Accurate and interpretable evaluation of surgical skills from kinematic data using fully convolutional neural networks - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Article Dans Une Revue International Journal of Computer Assisted Radiology and Surgery Année : 2019

Accurate and interpretable evaluation of surgical skills from kinematic data using fully convolutional neural networks

Résumé

Purpose Manual feedback from senior surgeons observing less experienced trainees is a laborious task that is very expensive, time-consuming and prone to subjec-tivity. With the number of surgical procedures increasing annually, there is an unprecedented need to provide an accurate, objective and automatic evaluation of trainees' surgical skills in order to improve surgical practice. Methods In this paper, we designed a convolutional neural network (CNN) to classify surgical skills by extracting latent patterns in the trainees' motions performed during robotic surgery. The method is validated on the JIGSAWS dataset for two surgical skills evaluation tasks: classification and regression. Results Our results show that deep neural networks constitute robust machine learning models that are able to reach new competitive state-of-the-art performance on the JIGSAWS dataset. While we leveraged from CNNs' efficiency, we were able to minimize its black-box effect using the class activation map technique. Conclusions This characteristic allowed our method to automatically pinpoint which parts of the surgery influenced the skill evaluation the most, thus allowing us to explain a surgical skill classification and provide surgeons with a novel personalized feedback technique. We believe this type of interpretable machine learning model could integrate within "Operation Room 2.0"
Fichier principal
Vignette du fichier
ijcars2019.pdf (3.38 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02434381 , version 1 (10-01-2020)

Identifiants

Citer

Hassan Ismail Fawaz, Germain Forestier, Jonathan Weber, Lhassane Idoumghar, Pierre-Alain Muller. Accurate and interpretable evaluation of surgical skills from kinematic data using fully convolutional neural networks. International Journal of Computer Assisted Radiology and Surgery, 2019, 14 (9), pp.1611-1617. ⟨10.1007/s11548-019-02039-4⟩. ⟨hal-02434381⟩

Collections

SITE-ALSACE IRIMAS
23 Consultations
62 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More