Faculty Bibliography

BACKGROUND AND PURPOSE/OBJECTIVE:Quantitative volumetric segmentation of gliomas has important implications for diagnosis, treatment, and prognosis. We present a deep-learning model that accommodates automated preoperative and postoperative glioma segmentation with a pipeline for clinical implementation. Developed and engineered in concert, the work seeks to accelerate clinical realization of such tools. MATERIALS AND METHODS/METHODS:A deep learning model, autoencoder regularization-cascaded anisotropic, was developed, trained, and tested fusing key elements of autoencoder regularization with a cascaded anisotropic convolutional neural network. We constructed a dataset consisting of 437 cases with 40 cases reserved as a held-out test and the remainder split 80:20 for training and validation. We performed data augmentation and hyperparameter optimization and used a mean Dice score to evaluate against baseline models. To facilitate clinical adoption, we developed the model with an end-to-end pipeline including routing, preprocessing, and end-user interaction. RESULTS:The autoencoder regularization-cascaded anisotropic model achieved median and mean Dice scores of 0.88/0.83 (SD, 0.09), 0.89/0.84 (SD, 0.08), and 0.81/0.72 (SD, 0.1) for whole-tumor, tumor core/resection cavity, and enhancing tumor subregions, respectively, including both preoperative and postoperative follow-up cases. The overall total processing time per case was ∼10 minutes, including data routing (∼1 minute), preprocessing (∼6 minute), segmentation (∼1-2 minute), and postprocessing (∼1 minute). Implementation challenges were discussed. CONCLUSIONS:We show the feasibility and advantages of building a coordinated model with a clinical pipeline for the rapid and accurate deep learning segmentation of both preoperative and postoperative gliomas. The ability of the model to accommodate cases of postoperative glioma is clinically important for follow-up. An end-to-end approach, such as used here, may lead us toward successful clinical translation of tools for quantitative volume measures for glioma.

Accelerating MRI scans is one of the principal outstanding problems in the MRI research community. Towards this goal, we hosted the second fastMRI competition targeted towards reconstructing MR images with subsampled k-space data. We provided participants with data from 7,299 clinical brain scans (de-identified via a HIPAA-compliant procedure by NYU Langone Health), holding back the fully-sampled data from 894 of these scans for challenge evaluation purposes. In contrast to the 2019 challenge, we focused our radiologist evaluations on pathological assessment in brain images. We also debuted a new Transfer track that required participants to submit models evaluated on MRI scanners from outside the training set. We received 19 submissions from eight different groups. Results showed one team scoring best in both SSIM scores and qualitative radiologist evaluations. We also performed analysis on alternative metrics to mitigate the effects of background noise and collected feedback from the participants to inform future challenges. Lastly, we identify common failure modes across the submissions, highlighting areas of need for future research in the MRI reconstruction community.

BACKGROUND AND PURPOSE/OBJECTIVE:Diffusion MR imaging sequences essential for clinical neuroradiology imaging protocols may be accelerated with simultaneous multislice acquisitions. We tested whether simultaneous multislice-accelerated diffusion data were clinically equivalent to standard acquisitions. MATERIALS AND METHODS/METHODS:; 60 directions). The corticospinal tract and arcuate fasciculus ipsilateral to the lesion were generated using the same ROIs and then blindly assessed by a neurosurgeon for anatomic fidelity, perceived quality, and impact on surgical management. Tract volumes were compared for spatial overlap. RESULTS:Two-slice simultaneous multislice diffusion reduced acquisition times from 141 to 45 seconds for routine diffusion and from 7.5 to 5.9 minutes for diffusion tractography using 3T MR imaging. The simultaneous multislice-accelerated diffusion sequence was rated equivalent for diagnostic utility despite reductions to perceived image quality. Simultaneous multislice-accelerated diffusion tractography was rated clinically equivalent. Dice similarity coefficients between routine and simultaneous multislice-generated corticospinal tract and arcuate fasciculus tract volumes were 0.78 (SD, 0.03) and 0.71 (SD, 0.05), respectively. CONCLUSIONS:-space-resolution diffusion acquisitions required for translating advanced diffusion models into clinical practice.

During the coronavirus disease 2019 (COVID-19) pandemic, rapid and accurate triage of patients at the emergency department is critical to inform decision-making. We propose a data-driven approach for automatic prediction of deterioration risk using a deep neural network that learns from chest X-ray images and a gradient boosting model that learns from routine clinical variables. Our AI prognosis system, trained using data from 3661 patients, achieves an area under the receiver operating characteristic curve (AUC) of 0.786 (95% CI: 0.745-0.830) when predicting deterioration within 96 hours. The deep neural network extracts informative areas of chest X-ray images to assist clinicians in interpreting the predictions and performs comparably to two radiologists in a reader study. In order to verify performance in a real clinical setting, we silently deployed a preliminary version of the deep neural network at New York University Langone Health during the first wave of the pandemic, which produced accurate predictions in real-time. In summary, our findings demonstrate the potential of the proposed system for assisting front-line physicians in the triage of COVID-19 patients.

