Brains with complex distortion of cerebral anatomy present several challenges to automatic tissue segmentation methods of T1-weighted MR images. First, the very high variability in the morphology of the tissues can be incompatible with the prior knowledge embedded within the algorithms. Second, the availability of MR images of distorted brains is very scarce, so the methods in the literature have not addressed such cases so far. In this work, we present the first evaluation of state-of-the-art automatic tissue segmentation pipelines on T1-weighted images of brains with different severity of congenital or acquired brain distortion. We compare traditional pipelines and a deep learning model, i.e. a 3D U-Net trained on normal-appearing brains. Unsurprisingly, traditional pipelines completely fail to segment the tissues with strong anatomical distortion. Surprisingly, the 3D U-Net provides useful segmentations that can be a valuable starting point for manual refinement by experts/neuroradiologists.

Automatic Tissue Segmentation with Deep Learning in Patients with Congenital or Acquired Distortion of Brain Anatomy / Amorosino, Gabriele; Peruzzo, Denis; Astolfi, Pietro; Redaelli, Daniela; Avesani, Paolo; Arrigoni, Filippo; Olivetti, Emanuele. - 12449:(2020), pp. 13-22. [10.1007/978-3-030-66843-3_2]

Automatic Tissue Segmentation with Deep Learning in Patients with Congenital or Acquired Distortion of Brain Anatomy

Amorosino, Gabriele;Astolfi, Pietro;Olivetti, Emanuele
2020

Abstract

Brains with complex distortion of cerebral anatomy present several challenges to automatic tissue segmentation methods of T1-weighted MR images. First, the very high variability in the morphology of the tissues can be incompatible with the prior knowledge embedded within the algorithms. Second, the availability of MR images of distorted brains is very scarce, so the methods in the literature have not addressed such cases so far. In this work, we present the first evaluation of state-of-the-art automatic tissue segmentation pipelines on T1-weighted images of brains with different severity of congenital or acquired brain distortion. We compare traditional pipelines and a deep learning model, i.e. a 3D U-Net trained on normal-appearing brains. Unsurprisingly, traditional pipelines completely fail to segment the tissues with strong anatomical distortion. Surprisingly, the 3D U-Net provides useful segmentations that can be a valuable starting point for manual refinement by experts/neuroradiologists.
Machine Learning in Clinical Neuroimaging and Radiogenomics in Neuro-oncology: Third International Workshop, MLCN 2020, and Second International Workshop, RNO-AI 2020 Held in Conjunction with MICCAI 2020 Lima, Peru, October 4-8, 2020 Proceedings
Cham, CH
Springer International Publishing
978-3-030-66842-6
978-3-030-66843-3
Amorosino, Gabriele; Peruzzo, Denis; Astolfi, Pietro; Redaelli, Daniela; Avesani, Paolo; Arrigoni, Filippo; Olivetti, Emanuele
Automatic Tissue Segmentation with Deep Learning in Patients with Congenital or Acquired Distortion of Brain Anatomy / Amorosino, Gabriele; Peruzzo, Denis; Astolfi, Pietro; Redaelli, Daniela; Avesani, Paolo; Arrigoni, Filippo; Olivetti, Emanuele. - 12449:(2020), pp. 13-22. [10.1007/978-3-030-66843-3_2]
File in questo prodotto:
File Dimensione Formato  
Automatic_Tissue_Segmentation_with_Deep_Learning_i.pdf

embargo fino al 31/12/2022

Descrizione: Articolo Principale Pre-print non referato (Non-refereed preprint)
Tipologia: Pre-print non referato (Non-refereed preprint)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 3.42 MB
Formato Adobe PDF
3.42 MB Adobe PDF   Visualizza/Apri
mlcn2020.pdf

Solo gestori archivio

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 4.86 MB
Formato Adobe PDF
4.86 MB Adobe PDF   Visualizza/Apri
paper003.pdf

embargo fino al 31/12/2022

Tipologia: Post-print referato (Refereed author’s manuscript)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 1.96 MB
Formato Adobe PDF
1.96 MB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11572/285697
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact