Learning shape distributions from large databases of healthy organs: applications to zero-shot and few-shot abnormal pancreas detection - Archive ouverte HAL Access content directly
Conference Papers Year :

Learning shape distributions from large databases of healthy organs: applications to zero-shot and few-shot abnormal pancreas detection

(1, 2, 3) , (1) , (1) , (4) , (1) , (5, 2, 3) , (6)
1
2
3
4
5
6

Abstract

We propose a scalable and data-driven approach to learn shape distributions from large databases of healthy organs. To do so, volumetric segmentation masks are embedded into a common probabilistic shape space that is learned with a variational auto-encoding network. The resulting latent shape representations are leveraged to derive zeroshot and few-shot methods for abnormal shape detection. The proposed distribution learning approach is illustrated on a large database of 1200 healthy pancreas shapes. Downstream qualitative and quantitative experiments are conducted on a separate test set of 224 pancreas from patients with mixed conditions. The abnormal pancreas detection AUC reached up to 65.41% in the zero-shot configuration, and 78.97% in the few-shot configuration with as few as 15 abnormal examples, outperforming a baseline approach based on the sole volume.
Fichier principal
Vignette du fichier
paper2366.pdf (1.82 Mo) Télécharger le fichier
Vignette du fichier
SupplementaryMaterial2366.pdf (287.75 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Origin : Files produced by the author(s)

Dates and versions

hal-03800705 , version 1 (10-10-2022)

Licence

Attribution - CC BY 4.0

Identifiers

Cite

Rebeca Vétil, Clément Abi Nader, Alexandre Bône, Marie-Pierre Vullierme, Marc-Michel Rohé, et al.. Learning shape distributions from large databases of healthy organs: applications to zero-shot and few-shot abnormal pancreas detection. Medical Image Computing and Computer Assisted Interventions, Sep 2022, Singapore, Singapore. pp.464-473, ⟨10.1007/978-3-031-16434-7_45⟩. ⟨hal-03800705⟩
8 View
3 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More