ASCHOPLEX: A generalizable approach for the automatic segmentation of choroid plexus

Valentina Visani; Mattia Veronese; Francesca B Pizzini; Annalisa Colombi; Valerio Natale; Corina Marjin; Agnese Tamanti; Julia J Schubert; Noha Althubaity; Inés Bedmar-Gómez; Neil A Harrison; Edward T Bullmore; Federico E Turkheimer; NIMA Consortium; Massimiliano Calabrese; Marco Castellaro

doi:10.1016/j.compbiomed.2024.109164

ASCHOPLEX: A generalizable approach for the automatic segmentation of choroid plexus

Comput Biol Med. 2024 Nov:182:109164. doi: 10.1016/j.compbiomed.2024.109164. Epub 2024 Sep 25.

Authors

Valentina Visani¹, Mattia Veronese², Francesca B Pizzini³, Annalisa Colombi⁴, Valerio Natale⁵, Corina Marjin⁶, Agnese Tamanti⁷, Julia J Schubert⁸, Noha Althubaity⁹, Inés Bedmar-Gómez¹⁰, Neil A Harrison¹¹, Edward T Bullmore¹², Federico E Turkheimer¹³; NIMA Consortium; Massimiliano Calabrese¹⁴, Marco Castellaro¹⁵

Affiliations

¹ Department of Information Engineering, University of Padova, Padova, Italy. Electronic address: [email protected].
² Department of Information Engineering, University of Padova, Padova, Italy; Department of Neuroimaging, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK. Electronic address: [email protected].
³ Department of Engineering for Innovation Medicine, University of Verona, Verona, Italy. Electronic address: [email protected].
⁴ Unit of Neurology, Fondazione Poliambulanza, Brescia, Italy. Electronic address: [email protected].
⁵ Department of Diagnostic and Public Health, University of Verona, Verona, Italy. Electronic address: [email protected].
⁶ Department of Neurosciences, Biomedicine and Movement Sciences, University of Verona, Verona, Italy. Electronic address: [email protected].
⁷ Department of Neurosciences, Biomedicine and Movement Sciences, University of Verona, Verona, Italy. Electronic address: [email protected].
⁸ Department of Neuroimaging, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK. Electronic address: [email protected].
⁹ Department of Neuroimaging, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK; Department of Radiological Sciences, College of Applied Medical Science, King Saud bin Abdulaziz University for Health Sciences, King Abdullah International Medical Research Center (KAIMRC), Riyadh, Saudi Arabia. Electronic address: [email protected].
¹⁰ Department of Neuroimaging, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK. Electronic address: [email protected].
¹¹ Cardiff University Brain Research Imaging Centre (CUBRIC), Cardiff University, Cardiff, UK. Electronic address: [email protected].
¹² Department of Psychiatry, School of Clinical Medicine, University of Cambridge, Cambridge, UK; Cambridgeshire and Peterborough NHS Foundation Trust, Cambridge, UK; Immuno-Psychiatry, Immuno-Inflammation Therapeutic Area Unit, GlaxoSmithKline R&D, Stevenage, UK. Electronic address: [email protected].
¹³ Department of Neuroimaging, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK. Electronic address: [email protected].
¹⁴ Department of Neurosciences, Biomedicine and Movement Sciences, University of Verona, Verona, Italy. Electronic address: [email protected].
¹⁵ Department of Information Engineering, University of Padova, Padova, Italy. Electronic address: [email protected].

PMID: 39326265
DOI: 10.1016/j.compbiomed.2024.109164

Abstract

Background: The Choroid Plexus (ChP) plays a vital role in brain homeostasis, serving as part of the Blood-Cerebrospinal Fluid Barrier, contributing to brain clearance pathways and being the main source of cerebrospinal fluid. Since the involvement of ChP in neurological and psychiatric disorders is not entirely established and currently under investigation, accurate and reproducible segmentation of this brain structure on large cohorts remains challenging. This paper presents ASCHOPLEX, a deep-learning tool for the automated segmentation of human ChP from structural MRI data that integrates existing software architectures like 3D UNet, UNETR, and DynUNet to deliver accurate ChP volume estimates.

Methods: Here we trained ASCHOPLEX on 128 T1-w MRI images comprising both controls and patients with Multiple Sclerosis. ASCHOPLEX's performances were evaluated using traditional segmentation metrics; manual segmentation by experts served as ground truth. To overcome the generalizability problem that affects data-driven approaches, an additional fine-tuning procedure (ASCHOPLEX_tune) was implemented on 77 T1-w PET/MRI images of both controls and depressed patients.

Results: ASCHOPLEX showed superior performance compared to commonly used methods like FreeSurfer and Gaussian Mixture Model both in terms of Dice Coefficient (ASCHOPLEX 0.80, ASCHOPLEX_tune 0.78) and estimated ChP volume error (ASCHOPLEX 9.22%, ASCHOPLEX_tune 9.23%).

Conclusion: These results highlight the high accuracy, reliability, and reproducibility of ASCHOPLEX ChP segmentations.

Keywords: Choroid plexus; Deep neural networks; Ensemble; Magnetic resonance imaging; Semantic segmentation.

MeSH terms

Adult
Choroid Plexus* / diagnostic imaging
Deep Learning
Female
Humans
Image Processing, Computer-Assisted / methods
Magnetic Resonance Imaging* / methods
Male
Middle Aged
Multiple Sclerosis / diagnostic imaging
Software