Expert-centered Evaluation of Deep Learning Algorithms for Brain Tumor Segmentation.

Purpose To present results from a literature survey on practices in deep learning segmentation algorithm evaluation and perform a study on expert quality perception of brain tumor segmentation. Materials and Methods A total of 180 articles reporting on brain tumor segmentation algorithms were surveyed for the reported quality evaluation. Additionally, ratings of segmentation quality on a four-point scale were collected from medical professionals for 60 brain tumor segmentation cases. Results Of the surveyed articles, Dice score, sensitivity, and Hausdorff distance were the most popular metrics to report segmentation performance. Notably, only 2.8% of the articles included clinical experts' evaluation of segmentation quality. The experimental results revealed a low interrater agreement (Krippendorff α, 0.34) in experts' segmentation quality perception. Furthermore, the correlations between the ratings and commonly used quantitative quality metrics were low (Kendall tau between Dice score and mean rating, 0.23; Kendall tau between Hausdorff distance and mean rating, 0.51), with large variability among the experts. Conclusion The results demonstrate that quality ratings are prone to variability due to the ambiguity of tumor boundaries and individual perceptual differences, and existing metrics do not capture the clinical perception of segmentation quality. Keywords: Brain Tumor Segmentation, Deep Learning Algorithms, Glioblastoma, Cancer, Machine Learning Clinical trial registration nos. NCT00756106 and NCT00662506 Supplemental material is available for this article. © RSNA, 2023.

Abnormal vascular structure and function within brain metastases is linked to pembrolizumab resistance.

BACKGROUND: We recently conducted a phase 2 trial (NCT028865685) evaluating intracranial efficacy of pembrolizumab for brain metastases (BM) of diverse histologies. Our study met its primary efficacy endpoint and illustrates that pembrolizumab exerts promising activity in a select group of patients with BM. Given the importance of aberrant vasculature in mediating immunosuppression, we explored the relationship between checkpoint inhibitor (ICI) efficacy and vascular architecture in the hopes of identifying potential mechanisms of intracranial ICI response or resistance for BM. METHODS: Using Vessel Architectural Imaging (VAI), a histologically validated quantitative metric for in vivo tumor vascular physiology, we analyzed dual echo DSC/DCE MRI for 44 patients on trial. Tumor and peri-tumor cerebral blood volume/flow, vessel size, arterial- and venous-dominance, and vascular permeability were measured before and after treatment with pembrolizumab. RESULTS: BM that progressed on ICI were characterized by a highly aberrant vasculature dominated by large-caliber vessels. In contrast, ICI-responsive BM possessed a more structurally balanced vasculature consisting of both small and large vessels, and there was a trend towards a decrease in under-perfused tissue, suggesting a reversal of the negative effects of hypoxia. In the peri-tumor region, development of smaller blood vessels, consistent with neo-angiogenesis, was associated with tumor growth before radiographic evidence of contrast enhancement on anatomical MRI. CONCLUSIONS: This study, one of the largest functional imaging studies for BM, suggests that vascular architecture is linked with ICI efficacy. Studies identifying modulators of vascular architecture, and effects on immune activity, are warranted and may inform future combination treatments.

Structural and functional vascular dysfunction within brain metastases is linked to pembrolizumab inefficacy.

Structurally and functionally aberrant vasculature is a hallmark of tumor angiogenesis and treatment resistance. Given the synergistic link between aberrant tumor vasculature and immunosuppression, we analyzed perfusion MRI for 44 patients with brain metastases (BM) undergoing treatment with pembrolizumab. To date, vascular-immune communication, or the relationship between immune checkpoint inhibitor (ICI) efficacy and vascular architecture, has not been well-characterized in human imaging studies. We found that ICI-responsive BM possessed a structurally balanced vascular makeup, which was linked to improved vascular efficiency and an immune-stimulatory microenvironment. In contrast, ICI-resistant BM were characterized by a lack of immune cell infiltration and a highly aberrant vasculature dominated by large-caliber vessels. Peri-tumor region analysis revealed early functional changes predictive of ICI resistance before radiographic evidence on conventional MRI. This study was one of the largest functional imaging studies for BM and establishes a foundation for functional studies that illuminate the mechanisms linking patterns of vascular architecture with immunosuppression, as targeting these aspects of cancer biology may serve as the basis for future combination treatments.

Combination of deep eutectic solvent and functionalized metal-organic frameworks as a green process for the production of 5-hydroxymethylfurfural and furfural from sugars.

