Background:Previous machine learning models to intraoperatively predict the molecular status of gliomas using stimulated Raman histology (SRH), such as DeepGlioma, have achieved high performance (91.5% accuracy) on curated datasets. However, when used intraoperatively, DeepGlioma (162M parameters) runs slowly on current SRH hardware and underperforms due to its lack of an image rejection mechanism and its validation on curated images. Here, we introduce SRH-Informed Glioma classificatioN with Attention Learning (SIGNAL) (27M parameters), a lighter model with a built-in attention-based rejection mechanism that outperforms DeepGlioma on uncurated clinical datasets. Methods:SIGNAL was developed using 1.56 million SRH fields-of-view from 967 adult diffuse glioma patients collected between December 2017 and July 2025. We used 412 patients from NYU for training and internal validation and a multi-institutional, international cohort of 555 patients for testing. SIGNAL uses a ResNet50 backbone pretrained using a hierarchical contrastive loss function followed by a multi-head multi-layer perceptron (MLP). Using a patch-based attention threshold of 0.6, a final MLP was trained to predict glioma subtypes: glioblastoma, oligodendroglioma, or astrocytoma. Results:SIGNAL outperformed DeepGlioma, achieving greater overall accuracy (90.10% vs. 72.59%) while running faster (16.0 vs. 6.7 patches/s). SIGNAL also outperformed DeepGlioma on all three molecular classification tasks, including IDH mutation (accuracy: 93.51% vs. 79.22%), 1p19q codeletion (93.51% vs. 88.31%), and ATRX loss (89.61% vs. 83.98%). SIGNAL's attention mechanism had a strong positive linear correlation with mean patch cellularity (r=0.96, p<0.001) and a strong negative correlation with patch blood coverage (r=-0.99,p<0.001). Finally, subtype and molecular accuracy between tumor core and margin samples were equivalent despite significantly lower patch retention in tumor margins (44.5% vs 60.2%, p<0.0001). Conclusion:SIGNAL is a lightweight model for intraoperative molecular classification of gliomas using SRH imaging. Its attention-based image quality filter allows for excellent performance, quick processing, and highly interpretable outputs critical for reliable use in intraoperative workflows. Brief 1-2 Sentence Description:We present SIGNAL, a lightweight machine learning model for intraoperative molecular classification of diffuse gliomas using stimulated Raman histology, whose core innovation is a learned attention mechanism that filters diagnostically uninformative tissue, such as blood and acellular regions, before classification, enabling robust real-world generalizability. Validated on 555 patients across four international centers, SIGNAL outperforms the previous state-of-the-art model DeepGlioma on glioma subtype classification (90.10% vs. 72.59% accuracy) while running 2.4 times faster on intraoperative hardware.

Genome-Wide Association Studies (GWAS) identify associations between genetic variants and disease; however, moving beyond associations to causal mechanisms is critical for therapeutic target prioritization. The recently proposed Knowledge Graph GWAS (KGWAS) framework addresses this challenge by linking genetic variants to downstream gene-gene interactions via a knowledge graph (KG), thereby improving detection power and providing mechanistic insights. However, the original KGWAS implementation relies on a large general-purpose KG, which can introduce spurious correlations. We hypothesize that cell-type specific KGs from disease-relevant cell types will better support disease mechanism discovery. Here, we show that the general-purpose KG in KGWAS can be substantially pruned with no loss of statistical power on downstream tasks, and that performance further improves by incorporating gene-gene relationships derived from perturb-seq data. Importantly, using a sparse, context-specific KG from direct perturb-seq evidence yields more consistent and biologically robust disease-critical networks.

