Development and validation of an artificial intelligence model to accurately predict spinopelvic parameters.

OBJECTIVE: Achieving appropriate spinopelvic alignment has been shown to be associated with improved clinical symptoms. However, measurement of spinopelvic radiographic parameters is time-intensive and interobserver reliability is a concern. Automated measurement tools have the promise of rapid and consistent measurements, but existing tools are still limited to some degree by manual user-entry requirements. This study presents a novel artificial intelligence (AI) tool called SpinePose that automatically predicts spinopelvic parameters with high accuracy without the need for manual entry. METHODS: SpinePose was trained and validated on 761 sagittal whole-spine radiographs to predict the 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 radiographs was labeled by four reviewers, including fellowship-trained spine surgeons and a fellowship-trained radiologist with neuroradiology subspecialty certification. Median errors relative to the most senior reviewer were calculated to determine model accuracy on test images. Intraclass correlation coefficients (ICCs) were used to assess interrater reliability. RESULTS: SpinePose exhibited the following median (interquartile range) parameter errors: SVA 2.2 mm (2.3 mm) (p = 0.93), PT 1.3° (1.2°) (p = 0.48), SS 1.7° (2.2°) (p = 0.64), PI 2.2° (2.1°) (p = 0.24), LL 2.6° (4.0°) (p = 0.89), T1PA 1.1° (0.9°) (p = 0.42), and L1PA 1.4° (1.6°) (p = 0.49). Model predictions also exhibited excellent reliability at all parameters (ICC 0.91-1.0). CONCLUSIONS: SpinePose accurately predicted spinopelvic parameters with excellent reliability comparable to that of fellowship-trained spine surgeons and neuroradiologists. Utilization of predictive AI tools in spinal imaging can substantially aid in patient selection and surgical planning.

Hierarchical discriminative learning improves visual representations of biomedical microscopy.

Learning high-quality, self-supervised, visual representations is essential to advance the role of computer vision in biomedical microscopy and clinical medicine. Previous work has focused on self-supervised representation learning (SSL) methods developed for instance discrimination and applied them directly to image patches, or fields-of-view, sampled from gigapixel whole-slide images (WSIs) used for cancer diagnosis. However, this strategy is limited because it (1) assumes patches from the same patient are independent, (2) neglects the patient-slide-patch hierarchy of clinical biomedical microscopy, and (3) requires strong data augmentations that can degrade downstream performance. Importantly, sampled patches from WSIs of a patient's tumor are a diverse set of image examples that capture the same underlying cancer diagnosis. This motivated HiDisc, a data-driven method that leverages the inherent patient-slide-patch hierarchy of clinical biomedical microscopy to define a hierarchical discriminative learning task that implicitly learns features of the underlying diagnosis. HiDisc uses a self-supervised contrastive learning framework in which positive patch pairs are defined based on a common ancestry in the data hierarchy, and a unified patch, slide, and patient discriminative learning objective is used for visual SSL. We benchmark HiDisc visual representations on two vision tasks using two biomedical microscopy datasets, and demonstrate that (1) HiDisc pretraining outperforms current state-of-the-art self-supervised pretraining methods for cancer diagnosis and genetic mutation prediction, and (2) HiDisc learns high-quality visual representations using natural patch diversity without strong data augmentations.

Unlocking glioma genetics with deep learning.

The AI era in medicine has ushered in new opportunities to improve the diagnosis and treatment of human disease. CHARM, an AI algorithm described in this issue,1 has the potential to streamline molecular classification, intraoperative diagnosis, surgical decision making, and trial enrollment for glioma patients.

A comparison of ventricular volume and linear indices in predicting shunt dependence in aneurysmal subarachnoid hemorrhage.

