Busca avançada
Ano de início
Entree


A Machine Learning Approach to Predict Instrument Bending in Stereotactic Neurosurgery

Texto completo
Autor(es):
Mostrar menos -
Granados, Alejandro ; Mancini, Matteo ; Vos, Sjoerd B. ; Lucena, Oeslle ; Vakharia, Vejay ; Rodionov, Roman ; Miserocchi, Anna ; McEvoy, Andrew W. ; Duncan, John S. ; Sparks, Rachel ; Ourselin, Sebastien ; Frangi, AF ; Schnabel, JA ; Davatzikos, C ; AlberolaLopez, C ; Fichtinger, G
Número total de Autores: 16
Tipo de documento: Artigo Científico
Fonte: MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2018, PT IV; v. 11073, p. 9-pg., 2018-01-01.
Resumo

The accurate implantation of stereo-electroencephalography (SEEG) electrodes is crucial for localising the seizure onset zone in patients with refractory epilepsy. Electrode placement may differ from planning due to instrument deflection during surgical insertion. We present a regression-based model to predict instrument bending using image features extracted from structural and diffusion images. We compare three machine learning approaches: Random Forest, Feed-Forward Neural Network and Long Short-Term Memory on accuracy in predicting global instrument bending in the context of SEEG implantation. We segment electrodes from post-implantation CT scans and interpolate position at 1mm intervals along the trajectory. Electrodes are modelled as elastic rods to quantify 3 degree-of-freedom (DOF) bending using Darboux vectors. We train our models to predict instrument bending from image features. We then iteratively infer instrument positions from the predicted bending. In 32 SEEG post-implantation cases we were able to predict trajectory position with a MAE of 0.49 mm using RF. Comparatively a FFNN had MAE of 0.71 mm and LSTM had a MAE of 0.93 mm. (AU)

Processo FAPESP: 17/23747-5 - Tractografia baseada em deep learning para planejamento cirúrgico no tratamento de epilepsia
Beneficiário:Oeslle Alexandre Soares de Lucena
Modalidade de apoio: Bolsas no Exterior - Estágio de Pesquisa - Mestrado
Processo FAPESP: 16/18332-8 - Segmentação de estruturas cerebrais de imagens de ressonância magnética utilizando deep learning
Beneficiário:Oeslle Alexandre Soares de Lucena
Modalidade de apoio: Bolsas no Brasil - Mestrado