Biomass is an abundant and sustainable resource that can be converted into energy and chemicals. Therefore, the development of efficient methods for the conversion of biomass into platform intermediates is crucial. In this study, the one-pot conversion of sugars into 5-hydroxymethylfurfural (HMF) and furfural was achieved using the metal-organic framework combined with metal ions [MIL-101(Cr)] as a high-activity catalyst, and a deep eutectic solvent (choline chloride and lactic acid) as a green solvent. The optimal temperature, time, amount of catalyst used, and amount of deep eutectic solvent used were all determined. The highest HMF yield of 49.74% and furfural yield of 55.90% were obtained. The recyclability of the catalysts and deep eutectic solvent was also investigated. After three reaction runs, the HMF yield was still nearly 30.00%. Finally, the MIL-101(Cr) catalytic system was selected to study the kinetic mechanism underlying the conversion of glucose into HMF.

Highly effective synthesis of 5-hydroxymethylfurfural from lignocellulosic biomass over a green and one-pot reaction in biphasic system.

In this study, different types of lignocellulosic biomas were used as substrates for the conversion to 5-HMF via biphasic reaction system that is composed of a reaction phase (aqueous phase) and an extraction phase (organic phase) under the catalysis of various metal salts. Deep eutectic solvents (DESs), ionic liquid [BMIM]Cl, aqueous choline chloride, aqueous betaine hydrochloride, and ethylamine hydrochloride were used as the reaction phase in the combination of dimethyl sulfoxide (DMSO) as organic solvents. The highest yields of 5-HMF obtained from pineapple stems in reactions with DES were 40.98%, 37.26%, and 23.44% for ChCl:Lac, ChCl:OA, and EaCl:Lac, respectively. Moreover, the combination of dimethyl sulfoxide, betaine hydrochloride aqueous solution, and AlCl3·6H2O with the pineapple stem conversion system resulted in a maximum yield of 61.04% ± 0.55% of 5-HMF. This study also demonstrated that AlCl3·6H2O and betaine hydrochloride could be effectively reused four times, which indicates a green and effective process.

Modeling of the Spatial Distribution of Forest Carbon Storage in a Tropical/Subtropical Island with Multiple Ecozones.

Visual data on the geographic distribution of carbon storage help policy makers to formulate countermeasures for global warming. However, Taiwan, as an island showing diversity in climate and topography, had lacked valid visual data on the distribution of forest carbon storage between the last two forest surveys (1993-2015). This study established a model to estimate and illustrate the distribution of forest carbon storage. This model uses land use, stand morphology, and carbon conversion coefficient databases accordingly for 51 types of major forests in Taiwan. An estimation in 2006 was conducted and shows an overall carbon storage of 165.65 Mt C, with forest carbon storage per unit area of 71.56 t C ha-1, where natural forests and plantations respectively contributed 114.15 Mt C (68.9%) and 51.50 Mt C (31.1%). By assuming no change in land use type, the carbon sequestration from 2006 to 2007 by the 51 forest types was estimated to be 5.21 Mt C yr-1 using historical tree growth and mortality rates. The result reflects the reality of the land use status and the events of coverage shifting with time by combining the two forest surveys in Taiwan.

Valorization of Glucose-Derived Humin as a Low-Cost, Green, Reusable Adsorbent for Dye Removal, and Modeling the Process.

Glucose can be isomerized into fructose and dehydrated into key platform biochemicals, following the "bio-refinery concept". However, this process generates black and intractable substances called humin, which possess a polymeric furanic-type structure. In this study, glucose-derived humin (GDH) was obtained by reacting D-glucose with an allylamine catalyst in a deep eutectic solvent medium, followed by a carbonization step. GDH was used as a low-cost, green, and reusable adsorbent for removing cationic methylene blue (MB) dye from water. The morphology of carbonized GDH differs from pristine GDH. The removal efficiencies of MB dye using pristine GDH and carbonized GDH were 52% and 97%, respectively. Temperature measurements indicated an exothermic process following pseudo-first-order kinetics, with adsorption behavior described by the Langmuir isotherm. The optimum parameters were predicted using the response surface methodology and found to be a reaction time of 600 min, an initial dye concentration of 50 ppm, and a GDH weight of 0.11 g with 98.7% desirability. The MB dye removal rate optimized through this model was 96.85%, which was in good agreement with the experimentally obtained value (92.49%). After 10 cycles, the MB removal rate remained above 80%, showcasing the potential for GDH reuse and cost-effective wastewater treatment.