Background: Guidelines for determining shunt dependence after aneurysmal subarachnoid hemorrhage (aSAH) remain unclear. We previously demonstrated change in ventricular volume (VV) between head CT scans taken pre- and post-EVD clamping was predictive of shunt dependence in aSAH. We sought to compare the predictive value of this measure to more commonly used linear indices. Methods: We retrospectively analyzed images of 68 patients treated for aSAH who required EVD placement and underwent one EVD weaning trial, 34 of whom underwent shunt placement. We utilized an in-house MATLAB program to analyze VV and supratentorial VV (sVV) in head CT scans obtained before and after EVD clamping. Evans' index (EI), frontal and occipital horn ratio (FOHR), Huckman's measurement, minimum lateral ventricular width (LV-Min.), and lateral ventricle body span (LV-Body) were measured using digital calipers in PACS. Receiver operating curves (ROC) were generated. Results: Area under the ROC curves (AUC) for the change in VV, sVV, EI, FOHR, Huckman's, LV-Min., and LV-Body with clamping were 0.84, 0.84, 0.65, 0.71.0.69, 0.67, and 0.66, respectively. AUC for post-clamp scan measurements were 0.75, 0.75, 0.74, 0.72, 0.72, 0.70, and 0.75, respectively. Conclusion: VV change with EVD clamping was more predictive of shunt dependence in aSAH than change in linear measurements with clamping and all post-clamp measurements. Measurement of ventricular size on serial imaging with volumetrics or linear indices utilizing multidimensional data points may therefore be a more robust metric than unidimensional linear indices in predicting shunt dependence in this cohort. Prospective studies are needed for validation.

Generation of 3D ex vivo mouse- and patient-derived glioma explant slice model for integration of confocal time-lapse imaging and spatial analysis.

Development of spatial-integrative pre-clinical models is needed for glioblastoma, which are heterogenous tumors with poor prognosis. Here, we present an optimized protocol to generate three-dimensional ex vivo explant slice glioma model from orthotopic tumors, genetically engineered mouse models, and fresh patient-derived specimens. We describe a step-by-step workflow for tissue acquisition, dissection, and sectioning of 300-µm tumor slices maintaining cell viability. The explant slice model allows the integration of confocal time-lapse imaging with spatial analysis for studying migration, invasion, and tumor microenvironment, making it a valuable platform for testing effective treatment modalities. For complete details on the use and execution of this protocol, please refer to Comba et al. (2022).1.

Perigeniculate Giant Cell Tumor of Temporal Bone.

Giant cell tumors of bone (GCTBs) are benign osteolytic neoplasms that can be treated with either gross-total resection or subtotal resection with adjuvant radiotherapy. For the rare GCTB of the temporal bone, close proximity to critical structures can produce functional deficits and make gross-total resection difficult to achieve without significant morbidity. We present the case of a 28-year-old woman with progressive facial paresis, otalgia, neck pain, imbalance, and subjective hearing loss. She was found to have a facial nerve mass centered at the geniculate ganglion extending into the labyrinthine segment and vestibule. We achieved gross-total resection with preserved facial nerve function as the tumor did not originate from the facial nerve and could be dissected free from the nerve. Final pathology was consistent with GCTB.

Spatiotemporal analysis of glioma heterogeneity reveals COL1A1 as an actionable target to disrupt tumor progression.

Intra-tumoral heterogeneity is a hallmark of glioblastoma that challenges treatment efficacy. However, the mechanisms that set up tumor heterogeneity and tumor cell migration remain poorly understood. Herein, we present a comprehensive spatiotemporal study that aligns distinctive intra-tumoral histopathological structures, oncostreams, with dynamic properties and a specific, actionable, spatial transcriptomic signature. Oncostreams are dynamic multicellular fascicles of spindle-like and aligned cells with mesenchymal properties, detected using ex vivo explants and in vivo intravital imaging. Their density correlates with tumor aggressiveness in genetically engineered mouse glioma models, and high grade human gliomas. Oncostreams facilitate the intra-tumoral distribution of tumoral and non-tumoral cells, and potentially the collective invasion of the normal brain. These fascicles are defined by a specific molecular signature that regulates their organization and function. Oncostreams structure and function depend on overexpression of COL1A1. Col1a1 is a central gene in the dynamic organization of glioma mesenchymal transformation, and a powerful regulator of glioma malignant behavior. Inhibition of Col1a1 eliminates oncostreams, reprograms the malignant histopathological phenotype, reduces expression of the mesenchymal associated genes, induces changes in the tumor microenvironment and prolongs animal survival. Oncostreams represent a pathological marker of potential value for diagnosis, prognosis, and treatment.

Laminectomy at T4 and T5 for Resection of Symptomatic Cavernous Malformation.

Although rare, intramedullary spinal cavernous malformations have a 1.4%-6.8% annual hemorrhage risk and can cause significant morbidity.1 Prior hemorrhage and size >1 cm are risk factors for future hemorrhage that, in addition to notable or progressive symptoms, may justify early surgical intervention.1,2 In this video, we present key steps in surgical management of a large, symptomatic thoracic cavernous malformation. A 56-year-old woman presented with worsening lower extremity weakness, imbalance, and difficulty ambulating. Strength was 3/5 in her right lower extremity and 4/5 in her left lower extremity. She had an incomplete T4 sensory level and hyperreflexia. Magnetic resonance imaging demonstrated a heterogeneous "popcorn"-appearing expansile intradural intramedullary 2.2- × 1.2-cm lesion at T4-5, consistent with a cavernous malformation. Angiography was deferred given the characteristic magnetic resonance imaging appearance. Given her progressive symptoms (including weakness), lesion size, and good health, resection was recommended. Using neurological monitoring, a T4-5 laminectomy, midline myelotomy, and piecemeal microsurgical resection of the lesion was performed, clearly identifying the cavernoma-spinal cord interface and avoiding spinal cord retraction. Histopathology confirmed a cavernoma. Postoperatively, the patient had improved left lower extremity strength and stable right lower extremity strength but worsened dorsiflexion (1/5), which improved with rehabilitation. At 1-year follow-up, she had full strength in her left lower extremity and 4/5 in her right lower extremity, with mild paresthesias below T10. Consistent with prior series demonstrating low complication rates and good long-term neurological outcomes,2 microsurgical resection of selected symptomatic intramedullary spinal cavernous malformations can halt neurological decline and potentially improve neurological function.

Rapid Automated Analysis of Skull Base Tumor Specimens Using Intraoperative Optical Imaging and Artificial Intelligence.

BACKGROUND: Accurate specimen analysis of skull base tumors is essential for providing personalized surgical treatment strategies. Intraoperative specimen interpretation can be challenging because of the wide range of skull base pathologies and lack of intraoperative pathology resources. OBJECTIVE: To develop an independent and parallel intraoperative workflow that can provide rapid and accurate skull base tumor specimen analysis using label-free optical imaging and artificial intelligence. METHODS: We used a fiber laser-based, label-free, nonconsumptive, high-resolution microscopy method (<60 seconds per 1 × 1 mm2), called stimulated Raman histology (SRH), to image a consecutive, multicenter cohort of patients with skull base tumor. SRH images were then used to train a convolutional neural network model using 3 representation learning strategies: cross-entropy, self-supervised contrastive learning, and supervised contrastive learning. Our trained convolutional neural network models were tested on a held-out, multicenter SRH data set. RESULTS: SRH was able to image the diagnostic features of both benign and malignant skull base tumors. Of the 3 representation learning strategies, supervised contrastive learning most effectively learned the distinctive and diagnostic SRH image features for each of the skull base tumor types. In our multicenter testing set, cross-entropy achieved an overall diagnostic accuracy of 91.5%, self-supervised contrastive learning 83.9%, and supervised contrastive learning 96.6%. Our trained model was able to segment tumor-normal margins and detect regions of microscopic tumor infiltration in meningioma SRH images. CONCLUSION: SRH with trained artificial intelligence models can provide rapid and accurate intraoperative analysis of skull base tumor specimens to inform surgical decision-making.

Cranio-Orbital Approach for Single-Stage En Bloc Resection of Optic Nerve Glioma: Technical Note.

BACKGROUND AND IMPORTANCE: There is no consensus on the optimal surgical approach for managing optic nerve gliomas. For solely intraorbital tumors, a single-stage lateral orbitotomy approach for resection may be performed, but when the nerve within the optic canal is affected, two-stage cranial and orbital approaches are often used. The authors describe their technique to safely achieve aggressive nerve resection to minimize the probability of recurrence that might affect the optic tracts, optic chiasm, and contralateral optic nerve. CLINICAL PRESENTATION: A 28-yr-old woman presented with painless progressive vision loss, resulting in blindness. The second of 2 transorbital biopsies was diagnostic and consistent with low-grade glioma. The lesion continued to grow on serial imaging. The patient was offered a globe-sparing operative approach, with aggressive resection of the lesion to minimize the probability of tumor recurrence, which could possibly affect vision in her contralateral eye. The patient did well postoperatively, with clean tumor margins on pathological analysis and no evidence of residual on imaging. On postoperative examination, she had a mild ptosis, which was nearly resolved at her 6-wk outpatient follow-up. CONCLUSION: This aggressive single-stage en bloc resection of an optic nerve glioma can achieve excellent tumor margins and preservation of extraocular muscle function.

