Learning 3D medical image keypoint descriptors with the triplet loss | Zendy

Nicolas Loiseau--Witon | Zendy; Razmig Kéchichian | Zendy; Sébastien Valette | Zendy; Adrien Bartoli | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

Learning 3D medical image keypoint descriptors with the triplet loss

Author(s) -

Nicolas Loiseau--Witon,

Razmig Kéchichian,

Sébastien Valette,

Adrien Bartoli

Publication year - 2021

Publication title -

international journal of computer assisted radiology and surgery

Language(s) - English

Resource type - Journals

SCImago Journal Rank - 0.701

H-Index - 49

eISSN - 1861-6429

pISSN - 1861-6410

DOI - 10.1007/s11548-021-02481-3

Subject(s) - computer science , artificial intelligence , benchmark (surveying) , affine transformation , matching (statistics) , pattern recognition (psychology) , labeled data , image (mathematics) , computer vision , synthetic data , mathematics , statistics , geodesy , pure mathematics , geography

We propose to learn a 3D keypoint descriptor which we use to match keypoints extracted from full-body CT scans. Our methods are inspired by 2D keypoint descriptor learning, which was shown to outperform hand-crafted descriptors. Adapting these to 3D images is challenging because of the lack of labelled training data and high memory requirements.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research