Stroke-Related Visceral Alterations: A Voxel-Based Neuroanatomic Localization Study.

OBJECTIVE: Functional and morphologic changes in extracranial organs can occur after acute brain injury. The neuroanatomic correlates of such changes are not fully known. Herein, we tested the hypothesis that brain infarcts are associated with cardiac and systemic abnormalities (CSAs) in a regionally specific manner. METHODS: We generated voxelwise p value maps of brain infarcts for poststroke plasma cardiac troponin T (cTnT) elevation, QTc prolongation, in-hospital infection, and acute stress hyperglycemia (ASH) in 1,208 acute ischemic stroke patients prospectively recruited into the Heart-Brain Interactions Study. We examined the relationship between infarct location and CSAs using a permutation-based approach and identified clusters of contiguous voxels associated with p < 0.05. RESULTS: cTnT elevation not attributable to a known cardiac reason was detected in 5.5%, QTc prolongation in the absence of a known provoker in 21.2%, ASH in 33.9%, and poststroke infection in 13.6%. We identified significant, spatially segregated voxel clusters for each CSA. The clusters for troponin elevation and QTc prolongation mapped to the right hemisphere. There were 3 clusters for ASH, the largest of which was in the left hemisphere. We found 2 clusters for poststroke infection, one associated with pneumonia in the left and one with urinary tract infection in the right hemisphere. The relationship between infarct location and CSAs persisted after adjusting for infarct volume. INTERPRETATION: Our results show that there are discrete regions of brain infarcts associated with CSAs. This information could be used to bootstrap toward new markers for better differentiation between neurogenic and non-neurogenic mechanisms of poststroke CSAs. ANN NEUROL 2023;94:1155-1163.

Bavituximab Decreases Immunosuppressive Myeloid-Derived Suppressor Cells in Newly Diagnosed Glioblastoma Patients.

PURPOSE: We evaluated the efficacy of bavituximab-a mAb with anti-angiogenic and immunomodulatory properties-in newly diagnosed patients with glioblastoma (GBM) who also received radiotherapy and temozolomide. Perfusion MRI and myeloid-related gene transcription and inflammatory infiltrates in pre-and post-treatment tumor specimens were studied to evaluate on-target effects (NCT03139916). PATIENTS AND METHODS: Thirty-three adults with IDH--wild-type GBM received 6 weeks of concurrent chemoradiotherapy, followed by 6 cycles of temozolomide (C1-C6). Bavituximab was given weekly, starting week 1 of chemoradiotherapy, for at least 18 weeks. The primary endpoint was proportion of patients alive at 12 months (OS-12). The null hypothesis would be rejected if OS-12 was ≥72%. Relative cerebral blood flow (rCBF) and vascular permeability (Ktrans) were calculated from perfusion MRIs. Peripheral blood mononuclear cells and tumor tissue were analyzed pre-treatment and at disease progression using RNA transcriptomics and multispectral immunofluorescence for myeloid-derived suppressor cells (MDSC) and macrophages. RESULTS: The study met its primary endpoint with an OS-12 of 73% (95% confidence interval, 59%-90%). Decreased pre-C1 rCBF (HR, 4.63; P = 0.029) and increased pre-C1 Ktrans were associated with improved overall survival (HR, 0.09; P = 0.005). Pre-treatment overexpression of myeloid-related genes in tumor tissue was associated with longer survival. Post-treatment tumor specimens contained fewer immunosuppressive MDSCs (P = 0.01). CONCLUSIONS: Bavituximab has activity in newly diagnosed GBM and resulted in on-target depletion of intratumoral immunosuppressive MDSCs. Elevated pre-treatment expression of myeloid-related transcripts in GBM may predict response to bavituximab.

FDU-Net: Deep Learning-Based Three-Dimensional Diffuse Optical Image Reconstruction.

