Soft labels noise tolerant loss functions for transcranial Doppler ultrasound signal classification - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Soft labels noise tolerant loss functions for transcranial Doppler ultrasound signal classification

Résumé

Transcranial Doppler (TCD) is an ultrasound monitoring method that enables real-time measurements of blood flow velocity, primarily in the Middle Cerebral Artery. Its common application lies in monitoring patients at risk of stroke by effectively detecting micro-emboli. This is done through the detection of high intensity transient signals (HITS), which can be categorized between artifacts, gaseous emboli, and solid emboli. State-of-the-art methods for HITS classification are not able to capture the uncertainty of HITS soft-annotation, nor the noise in their soft-labels (soft-noise), both coming from the expert annotation doubt. To better handle this, we propose to train deep learning models using soft labels cost functions, such as the soft cross entropy and the Jensen-Shanon divergence (JSD), which directly approximates the soft distribution of the input samples instead of a hard label proxy. We evaluate the robustness of our approach against symmetrical soft label noise in terms of final hard classification (using the Matthews correlation coefficient, MCC) and human expert uncertainty capturing (using the Hellinger distance). The obtained models trained with JSD soft-labels were robust against soft-noise with improvements of up to 24% in terms of MCC. At last, these models were able to better capture the human expert uncertainty of the true labels, achieving Hellinger distance improvements up to 0.10 (relative gap of 16%).
Fichier principal
Vignette du fichier
Vindas-23_IEEE-IUS_Soft labels noise tolerant loss functions for TCD signal classification.pdf (632.81 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04285806 , version 1 (15-11-2023)

Identifiants

Citer

Yamil Vindas, Blaise Kévin Guépié, Marilys Almar, Emmanuel Roux, Philippe Delachartre. Soft labels noise tolerant loss functions for transcranial Doppler ultrasound signal classification. 2023 IEEE International Ultrasonics Symposium (IUS), Sep 2023, Montreal, Canada. pp.1-4, ⟨10.1109/IUS51837.2023.10308259⟩. ⟨hal-04285806⟩
15 Consultations
25 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More