Timothy J Hendrickson, Paul Reiners, Lucille A Moore, Jacob T Lundquist, Begim Fayzullobekova, Anders J Perrone, Erik G Lee, Julia Moser, Trevor K M Day, Dimitrios Alexopoulos, Martin Styner, Omid Kardan, Taylor A Chamberlain, Anurima Mummaneni, Henrique A Caldas, Brad Bower, Sally Stoyell, Tabitha Martin, Sooyeon Sung, Ermias Fair, Kenevan Carter, Jonathan Uriarte-Lopez, Amanda R Rueter, Essa Yacoub, Monica D Rosenberg, Christopher D Smyser, Jed T Elison, Alice Graham, Damien A Fair, Eric Feczko
{"title":"BIBSNet: A Deep Learning Baby Image Brain Segmentation Network for MRI Scans.","authors":"Timothy J Hendrickson, Paul Reiners, Lucille A Moore, Jacob T Lundquist, Begim Fayzullobekova, Anders J Perrone, Erik G Lee, Julia Moser, Trevor K M Day, Dimitrios Alexopoulos, Martin Styner, Omid Kardan, Taylor A Chamberlain, Anurima Mummaneni, Henrique A Caldas, Brad Bower, Sally Stoyell, Tabitha Martin, Sooyeon Sung, Ermias Fair, Kenevan Carter, Jonathan Uriarte-Lopez, Amanda R Rueter, Essa Yacoub, Monica D Rosenberg, Christopher D Smyser, Jed T Elison, Alice Graham, Damien A Fair, Eric Feczko","doi":"10.1101/2023.03.22.533696","DOIUrl":null,"url":null,"abstract":"<p><strong>Objectives: </strong>Brain segmentation of infant magnetic resonance (MR) images is vitally important in studying developmental mental health and disease. The infant brain undergoes many changes throughout the first years of postnatal life, making tissue segmentation difficult for most existing algorithms. Here, we introduce a deep neural network BIBSNet (<b>B</b>aby and <b>I</b>nfant <b>B</b>rain <b>S</b>egmentation Neural <b>Net</b>work), an open-source, community-driven model that relies on data augmentation and a large sample size of manually annotated images to facilitate the production of robust and generalizable brain segmentations.</p><p><strong>Experimental design: </strong>Included in model training and testing were MR brain images on 84 participants with an age range of 0-8 months (median postmenstrual ages of 13.57 months). Using manually annotated real and synthetic segmentation images, the model was trained using a 10-fold cross-validation procedure. Testing occurred on MRI data processed with the DCAN labs infant-ABCD-BIDS processing pipeline using segmentations produced from gold standard manual annotation, joint-label fusion (JLF), and BIBSNet to assess model performance.</p><p><strong>Principal observations: </strong>Using group analyses, results suggest that cortical metrics produced using BIBSNet segmentations outperforms JLF segmentations. Additionally, when analyzing individual differences, BIBSNet segmentations perform even better.</p><p><strong>Conclusions: </strong>BIBSNet segmentation shows marked improvement over JLF segmentations across all age groups analyzed. The BIBSNet model is 600x faster compared to JLF and can be easily included in other processing pipelines.</p>","PeriodicalId":72407,"journal":{"name":"bioRxiv : the preprint server for biology","volume":" ","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10055337/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"bioRxiv : the preprint server for biology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1101/2023.03.22.533696","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Objectives: Brain segmentation of infant magnetic resonance (MR) images is vitally important in studying developmental mental health and disease. The infant brain undergoes many changes throughout the first years of postnatal life, making tissue segmentation difficult for most existing algorithms. Here, we introduce a deep neural network BIBSNet (Baby and Infant Brain Segmentation Neural Network), an open-source, community-driven model that relies on data augmentation and a large sample size of manually annotated images to facilitate the production of robust and generalizable brain segmentations.
Experimental design: Included in model training and testing were MR brain images on 84 participants with an age range of 0-8 months (median postmenstrual ages of 13.57 months). Using manually annotated real and synthetic segmentation images, the model was trained using a 10-fold cross-validation procedure. Testing occurred on MRI data processed with the DCAN labs infant-ABCD-BIDS processing pipeline using segmentations produced from gold standard manual annotation, joint-label fusion (JLF), and BIBSNet to assess model performance.
Principal observations: Using group analyses, results suggest that cortical metrics produced using BIBSNet segmentations outperforms JLF segmentations. Additionally, when analyzing individual differences, BIBSNet segmentations perform even better.
Conclusions: BIBSNet segmentation shows marked improvement over JLF segmentations across all age groups analyzed. The BIBSNet model is 600x faster compared to JLF and can be easily included in other processing pipelines.