- Title: 3D tool predicts nose jobs more accurately
- Date: 26th October 2016
- Summary: WIDE OF WOMAN'S FACE BEING PHOTOGRAPHED POINT OF VIEW SHOW OF RESEARCHER POINTING CAMERA TOWARDS WOMAN CLOSE OF GREEN MARKER LIGHT UNDER WOMAN'S NOSE MORE OF WOMAN BEING PHOTOGRAPHED (SOUNDBITE) (English) ARNE JANSEN, RESEARCHER AT THE MEANINGFUL INTERACTIONS LAB (MINTLAB), WITHIN THE UNIVERSITY OF LEUVEN, SAYING: "With a special lens, a 3D lens, we take three shots of the face from three different angles. And those are then, in existing software, off-the-shelf software; those are then stitched together into one 3D image. We then load that image into our own software and there we can, after a little while of processing, we can cut away the hair. We need to cut away the hair because that's really too much detail for the software to handle and could mess up the calculations made later. And then we have to pinpoint the landmarks onto the face which are used to know exactly where the nose is and also to know what the characteristics of the face are."
- Embargoed: 10th November 2016 12:06
- Keywords: University of Leuven rhinoplasty nose job prosthetic 3D software mintlab
- Location: LEUVEN, BELGIUM
- City: LEUVEN, BELGIUM
- Country: Belgium
- Topics: Information Technologies / Computer Sciences,Science
- Reuters ID: LVA00355N7AL7
- Aspect Ratio: 16:9
- Story Text: Having plastic surgery of any kind is a major decision, but knowing how you'll look in advance of going under the knife can help dispel some of the anxiety. Surgeons have been using imaging software for some time to help patients visualise the results of prospective work. But researchers from Belgium have developed software they say can help surgeons deliver even better results, while increasing the interaction with their patients.
At the Meaningful Interactions Lab (mintlab), a research group of the University of Leuven and research institute IMEC, they've collaborated with a consortium of research partners and companies to develop a 3D tool to accurately simulate the outcome of nose surgery. The tool uses a combination of facial modelling statistics with morphing algorithms. The 'average nose' is used as a baseline, computed based on the characteristics of a couple of hundreds of faces in their database.
The first step involves off-the-shelf components: three photographs are taken of the patient's face from three different angles with a 3D lens and then computer software stitches the images together into a complete 3D model.
"We combined this with an algorithm that was based on faces that were scanned - a lot of faces were scanned - so that the algorithm could calculate what a realistic nose could look like. So in Photoshop you could very easily make like a Pinocchio nose and that's really unrealistic, but with this software we've managed to keep the boundaries to what's really realistic," researcher Arne Jansen told Reuters.
The software integrates a number of predefined parameters - such as the shape of the nose bridge or nostril - and makes those easy to manipulate using the program, ultimately providing surgeons and their patients with a user-friendly 3D tool that helps them better visualise the outcome of a nose job.
While cosmetic procedures are one focus of the project, they believe it also has important applications in anaplastology; helping design prosthetic noses for patients who have had to have theirs amputated, often as a result of nasal cancer.
"This is for patients, most of the time due to cancer, had to get their nose taken off. And so they need a nose prosthesis. And the software can look at the same characteristics of the face and use that to calculate a nose that is fitting for this particular face. And so what the software won't do is make a general nose; make one nose for all - it will make a characteristic nose that you can still alter towards the needs of the patients," said Jansen.
By taking into account the landmarks on the face the tool can 'predict' a perfectly fitting whole new nose - even though there is no existing nasal structure to base it on. This can then be manipulated in the software to give the patient exactly what they want.
Once imported into their software, they manually locate a number of key facial features that the algorithm uses to generate a well-suited nose.
"We have to pinpoint the landmarks on the face, and typically that's the two cheekbones and then the tip of the nose... and the corners of the eyes. And if you have those, the software can then generate based on the data model it has, based on all the scans it did before, it can generate a nose that is really fitting for that face, that is realistic for that face. Not necessarily the perfect nose, but fitting that can then be adjusted towards the needs of the patient," added Jansen.
- Copyright Holder: REUTERS
- Copyright Notice: (c) Copyright Thomson Reuters 2016. Open For Restrictions - http://about.reuters.com/fulllegal.asp
- Usage Terms/Restrictions: None