Real-time instance segmentation of surgical instruments using attention and multi-scale feature fusion.

Cerón, Juan Carlos Ángeles; Ruiz, Gilberto Ochoa; Chang, Leonardo; Ali, Sharib

Cerón, Juan Carlos Ángeles; Ruiz, Gilberto Ochoa; Chang, Leonardo; Ali, Sharib.

Afiliação

Cerón JCÁ; Tecnologico de Monterrey, Escuela de Ingeniería y Ciencias, Mexico.
Ruiz GO; Tecnologico de Monterrey, Escuela de Ingeniería y Ciencias, Mexico. Electronic address: gilberto.ochoa@tec.mx.
Chang L; Tecnologico de Monterrey, Escuela de Ingeniería y Ciencias, Mexico.
Ali S; Institute of Biomedical Engineering (IBME), Department of Engineering Science, University of Oxford, Oxford, UK; Oxford NIHR Biomedical Research Centre, University of Oxford, Oxford, UK; School of Computing, University of Leeds, Leeds, UK. Electronic address: s.s.ali@leeds.ac.uk.

Med Image Anal ; 81: 102569, 2022 10.

Article em En | MEDLINE | ID: mdl-35985195

RESUMO

Precise instrument segmentation aids surgeons to navigate the body more easily and increases patient safety. While accurate tracking of surgical instruments in real-time plays a crucial role in minimally invasive computer-assisted surgeries, it is a challenging task to achieve, mainly due to: (1) a complex surgical environment, and (2) model design trade-off in terms of both optimal accuracy and speed. Deep learning gives us the opportunity to learn complex environment from large surgery scene environments and placements of these instruments in real world scenarios. The Robust Medical Instrument Segmentation 2019 challenge (ROBUST-MIS) provides more than 10,000 frames with surgical tools in different clinical settings. In this paper, we propose a light-weight single stage instance segmentation model complemented with a convolutional block attention module for achieving both faster and accurate inference. We further improve accuracy through data augmentation and optimal anchor localization strategies. To our knowledge, this is the first work that explicitly focuses on both real-time performance and improved accuracy. Our approach out-performed top team performances in the most recent edition of ROBUST-MIS challenge with over 44% improvement on area-based multi-instance dice metric MI_DSC and 39% on distance-based multi-instance normalized surface dice MI_NSD. We also demonstrate real-time performance (>60 frames-per-second) with different but competitive variants of our final approach.

Assuntos

Cirurgia Assistida por Computador; Instrumentos Cirúrgicos; Atenção; Humanos; Processamento de Imagem Assistida por Computador; Procedimentos Cirúrgicos Minimamente Invasivos

Palavras-chave

Attention; Deep learning; MIS instance segmentation; Multi-scale feature fusion; Real-time; Single-stage

Texto completo

Adicionar na Minha BVS

Imprimir

XML

PubMed Links

Buscar no Google

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Instrumentos Cirúrgicos / Cirurgia Assistida por Computador Limite: Humans Idioma: En Revista: Med Image Anal Assunto da revista: DIAGNOSTICO POR IMAGEM Ano de publicação: 2022 Tipo de documento: Article País de afiliação: México País de publicação: Holanda

Texto completo

Adicionar na Minha BVS

Imprimir

XML

PubMed Links

Buscar no Google