The thalamus is a subcortical brain structure linked to the motor system. Since certain changes within this structure are related to diseases, such as multiple sclerosis and Parkinson's, the characterization of the thalamus-e.g., shape assessment-is a crucial step in relevant studies and applications, including medical research and surgical planning. A robust and reliable thalamus-segmentation method is therefore, required to meet these demands. Despite presenting low contrast for this particular structure, T1-weighted imaging is still the most common MRI sequence for thalamus segmentation. However, diffusion MRI (dMRI) captures different micro-structural details of the biological tissue and reveals more contrast of the thalamic borders, thereby serving as a better candidate for thalamus-segmentation methods. Accordingly, we propose a baseline multimodality thalamus-segmentation pipeline that combines dMRI and T1-weighted images within a CNN approach, achieving state-of-the-art levels of Dice overlap. Furthermore, we are hosting an open benchmark with a large, preprocessed, publicly available dataset that includes co-registered, T1-weighted, dMRI, manual thalamic masks; masks generated by three distinct automated methods; and a STAPLE consensus of the masks. The dataset, code, environment, and instructions for the benchmark leaderboard can be found on our GitHub and CodaLab.

Thalamus Segmentation Using Deep Learning with Diffusion MRI Data: An Open Benchmark

Gustavo Retuci Pinheiro
;
Lorenza Brusini;Gloria Menegaz;Leticia Rittner
2023-01-01

Abstract

The thalamus is a subcortical brain structure linked to the motor system. Since certain changes within this structure are related to diseases, such as multiple sclerosis and Parkinson's, the characterization of the thalamus-e.g., shape assessment-is a crucial step in relevant studies and applications, including medical research and surgical planning. A robust and reliable thalamus-segmentation method is therefore, required to meet these demands. Despite presenting low contrast for this particular structure, T1-weighted imaging is still the most common MRI sequence for thalamus segmentation. However, diffusion MRI (dMRI) captures different micro-structural details of the biological tissue and reveals more contrast of the thalamic borders, thereby serving as a better candidate for thalamus-segmentation methods. Accordingly, we propose a baseline multimodality thalamus-segmentation pipeline that combines dMRI and T1-weighted images within a CNN approach, achieving state-of-the-art levels of Dice overlap. Furthermore, we are hosting an open benchmark with a large, preprocessed, publicly available dataset that includes co-registered, T1-weighted, dMRI, manual thalamic masks; masks generated by three distinct automated methods; and a STAPLE consensus of the masks. The dataset, code, environment, and instructions for the benchmark leaderboard can be found on our GitHub and CodaLab.
2023
thalamus
segmentation
diffusion MRI
public dataset
deep learning
benchmark
File in questo prodotto:
Non ci sono file associati a questo prodotto.

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: https://hdl.handle.net/11562/1126367
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? 0
social impact