OpenSRH: optimizing brain tumor surgery using intraoperative stimulated Raman histology.

Accurate intraoperative diagnosis is essential for providing safe and effective care during brain tumor surgery. Our standard-of-care diagnostic methods are time, resource, and labor intensive, which restricts access to optimal surgical treatments. To address these limitations, we propose an alternative workflow that combines stimulated Raman histology (SRH), a rapid optical imaging method, with deep learning-based automated interpretation of SRH images for intraoperative brain tumor diagnosis and real-time surgical decision support. Here, we present OpenSRH, the first public dataset of clinical SRH images from 300+ brain tumors patients and 1300+ unique whole slide optical images. OpenSRH contains data from the most common brain tumors diagnoses, full pathologic annotations, whole slide tumor segmentations, raw and processed optical imaging data for end-to-end model development and validation. We provide a framework for patch-based whole slide SRH classification and inference using weak (i.e. patient-level) diagnostic labels. Finally, we benchmark two computer vision tasks: multiclass histologic brain tumor classification and patch-based contrastive representation learning. We hope OpenSRH will facilitate the clinical translation of rapid optical imaging and real-time ML-based surgical decision support in order to improve the access, safety, and efficacy of cancer surgery in the era of precision medicine. Dataset access, code, and benchmarks are available at https://opensrh.mlins.org.

Microsurgical Excision of Ruptured Lenticulostriate Artery Aneurysm.

Lenticulostriate artery aneurysms are uncommon lesions, usually found in adults after hemorrhage. Despite their challenging location, mortality rates after initial hemorrhage are favorable. Securing the hemorrhage source is critical but may be complicated by lesional compression or thrombosis on posthemorrhage vascular imaging. We present key steps in the diagnosis and surgical management of a ruptured lenticulostriate aneurysm (Video 1). A healthy 18-year-old patient with prior intermittent prescription amphetamine use presented after acute severe headache onset while weight lifting. On examination, he had trace left upper extremity drift and weakness but was otherwise neurologically intact. A head computed tomography demonstrated a 2.9 × 2.6 × 1.7-cm right basal ganglia intraparenchymal hemorrhage, with trace subarachnoid hemorrhage in the basal cisterns. Secondary imaging including magnetic resonance imaging, computed tomography angiogram, and digital subtraction angiogram was negative for underlying lesions. After an uneventful recovery, a 4-month magnetic resonance angiogram and subsequent digital subtraction angiography demonstrated a 2.7-mm right lenticulostriate aneurysm in the area of the prior hemorrhage. Treatment was recommended to prevent a rehemorrhage, with the safety of local vessel sacrifice presumed based on prior local tissue damage. Microcatheterization was unsuccessful. A right frontotemporal craniotomy for transsylvian, transinsular microsurgical aneurysm excision was performed, with image guidance used for the insular entry site. The patient was discharged home neurologically intact on postoperative day 2. At 1-year follow-up, there were no new or recurrent vascular lesions on imaging. Delayed imaging is critical to identify initially occult cerebrovascular lesions after hemorrhage. The transsylvian, transinsular approach provides safe access to the basal ganglia region in selected patients.

Ventricular Volume Change as a Predictor of Shunt-Dependent Hydrocephalus in Aneurysmal Subarachnoid Hemorrhage.