Near-infrared diffuse optical tomography (DOT) is a promising functional modality for breast cancer imaging; however, the clinical translation of DOT is hampered by technical limitations. Specifically, conventional finite element method (FEM)-based optical image reconstruction approaches are time-consuming and ineffective in recovering full lesion contrast. To address this, we developed a deep learning-based reconstruction model (FDU-Net) comprised of a Fully connected subnet, followed by a convolutional encoder-Decoder subnet, and a U-Net for fast, end-to-end 3D DOT image reconstruction. The FDU-Net was trained on digital phantoms that include randomly located singular spherical inclusions of various sizes and contrasts. Reconstruction performance was evaluated in 400 simulated cases with realistic noise profiles for the FDU-Net and conventional FEM approaches. Our results show that the overall quality of images reconstructed by FDU-Net is significantly improved compared to FEM-based methods and a previously proposed deep-learning network. Importantly, once trained, FDU-Net demonstrates substantially better capability to recover true inclusion contrast and location without using any inclusion information during reconstruction. The model was also generalizable to multi-focal and irregularly shaped inclusions unseen during training. Finally, FDU-Net, trained on simulated data, could successfully reconstruct a breast tumor from a real patient measurement. Overall, our deep learning-based approach demonstrates marked superiority over the conventional DOT image reconstruction methods while also offering over four orders of magnitude acceleration in computational time. Once adapted to the clinical breast imaging workflow, FDU-Net has the potential to provide real-time accurate lesion characterization by DOT to assist the clinical diagnosis and management of breast cancer.

Collaborative Privacy-preserving Approaches for Distributed Deep Learning Using Multi-Institutional Data.

Deep learning (DL) algorithms have shown remarkable potential in automating various tasks in medical imaging and radiologic reporting. However, models trained on low quantities of data or only using data from a single institution often are not generalizable to other institutions, which may have different patient demographics or data acquisition characteristics. Therefore, training DL algorithms using data from multiple institutions is crucial to improving the robustness and generalizability of clinically useful DL models. In the context of medical data, simply pooling data from each institution to a central location to train a model poses several issues such as increased risk to patient privacy, increased costs for data storage and transfer, and regulatory challenges. These challenges of centrally hosting data have motivated the development of distributed machine learning techniques and frameworks for collaborative learning that facilitate the training of DL models without the need to explicitly share private medical data. The authors describe several popular methods for collaborative training and review the main considerations for deploying these models. They also highlight publicly available software frameworks for federated learning and showcase several real-world examples of collaborative learning. The authors conclude by discussing some key challenges and future research directions for distributed DL. They aim to introduce clinicians to the benefits, limitations, and risks of using distributed DL for the development of medical artificial intelligence algorithms. ©RSNA, 2023 Quiz questions for this article are available in the supplemental material.

Deep Learning for Noninvasive Assessment of H3 K27M Mutation Status in Diffuse Midline Gliomas Using MR Imaging.

BACKGROUND: Determination of H3 K27M mutation in diffuse midline glioma (DMG) is key for prognostic assessment and stratifying patient subgroups for clinical trials. MRI can noninvasively depict morphological and metabolic characteristics of H3 K27M mutant DMG. PURPOSE: This study aimed to develop a deep learning (DL) approach to noninvasively predict H3 K27M mutation in DMG using T2-weighted images. STUDY TYPE: Retrospective and prospective. POPULATION: For diffuse midline brain gliomas, 341 patients from Center-1 (27 ± 19 years, 184 males), 42 patients from Center-2 (33 ± 19 years, 27 males) and 35 patients (37 ± 18 years, 24 males). For diffuse spinal cord gliomas, 133 patients from Center-1 (30 ± 15 years, 80 males). FIELD STRENGTH/SEQUENCE: 5T and 3T, T2-weighted turbo spin echo imaging. ASSESSMENT: Conventional radiological features were independently reviewed by two neuroradiologists. H3 K27M status was determined by histopathological examination. The Dice coefficient was used to evaluate segmentation performance. Classification performance was evaluated using accuracy, sensitivity, specificity, and area under the curve. STATISTICAL TESTS: Pearson's Chi-squared test, Fisher's exact test, two-sample Student's t-test and Mann-Whitney U test. A two-sided P value <0.05 was considered statistically significant. RESULTS: In the testing cohort, Dice coefficients of tumor segmentation using DL were 0.87 for diffuse midline brain and 0.81 for spinal cord gliomas. In the internal prospective testing dataset, the predictive accuracies, sensitivities, and specificities of H3 K27M mutation status were 92.1%, 98.2%, 82.9% in diffuse midline brain gliomas and 85.4%, 88.9%, 82.6% in spinal cord gliomas. Furthermore, this study showed that the performance generalizes to external institutions, with predictive accuracies of 85.7%-90.5%, sensitivities of 90.9%-96.0%, and specificities of 82.4%-83.3%. DATA CONCLUSION: In this study, an automatic DL framework was developed and validated for accurately predicting H3 K27M mutation using T2-weighted images, which could contribute to the noninvasive determination of H3 K27M status for clinical decision-making. EVIDENCE LEVEL: 2 Technical Efficacy: Stage 2.

