Brain extraction on MRI scans in presence of diffuse glioma: Multi-institutional performance evaluation of deep learning methods and robust modality-agnostic training

• Published in: NeuroImage (Orlando, Fla.) Vol. 220; p. 117081
• Main Authors: Thakur, Siddhesh, Doshi, Jimit, Pati, Sarthak, Rathore, Saima, Sako, Chiharu, Bilello, Michel, Ha, Sung Min, Shukla, Gaurav, Flanders, Adam, Kotrotsou, Aikaterini, Milchenko, Mikhail, Liem, Spencer, Alexander, Gregory S., Lombardo, Joseph, Palmer, Joshua D., LaMontagne, Pamela, Nazeri, Arash, Talbar, Sanjay, Kulkarni, Uday, Marcus, Daniel, Colen, Rivka, Davatzikos, Christos, Erus, Guray, Bakas, Spyridon
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 15.10.2020; Elsevier Limited; Elsevier
• Subjects: Algorithms; Automation; Brain - diagnostic imaging; Brain cancer; Brain Extraction; Brain Neoplasms - diagnostic imaging; Brain research; Brain tumor; Brain tumors; Cancer therapies; Clinical medicine; Collections; Computational neuroscience; Databases, Factual; Datasets; Deep Learning; Evaluation; Genomes; Glioblastoma; Glioma; Glioma - diagnostic imaging; Humans; Image Processing, Computer-Assisted - methods; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Neuroimaging; Performance evaluation; Retrospective Studies; Skull-stripping; Software; TCIA; Tumors; Brain tumor; Deep learning; TCIA; Brain Extraction; Evaluation; Glioma; Glioblastoma; Skull-stripping
• ISSN: 1053-8119; 1095-9572; 1095-9572
• DOI: 10.1016/j.neuroimage.2020.117081

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 approach11Publicly available source code: https://github.com/CBICA/BrainMaGe obtains accurate results, providing a generic and practical tool for brain extraction on scans with brain tumors. •Accurate brain extraction on MRI scans in presence of diffuse gliomas is critical.•Comprehensive evaluation of prominent deep learning architectures, BET & FreeSurfer.•Multi-institutional data to test generalizability and to facilitate collaborations.•A novel “modality-agnostic” strategy to promote widespread application.