A5081763875- Medical Image Segmentation Techniques
- Advanced Neuroimaging Techniques and Applications
- Fetal and Pediatric Neurological Disorders
- Functional Brain Connectivity Studies
- Advanced MRI Techniques and Applications
- Radiomics and Machine Learning in Medical Imaging
- Image Retrieval and Classification Techniques
- Domain Adaptation and Few-Shot Learning
- Medical Imaging Techniques and Applications
- Neural dynamics and brain function
- Morphological variations and asymmetry
- Cerebrovascular and Carotid Artery Diseases
- Neonatal and fetal brain pathology
- 3D Shape Modeling and Analysis
- Acute Ischemic Stroke Management
- Advanced Neural Network Applications
- Advanced Image and Video Retrieval Techniques
- Cell Image Analysis Techniques
- AI in cancer detection
- Medical Imaging and Analysis
- Sparse and Compressive Sensing Techniques
- MRI in cancer diagnosis
- Robotics and Sensor-Based Localization
- Advanced Vision and Imaging
- Advanced Image Processing Techniques
Massachusetts Institute of Technology
2016-2025
Harvard–MIT Division of Health Sciences and Technology
2024
Vanderbilt University
2024
IIT@MIT
2008-2024
Harvard University
2002-2023
Boston Children's Hospital
2022-2023
Intel (United States)
2002-2023
Athinoula A. Martinos Center for Biomedical Imaging
2023
University of Maryland, College Park
2023
Centro Científico Tecnológico - Santa Fe
2023
Abstract Biologists can now prepare and image thousands of samples per day using automation, enabling chemical screens functional genomics (for example, RNA interference). Here we describe the first free, open-source system designed for flexible, high-throughput cell analysis, CellProfiler. CellProfiler address a variety biological questions quantitatively, including standard assays count, size, per-cell protein levels) complex morphological cell/organelle shape or subcellular patterns DNA staining).
Abstract Background Image-based screens can produce hundreds of measured features for each millions individual cells in a single experiment. Results Here, we describe CellProfiler Analyst, open-source software the interactive exploration and analysis multidimensional data, particularly data from high-throughput, image-based experiments. Conclusion The system enables automated scoring complex phenotypes that require combinations multiple per cell.
We propose a nonparametric, probabilistic model for the automatic segmentation of medical images, given training set images and corresponding label maps. The resulting inference algorithms rely on pairwise registrations between test image individual images. labels are then transferred to fused compute final subject. Such fusion methods have been shown yield accurate segmentation, since use multiple captures greater inter-subject anatomical variability improves robustness against occasional...
Abstract Recent developments in MRI data acquisition technology are starting to yield images that show anatomical features of the hippocampal formation at an unprecedented level detail, providing basis for subfield measurement. However, a fundamental bottleneck studies hippocampus is they currently depend on manual segmentation, laborious process severely limits amount can be analyzed. In this article, we present computational method segmenting subfields ultra‐high resolution fully automated...
Many biological pathways were first uncovered by identifying mutants with visible phenotypes and scoring every sample in a screen via tedious subjective visual inspection. Now, automated image analysis can effectively score many phenotypes. In practical application, customizing an image-analysis algorithm or finding sufficient number of example cells to train machine learning be infeasible, particularly when positive control samples are not available the phenotype interest is rare. Here we...
We present the Spherical Demons algorithm for registering two spherical images. By exploiting vector spline interpolation theory, we show that a large class of regularizors modified objective function can be efficiently approximated on sphere using iterative smoothing. Based one parameter subgroups diffeomorphisms, resulting registration is diffeomorphic and fast. The also to register given image probabilistic atlas. demonstrate variants corresponding warping atlas or subject. Registration...
Every year, millions of brain magnetic resonance imaging (MRI) scans are acquired in hospitals across the world. These have potential to revolutionize our understanding many neurological diseases, but their morphometric analysis has not yet been possible due anisotropic resolution. We present an artificial intelligence technique, "SynthSR," that takes clinical MRI with any MR contrast (T1, T2, etc.), orientation (axial/coronal/sagittal), and resolution turns them into high-resolution T1...
Colonoscopy for colorectal cancer screening is endoscopist dependent, and colonoscopy quality improvement programs aim to improve efficacy. This study evaluated the clinical benefit safety of using a computer-aided detection (CADe) device in procedures.This randomized prospectively use CADe at 5 academic community centers by US board-certified gastroenterologists (n = 22). Participants aged ≥40 scheduled or surveillance (≥3 years) were included; exclusion criteria included incomplete...
Reconstructing 3D MR volumes from multiple motion-corrupted stacks of 2D slices has shown promise in imaging moving subjects, e. g., fetal MRI. However, existing slice-to-volume reconstruction methods are time-consuming, especially when a high-resolution volume is desired. Moreover, they still vulnerable to severe subject motion and image artifacts present acquired slices. In this work, we NeSVoR, resolution-agnostic method, which models the underlying as continuous function spatial...
Most existing algorithms for automatic 3D morphometry of human brain MRI scans are designed data with near-isotropic voxels at approximately 1 mm resolution, and frequently have contrast constraints as well-typically requiring T1-weighted images (e.g., MP-RAGE scans). This limitation prevents the analysis millions acquired large inter-slice spacing in clinical settings every year. In turn, inability to quantitatively analyze these hinders adoption quantitative neuro imaging healthcare, also...