Frontier artificial intelligence (AI) models have advanced rapidly through training on internet-scale public data, yet such systems lack access to private clinical data. Neuroimaging is underrepresented in the public domain due to identifiable facial features within magnetic resonance imaging (MRI) and computed tomography (CT) scans, restricting model performance in clinical medicine. Here we show that frontier models underperform on neuroimaging tasks and that learning directly from uncurated data generated during routine clinical care at health systems, a paradigm we call 'health system learning', yields high-performance, generalist neuroimaging models. We introduce NeuroVFM, a visual foundation model trained on 5.24 million clinical MRI and CT volumes using a scalable volumetric predictive architecture. NeuroVFM learns comprehensive representations of brain anatomy and pathology, achieving state-of-the-art performance across multiple clinical tasks, including radiologic diagnosis and report generation. The model embeds MRI and CT scans into a shared neuroanatomic latent space and grounds diagnostic findings. When paired with open-source language models, NeuroVFM generates radiology reports that surpass frontier models in accuracy, clinical triage and expert preference. NeuroVFM reduces hallucinated findings and critical errors, offering safer clinical decision support. These results establish health system learning as a paradigm for building generalist medical AI and provide a scalable framework for clinical foundation models.

The importance of rapid and accurate histologic analysis of surgical tissue in the operating room has been recognized for over a century. Our standard-of-care intraoperative pathology workflow is based on light microscopy and H&E histology, which is slow, resource-intensive, and lacks real-time digital imaging capabilities. Here, we describe an emerging and innovative method for intraoperative histologic analysis, called Intelligent Histology, that integrates artificial intelligence (AI) with stimulated Raman histology (SRH). SRH is a rapid, label-free, digital imaging method for real-time microscopic tumor tissue analysis. SRH generates high-resolution digital images of surgical specimens within seconds, enabling AI-driven tumor histologic analysis, molecular classification, and tumor infiltration detection. We review the scientific background, clinical translation, and future applications of intelligent histology in tumor neurosurgery. We focus on the major scientific and clinical studies that have demonstrated the transformative potential of intelligent histology across multiple neurosurgical specialties, including neurosurgical oncology, skull base, spine oncology, pediatric tumors, and peripheral nerve tumors. Future directions include the development of AI foundation models through multi-institutional datasets, incorporating clinical and radiologic data for multimodal learning, and predicting patient outcomes. Intelligent histology represents a transformative intraoperative workflow that can reinvent real-time tumor analysis for 21st century neurosurgery.

Abstract Spinal tumor surgery requires rapid tissue diagnosis to guide surgical decisions and further treatment strategies, yet current intraoperative methods are time-intensive and require specialized expertise. No AI systems exist for real-time spinal tumor classification during surgery. We developed SpineXtract, the first AI-powered system for rapid intraoperative spinal tumor diagnosis using stimulated Raman histology (SRH) — a label-free Raman spectromics imaging technique without tissue processing available during surgery. We created a transformer-based classifier optimized for spinal tissue characteristics to identify common tumor types: meningioma, schwannoma, ependymoma, and metastasis. The system was tested in an international, multicenter, simulated, single-arm study using existing SRH datasets (44 patients, 142 slide-images) from three international institutions, with final pathological diagnosis as reference standard. SpineXtract achieved a 92.9% macro-average balanced accuracy (95% CI: 85.5–98.2) within 5 minutes (tumor-specific accuracy range, 84.2–98.6%), while providing quantitative microscopic feedback for granular tissue analysis. Performance remained consistent across institutions (macro balanced accuracy 91.4–92.0%) and outperformed existing brain tumor classifiers by 15.6%. Our results demonstrate clinical applicability, enabling rapid intraoperative diagnosis with performance exceeding current methods, potentially transforming intraoperative diagnostic workflows in spinal tumor surgery.

Frontier artificial intelligence (AI) models, such as OpenAI's GPT-5 and Meta's DINOv3, have advanced rapidly through training on internet-scale public data, yet such systems lack access to private clinical data. Neuroimaging, in particular, is underrepresented in the public domain due to identifiable facial features within MRI and CT scans, fundamentally restricting model performance in clinical medicine. Here, we show that frontier models underperform on neuroimaging tasks and that learning directly from uncurated data generated during routine clinical care at health systems, a paradigm we call health system learning, yields high-performance, generalist neuroimaging models. We introduce NeuroVFM, a visual foundation model trained on 5.24 million clinical MRI and CT volumes using a scalable volumetric joint-embedding predictive architecture. NeuroVFM learns comprehensive representations of brain anatomy and pathology, achieving state-of-the-art performance across multiple clinical tasks, including radiologic diagnosis and report generation. The model exhibits emergent neuroanatomic understanding and interpretable visual grounding of diagnostic findings. When paired with open-source language models through lightweight visual instruction tuning, NeuroVFM generates radiology reports that surpass frontier models in accuracy, clinical triage, and expert preference. Through clinically grounded visual understanding, NeuroVFM reduces hallucinated findings and critical errors, offering safer clinical decision support. These results establish health system learning as a paradigm for building generalist medical AI and provide a scalable framework for clinical foundation models.

