ArticlebioRxiv : the preprint server for biology2026
AI segmentation requires accounting for brain size to maintain performance on developmental MRI cohorts.
Lena Dorfschmidt, Milly Hang Chi Mak, Sophie Adler, Konrad Wagstyl
Abstract readPreprint
In one paragraphArticle in bioRxiv : the preprint server for biology, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Not yet cited in PubMed.
0numbers the graph read from it
0cells of the map it votes in
0citing papers in PubMed
–field-weighted citation impact
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
2 · The registryThe trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
3 · Its place in the literatureWho cites it
0 citing papers in PubMed.
No citing paper in PubMed yet.
4 · The recordCorrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
5 · Who and what moneyAuthors and funding
4 authors.
Milly Hang Chi MakSchool of Biomedical Engineering & Imaging Sciences, King's College London, UK.
Konrad WagstylSchool of Biomedical Engineering & Imaging Sciences, King's College London, UK.
Funding
ABCD-USA Consortium: Coordinating CenterU24DA041147 · NIDA · UNIVERSITY OF CALIFORNIA, SAN DIEGO · PI SANDRA A BROWN, TERRY L. JERNIGAN · 2015 to 2026
$52.0MABCD-USA Consortium: Data Analysis, Informatics and Resource CenterU24DA041123 · NIDA · UNIVERSITY OF CALIFORNIA, SAN DIEGO · PI ANDERS M DALE · 2015 to 2026
$51.5MThe Healthy Brain and Child Development National Consortium Administrative CoreU24DA055325 · NIDA · UNIVERSITY OF CALIFORNIA, SAN DIEGO · PI CHRISTINA CHAMBERS, CHARLES Alexander NELSON · 2021 to 2026
$40.8MHealthy Brain and Child Development National Consortium Data Coordinating CenterU24DA055330 · NIDA · WASHINGTON UNIVERSITY · PI ANDERS M DALE, Damien A Fair · 2021 to 2026
$34.6MAdolescent Substance Use Initiation: Disentangling neurocognitive risks from consequences using longitudinal and genetically-informed methodsU01DA041120 · NIDA · UNIVERSITY OF MINNESOTA · PI Monica Luciana, Sylia Wilson · 2015 to 2026
$34.5MABCD-USA Consortium: Research ProjectU01DA041089 · NIDA · UNIVERSITY OF CALIFORNIA, SAN DIEGO · PI Joanna Jacobus, Susan F. Tapert · 2015 to 2026
$31.7MProspective Research Studies of Maturation (PRISM)- Research ProjectU01DA041134 · NIDA · UTAH STATE HIGHER EDUCATION SYSTEM--UNIVERSITY OF UTAH · PI ERIN MCGLADE, PERRY FRANKLIN RENSHAW · 2015 to 2026
$29.2MABCD-USA CONSORTIUM: RESEARCH PROJECTU01DA041048 · NIDA · CHILDREN'S HOSPITAL OF LOS ANGELES · PI Megan Marie Herting, ELIZABETH R SOWELL · 2015 to 2026
$28.7MABCD-USA Consortium: Research ProjectU01DA041106 · NIDA · UNIVERSITY OF MICHIGAN AT ANN ARBOR · PI Mary M Heitzeg, Chandra Sekhar Sripada · 2015 to 2026
$24.9MFIU-ABCD: Pathways and Mechanisms to Addiction in the Latino Youth of South FloridaU01DA041156 · NIDA · FLORIDA INTERNATIONAL UNIVERSITY · PI Raul Gonzalez, Angela R Laird · 2015 to 2026
$22.8MABCD-USA Consortium: Research ProjectU01DA041148 · NIDA · OREGON HEALTH & SCIENCE UNIVERSITY · PI Damien A Fair, Rebekah S Huber · 2015 to 2026
$22.3MABCD-USA: NYC Research ProjectU01DA041174 · NIDA · YALE UNIVERSITY · PI Arielle Ryan Baskin-Sommers, Betty J Casey · 2015 to 2026
$19.7MNIDA NIH HHS U01 DA041022NIDA NIH HHS U01 DA041025NIDA NIH HHS U01 DA041028NIDA NIH HHS U01 DA041048NIDA NIH HHS U01 DA041089NIDA NIH HHS U01 DA041093NIDA NIH HHS U01 DA041106NIDA NIH HHS U01 DA041117NIDA NIH HHS U01 DA041120NIDA NIH HHS U01 DA041134NIDA NIH HHS U01 DA041148NIDA NIH HHS U01 DA041156NIDA NIH HHS U01 DA041174NIDA NIH HHS U01 DA050987NIDA NIH HHS U01 DA050988NIDA NIH HHS U01 DA050989NIDA NIH HHS U01 DA051016NIDA NIH HHS U01 DA051018NIDA NIH HHS U01 DA051037NIDA NIH HHS U01 DA051038NIDA NIH HHS U01 DA051039NIDA NIH HHS U01 DA055316NIDA NIH HHS U01 DA055322NIDA NIH HHS U01 DA055338NIDA NIH HHS U01 DA055342NIDA NIH HHS U01 DA055344NIDA NIH HHS U01 DA055347NIDA NIH HHS U01 DA055349NIDA NIH HHS U01 DA055350NIDA NIH HHS U01 DA055352NIDA NIH HHS U01 DA055353NIDA NIH HHS U01 DA055354NIDA NIH HHS U01 DA055355NIDA NIH HHS U01 DA055357NIDA NIH HHS U01 DA055358NIDA NIH HHS U01 DA055359NIDA NIH HHS U01 DA055360NIDA NIH HHS U01 DA055361NIDA NIH HHS U01 DA055362NIDA NIH HHS U01 DA055363NIDA NIH HHS U01 DA055365NIDA NIH HHS U01 DA055366NIDA NIH HHS U01 DA055367NIDA NIH HHS U01 DA055369NIDA NIH HHS U01 DA055370NIDA NIH HHS U01 DA055371NIDA NIH HHS U24 DA041123NIDA NIH HHS U24 DA041147NIDA NIH HHS U24 DA055325NIDA NIH HHS U24 DA055330Wellcome Trust
6 · The paper itselfAbstract
The human brain undergoes rapid developmental changes through early life, underpinning the emergence of function but also marking a period of vulnerability to a range of neurodevelopmental disorders. With dynamic changes to brain size, morphology, and imaging contrast, consistent and accurate computational neuroanatomy remains a challenge. Deep learning tools for segmentation, like SynthSeg, offer robustness to heterogeneously acquired MRI contrast but remain unproven in early development. Here, we aggregated a large cohort (26k) of MRI scans spanning infant to adult development, and evaluated SynthSeg performance. Automated quality control scores, visual inspection, and spatial overlap with expert-segmented MRI scans revealed poor quality output segmentations during development. In the infant period only 36% of scans (1094/3069) passed automated QC. Rescaling infant scans to adult brain sizes significantly improved spatial overlap, and cropping scans to match adult fields of view retrieved automated quality control. Evaluation of the
Indexed as
Deep LearningMRINeurodevelopmentSegmentationSynthSeg
Identifiers
PMID42539016
PMCPMC13419518
What Socratic holds
Textmetadata
LicenceCC BY
Read underepoch 390