Explore the vast range of titles available.

Intraoperative diagnosis is essential for providing safe and effective care during cancer surgery 1 . The existing workflow for intraoperative diagnosis based on hematoxylin and eosin staining of processed tissue is time, resource and labor intensive 2 , 3 . Moreover, interpretation of intraoperative histologic images is dependent on a contracting, unevenly distributed, pathology workforce 4 . In the present study, we report a parallel workflow that combines stimulated Raman histology (SRH) 5 – 7 , a label-free optical imaging method and deep convolutional neural networks (CNNs) to predict diagnosis at the bedside in near real-time in an automated fashion. Specifically, our CNNs, trained on over 2.5 million SRH images, predict brain tumor diagnosis in the operating room in under 150 s, an order of magnitude faster than conventional techniques (for example, 20–30 min) 2 . In a multicenter, prospective clinical trial ( n  = 278), we demonstrated that CNN-based diagnosis of SRH images was noninferior to pathologist-based interpretation of conventional histologic images (overall accuracy, 94.6% versus 93.9%). Our CNNs learned a hierarchy of recognizable histologic feature representations to classify the major histopathologic classes of brain tumors. In addition, we implemented a semantic segmentation method to identify tumor-infiltrated diagnostic regions within SRH images. These results demonstrate how intraoperative cancer diagnosis can be streamlined, creating a complementary pathway for tissue diagnosis that is independent of a traditional pathology laboratory. A prospective, multicenter, case–control clinical trial evaluates the potential of artificial intelligence for providing accurate bedside diagnosis of patients with brain tumors.

Abstract Enabling technologies include surgical planning software, computer-assisted navigation, intraoperative three-dimensional (3D) imaging, and robotic systems. Presently, these technologies are in various stages of refinement. Spinal robots in particular are currently limited to the positioning of an alignment guide for pedicle screw placement. Current generation spinal robots, therefore, play a more limited role in spinal surgery. In contrast to spinal robots, intraoperative imaging technology has been developed further, to a stage that allows accurate 3D spinal image acquisition that can be readily utilized for spinal navigation. The integration of these various technologies has the potential to maximize the safety, consistency, reliability, and efficacy of surgical procedures. To that end, the trend for manufacturers is to incorporate various enabling technologies into the spinal robotic systems. In the near-term, it is expected that integration of more advanced planning software and navigation will result in wider applicability and value. In the long-term, there are a variety of enabling technologies such as augmented reality that may be a component of spinal robots. This article reviews the features of currently available spinal robots and discusses the likely future advancements of robotic platforms in the near- and long-term.

The discovery of a new mass involving the brain or spine typically prompts referral to a neurosurgeon to consider biopsy or surgical resection. Intraoperative decision-making depends significantly on the histologic diagnosis, which is often established when a small specimen is sent for immediate interpretation by a neuropathologist. Access to neuropathologists may be limited in resource-poor settings, which has prompted several groups to develop machine learning algorithms for automated interpretation. Most attempts have focused on fixed histopathology specimens, which do not apply in the intraoperative setting. The greatest potential for clinical impact probably lies in the automated diagnosis of intraoperative specimens. Successful future studies may use machine learning to automatically classify whole-slide intraoperative specimens among a wide array of potential diagnoses.

OBJECTIVES/GOALS: The correction of spinopelvic parameters is associated with better outcomes in patients with adult spinal deformity (ASD). This study presents a novel artificial intelligence (AI) tool that automatically predicts spinopelvic parameters from spine x-rays with high accuracy and without need for any manual entry. METHODS/STUDY POPULATION: The AI model was trained/validated on 761 sagittal whole-spine x-rays to predict the following parameters: Sagittal Vertical Axis (SVA), Pelvic Tilt (PT), Pelvic Incidence (PI), Sacral Slope (SS), Lumbar Lordosis (LL), T1-Pelvic Angle (T1PA), and L1-Pelvic Angle (L1PA). A separate test set of 40 x-rays was labeled by 4 reviewers including fellowship-trained spine surgeons and a neuroradiologist. Median errors relative to the most senior reviewer were calculated to determine model accuracy on test and cropped-test (i.e. lumbosacral) images. Intraclass correlation coefficients (ICC) were used to assess inter-rater reliability RESULTS/ANTICIPATED RESULTS: The AI model exhibited the following median (IQR) parameter errors: SVA[2.1mm (8.5mm), p=0.97], PT [1.5° (1.4°), p=0.52], PI[2.3° (2.4°), p=0.27], SS[1.7° (2.2°), p=0.64], LL [2.6° (4.0°), p=0.89], T1PA [1.3° (1.1°), p=0.41], and L1PA [1.3° (1.2°), p=0.51]. The parameter errors on cropped lumbosacral images were: LL[2.9° (2.6°), p=0.80] and SS[1.9° (2.2°), p=0.78]. The AI model exhibited excellent reliability at all parameters in both whole-spine (ICC: 0.92-1.0) and lumbosacral x-rays: (ICC: 0.92-0.93). DISCUSSION/SIGNIFICANCE: Our AI model accurately predicts spinopelvic parameters with excellent reliability comparable to fellowship-trained spine surgeons and neuroradiologists. Utilization of predictive AI tools in spine-imaging can substantially aid in patient selection and surgical planning.

