Eye-tracking – A first step towards an automated measure of success in cleft lip surgery

Lead researcher: Sophie Butterworth

Institution: Royal Victoria Infirmary, The Newcastle upon Tyne Hospitals NHS Foundation Trust

Completed July 2024

Repair of a cleft of the lip leaves a scar, and nearly always some visible difference in appearance of the lip such as asymmetry. Such differences in appearance can cause significant distress so it is important that surgery results in the ‘best’ outcome possible.

However, in order to know which method of lip repair gives the best outcomes, it is necessary to have a way of measuring how good the outcome of a lip repair is. At the moment studies which look at how good the outcomes of cleft lip repair are mainly use photographs. They measure the quality of the outcome by asking viewers to rate the quality of the repair. This is a subjective way of measuring and depends on the viewers using the same criteria in their assessment. It has been shown that assessing the outcomes of lip repair surgery using these sorts of measuring tools gives unreliable results which are difficult to repeat with the same result.

The researchers in this study want to use a more objective way of measuring lip repair outcomes, by looking at eye tracking. Eye tracking records the path the eyes take when looking at something. It is already known that people scan a face with their eyes in a particular way: there is a regular and predictable ‘scanpath’. The researchers hypothesise that a cleft of the lip will disrupt this usual scanpath, and that the better the repair, the closer to normal the scanpath will be after surgery.

In this initial study, the researchers will compare the scanpath of viewers looking at photographs of babies with an unrepaired cleft lip to the scanpath of the same viewers looking at photographs of the same children soon after their cleft lip repair and at 5 years of age. The aim is to see if the eye tracking technique can reliably differentiate between children with repaired and unrepaired clefts of the lip.

The researchers will also look to see if the amount of disruption of the usual scanpath is related to the ratings given to the lip repair using the more traditional subjective techniques. They hypothesise that a repaired cleft lip given a good subjective rating will have less disruption of the usual eye-tracking scanpath than a repaired cleft lip given a poor subjective rating.

This is the first stage of a developing an objective method of measuring the quality of a cleft lip repair.

Project Outcomes:

This project was the first step towards developing a reliable tool to measure the results of cleft lip surgery. By using eye-tracking technology, the team was able to study how surgeons look at photos of children before and after cleft lip repair. The findings showed that gaze patterns changed over time and, to some extent, could predict how surgeons rated the quality of the repair. Although agreement between surgeons was low, the results highlight the need for an objective tool that can give consistent, unbiased scores and help compare different surgical techniques fairly.

Alongside this, the team also created a facial image bank linked with the Cleft Collective, containing images of 170 children who consented to take part. This valuable resource will support future studies by combining images with other information such as cleft type, genetics and outcomes. Together, these achievements mark an important step towards building a standardised way of assessing cleft lip repair that could benefit patients, parents and surgeons in the years ahead.