SAM: Self-Supervised Learning of Pixel-Wise Anatomical Embeddings in Radiological Images

Radiological images such as computed tomography (CT) and X-rays render anatomy with intrinsic structures. Being able to reliably locate the same anatomical structure across varying images is a fundamental task in medical image analysis. In principle it is possible to use landmark detection or semant...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on medical imaging 2022-10, Vol.41 (10), p.2658-2669
Hauptverfasser:	Yan, Ke, Cai, Jinzheng, Jin, Dakai, Miao, Shun, Guo, Dazhou, Harrison, Adam P., Tang, Youbao, Xiao, Jing, Lu, Jingjing, Lu, Le
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Body parts Computed tomography Contrastive learning Datasets Embedding follow-up lesion matching Image analysis Image processing Image registration Image segmentation landmark detection Lesions Medical imaging pixel-wise embedding Pixels Prediction algorithms Self-supervised learning Semantic segmentation Semantics Supervised learning Task analysis Three-dimensional displays Training X-rays
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!