Detail publikace

Iterative machine learning based rotational alignment of brain 3D CT data

Originální název

Iterative machine learning based rotational alignment of brain 3D CT data

Anglický název

Iterative machine learning based rotational alignment of brain 3D CT data

Jazyk

en

Originální abstrakt

The optimal rotational alignment of brain Computed Tomography (CT) images to a required standard position has a crucial importance for both automatic and manual diagnostic analysis. In this contribution, we present a novel two-step iterative approach for the automatic 3D rotational alignment of brain CT data. The angles of axial and coronal rotations are determined by an unsupervised by localisation of the Midsagittal Plane (MSP) method. This includes detection and pairing of medially symmetrical feature points. The sagittal rotation angle is subsequently estimated by regression convolutional neural network (CNN). The proposed methodology has been evaluated on a dataset of CT data manually aligned by radiologists. It has been shown that the algorithm achieved the low error of estimated rotations (1 degree) and in a significantly shorter time than the experts (2 minutes per case).

Anglický abstrakt

The optimal rotational alignment of brain Computed Tomography (CT) images to a required standard position has a crucial importance for both automatic and manual diagnostic analysis. In this contribution, we present a novel two-step iterative approach for the automatic 3D rotational alignment of brain CT data. The angles of axial and coronal rotations are determined by an unsupervised by localisation of the Midsagittal Plane (MSP) method. This includes detection and pairing of medially symmetrical feature points. The sagittal rotation angle is subsequently estimated by regression convolutional neural network (CNN). The proposed methodology has been evaluated on a dataset of CT data manually aligned by radiologists. It has been shown that the algorithm achieved the low error of estimated rotations (1 degree) and in a significantly shorter time than the experts (2 minutes per case).

BibTex


@inproceedings{BUT157792,
  author="Jiří {Chmelík} and Roman {Jakubíček} and Tomáš {Vičar} and Petr {Walek} and Petr {Ouředníček} and Jiří {Jan}",
  title="Iterative machine learning based rotational alignment of brain 3D CT data",
  annote="The optimal rotational alignment of brain Computed Tomography (CT) images to a required standard position has a crucial importance for both automatic and manual diagnostic analysis. In this contribution, we present a novel two-step iterative approach for the automatic 3D rotational alignment of brain CT data. The angles of axial and coronal rotations are determined by an unsupervised by localisation of the Midsagittal Plane (MSP) method. This includes detection and pairing of medially symmetrical feature points. The sagittal rotation angle is subsequently estimated by regression convolutional neural network (CNN). The proposed methodology has been evaluated on a dataset of CT data manually aligned by radiologists. It has been shown that the algorithm achieved the low error of estimated rotations (1 degree) and in a significantly shorter time than the experts (2 minutes per case).",
  address="IEEE",
  booktitle="2019 41th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)",
  chapter="157792",
  doi="10.1109/EMBC.2019.8857858",
  howpublished="print",
  institution="IEEE",
  year="2019",
  month="october",
  pages="4404--4408",
  publisher="IEEE",
  type="conference paper"
}