BACKGROUND: Hydrocephalus is a common complication of aneurysmal subarachnoid hemorrhage (aSAH) that often requires acute placement of an external ventricular drain (EVD). The current systems available for determining which patients will require long-term cerebrospinal fluid diversion remain subjective. We investigated the ventricular volume change (ΔVV) after EVD clamping as an objective predictor of shunt dependence in patients with aSAH. METHODS: We performed a retrospective medical record review and image analysis of patients treated for aSAH at a single academic institution who had required EVD placement for acute hydrocephalus and had undergone 1 EVD weaning trial. Head computed tomography (CT) scans obtained before and after EVD clamping were analyzed using a custom semiautomated MATLAB program (MathWorks, Natick, Massachusetts, USA), which segments each CT scan into 5 tissue types using k-means clustering. Differences in the pre- and postclamp ventricular volumes were calculated. RESULTS: A total of 34 patients with an indwelling shunt met the inclusion criteria and were sex- and age-matched to 34 controls without a shunt. The mean ΔVV was 19.8 mL in the shunt patients and 3.8 mL in the nonshunt patients (P < 0.0001). The area under the receiver operating characteristic curve was 0.84. The optimal ΔVV threshold was 11.4 mL, with a sensitivity of 76.5% and specificity of 88.2% for predicting shunt dependence. The mean ΔVV was significantly greater for the patients readmitted for shunt placement compared with the patients not requiring cerebrospinal fluid diversion (18.69 mL vs. 3.84 mL; P = 0.005). Finally, 70% of the patients with delayed shunt dependence had ΔVV greater than the identified threshold. CONCLUSIONS: The ΔVV volume between head CT scans taken before and after EVD clamping was predictive of early and delayed shunt dependence.

Idiopathic chronic temporal lobe herniation with associated epilepsy.

Herniation of parahippocampal gyrus is usually caused by pressure differentials intracranially, and herniation without known risk factors is extremely rare. We describe a patient with a long history of seizures and a remote status epilepticus event. On magnetic resonance imaging, a presumed left temporal lobe tumor was observed. On neurosurgical consultation, the lesion was identified as a chronic mesial temporal lobe herniation. The patient lacked history that would suggest risk of cerebral herniation. Accurately identifying the patient's chronic temporal lobe herniation radiographically likely saved this patient from unnecessary surgery or biopsy and allowed the patient to receive appropriate conservative care.

Lateral Suboccipital Craniotomy With C1-C2 Hemilaminectomies and C1-C3 Fusion for the Treatment of a C1-C2 Synovial Cyst Causing Spinal Cord Compression: 2-Dimensional Operative Video.

Atlantoaxial synovial cysts are a rare cause of cervical myelopathy. Here we describe a case of a 26-yr-old woman who presented with progressively decreasing right arm and leg strength and associated gait imbalance. On examination, she had diffuse weakness in the right upper and lower extremities, a positive right-sided Hoffman sign, and clonus in the right lower extremity. Computed tomography demonstrated an os odontoideum and a retro-odontoid cyst. Magnetic resonance imaging demonstrated a T1 hypointense, T2 hyperintense, slightly rim-enhancing retro-odontoid cyst causing a marked narrowing of the spinal canal, with resultant flattening and leftward deviation of the spinal cord. The patient consented to undergo cyst fenestration via a right suboccipital craniotomy and right C1-C2 hemilaminectomies, along with a C1-C3 instrumented posterior spinal fusion. This approach was chosen because it allows for cyst fenestration and instrumentation of the hypermobile cervical spine within the same incision. After the dura was opened and the arachnoid was dissected, the cyst was visualized compressing the spinal cord. The cyst was fenestrated just inferior to the C1 nerve rootlets, resulting in immediate egress of a gelatinous content; thereafter, all accessible cyst wall portions were removed. Fusion was performed with lateral mass screws at C1 and C3 and pars screws at C2. Pathological analysis described the cyst content as reactive fibrovascular tissue with cholesterol deposition. There were no complications associated with the procedure, and the patient's right-sided weakness had nearly resolved by postoperative day 1. Patient consent was granted for publication.

Far Lateral Craniotomy for Obliteration of High-Risk Craniocervical Junction Arteriovenous Fistula.

