Convolution neural networks for real-time needle detection and localization in 2D ultrasound.
Int J Comput Assist Radiol Surg
; 13(5): 647-657, 2018 May.
Article
em En
| MEDLINE
| ID: mdl-29512006
ABSTRACT
PURPOSE:
We propose a framework for automatic and accurate detection of steeply inserted needles in 2D ultrasound data using convolution neural networks. We demonstrate its application in needle trajectory estimation and tip localization.METHODS:
Our approach consists of a unified network, comprising a fully convolutional network (FCN) and a fast region-based convolutional neural network (R-CNN). The FCN proposes candidate regions, which are then fed to a fast R-CNN for finer needle detection. We leverage a transfer learning paradigm, where the network weights are initialized by training with non-medical images, and fine-tuned with ex vivo ultrasound scans collected during insertion of a 17G epidural needle into freshly excised porcine and bovine tissue at depth settings up to 9 cm and [Formula see text]-[Formula see text] insertion angles. Needle detection results are used to accurately estimate needle trajectory from intensity invariant needle features and perform needle tip localization from an intensity search along the needle trajectory.RESULTS:
Our needle detection model was trained and validated on 2500 ex vivo ultrasound scans. The detection system has a frame rate of 25 fps on a GPU and achieves 99.6% precision, 99.78% recall rate and an [Formula see text] score of 0.99. Validation for needle localization was performed on 400 scans collected using a different imaging platform, over a bovine/porcine lumbosacral spine phantom. Shaft localization error of [Formula see text], tip localization error of [Formula see text] mm, and a total processing time of 0.58 s were achieved.CONCLUSION:
The proposed method is fully automatic and provides robust needle localization results in challenging scanning conditions. The accurate and robust results coupled with real-time detection and sub-second total processing make the proposed method promising in applications for needle detection and localization during challenging minimally invasive ultrasound-guided procedures.Palavras-chave
Texto completo:
1
Coleções:
01-internacional
Base de dados:
MEDLINE
Assunto principal:
Ultrassonografia
/
Redes Neurais de Computação
/
Imagens de Fantasmas
/
Anestesia Epidural
/
Agulhas
Tipo de estudo:
Diagnostic_studies
/
Prognostic_studies
Limite:
Animals
Idioma:
En
Ano de publicação:
2018
Tipo de documento:
Article