A showcase of ÉTS researchers’ publications and other contributions

Assisting Surgeons with Artificial Intelligence


Downloads per month over past year

Agomma, Roseline Olory, Vázquez, Carlos, Cresson, Thierry and De Guise, Jacques. 4 July 2018. « Assisting Surgeons with Artificial Intelligence ». [Research article]. Substance ÉTS.

[thumbnail of Substance 2018 17180 Assisting Surgeons with Artificial Intelligence.pdf]
Substance 2018 17180 Assisting Surgeons with Artificial Intelligence.pdf - Published Version
Use licence: Creative Commons CC BY-NC.

Download (1MB) | Preview


Identifying information on X-rays is essential in establishing a diagnosis and planning a medical procedure. This process, usually performed manually by a radiologist, is repetitive, time-consuming and can produce highly variable results. The purpose of this work is to develop a fully automatic method based on convolutional neural networks (CNN) to estimate the anatomical area of thirteen lower limb landmarks on frontal X-rays. To estimate these anatomical areas, we started with an automatic identification of salient points in a database consisting of 180 frontal X-rays. Knowing the relative position of the thirteen landmarks points manually labelled by an expert, the proposed approach was to train a CNN on the displacement of each salient point toward each of the thirteen landmarks. Once training is complete, it is possible to predict and combine the displacement of each salient point to estimate the probable area where the landmarks are likely to be found. Mean Euclidean distances between the thirteen predicted points and those identified by an expert are 29 +/- 18 mm, which is acceptable for a reliable identification of the anatomical areas of each landmark.

Item Type: Non-peer reviewed article published in a journal or magazine
Refereed: No
Vázquez, Carlos
de Guise, Jacques A.
Affiliation: Génie logiciel et des technologies de l'information, Génie de la production automatisée
Date Deposited: 07 Aug 2018 14:51
Last Modified: 17 Jan 2020 21:06

Actions (login required)

View Item View Item