Faculty Bibliography
Searched for:
person:luiy01
in-biosketch:true
Total Results:
106
Critical Appraisal of Artificial Intelligence-Enabled Imaging Tools Using the Levels of Evidence System
Clinical adoption of an artificial intelligence-enabled imaging tool requires critical appraisal of its life cycle from development to implementation by using a systematic, standardized, and objective approach that can verify both its technical and clinical efficacy. Toward this concerted effort, the ASFNR/ASNR Artificial Intelligence Workshop Technology Working Group is proposing a hierarchal evaluation system based on the quality, type, and amount of scientific evidence that the artificial intelligence-enabled tool can demonstrate for each component of its life cycle. The current proposal is modeled after the levels of evidence in medicine, with the uppermost level of the hierarchy showing the strongest evidence for potential impact on patient care and health care outcomes. The intended goal of establishing an evidence-based evaluation system is to encourage transparency, foster an understanding of the creation of artificial intelligence tools and the artificial intelligence decision-making process, and to report the relevant data on the efficacy of artificial intelligence tools that are developed. The proposed system is an essential step in working toward a more formalized, clinically validated, and regulated framework for the safe and effective deployment of artificial intelligence imaging applications that will be used in clinical practice.
PMID: 37080722
ISSN: 1936-959x
CID: 5466292
Author Correction: Federated learning enables big data for rare cancer boundary detection
PMID: 36702828
ISSN: 2041-1723
CID: 5426632
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.
PMCID:9722782
PMID: 36470898
ISSN: 2041-1723
CID: 5381682
Exploring the Acceleration Limits of Deep Learning Variational Network-based Two-dimensional Brain MRI
PURPOSE/UNASSIGNED:To explore the limits of deep learning-based brain MRI reconstruction and identify useful acceleration ranges for general-purpose imaging and potential screening. MATERIALS AND METHODS/UNASSIGNED:potential use in a screening protocol. A Monte Carlo procedure was developed to estimate reconstruction error with only undersampled data. The model was evaluated on both in-domain and out-of-domain data. The 95% CIs were calculated using the percentile bootstrap method. RESULTS/UNASSIGNED:Radiologists rated 100% of 69 volumes as having sufficient image quality for general-purpose imaging at up to 4× acceleration and 65 of 69 volumes (94%) as having sufficient image quality for screening at up to 14× acceleration. The Monte Carlo procedure estimated ground truth peak signal-to-noise ratio and mean squared error with coefficients of determination greater than 0.5 at 2× to 20× acceleration levels. Out-of-distribution experiments demonstrated the model's ability to produce images substantially distinct from the training set, even at 100× acceleration. CONCLUSION/UNASSIGNED:© RSNA, 2022.
PMCID:9745443
PMID: 36523647
ISSN: 2638-6100
CID: 5382452
Deep multi-task learning and random forest for series classification by pulse sequence type and orientation
PURPOSE/OBJECTIVE:Increasingly complex MRI studies and variable series naming conventions reveal limitations of rule-based image routing, especially in health systems with multiple scanners and sites. Accurate methods to identify series based on image content would aid post-processing and PACS viewing. Recent deep/machine learning efforts classify 5-8 basic brain MR sequences. We present an ensemble model combining a convolutional neural network and a random forest classifier to differentiate 25 brain sequences and image orientation. METHODS:Series were grouped by descriptions into 25 sequences and 4 orientations. Dataset A, obtained from our institution, was divided into training (16,828 studies; 48,512 series; 112,028 images), validation (4746 studies; 16,612 series; 26,222 images) and test sets (6348 studies; 58,705 series; 3,314,018 images). Dataset B, obtained from a separate hospital, was used for out-of-domain external validation (1252 studies; 2150 series; 234,944 images). We developed an ensemble model combining a 2D convolutional neural network with a custom multi-task learning architecture and random forest classifier trained on DICOM metadata to classify sequence and orientation by series. RESULTS:The neural network, random forest, and ensemble achieved 95%, 97%, and 98% overall sequence accuracy on dataset A, and 98%, 99%, and 99% accuracy on dataset B, respectively. All models achieved > 99% orientation accuracy on both datasets. CONCLUSION/CONCLUSIONS:The ensemble model for series identification accommodates the complexity of brain MRI studies in state-of-the-art clinical practice. Expanding on previous work demonstrating proof-of-concept, our approach is more comprehensive with greater sequence diversity and orientation classification.