Inconsistent Partitioning and Unproductive Feature Associations Yield Idealized Radiomic Models.

Background Radiomics is the extraction of predefined mathematic features from medical images for the prediction of variables of clinical interest. While some studies report superlative accuracy of radiomic machine learning (ML) models, the published methodology is often incomplete, and the results are rarely validated in external testing data sets. Purpose To characterize the type, prevalence, and statistical impact of methodologic errors present in radiomic ML studies. Materials and Methods Radiomic ML publications were reviewed for the presence of performance-inflating methodologic flaws. Common flaws were subsequently reproduced with randomly generated features interpolated from publicly available radiomic data sets to demonstrate the precarious nature of reported findings. Results In an assessment of radiomic ML publications, the authors uncovered two general categories of data analysis errors: inconsistent partitioning and unproductive feature associations. In simulations, the authors demonstrated that inconsistent partitioning augments radiomic ML accuracy by 1.4 times from unbiased performance and that correcting for flawed methodologic results in areas under the receiver operating characteristic curve approaching a value of 0.5 (random chance). With use of randomly generated features, the authors illustrated that unproductive associations between radiomic features and gene sets can imply false causality for biologic phenomenon. Conclusion Radiomic machine learning studies may contain methodologic flaws that undermine their validity. This study provides a review template to avoid such flaws. © RSNA, 2022 Supplemental material is available for this article. See also the editorial by Jacobs in this issue.

Federated learning enables big data for rare cancer boundary detection.

Although machine learning (ML) has shown promise across disciplines, out-of-sample generalizability is concerning. This is currently addressed by sharing multi-site data, but such centralization is challenging/infeasible to scale due to various limitations. Federated ML (FL) provides an alternative paradigm for accurate and generalizable ML, by only sharing numerical model updates. Here we present the largest FL study to-date, involving data from 71 sites across 6 continents, to generate an automatic tumor boundary detector for the rare disease of glioblastoma, reporting the largest such dataset in the literature (n = 6, 314). We demonstrate a 33% delineation improvement for the surgically targetable tumor, and 23% for the complete tumor extent, over a publicly trained model. We anticipate our study to: 1) enable more healthcare studies informed by large diverse data, ensuring meaningful results for rare diseases and underrepresented populations, 2) facilitate further analyses for glioblastoma by releasing our consensus model, and 3) demonstrate the FL effectiveness at such scale and task-complexity as a paradigm shift for multi-site collaborations, alleviating the need for data-sharing.

ACR's Connect and AI-LAB technical framework.

Objective: To develop a free, vendor-neutral software suite, the American College of Radiology (ACR) Connect, which serves as a platform for democratizing artificial intelligence (AI) for all individuals and institutions. Materials and Methods: Among its core capabilities, ACR Connect provides educational resources; tools for dataset annotation; model building and evaluation; and an interface for collaboration and federated learning across institutions without the need to move data off hospital premises. Results: The AI-LAB application within ACR Connect allows users to investigate AI models using their own local data while maintaining data security. The software enables non-technical users to participate in the evaluation and training of AI models as part of a larger, collaborative network. Discussion: Advancements in AI have transformed automated quantitative analysis for medical imaging. Despite the significant progress in research, AI is currently underutilized in current clinical workflows. The success of AI model development depends critically on the synergy between physicians who can drive clinical direction, data scientists who can design effective algorithms, and the availability of high-quality datasets. ACR Connect and AI-LAB provide a way to perform external validation as well as collaborative, distributed training. Conclusion: In order to create a collaborative AI ecosystem across clinical and technical domains, the ACR developed a platform that enables non-technical users to participate in education and model development.

Synthetic Medical Images for Robust, Privacy-Preserving Training of Artificial Intelligence: Application to Retinopathy of Prematurity Diagnosis.

