Brain extraction on MRI scans in presence of diffuse glioma: Multi-institutional performance evaluation of deep learning methods and robust modality-agnostic training
| العنوان: | Brain extraction on MRI scans in presence of diffuse glioma: Multi-institutional performance evaluation of deep learning methods and robust modality-agnostic training |
|---|---|
| المؤلفون: | Guray Erus, Gregory S. Alexander, Uday Kulkarni, Sarthak Pati, Rivka R. Colen, Spyridon Bakas, Siddhesh Thakur, Jimit Doshi, Gaurav Shukla, Chiharu Sako, Sanjay N. Talbar, Arash Nazeri, Daniel S. Marcus, Sung Min Ha, Pamela LaMontagne, Joshua D. Palmer, Adam E. Flanders, Christos Davatzikos, Mikhail Milchenko, Spencer Liem, Aikaterini Kotrotsou, Saima Rathore, Michel Bilello, Joseph Lombardo |
| المصدر: | NeuroImage, Vol 220, Iss, Pp 117081-(2020) NeuroImage |
| بيانات النشر: | Elsevier BV, 2020. |
| سنة النشر: | 2020 |
| مصطلحات موضوعية: | Databases, Factual, Computer science, Cognitive Neuroscience, Skull-stripping, Brain tumor, Machine learning, computer.software_genre, Article, 050105 experimental psychology, lcsh:RC321-571, 03 medical and health sciences, Diffuse Glioma, 0302 clinical medicine, Neuroimaging, Glioma, Image Processing, Computer-Assisted, medicine, Humans, 0501 psychology and cognitive sciences, Evaluation, lcsh:Neurosciences. Biological psychiatry. Neuropsychiatry, Retrospective Studies, Modality (human–computer interaction), medicine.diagnostic_test, Brain Neoplasms, business.industry, Deep learning, 05 social sciences, Brain, TCIA, Magnetic resonance imaging, Brain Extraction, medicine.disease, Magnetic Resonance Imaging, Neurology, Artificial intelligence, Glioblastoma, business, computer, 030217 neurology & neurosurgery |
| الوصف: | Brain extraction, or skull-stripping, is an essential pre-processing step in neuro-imaging that has a direct impact on the quality of all subsequent processing and analyses steps. It is also a key requirement in multi-institutional collaborations to comply with privacy-preserving regulations. Existing automated methods, including Deep Learning (DL) based methods that have obtained state-of-the-art results in recent years, have primarily targeted brain extraction without considering pathologically-affected brains. Accordingly, they perform sub-optimally when applied on magnetic resonance imaging (MRI) brain scans with apparent pathologies such as brain tumors. Furthermore, existing methods focus on using only T1-weighted MRI scans, even though multi-parametric MRI (mpMRI) scans are routinely acquired for patients with suspected brain tumors. In this study, we present a comprehensive performance evaluation of recent deep learning architectures for brain extraction, training models on mpMRI scans of pathologically-affected brains, with a particular focus on seeking a practically-applicable, low computational footprint approach, generalizable across multiple institutions, further facilitating collaborations. We identified a large retrospective multi-institutional dataset of n=3340 mpMRI brain tumor scans, with manually-inspected and approved gold-standard segmentations, acquired during standard clinical practice under varying acquisition protocols, both from private institutional data and public (TCIA) collections. To facilitate optimal utilization of rich mpMRI data, we further introduce and evaluate a novel ‘‘modality-agnostic training’’ technique that can be applied using any available modality, without need for model retraining. Our results indicate that the modality-agnostic approach11 Publicly available source code: https://github.com/CBICA/BrainMaGeTest obtains accurate results, providing a generic and practical tool for brain extraction on scans with brain tumors. |
| تدمد: | 1053-8119 |
| الوصول الحر: | https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1782a1713102b07e94fe3224a577ef85Test https://doi.org/10.1016/j.neuroimage.2020.117081Test |
| حقوق: | OPEN |
| رقم الانضمام: | edsair.doi.dedup.....1782a1713102b07e94fe3224a577ef85 |
| قاعدة البيانات: | OpenAIRE |
| تدمد: | 10538119 |
|---|