3D Magnetic Resonance (MR) and Diffusion Tensor Imaging (DTI) have become important noninvasive tools for the study of animal models of brain development and neuropathologies. Fully automated analysis methods adapted to rodent scale for these images will allow high-throughput studies. A fundamental first step for most quantitative analysis algorithms is skull-stripping, which refers to the segmentation of the image into two tissue categories, brain and non-brain. In this manuscript, we present a fully automatic skull-stripping algorithm in an atlas-based manner. We also demonstrate how to either modify an external atlas or to build an atlas from the population itself to present a self-contained approach. We applied our method to three datasets of rat brain scans, at different ages (PND5, PND14 and adult), different study groups (control, ethanol exposed), as well as different image acquisition parameters. We validated our method by comparing the automated skull-strip results to manual delineations performed by our expert, which showed a discrepancy of less than a single voxel on average. We thus demonstrate that our algorithm can robustly and accurately perform the skull-stripping within one voxel of the manual delineation, and in a fraction of the time it takes a human expert.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3168953 | PMC |
| http://dx.doi.org/10.1117/12.878405 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Automated pediatric brain tumor imaging assessment tool from CBTN: Enhancing suprasellar region inclusion and managing limited data with deep learning.
Neurooncol Adv
December 2024
Department of Neurosurgery, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA.
Background: Fully automatic skull-stripping and tumor segmentation are crucial for monitoring pediatric brain tumors (PBT). Current methods, however, often lack generalizability, particularly for rare tumors in the sellar/suprasellar regions and when applied to real-world clinical data in limited data scenarios. To address these challenges, we propose AI-driven techniques for skull-stripping and tumor segmentation.
View Article and Find Full Text PDFDeep learning-based overall survival prediction in patients with glioblastoma: An automatic end-to-end workflow using pre-resection basic structural multiparametric MRIs.
Comput Biol Med
December 2024
Department of Radiation Oncology, Stanford University School of Medicine, Stanford, CA, USA; Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, TX, USA. Electronic address:
Article Synopsis
- The study focuses on developing a deep learning workflow to predict overall survival in glioblastoma (GBM) patients using pre-resection multiparametric MRI images, addressing the need for timely treatment decisions due to the poor prognosis of GBM.
- The process involves a series of models for skull-stripping, GBM sub-region segmentation, and survival prediction, using two datasets: a multi-institutional public dataset and an institutional dataset from a clinical trial, which includes various patient data like MRI scans and survival days.
- Results show the workflow has a strong predictive capability, achieving an AUC of 0.86 for the public dataset and 0.72 for the institutional dataset, successfully classifying patients into long-survivor
nnU-Net-based Segmentation of Tumor Subcompartments in Pediatric Medulloblastoma Using Multiparametric MRI: A Multi-institutional Study.
Radiol Artif Intell
September 2024
From the Department of Radiology, University of Wisconsin-Madison, Madison, Wis (R.B., M.I., I.Y.); University Hospitals, Cleveland, Ohio (D.M., A.N.); Departments of Biomedical Engineering (M.L., S.G., S.I.) and Neurosciences (P.D.), Case Western Reserve University, Cleveland, Ohio; Department of Radiology, Children's Hospital Los Angeles, Los Angeles, Calif (B.T.); Division of Hematology, Oncology & Bone Marrow Transplant, Nationwide Children's Hospital, Columbus, Ohio (R.S.); Department of Pediatrics, Keck School of Medicine of University of Southern California, Children's Hospital Los Angeles, Los Angeles, Calif (A.M.); Department of Pathology, Children's Hospital Los Angeles, Los Angeles, Calif (A.J.); Division of Oncology, Cincinnati Children's Hospital Medical Center, Cincinnati, Ohio (P.d.B.); William S. Middleton Memorial Veterans Affairs (VA) Healthcare, Madison, Wis (P.T.); and Department of Radiology and Biomedical Engineering, University of Wisconsin-Madison, 750 Highland Ave, Madison, WI 53726 (P.T.).
Article Synopsis
- The study aimed to assess nnU-Net-based segmentation models for accurately identifying medulloblastoma tumors in pediatric patients using multi-institutional MRI scans.
- It involved 78 patients aged 2 to 18 years and utilized various MRI protocols collected from three hospitals over 19 years, with tumor annotations prepared by expert neuroradiologists.
- Results showed that both transfer learning and direct nnU-Net models achieved decent Dice scores for tumor segmentation, indicating their effectiveness and robustness across different clinical sites.
Automated neonatal nnU-Net brain MRI extractor trained on a large multi-institutional dataset.
Sci Rep
February 2024
Division of Neuroradiology, Department of Radiology, Duke University Medical Center, Durham, NC, 27710, USA.
Brain extraction, or skull-stripping, is an essential data preprocessing step for machine learning approaches to brain MRI analysis. Currently, there are limited extraction algorithms for the neonatal brain. We aim to adapt an established deep learning algorithm for the automatic segmentation of neonatal brains from MRI, trained on a large multi-institutional dataset for improved generalizability across image acquisition parameters.
View Article and Find Full Text PDFPseudo-Label Assisted nnU-Net enables automatic segmentation of 7T MRI from a single acquisition.
Front Neuroimaging
December 2023
qMRI Core, NINDS, National Institutes of Health, Bethesda, MD, United States.
Introduction: Automatic whole brain and lesion segmentation at 7T presents challenges, primarily from bias fields, susceptibility artifacts including distortions, and registration errors. Here, we sought to use deep learning algorithms (D/L) to do both skull stripping and whole brain segmentation on multiple imaging contrasts generated in a single Magnetization Prepared 2 Rapid Acquisition Gradient Echoes (MP2RAGE) acquisition on participants clinically diagnosed with multiple sclerosis (MS), bypassing registration errors.
Methods: Brain scans Segmentation from 3T and 7T scanners were analyzed with software packages such as FreeSurfer, Classification using Derivative-based Features (C-DEF), nnU-net, and a novel 3T-to-7T transfer learning method, Pseudo-Label Assisted nnU-Net (PLAn).
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!