This paper presents LoRIS (Localized Reconstruction-by-Inpainting with Single-mask), a novel weakly-supervised anomaly detection technique designed to identify knee joint recess distension in musculoskeletal ultrasound images, which are noisy and unbalanced (as distended cases are rarer). In this context, supervised techniques require a high number of annotated images of both classes (distended and non-distended). On the other hand, we show that existing unsupervised anomaly detection techniques, which can be trained with images from a single class, are ineffective and often unable to correctly localize the anomaly. To overcome these issues, LoRIS is trained with non distended images only and uses the recess bounding box as location prior to guide the reconstruction. Experimental results show that LoRIS outperforms state-of-the-art unsupervised anomaly detection techniques. When compared to a state-of-the-art fully supervised solution, LoRIS presents similar performance but has two key advantages: during training it requires images from a single class only, and it also outputs the recess segmentation, without the need for segmentation annotations.
LoRIS - Weakly-Supervised Anomaly Detection for Ultrasound Images / M. Colussi, D. Ahmetovic, G. Civitarese, C. Bettini, A. Solyman, R. Gualtierotti, F. Peyvandi, S. Mascetti (LECTURE NOTES IN COMPUTER SCIENCE). - In: Simplifying Medical Ultrasound / [a cura di] A. Gomez, B. Khanal, A. King, A. Namburete. - [s.l] : Springer Nature, 2024 Oct 05. - ISBN 978-3-031-73646-9. - pp. 198-208 (( Intervento presentato al 5. convegno International Workshop on Advances in Simplifying Medical Ultrasound tenutosi a Marrakech nel 2024 [10.1007/978-3-031-73647-6_19].
LoRIS - Weakly-Supervised Anomaly Detection for Ultrasound Images
M. Colussi
;D. Ahmetovic;G. Civitarese;C. Bettini;A. Solyman;R. Gualtierotti;F. Peyvandi;S. Mascetti
2024
Abstract
This paper presents LoRIS (Localized Reconstruction-by-Inpainting with Single-mask), a novel weakly-supervised anomaly detection technique designed to identify knee joint recess distension in musculoskeletal ultrasound images, which are noisy and unbalanced (as distended cases are rarer). In this context, supervised techniques require a high number of annotated images of both classes (distended and non-distended). On the other hand, we show that existing unsupervised anomaly detection techniques, which can be trained with images from a single class, are ineffective and often unable to correctly localize the anomaly. To overcome these issues, LoRIS is trained with non distended images only and uses the recess bounding box as location prior to guide the reconstruction. Experimental results show that LoRIS outperforms state-of-the-art unsupervised anomaly detection techniques. When compared to a state-of-the-art fully supervised solution, LoRIS presents similar performance but has two key advantages: during training it requires images from a single class only, and it also outputs the recess segmentation, without the need for segmentation annotations.File | Dimensione | Formato | |
---|---|---|---|
24-asmus.pdf
accesso riservato
Descrizione: Paper pre-print
Tipologia:
Post-print, accepted manuscript ecc. (versione accettata dall'editore)
Dimensione
1.2 MB
Formato
Adobe PDF
|
1.2 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
978-3-031-73647-6_19.pdf
accesso riservato
Tipologia:
Publisher's version/PDF
Dimensione
1.22 MB
Formato
Adobe PDF
|
1.22 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.