Application of Deep Learning for Real-Time Ablation Zone Measurement in Ultrasound Imaging.

ablation techniques artificial intelligence computer-assisted image processing radiofrequency ablation ultrasonography

Journal

Cancers
ISSN: 2072-6694
Titre abrégé: Cancers (Basel)
Pays: Switzerland
ID NLM: 101526829

Informations de publication

Date de publication:
27 Apr 2024
Historique:
received: 03 04 2024
revised: 24 04 2024
accepted: 26 04 2024
medline: 11 5 2024
pubmed: 11 5 2024
entrez: 11 5 2024
Statut: epublish

Résumé

The accurate delineation of ablation zones (AZs) is crucial for assessing radiofrequency ablation (RFA) therapy's efficacy. Manual measurement, the current standard, is subject to variability and potential inaccuracies. This study aims to assess the effectiveness of Artificial Intelligence (AI) in automating AZ measurements in ultrasound images and compare its accuracy with manual measurements in ultrasound images. An in vitro study was conducted using chicken breast and liver samples subjected to bipolar RFA. Ultrasound images were captured every 15 s, with the AI model Mask2Former trained for AZ segmentation. The measurements were compared across all methods, focusing on short-axis (SA) metrics. We performed 308 RFA procedures, generating 7275 ultrasound images across liver and chicken breast tissues. Manual and AI measurement comparisons for ablation zone diameters revealed no significant differences, with correlation coefficients exceeding 0.96 in both tissues ( The study validates the Mask2Former model as a promising tool for automating AZ measurement in RFA research, offering a significant step towards reducing manual measurement variability.

Sections du résumé

BACKGROUND BACKGROUND
The accurate delineation of ablation zones (AZs) is crucial for assessing radiofrequency ablation (RFA) therapy's efficacy. Manual measurement, the current standard, is subject to variability and potential inaccuracies.
AIM OBJECTIVE
This study aims to assess the effectiveness of Artificial Intelligence (AI) in automating AZ measurements in ultrasound images and compare its accuracy with manual measurements in ultrasound images.
METHODS METHODS
An in vitro study was conducted using chicken breast and liver samples subjected to bipolar RFA. Ultrasound images were captured every 15 s, with the AI model Mask2Former trained for AZ segmentation. The measurements were compared across all methods, focusing on short-axis (SA) metrics.
RESULTS RESULTS
We performed 308 RFA procedures, generating 7275 ultrasound images across liver and chicken breast tissues. Manual and AI measurement comparisons for ablation zone diameters revealed no significant differences, with correlation coefficients exceeding 0.96 in both tissues (
CONCLUSION CONCLUSIONS
The study validates the Mask2Former model as a promising tool for automating AZ measurement in RFA research, offering a significant step towards reducing manual measurement variability.

Identifiants

pubmed: 38730652
pii: cancers16091700
doi: 10.3390/cancers16091700
pii:
doi:

Types de publication

Journal Article

Langues

eng

Auteurs

Corinna Zimmermann (C)

Erbe Elektromedizin GmbH, 72072 Tübingen, Germany.

Adrian Michelmann (A)

Erbe Elektromedizin GmbH, 72072 Tübingen, Germany.

Yannick Daniel (Y)

Erbe Elektromedizin GmbH, 72072 Tübingen, Germany.

Markus D Enderle (MD)

Erbe Elektromedizin GmbH, 72072 Tübingen, Germany.

Nermin Salkic (N)

Erbe Elektromedizin GmbH, 72072 Tübingen, Germany.
Faculty of Medicine, University of Tuzla, 75000 Tuzla, Bosnia and Herzegovina.

Walter Linzenbold (W)

Erbe Elektromedizin GmbH, 72072 Tübingen, Germany.

Classifications MeSH