Understanding the brain connectome and the anatomical organization of neural circuits in the mouse brain using histological sections is a prominent area of research in the neuroscience field. Accurate quantitative and comparative analysis of anatomical data requires precise mapping of brain sections to a common reference atlas. The existing methods rely either on using 2D coronal atlases or 3D reconstruction prior to registration. The problem with the former is that atlases are not always a good match, since they do not account for the slicing angle. The drawback of the latter is that 3D to 3D registration methods are not only computationally expensive but also require a full set of consecutive sections which are not always available due to technical limitations. In this study, we propose a deep learning-based approach, to automatically detect the position and angle of individual mouse brain sections in the 3D reference atlas. The novel method is implemented as a pipeline consisting of 3 blocks of Convolutional Neural Network (CNN) regression models that detect the slicing angle and the position of the section in the anterior-posterior (AP) axis of the brain. The proposed method not only generates matching 2D atlases by taking the slicing angle into account but is also considerably faster and more robust to histological artifacts, compared to 3D registration approaches. We have shown that predictions of our method are comparable to a neuroscientist expert.

Automatic 2D to 3D localization of histological mouse brain sections in the reference atlas using deep learning / Sadeghi, M.; Neto, P.; Ramos-Prats, A.; Castaldi, F.; Paradiso, E.; Mahmoodian, N.; Ferraguti, F.; Goebel, G.. - 12032:(2022). (Intervento presentato al convegno Medical Imaging 2022: Image Processing tenutosi a on line nel FEB 20-MAR 27, 2022) [10.1117/12.2604231].

Automatic 2D to 3D localization of histological mouse brain sections in the reference atlas using deep learning

Ferraguti F.;
2022

Abstract

Understanding the brain connectome and the anatomical organization of neural circuits in the mouse brain using histological sections is a prominent area of research in the neuroscience field. Accurate quantitative and comparative analysis of anatomical data requires precise mapping of brain sections to a common reference atlas. The existing methods rely either on using 2D coronal atlases or 3D reconstruction prior to registration. The problem with the former is that atlases are not always a good match, since they do not account for the slicing angle. The drawback of the latter is that 3D to 3D registration methods are not only computationally expensive but also require a full set of consecutive sections which are not always available due to technical limitations. In this study, we propose a deep learning-based approach, to automatically detect the position and angle of individual mouse brain sections in the 3D reference atlas. The novel method is implemented as a pipeline consisting of 3 blocks of Convolutional Neural Network (CNN) regression models that detect the slicing angle and the position of the section in the anterior-posterior (AP) axis of the brain. The proposed method not only generates matching 2D atlases by taking the slicing angle into account but is also considerably faster and more robust to histological artifacts, compared to 3D registration approaches. We have shown that predictions of our method are comparable to a neuroscientist expert.
2022
Medical Imaging 2022: Image Processing
on line
FEB 20-MAR 27, 2022
12032
Sadeghi, M.; Neto, P.; Ramos-Prats, A.; Castaldi, F.; Paradiso, E.; Mahmoodian, N.; Ferraguti, F.; Goebel, G.
Automatic 2D to 3D localization of histological mouse brain sections in the reference atlas using deep learning / Sadeghi, M.; Neto, P.; Ramos-Prats, A.; Castaldi, F.; Paradiso, E.; Mahmoodian, N.; Ferraguti, F.; Goebel, G.. - 12032:(2022). (Intervento presentato al convegno Medical Imaging 2022: Image Processing tenutosi a on line nel FEB 20-MAR 27, 2022) [10.1117/12.2604231].
File in questo prodotto:
Non ci sono file associati a questo prodotto.
Pubblicazioni consigliate

Licenza Creative Commons
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11380/1344992
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 1
social impact