OBJECTIVE:SpinePose was developed in 2024 as a novel artificial intelligence (AI) tool to automatically predict spinopelvic parameters with high accuracy and without the need for manual entry. The authors' published results demonstrated excellent performance comparable to a fellowship-trained spine surgeon with more than 15 years of experience. To date, there have not been any studies that have externally validated the performance of AI-based spinopelvic parameter measurement tools on data acquired from other institutions. To assess the generalizability of SpinePose, the authors report its performance on an external set of heterogeneous whole-spine scoliosis radiographs obtained from an outside institution. METHODS:SpinePose was trained/validated on a dataset of 761 sagittal whole-spine scoliosis radiographs from a single institution, with expert-level performance on both whole-spine and lumbosacral radiographs. In this study, the existing SpinePose model was used for inference on a new set of 49 whole-spine radiographs acquired at a tertiary academic hospital located out of state. Externally acquired radiographs represented a diverse set of images, incorporating patients who had undergone instrumentation and those who had not, and a wide variety of fusion constructs including complex deformity patients. Predicted measures included sagittal vertical axis (SVA), pelvic tilt (PT), pelvic incidence (PI), lumbar lordosis (LL), and T1-pelvic angle (T1PA). Predicted parameter values relative to ground-truth manual annotations were calculated to determine the model's accuracy. RESULTS:Of the 49 images, 35 (71.4%) had instrumentation compared with 51.0% and 57.5% in the original SpinePose training and testing sets, respectively. All 5 parameters in the external dataset were significantly different at baseline compared with the original test set (p < 0.01). SpinePose accurately predicted all 5 spinopelvic parameters without any statistically significant differences: SVA, 50.7 mm vs 52.3 mm (p = 0.85); PT, 27.6° vs 30.5° (p = 0.24); PI, 58.0° vs 61.8° (p = 0.17); LL, 40.4° vs 42.4° (p = 0.77); and T1PA, 24.8° vs 28.0° (p = 0.21) when comparing ground truth annotations with predicted values. CONCLUSIONS:SpinePose was able to accurately predict spinopelvic parameters on an external validation cohort that was generated independently from the images on which the model was trained and validated. This highlights the generalizability of SpinePose to be implemented on novel images from other institutions and geographic settings with high accuracy and minimal preprocessing. The implementation of AI tools more broadly will help standardize our ability to both deliver and provide spine care and assist with surgical treatment and management of spine patients.

BACKGROUND:Accurate intraoperative diagnosis is crucial for differentiating between primary central nervous system (CNS) lymphoma (PCNSL) and other CNS entities, guiding surgical decision-making, but represents significant challenges due to overlapping histomorphological features, time constraints, and differing treatment strategies. We combined stimulated Raman histology (SRH) with deep learning to address this challenge. METHODS:We imaged unprocessed, label-free tissue samples intraoperatively using a portable Raman scattering microscope, generating virtual H&E-like images within <3 min. We developed a deep learning pipeline called RapidLymphoma based on a self-supervised learning strategy to (1) detect PCNSL, (2) differentiate from other CNS entities, and (3) test the diagnostic performance in a prospective international multicenter cohort and 2 additional independent test cohorts. We trained on 54 000 SRH patch images sourced from surgical resections and stereotactic-guided biopsies, including various CNS neoplastic/nonneoplastic lesions. Training and test data were collected from 4 tertiary international medical centers. The final histopathological diagnosis served as ground truth. RESULTS:In the prospective test cohort of PCNSL and non-PCNSL entities (n = 160), RapidLymphoma achieved an overall balanced accuracy of 97.81% ± 0.91, non-inferior to frozen section analysis in detecting PCNSL (100% vs. 77.77%). The additional test cohorts (n = 420, n = 59) reached balanced accuracy rates of 95.44% ± 0.74 and 95.57% ± 2.47 in differentiating IDH-wildtype diffuse gliomas and various brain metastasis from PCNSL. Visual heatmaps revealed RapidLymphoma's capabilities to detect class-specific histomorphological key features. CONCLUSIONS:RapidLymphoma proves reliable and valid for intraoperative PCNSL detection and differentiation from other CNS entities. It provides visual feedback within 3 min, enabling fast clinical decision-making and subsequent treatment strategy planning.

