About

Lawrence H. Staib is a Professor of Biomedical Engineering at Yale University, with additional appointments in Electrical & Computer Engineering and Radiology & Biomedical Imaging. His research focuses on automated medical image analysis, including model-based image segmentation, nonrigid registration methods, characterization of deformation, machine learning, structural connectivity image analysis, and functional magnetic resonance image analysis. His work has applications in neuroscience, cardiology, and cancer. Dr. Staib holds a Ph.D. from Yale University and has been recognized as a Fellow of the American Institute for Medical and Biological Engineering in 2015. His contributions include developing advanced techniques for medical image analysis and securing patents related to 3D ultrasound computed tomography imaging systems.

Research topics

• Artificial Intelligence
• Machine Learning
• Computer Science
• Data Mining
• Computer vision
• Theoretical computer science
• Neuroscience
• Psychology

Selected publications

• Causal Modeling of FMRI Time-Series for Interpretable Autism Spectrum Disorder Classification

  2025-04-14 · 2 citations

  articleOpen access

  Autism spectrum disorder (ASD) is a neurological and developmental disorder that affects social and communicative behaviors. It emerges in early life and is generally associated with lifelong disabilities. Thus, accurate and early diagnosis could facilitate treatment outcomes for those with ASD. Functional magnetic resonance imaging (fMRI) is a useful tool that measures changes in brain signaling to facilitate our understanding of ASD. Much effort is being made to identify ASD biomarkers using various connectome-based machine learning and deep learning classifiers. However, correlation-based models cannot capture the non-linear interactions between brain regions. To solve this problem, we introduce a causality-inspired deep learning model that uses time-series information from fMRI and captures causality among ROIs useful for ASD classification. The model is compared with other baseline and state-of-the-art models with 5-fold cross-validation on the ABIDE dataset. We filtered the dataset by choosing all the images with mean FD less than 15mm to ensure data quality. Our proposed model achieved the highest average classification accuracy of 71.9% and an average AUC of 75.8%. Moreover, the inter-ROI causality interpretation of the model suggests that the left precuneus, right precuneus, and cerebellum are placed in the top 10 ROIs in inter-ROI causality among the ASD population. In contrast, these ROIs are not ranked in the top 10 in the control population. We have validated our findings with the literature and found that abnormalities in these ROIs are often associated with ASD.

  PublisherOA PDFDOI

• Enhancing Uncertainty Estimation in Semantic Segmentation via Monte-Carlo Frequency Dropout

  2025-04-14 · 6 citations

  article

  Monte-Carlo (MC) Dropout provides a practical solution for estimating predictive distributions in deterministic neural networks. Traditional dropout, applied within the signal space, may fail to account for frequency-related noise common in medical imaging, leading to biased predictive estimates. A novel approach extends Dropout to the frequency domain, allowing stochastic attenuation of signal frequencies during inference. This creates diverse global textural variations in feature maps while preserving structural integrity - a factor we hypothesize and empirically show is contributing to accurately estimating uncertainties in semantic segmentation. We evaluated traditional MC-Dropout and the MC-frequency Dropout in three segmentation tasks involving different imaging modalities: (i) prostate zones in biparametric MRI, (ii) liver tumors in contrast-enhanced CT, and (iii) lungs in chest X-ray scans. Our results show that MC-Frequency Dropout improves calibration, convergence, and semantic uncertainty, thereby improving prediction scrutiny, boundary delineation, and has the potential to enhance medical decision-making.

  PublisherDOI

• Comparative Performance of Machine Learning Models in Reducing Unnecessary Targeted Prostate Biopsies

  European Urology Oncology · 2025-02-08 · 4 citations

  articleOpen access
  PublisherOA PDFDOI

• STNAGNN: Data-driven Spatio-temporal Brain Connectivity beyond FC.