BACKGROUND AND INTRODUCTION: Dural arteriovenous fistulas (dAVFs) are a rare pathology with a clinical presentation related to their anatomical location. Craniocervical junction (CCJ) dAVFs are challenging to treat given the delicate structures that surround the CCJ. Endovascular treatment has evolved significantly in the past decade, but open microsurgery remains an invaluable tool for this pathology. OBJECTIVE: To demonstrate the step-by-step elements of the far lateral approach for microsurgical ligation of CCJ dAVF. SURGICAL TECHNIQUE: A retroauricular incision is created, extending down the neck, and the suboccipital triangle muscles are dissected, exposing the posterior arch of C1. The vertebral artery (VA), as well as its entrance point in the dura, is also dissected and exposed. Next, a C1 hemilaminectomy is performed, followed by a suboccipital craniectomy and drilling of the posteromedial portion of the condyle. The dura is opened behind the VA entrance in the dura, and the intradural VA is exposed. Once the fistula is identified, a temporary clip is placed on the draining vein. Indocyanine green video angiography is used to confirm that there is no further connection; the clip is then removed and the fistula obliterated. The dura is closed in a watertight fashion with a fat bolster to prevent a pseudomeningocele. RESULTS: Postoperative angiogram showed complete resolution of the pathology. The patient was discharged neurologically intact on postoperative day 4. CONCLUSIONS: Microsurgical obliteration of CCJ dAVFs can be achieved safely and efficiently through a far lateral approach.

Rapid, label-free detection of diffuse glioma recurrence using intraoperative stimulated Raman histology and deep neural networks.

BACKGROUND: Detection of glioma recurrence remains a challenge in modern neuro-oncology. Noninvasive radiographic imaging is unable to definitively differentiate true recurrence versus pseudoprogression. Even in biopsied tissue, it can be challenging to differentiate recurrent tumor and treatment effect. We hypothesized that intraoperative stimulated Raman histology (SRH) and deep neural networks can be used to improve the intraoperative detection of glioma recurrence. METHODS: We used fiber laser-based SRH, a label-free, nonconsumptive, high-resolution microscopy method (<60 sec per 1 × 1 mm2) to image a cohort of patients (n = 35) with suspected recurrent gliomas who underwent biopsy or resection. The SRH images were then used to train a convolutional neural network (CNN) and develop an inference algorithm to detect viable recurrent glioma. Following network training, the performance of the CNN was tested for diagnostic accuracy in a retrospective cohort (n = 48). RESULTS: Using patch-level CNN predictions, the inference algorithm returns a single Bernoulli distribution for the probability of tumor recurrence for each surgical specimen or patient. The external SRH validation dataset consisted of 48 patients (recurrent, 30; pseudoprogression, 18), and we achieved a diagnostic accuracy of 95.8%. CONCLUSION: SRH with CNN-based diagnosis can be used to improve the intraoperative detection of glioma recurrence in near-real time. Our results provide insight into how optical imaging and computer vision can be combined to augment conventional diagnostic methods and improve the quality of specimen sampling at glioma recurrence.

Normal cerebral ventricular volume growth in childhood.

OBJECTIVE: Normal percentile growth charts for head circumference, length, and weight are well-established tools for clinicians to detect abnormal growth patterns. Currently, no standard exists for evaluating normal size or growth of cerebral ventricular volume. The current standard practice relies on clinical experience for a subjective assessment of cerebral ventricular size to determine whether a patient is outside the normal volume range. An improved definition of normal ventricular volumes would facilitate a more data-driven diagnostic process. The authors sought to develop a growth curve of cerebral ventricular volumes using a large number of normal pediatric brain MR images. METHODS: The authors performed a retrospective analysis of patients aged 0 to 18 years, who were evaluated at their institution between 2009 and 2016 with brain MRI performed for headaches, convulsions, or head injury. Patients were excluded for diagnoses of hydrocephalus, congenital brain malformations, intracranial hemorrhage, meningitis, or intracranial mass lesions established at any time during a 3- to 10-year follow-up. The volume of the cerebral ventricles for each T2-weighted MRI sequence was calculated with a custom semiautomated segmentation program written in MATLAB. Normal percentile curves were calculated using the lambda-mu-sigma smoothing method. RESULTS: Ventricular volume was calculated for 687 normal brain MR images obtained in 617 different patients. A chart with standardized growth curves was developed from this set of normal ventricular volumes representing the 5th, 10th, 25th, 50th, 75th, 90th, and 95th percentiles. The charted data were binned by age at scan date by 3-month intervals for ages 0-1 year, 6-month intervals for ages 1-3 years, and 12-month intervals for ages 3-18 years. Additional percentile values were calculated for boys only and girls only. CONCLUSIONS: The authors developed centile estimation growth charts of normal 3D ventricular volumes measured on brain MRI for pediatric patients. These charts may serve as a quantitative clinical reference to help discern normal variance from pathologic ventriculomegaly.

Automated histologic diagnosis of CNS tumors with machine learning.

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.