Purpose: Developing robust artificial intelligence (AI) models for medical image analysis requires large quantities of diverse, well-chosen data that can prove challenging to collect because of privacy concerns, disease rarity, or diagnostic label quality. Collecting image-based datasets for retinopathy of prematurity (ROP), a potentially blinding disease, suffers from these challenges. Progressively growing generative adversarial networks (PGANs) may help, because they can synthesize highly realistic images that may increase both the size and diversity of medical datasets. Design: Diagnostic validation study of convolutional neural networks (CNNs) for plus disease detection, a component of severe ROP, using synthetic data. Participants: Five thousand eight hundred forty-two retinal fundus images (RFIs) collected from 963 preterm infants. Methods: Retinal vessel maps (RVMs) were segmented from RFIs. PGANs were trained to synthesize RVMs with normal, pre-plus, or plus disease vasculature. Convolutional neural networks were trained, using real or synthetic RVMs, to detect plus disease from 2 real RVM test datasets. Main Outcome Measures: Features of real and synthetic RVMs were evaluated using uniform manifold approximation and projection (UMAP). Similarities were evaluated at the dataset and feature level using Fréchet inception distance and Euclidean distance, respectively. CNN performance was assessed via area under the receiver operating characteristic curve (AUC); AUCs were compared via bootstrapping and Delong's test for correlated receiver operating characteristic curves. Confusion matrices were compared using McNemar's chi-square test and Cohen's κ value. Results: The CNN trained on synthetic RVMs showed a significantly higher AUC (0.971; P = 0.006 and P = 0.004) and classified plus disease more similarly to a set of 8 international experts (κ = 0.922) than the CNN trained on real RVMs (AUC = 0.934; κ = 0.701). Real and synthetic RVMs overlapped, by plus disease diagnosis, on the UMAP manifold, showing that synthetic images spanned the disease severity spectrum. Fréchet inception distance and Euclidean distances suggested that real and synthetic RVMs were more dissimilar to one another than real RVMs were to one another, further suggesting that synthetic RVMs were distinct from the training data with respect to privacy considerations. Conclusions: Synthetic datasets may be useful for training robust medical AI models. Furthermore, PGANs may be able to synthesize realistic data for use without protected health information concerns.

Microwave-assisted deep eutectic solvents/dimethyl sulfoxide system for efficient valorization of sugar bagasse waste into platform chemicals: A biorefinery approach for circular bioeconomy.

The exploitation of lignocellulosic biomass (LB) such as sugar bagasse waste in biorefineries is the most cost-effective and favourable sustainable approach to producing essential platform chemicals, materials, and energy environmentally benignly. Herein, a microwave-mediated deep eutectic solvents (DESs)/dimethyl sulfoxide (DMSO) system for efficiently processing LB waste into platform chemicals was proposed thereof. Under optimized appropriate diverse parameters such as solvent varieties, catalyst dosage, DMSO addition, reaction time and temperature, the proposed catalytic system (i.e., microwave mediated DESs/DMSO system) has demonstrated significant yields of 5-hydroxymethylfurfural (5-HMF), furfural (FF) and levulinic acid (LevA) of 31.29 %, 28.38 % and 35.65 %, respectively. These favourable results were obtained at the reaction temperature of 140 °C for 40 min. The anticipated catalytic system's activation energy (Ea) was found to be 29.11 kJ/mol. Hence, a practical, inexpensive and sustainable process with the potential of high-value platform chemicals, explicitly for a sustainable strategy in a circular bioeconomy was proposed.

End-to-end artificial intelligence platform for the management of large vessel occlusions: A preliminary study.

OBJECTIVES: In this study, we developed a deep learning pipeline that detects large vessel occlusion (LVO) and predicts functional outcome based on computed tomography angiography (CTA) images to improve the management of the LVO patients. METHODS: A series identifier picked out 8650 LVO-protocoled studies from 2015 to 2019 at Rhode Island Hospital with an identified thin axial series that served as the data pool. Data were annotated into 2 classes: 1021 LVOs and 7629 normal. The Inception-V1 I3D architecture was applied for LVO detection. For outcome prediction, 323 patients undergoing thrombectomy were selected. A 3D convolution neural network (CNN) was used for outcome prediction (30-day mRS) with CTA volumes and embedded pre-treatment variables as inputs. RESULT: For LVO-detection model, CTAs from 8,650 patients (median age 68 years, interquartile range (IQR): 58-81; 3934 females) were analyzed. The cross-validated AUC for LVO vs. not was 0.74 (95% CI: 0.72-0.75). For the mRS classification model, CTAs from 323 patients (median age 75 years, IQR: 63-84; 164 females) were analyzed. The algorithm achieved a test AUC of 0.82 (95% CI: 0.79-0.84), sensitivity of 89%, and specificity 66%. The two models were then integrated with hospital infrastructure where CTA was collected in real-time and processed by the model. If LVO was detected, interventionists were notified and provided with predicted clinical outcome information. CONCLUSION: 3D CNNs based on CTA were effective in selecting LVO and predicting LVO mechanical thrombectomy short-term prognosis. End-to-end AI platform allows users to receive immediate prognosis prediction and facilitates clinical workflow.