ObjectivesTo integrate morphological, haemodynamic and mechanical analysis of carotid atheroma driving plaque disruption.Materials and methodsFirst, we analysed the phenotypes of carotid endarterectomy specimens in a photographic dataset A, and matched them with the likelihood of preoperative stroke. Second, laser angioscopy was used to further define the phenotypes in intact specimens (dataset B) and benchmark with histology. Third, representative vascular geometries for each structural phenotype were analysed with Computational Fluid Dynamics (CFD), and the mechanical strength of the complicated atheroma to resist penetrating forces was quantified (n=14).ResultsIn dataset A (n=345), ulceration (fibrous cap disruption) was observed in 82% of all plaques, intraplaque haemorrhage in 68% (93% subjacent to an ulcer) and false luminal formation in 48%. At least one of these ‘rupture’ phenotypes was found in 97% of symptomatic patients (n=69) compared with 61% in asymptomatic patients. In dataset B (n=30), laser angioscopy redemonstrated the structural phenotypes with near-perfect agreement with histology. In CFD, haemodynamic stress showed a large pulse magnitude, highest upstream to the point of maximal stenosis and on ulceration the inflow stream excavates the necrotic core cranially and then recirculates into the true lumen. Based on mechanical testing (n=14), the necrotic core is mechanically weak and penetrated by the blood on fibrous cap disruption.ConclusionsFibrous cap ulceration, plaque haemorrhage and excavation are sequential phenotypes of plaque disruption resulting from the chiselling effect of haemodynamic forces over unmatched mechanical tissue strength. This chain of events may result in thromboembolic events independently of the degree of stenosis.

Abstract Myxopapillary ependymomas are slow-growing tumors that are located almost exclusively in the region of the conus medullaris, cauda equina, and filum terminale of the spinal cord. Surgical intervention achieving a gross total resection is the main treatment modality. If, however, a gross total resection cannot be achieved, surgery is augmented with radiation therapy. In this video, we present the case of a 27-yr-old male with persistent back pain and radiculopathy who was found to have a myxopapillary ependymoma that was adherent to the conus. Preoperative imaging demonstrated that the tumor was displacing the conus and nerve roots ventrally. A laminoplasty at L1-L2 was performed with near-total resection because of the intimate involvement of neural tissue. The key features of the video include performing laminoplasty and rationale, and performing maximum safe tumor resection with a combination of bipolar cautery, suction, and ultrasonic aspiration augmented with frequent stimulation, gel foam pledgets intradurally, and achieving a watertight closure of the dura and fascia. The patient tolerated the surgery well without any complications. Given his gross residual disease along the conus and young age, he was at a high risk for continued tumor growth without adjuvant therapy, with a recurrence rate of roughly 33% to 45% in patients who underwent subtotal resection. With the addition of adjuvant radiation therapy, the recurrence rate is 20% to 29%.1,2 He was discharged to home with a plan for conventional fractionated external beam radiation. At the most recent follow-up, he reported decreased back pain and radiculopathy. Appropriate patient consent was obtained.

Schwannomas are typically benign tumors that arise from the sheaths of nerves in the peripheral nervous system. In the spine, schwannomas usually arise from spinal nerve roots and are therefore extramedullary in nature. Surgical resection-achieving a gross total resection, is the main treatment modality and is typically curative for patients with sporadic tumors. In this video, we present the case of a 38-yr-old male with worsening left leg radiculopathy, found to have a lumbar schwannoma. Preoperative imaging demonstrated that the tumor was at the level of L4-L5. A laminectomy at this level was performed with gross total resection of the tumor. The key points of the video include use of intraoperative fluoroscopy to confirm surgical level and help plan surgical exposure, use of ultrasound for intradural tumor localization, and advocating for maximum safe resection using neurostimulation. The patient tolerated the surgery well without any complications. He was discharged home with no additional therapy needed. Appropriate patient consent was obtained.

Abstract Spondylolisthesis is a common cause of lower back and leg pain in adults. The initial treatment for patients is typically nonoperative in nature. However, when patients fail conservative management and their back and/or leg pain is recalcitrant, surgical intervention is warranted. Spinal decompression, either directly or indirectly, as well as fusion is often considered at this point. There are numerous approaches to fuse the spine, including anterior, lateral, or posterior, each with their own advantages and disadvantages.   This video illustrates a case of symptomatic spondylolisthesis occurring after laminectomy treated by lateral lumbar interbody fusion for indirect decompression and stabilization. The approach utilizes 3-dimensional navigation rather than traditional fluoroscopy, resulting in markedly decreased radiation exposure for the surgeon and staff while maintaining accuracy. Appropriate patient consent was obtained. This video demonstrates the technique for a lateral lumbar interbody fusion using navigation assistance, which is a minimally invasive technique for the treatment of spondylolisthesis.

Abstract Nerve root compression by foraminal pathology is challenging for a surgeon to decompress without violating the facet joint, which may necessitate a fusion procedure. One nonfusion approach to foraminal pathology is a combination intracanal approach for a laminotomy/foraminotomy followed by a paraspinal Wiltse approach for far lateral decompression. Unfortunately, even with the combination approach, it continues to be difficult to achieve adequate decompression without violating much of the facet joint overlying the nerve root. Spine endoscopy offers the ability to decompress the foraminal portion of the nerve without significant violation of the facet joint. We present a surgical video describing the technique for performing a percutaneous endoscopic contralateral L5-S1 foraminal decompression via an interlaminar approach, for a patient presenting with a left L5 radiculopathy due to L5-S1 foraminal stenosis. We explain the differences in the endoscopic channel docking point between ipsilateral and contralateral interlaminar approaches. The steps of an endoscopic foraminotomy are then described: dissect soft tissue and ligamentum flavum off the medial left S1 lamina and superior articulating process (SAP), undercut the superior articulating process of S1 and the inferior articulating process (IAP) of L5 with a drill, resect lateral ligamentum flavum off SAP and IAP exposing epidural fat, and finally dissect the left L5 nerve root and remove compressive lesions throughout its course in the lateral recess, foramen, and laterally. The presentation ends with an intraoperative photograph showing a decompressed L5 nerve root and postoperative imaging confirming this decompression. Appropriate patient consent was obtained.