PWML Detection in 3D Cranial Ultrasound Volumes using Over-segmentation and Multimodal Classification with Deep Learning - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

PWML Detection in 3D Cranial Ultrasound Volumes using Over-segmentation and Multimodal Classification with Deep Learning

Résumé

Punctate white matter lesions (PWML) are the most common white matter injuries observed in preterm neonates. Automatic detection of these lesions could better assist doctors in diagnosis. Recent advances in deep learning have resulted in optimistic results on many MR biomedical image benchmark datasets, but few methods seem to tackle the detection of very small lesions in ultrasound images. In this paper, we propose a two-phase strategy. Firstly, we highlight the foreground information by aggregating the lesions in the ground truth along the coronal projection of the brain, then we train a segmentation network to detect PWML with the resulting oversegmented masks. Secondly, we introduce a novel deep architecture for multimodal classification, called 2.5D SC-Net, which is used to eliminate false alarms and improve specificity. Experimental results demonstrate the effectiveness of our method to detect PWML in ultrasound images, improving the recall by 15% compared to the best published models, while limiting the number of false alarms efficiently.
Fichier principal
Vignette du fichier
Estermann-23_PWML_Detection_in_3D_Cranial_Ultrasound_Volumes_using_Over_segmentation_and_Multimodal_Classification_with_Deep_Learning_VF (2).pdf (533.05 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04228359 , version 1 (04-10-2023)

Identifiants

Citer

Flora Estermann, Valérie Kaftandjian, Philippe Guy, Philippe Quetin, Philippe Delachartre. PWML Detection in 3D Cranial Ultrasound Volumes using Over-segmentation and Multimodal Classification with Deep Learning. 2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI), Apr 2023, Cartagena, Colombia. pp.1-5, ⟨10.1109/ISBI53787.2023.10230607⟩. ⟨hal-04228359⟩
40 Consultations
55 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More