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.

Whole slide imaging is fundamental to biomedical microscopy and computational pathology. Previously, learning representations for gigapixel-sized whole slide images (WSIs) has relied on multiple instance learning with weak labels, which do not annotate the diverse morphologic features and spatial heterogeneity of WSIs. A high-quality self-supervised learning method for WSIs would provide transferable visual representations for downstream computational pathology tasks, without the need for dense annotations. We present Slide Pre-trained Transformers (SPT) for gigapixel-scale self-supervision of WSIs. Treating WSI patches as tokens, SPT combines data transformation strategies from language and vision modeling into a general and unified framework to generate views of WSIs for self-supervised pretraining. SPT leverages the inherent regional heterogeneity, histologic feature variability, and information redundancy within WSIs to learn high-quality whole slide representations. We benchmark SPT visual representations on five diagnostic tasks across three biomedical microscopy datasets. SPT significantly outperforms baselines for histopathologic diagnosis, cancer subtyping, and genetic mutation prediction. Finally, we demonstrate that SPT consistently improves whole slide representations when using off-the-shelf, in-domain, and foundational patch encoders for whole slide multiple instance learning.

Volumetric biomedical microscopy has the potential to increase the diagnostic information extracted from clinical tissue specimens and improve the diagnostic accuracy of both human pathologists and computational pathology models. Unfortunately, barriers to integrating 3-dimensional (3D) volumetric microscopy into clinical medicine include long imaging times, poor depth / z-axis resolution, and an insufficient amount of high-quality volumetric data. Leveraging the abundance of high-resolution 2D microscopy data, we introduce masked slice diffusion for super-resolution (MSDSR), which exploits the inherent equivalence in the data-generating distribution across all spatial dimensions of biological specimens. This intrinsic characteristic allows for super-resolution models trained on high-resolution images from one plane (e.g., XY) to effectively generalize to others (XZ, YZ), overcoming the traditional dependency on orientation. We focus on the application of MSDSR to stimulated Raman histology (SRH), an optical imaging modality for biological specimen analysis and intraoperative diagnosis, characterized by its rapid acquisition of high-resolution 2D images but slow and costly optical z-sectioning. To evaluate MSDSR's efficacy, we introduce a new performance metric, SliceFID, and demonstrate MSDSR's superior performance over baseline models through extensive evaluations. Our findings reveal that MSDSR not only significantly enhances the quality and resolution of 3D volumetric data, but also addresses major obstacles hindering the broader application of 3D volumetric microscopy in clinical diagnostics and biomedical research.

INTRODUCTION: Molecular classification has transformed the management of brain tumors by enabling more accurate prognostication and personalized treatment. Access to timely molecular diagnostic testing for brain tumor patients is limited, complicating surgical and adjuvant treatment and obstructing clinical trial enrollment. METHODS: By combining stimulated Raman histology (SRH), a rapid, label-free, non-consumptive, optical imaging method, and deep learning-based image classification, we are able to predict the molecular genetic features used by the World Health Organization (WHO) to define the adult-type diffuse glioma taxonomy, including IDH-1/2, 1p19q-codeletion, and ATRX loss. We developed a multimodal deep neural network training strategy that uses both SRH images and large-scale, public diffuse glioma genomic data (i.e. TCGA, CGGA, etc.) in order to achieve optimal molecular classification performance. RESULTS: One institution was used for model training (University of Michigan) and four institutions (NYU, UCSF, Medical University of Vienna, and University Hospital Cologne) were included for patient enrollment in the prospective testing cohort. Using our system, called DeepGlioma, we achieved an average molecular genetic classification accuracy of 93.2% and identified the correct diffuse glioma molecular subgroup with 91.5% accuracy within 2 minutes in the operating room. DeepGlioma outperformed conventional IDH1-R132H immunohistochemistry (94.2% versus 91.4% accuracy) as a first-line molecular diagnostic screening method for diffuse gliomas and can detect canonical and non-canonical IDH mutations. CONCLUSIONS: Our results demonstrate how artificial intelligence and optical histology can be used to provide a rapid and scalable alternative to wet lab methods for the molecular diagnosis of brain tumor patients during surgery.

