The purpose of this study was to develop an automatic method for the segmentation of muscle cross-sectional area on transverse B-mode ultrasound images of gastrocnemius medialis using a convolutional neural network(CNN). In the provided dataset images with both normal and increased echogenicity are present. The manually annotated dataset consisted of 591 images, from 200 subjects, 400 relative to subjects with normal echogenicity and 191 to subjects with augmented echogenicity. From the DICOM files, the image has been extracted and processed using the CNN, then the output has been post-processed to obtain a finer segmentation. Final results have been compared to the manual segmentations. Precision and Recall scores as mean ± standard deviation for training, validation, and test sets are 0.96 ± 0.05, 0.90 ± 0.18, 0.89 ± 0.15 and 0.97 ±0.03, 0.89± 0.17, 0.90 ± 0.14 respectively. The CNN approach has also been compared to another automatic algorithm, showing better performances. The proposed automatic method provides an accurate estimation of muscle cross-sectional area in muscles with different echogenicity levels.

Automatic segmentation of ultrasound images of gastrocnemius medialis with different echogenicity levels using convolutional neural networks / Marzola, F.; Alfen, N. V.; Salvi, M.; De Santi, B.; Doorduin, J.; Meiburger, K. M.. - ELETTRONICO. - 2020:(2020), pp. 2113-2116. (Intervento presentato al convegno 42nd Annual International Conferences of the IEEE Engineering in Medicine and Biology Society, EMBC 2020 tenutosi a Montreal, QC, Canada nel 20-24 July 2020) [10.1109/EMBC44109.2020.9176343].

Automatic segmentation of ultrasound images of gastrocnemius medialis with different echogenicity levels using convolutional neural networks

Marzola F.;Salvi M.;De Santi B.;Meiburger K. M.
2020

Abstract

The purpose of this study was to develop an automatic method for the segmentation of muscle cross-sectional area on transverse B-mode ultrasound images of gastrocnemius medialis using a convolutional neural network(CNN). In the provided dataset images with both normal and increased echogenicity are present. The manually annotated dataset consisted of 591 images, from 200 subjects, 400 relative to subjects with normal echogenicity and 191 to subjects with augmented echogenicity. From the DICOM files, the image has been extracted and processed using the CNN, then the output has been post-processed to obtain a finer segmentation. Final results have been compared to the manual segmentations. Precision and Recall scores as mean ± standard deviation for training, validation, and test sets are 0.96 ± 0.05, 0.90 ± 0.18, 0.89 ± 0.15 and 0.97 ±0.03, 0.89± 0.17, 0.90 ± 0.14 respectively. The CNN approach has also been compared to another automatic algorithm, showing better performances. The proposed automatic method provides an accurate estimation of muscle cross-sectional area in muscles with different echogenicity levels.
2020
978-1-7281-1990-8
File in questo prodotto:
File Dimensione Formato  
EMBC_final.pdf

non disponibili

Descrizione: Articolo principale
Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 1.62 MB
Formato Adobe PDF
1.62 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
EMBC_2020_author.pdf

accesso aperto

Descrizione: Articolo principale
Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 1.59 MB
Formato Adobe PDF
1.59 MB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2874938