Surgical video analysis facilitates education and research. However, video recordings of endoscopic surgeries can contain privacy-sensitive information, especially if the endoscopic camera is moved out of the body of patients and out-of-body scenes are recorded. Therefore, identification of out-of-body scenes in endoscopic videos is of major importance to preserve the privacy of patients and operating room staff. This study developed and validated a deep learning model for the identification of out-of-body images in endoscopic videos. The model was trained and evaluated on an internal dataset of 12 different types of laparoscopic and robotic surgeries and was externally validated on two independent multicentric test datasets of laparoscopic gastric bypass and cholecystectomy surgeries. Model performance was evaluated compared to human ground truth annotations measuring the receiver operating characteristic area under the curve (ROC AUC). The internal dataset consisting of 356,267 images from 48 videos and the two multicentric test datasets consisting of 54,385 and 58,349 images from 10 and 20 videos, respectively, were annotated. The model identified out-of-body images with 99.97% ROC AUC on the internal test dataset. Mean ± standard deviation ROC AUC on the multicentric gastric bypass dataset was 99.94 ± 0.07% and 99.71 ± 0.40% on the multicentric cholecystectomy dataset, respectively. The model can reliably identify out-of-body images in endoscopic videos and is publicly shared. This facilitates privacy preservation in surgical video analysis.

Preserving privacy in surgical video analysis using a deep learning classifier to identify out-of-body scenes in endoscopic videos / J. Lavanchy, A. Vardazaryan, P. Mascagni, D. Mutter, N. Padoy, G.G. Laracca, G. Ludovica, C. Fiorillo, G. Quero, S. Alfieri, L. Baldari, E. Cassinotti, L. Boni, D. Cuccurullo, G. Costamagna, B. Dallemagne. - In: SCIENTIFIC REPORTS. - ISSN 2045-2322. - 13:1(2023 Jun 07), pp. 9235.1-9235.8. [10.1038/s41598-023-36453-1]

Preserving privacy in surgical video analysis using a deep learning classifier to identify out-of-body scenes in endoscopic videos

L. Baldari;E. Cassinotti;L. Boni;
2023

Abstract

Surgical video analysis facilitates education and research. However, video recordings of endoscopic surgeries can contain privacy-sensitive information, especially if the endoscopic camera is moved out of the body of patients and out-of-body scenes are recorded. Therefore, identification of out-of-body scenes in endoscopic videos is of major importance to preserve the privacy of patients and operating room staff. This study developed and validated a deep learning model for the identification of out-of-body images in endoscopic videos. The model was trained and evaluated on an internal dataset of 12 different types of laparoscopic and robotic surgeries and was externally validated on two independent multicentric test datasets of laparoscopic gastric bypass and cholecystectomy surgeries. Model performance was evaluated compared to human ground truth annotations measuring the receiver operating characteristic area under the curve (ROC AUC). The internal dataset consisting of 356,267 images from 48 videos and the two multicentric test datasets consisting of 54,385 and 58,349 images from 10 and 20 videos, respectively, were annotated. The model identified out-of-body images with 99.97% ROC AUC on the internal test dataset. Mean ± standard deviation ROC AUC on the multicentric gastric bypass dataset was 99.94 ± 0.07% and 99.71 ± 0.40% on the multicentric cholecystectomy dataset, respectively. The model can reliably identify out-of-body images in endoscopic videos and is publicly shared. This facilitates privacy preservation in surgical video analysis.
Settore MED/18 - Chirurgia Generale
7-giu-2023
Article (author)
File in questo prodotto:
File Dimensione Formato  
da inserire in AIR 2023-Preserving privacy in surgical video.pdf

accesso aperto

Tipologia: Publisher's version/PDF
Dimensione 1.62 MB
Formato Adobe PDF
1.62 MB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2434/979448
Citazioni
  • ???jsp.display-item.citation.pmc??? 0
  • Scopus 3
  • ???jsp.display-item.citation.isi??? 3
social impact