Abstract INTRODUCTION Fast and accurate detection of tumor infiltration is a central challenge in the comprehensive management of diffuse glioma patients. Despite our best real-time tumor detection strategies, such as intraoperative MRI and fluorescence-guided surgery, dense and safely resectable tumor infiltration remains at the surgical margin in over 85% of diffuse glioma patients. Patterns of treatment failure demonstrate that glioma recurrence occurs at the surgical margin in the majority of patients due to residual tumor burden. Objective Here, we present FastGlioma, an artificial intelligence (AI)-based intraoperative diagnostic system for fast (< 10 seconds) detection of diffuse glioma infiltration at microscopic resolution without the need for tumor-specific markers. Method FastGlioma is trained using large-scale, self-supervised visual feature learning on stimulated Raman histology (SRH), a rapid, label-free, optical microscopy technique, and a GPT-style whole slide SRH tumor infiltration scoring method. We pushed the performance limits of FastGlioma by investigating the trade-off between imaging speed versus accuracy for microscopic tumor detection. RESULTS In a large prospective external testing cohort of diffuse glioma patients (180 patients, 935 surgical margin specimens) who underwent intraoperative SRH imaging, we demonstrate that FastGlioma was able to detect and quantify microscopic tumor infiltration with an average AUROC of 92.1 +/- 0.0%, performing on par with three expert neuropathologists on the same task. FastGlioma is over 10X faster than previous SRH-based methods and 100X faster than conventional H&E histology. Finally, we demonstrate that FastGlioma was > 20% more accurate at detecting dense tumor infiltration when compared to radiologic features or 5-aminolevulinic fluorescence (98.0% versus 77.8% accuracy) for both IDH-mutant diffuse gliomas and IDH-wildtype glioblastomas. CONCLUSION Our results demonstrate how intraoperative optical imaging and deep neural networks can achieve fast and accurate tumor detection, unlocking the role of AI in improving the surgical management of brain tumor patients.

Molecular classification has transformed the management of brain tumors by enabling more accurate prognostication and personalized treatment. However, timely molecular diagnostic testing for patients with brain tumors is limited, complicating surgical and adjuvant treatment and obstructing clinical trial enrollment. In this study, we developed DeepGlioma, a rapid (<90 seconds), artificial-intelligence-based diagnostic screening system to streamline the molecular diagnosis of diffuse gliomas. DeepGlioma is trained using a multimodal dataset that includes stimulated Raman histology (SRH); a rapid, label-free, non-consumptive, optical imaging method; and large-scale, public genomic data. In a prospective, multicenter, international testing cohort of patients with diffuse glioma (n = 153) who underwent real-time SRH imaging, we demonstrate that DeepGlioma can predict the molecular alterations used by the World Health Organization to define the adult-type diffuse glioma taxonomy (IDH mutation, 1p19q co-deletion and ATRX mutation), achieving a mean molecular classification accuracy of 93.3 ± 1.6%. Our results represent how artificial intelligence and optical histology can be used to provide a rapid and scalable adjunct to wet lab methods for the molecular screening of patients with diffuse glioma.

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.

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.