PMID: 35906437
ISSN: 1432-1920
CID: 5277082
Investigating Brain White Matter in Football Players with and without Concussion Using a Biophysical Model from Multishell Diffusion MRI
BACKGROUND AND PURPOSE:There have been growing concerns around potential risks related to sports-related concussion and contact sport exposure to repetitive head impacts in young athletes. Here we investigate WM microstructural differences between collegiate football players with and without sports-related concussion. MATERIALS AND METHODS:The study included 78 collegiate athletes (24 football players with sports-related concussion, 26 football players with repetitive head impacts, and 28 non-contact-sport control athletes), available through the Federal Interagency Traumatic Brain Injury Research registry. Diffusion metrics of diffusion tensor/kurtosis imaging and WM tract integrity were calculated. Tract-Based Spatial Statistics and post hoc ROI analyses were performed to test group differences. RESULTS:Significantly increased axial kurtosis in those with sports-related concussion compared with controls was observed diffusely across the whole-brain WM, and some focal areas demonstrated significantly higher mean kurtosis and extra-axonal axial diffusivity in sports-related concussion. The extent of significantly different WM regions decreased across time points and remained present primarily in the corpus callosum. Similar differences in axial kurtosis were found between the repetitive head impact and control groups. Other significant differences were seen at unrestricted return-to-play with lower radial kurtosis and intra-axonal diffusivity in those with sports-related concussion compared with the controls, mainly restricted to the posterior callosum. CONCLUSIONS:This study highlights the fact that there are differences in diffusion microstructure measures that are present not only between football players with sports-related injuries and controls, but that there are also measurable differences between football players with repetitive head impacts and controls. This work reinforces previous work showing that the corpus callosum is specifically implicated in sports-related concussion and also suggests this to be true for repetitive head impacts.
PMID: 35589140
ISSN: 1936-959x
CID: 5249482
Artificial Intelligence with Statistical Confidence Scores for Detection of Acute or Subacute Hemorrhage on Noncontrast CT Head Scans
Purpose/UNASSIGNED:To present a method that automatically detects, subtypes, and locates acute or subacute intracranial hemorrhage (ICH) on noncontrast CT (NCCT) head scans; generates detection confidence scores to identify high-confidence data subsets with higher accuracy; and improves radiology worklist prioritization. Such scores may enable clinicians to better use artificial intelligence (AI) tools. Materials and Methods/UNASSIGNED:764). Internal centers contributed developmental data, whereas external centers did not. Deep neural networks predicted the presence of ICH and subtypes (intraparenchymal, intraventricular, subarachnoid, subdural, and/or epidural hemorrhage) and segmentations per case. Two ICH confidence scores are discussed: a calibrated classifier entropy score and a Dempster-Shafer score. Evaluation was completed by using receiver operating characteristic curve analysis and report turnaround time (RTAT) modeling on the evaluation set and on confidence score-defined subsets using bootstrapping. Results/UNASSIGNED:< .001). Conclusion/UNASSIGNED:. © RSNA, 2022.
PMCID:9152881
PMID: 35652116
ISSN: 2638-6100
CID: 5283522
fastMRI+, Clinical pathology annotations for knee and brain fully sampled magnetic resonance imaging data
Improving speed and image quality of Magnetic Resonance Imaging (MRI) using deep learning reconstruction is an active area of research. The fastMRI dataset contains large volumes of raw MRI data, which has enabled significant advances in this field. While the impact of the fastMRI dataset is unquestioned, the dataset currently lacks clinical expert pathology annotations, critical to addressing clinically relevant reconstruction frameworks and exploring important questions regarding rendering of specific pathology using such novel approaches. This work introduces fastMRI+, which consists of 16154 subspecialist expert bounding box annotations and 13 study-level labels for 22 different pathology categories on the fastMRI knee dataset, and 7570 subspecialist expert bounding box annotations and 643 study-level labels for 30 different pathology categories for the fastMRI brain dataset. The fastMRI+ dataset is open access and aims to support further research and advancement of medical imaging in MRI reconstruction and beyond.
PMCID:8983757
PMID: 35383186
ISSN: 2052-4463
CID: 5201602
A No-Math Primer on the Principles of Machine Learning for Radiologists
Machine learning is becoming increasingly important in both research and clinical applications in radiology due to recent technological developments, particularly in deep learning. As these technologies are translated toward clinical practice, there is a need for radiologists and radiology trainees to understand the basic principles behind them. This primer provides an accessible introduction to the vocabulary and concepts that are central to machine learning and relevant to the radiologist.
PMID: 35339253
ISSN: 1558-5034
CID: 5190662
Radial spoiled gradient T1 weighted imaging of the internal auditory canal: Is Scarpa's ganglion now an expected finding and source of fundal enhancement?
StarVIBE is a 3D gradient-echo sequence with a radial, stack-of-stars acquisition having spatial resolution and tissue contrast. With newer sequences, it is important to be familiar with sequence tissue contrasts and appearance of anatomical variants. We evaluated 450 patients utilizing this sequence; 35 patients demonstrated fluffy "cotton wool" enhancement at the internal auditory canal fundus without clear pathology. We favor this represents anatomic neurovascular enhancement that StarVIBE is sensitive to and is a touch-me-not finding.
PMID: 35015577
ISSN: 2385-1996
CID: 5118602