BACKGROUND AND PURPOSE/OBJECTIVE:Studies associate repeat gadolinium-based contrast agent administration with T1 shortening in the dentate nucleus and globus pallidus, indicating CNS gadolinium deposition, most strongly with linear agents but also reportedly with macrocyclics. Renal impairment effects on long-term CNS gadolinium deposition remain underexplored. We investigated the relationship between signal intensity changes and renal function in patients who received ≥10 administrations of the macrocyclic agent gadobutrol. MATERIALS AND METHODS/METHODS:Patients who underwent ≥10 brain MR imaging examinations with administration of intravenous gadobutrol between February 1, 2014, and January 1, 2018, were included in this retrospective study. Dentate nucleus-to-pons and globus pallidus-to-thalamus signal intensity ratios were calculated, and correlations were calculated between the estimated glomerular filtration rate (minimum and mean) and the percentage change in signal intensity ratios from the first to last scan. Partial correlations were calculated to control for potential confounders. RESULTS:= .09). CONCLUSIONS:In patients receiving an average of 12 intravenous gadobutrol administrations, no correlation was found between renal function and signal intensity ratio changes, even in those with mild or moderate renal impairment.

Artificial intelligence (AI) shows tremendous promise in the field of medical imaging, with recent breakthroughs applying deep-learning models for data acquisition, classification problems, segmentation, image synthesis, and image reconstruction. With an eye towards clinical applications, we summarize the active field of deep-learning-based MR image reconstruction. We review the basic concepts of how deep-learning algorithms aid in the transformation of raw k-space data to image data, and specifically examine accelerated imaging and artifact suppression. Recent efforts in these areas show that deep-learning-based algorithms can match and, in some cases, eclipse conventional reconstruction methods in terms of image quality and computational efficiency across a host of clinical imaging applications, including musculoskeletal, abdominal, cardiac, and brain imaging. This article is an introductory overview aimed at clinical radiologists with no experience in deep-learning-based MR image reconstruction and should enable them to understand the basic concepts and current clinical applications of this rapidly growing area of research across multiple organ systems.

The transformation of patient-clinician relationships with AI-based medical advice is discussed. many new tools are based on entirely new "˜black-box"™ AI-based technologies, whose inner workings are likely not fully understood by patients or clinicians. Most patients with Type 1 diabetes now use continuous glucose monitors and insulin pumps to tightly manage their disease. Their clinicians carefully review the data streams from both devices to recommend dosage adjustments. Recently new automated recommender systems to monitor and analyze food intake, insulin doses, physical activity, and other factors influencing glucose levels, and provide data-intensive, AI-based recommendations on how to titrate the regimen, are in different stages of FDA approval using "˜black box"™ technology, which is an alluring proposition for a clinical scenario that requires identification of meaningful patterns in complex and voluminous data.

PURPOSE/OBJECTIVE:To develop and evaluate a neural network-based method for Gibbs artifact and noise removal. METHODS:A convolutional neural network (CNN) was designed for artifact removal in diffusion-weighted imaging data. Two implementations were considered: one for magnitude images and one for complex images. Both models were based on the same encoder-decoder structure and were trained by simulating MRI acquisitions on synthetic non-MRI images. RESULTS:Both machine learning methods were able to mitigate artifacts in diffusion-weighted images and diffusion parameter maps. The CNN for complex images was also able to reduce artifacts in partial Fourier acquisitions. CONCLUSIONS:The proposed CNNs extend the ability of artifact correction in diffusion MRI. The machine learning method described here can be applied on each imaging slice independently, allowing it to be used flexibly in clinical applications.

During the COVID-19 pandemic, rapid and accurate triage of patients at the emergency department is critical to inform decision-making. We propose a data-driven approach for automatic prediction of deterioration risk using a deep neural network that learns from chest X-ray images, and a gradient boosting model that learns from routine clinical variables. Our AI prognosis system, trained using data from 3,661 patients, achieves an AUC of 0.786 (95% CI: 0.742-0.827) when predicting deterioration within 96 hours. The deep neural network extracts informative areas of chest X-ray images to assist clinicians in interpreting the predictions, and performs comparably to two radiologists in a reader study. In order to verify performance in a real clinical setting, we silently deployed a preliminary version of the deep neural network at NYU Langone Health during the first wave of the pandemic, which produced accurate predictions in real-time. In summary, our findings demonstrate the potential of the proposed system for assisting front-line physicians in the triage of COVID-19 patients.