  PubMed · 2025-04-08

  preprintOpen access

  In recent years, graph neural networks (GNNs) have been widely applied in the analysis of brain fMRI, yet defining the connectivity between ROIs remains a challenge in noisy fMRI data. Among all approaches, Functional Connectome (FC) is the most popular method. Computed by the correlation coefficients between ROI time series, FC is a powerful and computationally efficient way to estimate ROI connectivity. However, it is well known for neglecting structural connections and causality in ROI interactions. Also, FC becomes much more noisy in the short spatio-temporal sliding-window subsequences of fMRI. Effective Connectome (EC) is proposed as a directional alternative, but is difficult to accurately estimate. Furthermore, for optimal GNN performance, usually only a small percentage of the strongest connections are selected as sparse edges, resulting in oversimplification of complex brain connections. To tackle these challenges, we propose the Spatio-Temporal Node Attention Graph Neural Network (STNAGNN) as a data-driven alternative that combines sparse predefined FC with dense data-driven spatio-temporal connections, allowing for flexible and spatio-temporal learning of ROI interaction patterns.

  PublisherOA PDF

• Corrigendum to “Applying dual energy computed tomography to postmortem coronary computed tomographic angiography” [J Cardiovasc Comput Tomogr (in press)]

  Journal of cardiovascular computed tomography · 2025-11-26

  erratumOpen access
  PublisherOA PDFDOI

• Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation

  2025-06-10

  article

  Accurate uncertainty estimation is crucial for deploying neural networks in risk-sensitive applications such as medical diagnosis. Monte Carlo Dropout is a widely used technique for approximating predictive uncertainty by performing stochastic forward passes with dropout during inference. However, using static dropout rates across all layers and inputs can lead to suboptimal uncertainty estimates, as it fails to adapt to the varying characteristics of individual inputs and network layers. Existing approaches optimize dropout rates during training using labeled data, resulting in fixed inference-time parameters that cannot adjust to new data distributions, compromising uncertainty estimates in Monte Carlo simulations.In this paper, we propose Rate-In, an algorithm that dynamically adjusts dropout rates during inference by quantifying the information loss induced by dropout in each layer’s feature maps. By treating dropout as controlled noise injection and leveraging information-theoretic principles, Rate-In adapts dropout rates per layer and per input instance without requiring ground truth labels. By quantifying the functional information loss in feature maps, we adaptively tune dropout rates to maintain perceptual quality across diverse medical imaging tasks and architectural configurations. Our extensive empirical study on synthetic data and real-world medical imaging tasks demonstrates that Rate-In improves calibration and sharpens uncertainty estimates compared to fixed or heuristic dropout rates without compromising predictive performance. Rate-In offers a practical, unsupervised, inference-time approach to optimizing dropout for more reliable predictive uncertainty estimation in critical applications.

  PublisherDOI

• Towards Zero-Shot Task-Generalizable Learning on fMRI

  ArXiv.org · 2025-02-15

  preprintOpen access

  Functional MRI measuring BOLD signal is an increasingly important imaging modality in studying brain functions and neurological disorders. It can be acquired in either a resting-state or a task-based paradigm. Compared to resting-state fMRI, task-based fMRI is acquired while the subject is performing a specific task designed to enhance study-related brain activities. Consequently, it generally has more informative task-dependent signals. However, due to the variety of task designs, it is much more difficult than in resting state to aggregate task-based fMRI acquired in different tasks to train a generalizable model. To resolve this complication, we propose a supervised task-aware network TA-GAT that jointly learns a general-purpose encoder and task-specific contextual information. The encoder-generated embedding and the learned contextual information are then combined as input to multiple modules for performing downstream tasks. We believe that the proposed task-aware architecture can plug-and-play in any neural network architecture to incorporate the prior knowledge of fMRI tasks into capturing functional brain patterns.

