programmable shunts were inserted. Four (7%) of 57 patients with programmable devices underwent shunt revision, whereas 8 (21.6%) of 37 patients with nonprogrammable shunts underwent shunt revision (p = 0.0413), and 4 of these patients had programmable shunts inserted during shunt revision. In 33 of 57 patients with programmable shunts, adjustments were made. The adjustments were for a trial of functional improvement (n = 21), overdrainage (n = 5), underdrainage (n = 6), or overly sunken skull defect (n = 1). Of these 33 patients, 24 showed neurological improvements (p = 0.012). Cost-benefit analysis showed $646.60 savings (US dollars) per patient if programmable shunts were used, because the cost of shunt revision is a lot higher than the cost of the shunt.Conclusions. The rate of shunt revision is lower in patients with programmable devices, and these are therefore more cost-effective. In addition, the shunt adjustments made for patients with programmable devices also resulted in better neurological outcomes.
INTRODUCTIONThe present study aimed to assess the immediate/early clinical outcomes and surgical results of 11 consecutive patients who underwent palliative cervical spine surgery for symptomatic spinal metastases.
METHODSThis single-surgeon retrospective case series analysed 12 surgical procedures that were performed for symptomatic cervical spinal metastasis in 11 consecutive patients. All surgeries were carried out at Singapore General Hospital, Singapore, from 2007 to 2013. Preoperative medical oncological assessment/staging was performed on each patient -all patients presented with either axial neck pain or neurological deficits, and had no bladder or bowel symptoms. The primary outcomes analysed were postoperative neurological power and improvement in neck pain.RESULTS Anterior (n = 5), posterior (n = 4) and combined (n = 2) surgical approaches were used for decompression and stabilisation. Comparing between pre-and postoperative pain scores (scored according to the visual analog scale), and pre-and postoperative limb power scores (scored according to the Medical Research Council scale for muscle strength), we found that all patients showed improvement in their symptoms. Postoperatively, patients had either improvement or preservation of neurological power, and all patients had a decrease in axial neck pain after surgery. Although there was one case of minor pedicle screw instrumentation malplacement, this did not result in any neurological symptoms. Median survival for the patients was 108 (range 7-1,095) days.CONCLUSION Palliative surgery for cervical spine metastasis is safe with good neurological results, low complication rates, and improvement in neck pain. A multidisciplinary approach involving surgeons, medical oncologists and radiotherapists is needed to optimise patient care and outcome.
Fluorescein sodium fluorescence is as accurate as frozen section assessment in confirming sampling of pathological tissue in the stereotactic biopsy of gadolinium-contrast-enhancing brain lesions. Fluorescein sodium fluorescence-guided stereotactic biopsy is a useful addition to the neurosurgical armamentarium.
The Fluoropen is a low-cost and simple standalone device for the detection of fluorescein fluorescence that can expedite stereotactic needle biopsy by providing instant confirmation of the diagnostic sample and therefore avoid the need for an intraoperative frozen section. In patients with non-contrast enhancing tumors and those who were pre-treated with dexamethasone prior to surgery, fluorescein fluorescence-guided stereotactic needle biopsy will need to be used with caution.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.