Abstract INTRODUCTION Molecular classification has transformed the management of brain tumors by enabling more accurate prognostication and personalized treatment. Access to timely molecular diagnostic testing for brain tumor patients is limited, complicating surgical and adjuvant treatment and obstructing clinical trial enrollment. OBJECTIVE We aim to develop a rapid (< 90 seconds), AI-based diagnostic screening system that can provide molecular classification of diffuse gliomas and report its use in a prospective, multicenter, international clinical trial of diffuse glioma patients (n = 153). METHODS By combining stimulated Raman histology (SRH), a rapid, label-free, non-consumptive, optical imaging method, and deep learning-based image classification, we are able to predict the molecular genetic features used by the World Health Organization (WHO) to define the adult-type diffuse glioma taxonomy, including IDH-1/2, 1p19q-codeletion, and ATRX loss. We developed a multimodal deep neural network training strategy that uses both SRH images and large-scale, public diffuse glioma genomic data in order to achieve optimal molecular classification performance. RESULTS One institution was used for model training (University of Michigan) and four institutions (NYU, UCSF, Medical University of Vienna, and University Hospital Cologne) were included for prospective patient enrollment and model testing. Using our system, called DeepGlioma, we achieved an average molecular genetic classification accuracy of 93.2% and identified the correct diffuse glioma molecular subgroup with 91.5% accuracy. DeepGlioma outperformed conventional IDH1-R132H immunohistochemistry (94.2% versus 91.4% accuracy, respectively) as a first-line molecular diagnostic screening method for diffuse gliomas, detecting canonical and non-canonical IDH mutations with high accuracy. CONCLUSION Our results demonstrate how artificial intelligence and optical histology can be used to provide a rapid and scalable alternative to wet lab methods for the molecular diagnosis of brain tumor patients during surgery.

Predicting the interactions between drugs and targets plays an important role in the process of new drug discovery, drug repurposing (also known as drug repositioning). There is a need to develop novel and efficient prediction approaches in order to avoid the costly and laborious process of determining drug-target interactions (DTIs) based on experiments alone. These computational prediction approaches should be capable of identifying the potential DTIs in a timely manner. Matrix factorization methods have been proven to be the most reliable group of methods. Here, we first propose a matrix factorization-based method termed 'Coupled Matrix-Matrix Completion' (CMMC). Next, in order to utilize more comprehensive information provided in different databases and incorporate multiple types of scores for drug-drug similarities and target-target relationship, we then extend CMMC to 'Coupled Tensor-Matrix Completion' (CTMC) by considering drug-drug and target-target similarity/interaction tensors. Results: Evaluation on two benchmark datasets, DrugBank and TTD, shows that CTMC outperforms the matrix-factorization-based methods: GRMF, $L_{2,1}$-GRMF, NRLMF and NRLMF$\beta $. Based on the evaluation, CMMC and CTMC outperform the above three methods in term of area under the curve, F1 score, sensitivity and specificity in a considerably shorter run time.

This paper introduces a novel method for classifying and predicting cardiac arrhythmia events via a special type of deterministic probabilistic finite-state automata (DPFA). The proposed method constructs the underlying state space and transition probabilities of the DPFA model directly from the input data. The algorithm was employed in the prediction of two types of cardiac events, supraventricular tachycardia (SVT) and atrial high-rate episodes (AHRE), with its performance compared to five other well-established methods. In all experiments, the proposed method achieved over 0.8 AUC for both SVT and AHRE prediction.

Detection and severity assessment of subdural hematoma is a major step in the evaluation of traumatic brain injuries. This is a retrospective study of 110 computed tomography (CT) scans from patients admitted to the Michigan Medicine Neurological Intensive Care Unit or Emergency Department. A machine learning pipeline was developed to segment and assess the severity of subdural hematoma. First, the probability of each point belonging to the hematoma region was determined using a combination of hand-crafted and deep features. This probability provided the initial state of the segmentation. Next, a 3D post-processing model was applied to evolve the initial state and delineate the hematoma. The recall, precision, and Dice similarity coefficient of the proposed segmentation method were 78.61%, 76.12%, and 75.35%, respectively, for the entire population. The Dice similarity coefficient was 79.97% for clinically significant hematomas, which compared favorably to an inter-rater Dice similarity coefficient. In volume-based severity analysis, the proposed model yielded an F1, recall, and specificity of 98.22%, 98.81%, and 92.31%, respectively, in detecting moderate and severe subdural hematomas based on hematoma volume. These results show that the combination of classical image processing and deep learning can outperform deep learning only methods to achieve greater average performance and robustness. Such a system can aid critical care physicians in reducing time to intervention and thereby improve long-term patient outcomes.