Your browser doesn't support javascript.
loading
Artificial Intelligence for Surgical Safety: Automatic Assessment of the Critical View of Safety in Laparoscopic Cholecystectomy Using Deep Learning.
Mascagni, Pietro; Vardazaryan, Armine; Alapatt, Deepak; Urade, Takeshi; Emre, Taha; Fiorillo, Claudio; Pessaux, Patrick; Mutter, Didier; Marescaux, Jacques; Costamagna, Guido; Dallemagne, Bernard; Padoy, Nicolas.
Afiliación
  • Mascagni P; ICube, University of Strasbourg, CNRS, IHU Strasbourg, France.
  • Vardazaryan A; Fondazione Policlínico Universitario A. Gemelli IRCCS, Rome, Italy.
  • Alapatt D; ICube, University of Strasbourg, CNRS, IHU Strasbourg, France.
  • Urade T; ICube, University of Strasbourg, CNRS, IHU Strasbourg, France.
  • Emre T; IHU-Strasbourg, Institute of Image-Guided Surgery, Strasbourg, France.
  • Fiorillo C; ICube, University of Strasbourg, CNRS, IHU Strasbourg, France.
  • Pessaux P; Fondazione Policlínico Universitario A. Gemelli IRCCS, Rome, Italy.
  • Mutter D; IHU-Strasbourg, Institute of Image-Guided Surgery, Strasbourg, France.
  • Marescaux J; Institute for Research against Digestive Cancer (IRCAD), Strasbourg, France.
  • Costamagna G; Department of Digestive and Endocrine Surgery, University of Strasbourg, Strasbourg, France.
  • Dallemagne B; Institute for Research against Digestive Cancer (IRCAD), Strasbourg, France.
  • Padoy N; Department of Digestive and Endocrine Surgery, University of Strasbourg, Strasbourg, France.
Ann Surg ; 275(5): 955-961, 2022 05 01.
Article en En | MEDLINE | ID: mdl-33201104
OBJECTIVE: To develop a deep learning model to automatically segment hepatocystic anatomy and assess the criteria defining the critical view of safety (CVS) in laparoscopic cholecystectomy (LC). BACKGROUND: Poor implementation and subjective interpretation of CVS contributes to the stable rates of bile duct injuries in LC. As CVS is assessed visually, this task can be automated by using computer vision, an area of artificial intelligence aimed at interpreting images. METHODS: Still images from LC videos were annotated with CVS criteria and hepatocystic anatomy segmentation. A deep neural network comprising a segmentation model to highlight hepatocystic anatomy and a classification model to predict CVS criteria achievement was trained and tested using 5-fold cross validation. Intersection over union, average precision, and balanced accuracy were computed to evaluate the model performance versus the annotated ground truth. RESULTS: A total of 2854 images from 201 LC videos were annotated and 402 images were further segmented. Mean intersection over union for segmentation was 66.6%. The model assessed the achievement of CVS criteria with a mean average precision and balanced accuracy of 71.9% and 71.4%, respectively. CONCLUSIONS: Deep learning algorithms can be trained to reliably segment hepatocystic anatomy and assess CVS criteria in still laparoscopic images. Surgical-technical partnerships should be encouraged to develop and evaluate deep learning models to improve surgical safety.
Asunto(s)
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Enfermedades de los Conductos Biliares / Colecistectomía Laparoscópica / Aprendizaje Profundo Tipo de estudio: Prognostic_studies Límite: Humans Idioma: En Revista: Ann Surg Año: 2022 Tipo del documento: Article País de afiliación: Francia Pais de publicación: Estados Unidos
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Enfermedades de los Conductos Biliares / Colecistectomía Laparoscópica / Aprendizaje Profundo Tipo de estudio: Prognostic_studies Límite: Humans Idioma: En Revista: Ann Surg Año: 2022 Tipo del documento: Article País de afiliación: Francia Pais de publicación: Estados Unidos