Vision Transformer and Multiview Classification for Lesion Detection in 3D Cranial Ultrasound - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Vision Transformer and Multiview Classification for Lesion Detection in 3D Cranial Ultrasound

Résumé

With increasing advances in the field of medical brain imaging, we can now assess the presence of punctate white matter lesions (PWML) in the preterm infant. While some studies report a link between these lesions and adverse long-term outcomes, automatic detection of PWML through ultrasound (US) imaging could better assist doctors in diagnosis, at a lower cost than MRI. Many papers focus on MR biomedical image benchmark datasets, but few methods seem to tackle the detection of very small lesions in US images, because it is really challenging due to high class imbalance and low contrast. In this work, we propose a two-phase strategy: 1) Segmentation with a vision transformer to increase the number of detected lesions. 2) Multi-view classification of the lesions predicted in the output mask to reduce the number of false alarms and improve precision. We also compare 3 methods of preprocessing for input data. As a result, our method achieves better performances for PWML detection in US images compared to the best published models, with recall and precision reaching 82% and 60% respectively.
Fichier principal
Vignette du fichier
Estermann-23_IEEE-IUS_ViT_and_Multi_View_Classification_for_Lesion_Detection_in_3DcUS_0.pdf (861.68 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04285810 , version 1 (15-11-2023)

Identifiants

Citer

Flora Estermann, Valérie Kaftandjian, Philippe Guy, Philippe Quetin, Philippe Delachartre. Vision Transformer and Multiview Classification for Lesion Detection in 3D Cranial Ultrasound. 2023 IEEE International Ultrasonics Symposium (IUS), Sep 2023, Montreal, Canada. pp.1-5, ⟨10.1109/IUS51837.2023.10306345⟩. ⟨hal-04285810⟩
15 Consultations
27 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More