  PublisherOA PDFDOI

• Gender Differences in Cognitive and Neural Correlates of Remembrance of Emotional Words

  Psychopharmacology Bulletin · 2025-08-12 · 73 citations

  article

  Studies suggest that men and women have important differences in specific cognitive functions. Men show superior spatial memory and women demonstrate superior verbal memory, and women rely on emotional content to a greater degree in the processing of information. In spite of extensive research in neural correlates of human cognition, little is known about possible gender differences or the role of emotional content in the mediation of cognition. Two sets of lists of word pairs were developed, one with neutral (e.g., school-grocery) and the other with emotional (e.g., mutilate-beat) content. Male and female subjects were asked to rate emotions related to the words on several dimensions (e.g., nervous, fearful, happy). In a second experiment, men and women underwent positron emission tomographic (PET) measurement of brain blood flow during retrieval of word pairs. Words in the "emotional" category were rated more highly on the emotional dimensions, and women rated them as having more emotional impact than did the men. During retrieval of emotional words (but not neutral words) there was a different pattern of activation among the women compared with the men, with greater activation in bilateral posterior hippocampus and cerebellum, and decreased activity in medial prefrontal cortex, which are brain areas previously implicated in emotion. There were no significant differences in retrieval of emotional versus neutral words, or in differences in memory performance between men and women. The findings suggest differences in cognitive appraisal and involvement of a broader network of brain regions mediating emotion during remembrance of emotional words in women compared with men.

  PublisherDOI

• Enhancing Uncertainty Estimation in Semantic Segmentation via Monte-Carlo Frequency Dropout

  ArXiv.org · 2025-01-20

  preprintOpen access

  Monte-Carlo (MC) Dropout provides a practical solution for estimating predictive distributions in deterministic neural networks. Traditional dropout, applied within the signal space, may fail to account for frequency-related noise common in medical imaging, leading to biased predictive estimates. A novel approach extends Dropout to the frequency domain, allowing stochastic attenuation of signal frequencies during inference. This creates diverse global textural variations in feature maps while preserving structural integrity -- a factor we hypothesize and empirically show is contributing to accurately estimating uncertainties in semantic segmentation. We evaluated traditional MC-Dropout and the MC-frequency Dropout in three segmentation tasks involving different imaging modalities: (i) prostate zones in biparametric MRI, (ii) liver tumors in contrast-enhanced CT, and (iii) lungs in chest X-ray scans. Our results show that MC-Frequency Dropout improves calibration, convergence, and semantic uncertainty, thereby improving prediction scrutiny, boundary delineation, and has the potential to enhance medical decision-making.

  PublisherOA PDFDOI

• Progressive Test Time Energy Adaptation for Medical Image Segmentation

  2025-10-19

  articleOpen access

  We propose a model-agnostic, progressive test-time energy adaptation approach for medical image segmentation. Maintaining model performance across diverse medical datasets is challenging, as distribution shifts arise from inconsistent imaging protocols and patient variations. Unlike domain adaptation methods that require multiple passes through target data - impractical in clinical settings - our approach adapts pretrained models progressively as they process test data. Our method leverages a shape energy model trained on source data, which assigns an energy score at the patch level to segmentation maps: low energy represents in-distribution (accurate) shapes, while high energy signals out-of-distribution (erroneous) predictions. By minimizing this energy score at test time, we refine the segmentation model to align with the target distribution. To validate the effectiveness and adaptability, we evaluated our framework on eight public MRI (bSSFP, T1- and T2-weighted) and X-ray datasets spanning cardiac, spinal cord, and lung segmentation. We consistently outperform baselines both quantitatively and qualitatively.

  PublisherOA PDFDOI

Recent grants

• NIH Grant R01EB000311

  NIH · $355k · 2005

• Dynamic Functional Image-based Deep Learning for Therapy Assessment in Autism

  NIH · $10.0M · 1996–2027

• NIH Grant R56NS035193

  NIH · $385k · 2011

Frequent coauthors

• Fred R. Volkmar

  Yale University

  1689 shared

• Thomas Zane

  University of Kansas

  632 shared

• Lawrence David Scahill

  489 shared

• Diana B. Newman

  486 shared

• Jennifer McCullagh

  Southern Connecticut State University

  465 shared

• Sarita Austin

  Yale University

  462 shared

• Johnny L. Matson

  322 shared

• Evdokia Anagnostou

  Holland Bloorview Kids Rehabilitation Hospital

  320 shared

Awards & honors

• Fellow of the American Institute for Medical and Biological…