Verhaert : AI assisted robotic spinal surgery

digital rendering of a robotic arm scanning a patient lying on a surgical table

DSP member Verhaert Masters in Innovation has received a research grant from VLAIO to develop state-of-the-art artificial intelligence (AI-)driven robot technology.

In the research project, Verhaert will develop a robotic platform for spinal surgery which uses algorithms developed by Deep Learning (AI). The developed algorithms will transform high resolution preoperative 3D images, like CT scans and MRIs, to high resolution images of the patient in his or her new physical laying position during surgery. The novel part of the proposed procedure is the significant reduction of the use of cancerogenous ionizing x-ray beams during surgery, like CT-scans, while still being able to perform sub-millimeter surgery and catheter tracking.

3-step surgical procedure
Defining the concept
The physical laying position of the patient changes before, at the start and during surgery, which has an impact on the physical position and form of the spinal cord. All these changes in position need to be taken into account in order to perform sub-mm surgery.

  • Before: the patient is laying on her back for high resolution CT/MRI scans.
  • At the start: the patient is laying on her stomach.
  • During: the patient is laying on her stomach and slightly moves because of breathing, heartbeat and the impact of the surgery itself.
Overview of the patient’s physical position before, at the start, and during surgery © VERHAERT

 Before surgery

A high resolution sub millimeter 3D image is taken from the patient several days before surgery. This is done either by a CT-scan or MRI. Typically, the scan is taken while the patient is laying on his/her back. Based on the image the surgery is planned and a trajectory is calculated in order to reach the desired location in the spinal cord.

Before surgery the patient is lying on her back for high resolution CT/MRI scans © VERHAERT

At the start of surgery
At this stage the patient will be laying on his/her stomach. Markers are placed on the patient which are detected by a set of Infra-Red cameras in order to create a 3D model of the patients’ physical position on the operating table. In this new position, a low dose low resolution (supra-millimeter) 2D image is take of the patients’ spine. The 2D image is taken with a C-arm 2D fluoroscopic scanner.

At the start of the surgery the patient is laying on her stomach © VERHAERT

The 2D image and the external marker localizations are used to transform the high resolution pre-surgery 3D image into a newly reconstructed high resolution 3D image of the spine in its new position and form. At this point, the surgeon and its team has a 3D image of the patients’ anatomy in combination with an external reference frame.

This article was written by the Verheart Team

You can visit Verhaert at their website and follow them at their social media accounts:

AI-based platform Hai brings COVID-related safety awareness to the public

To help face COVID-19 and ensure both health and well-being, the European service provider in product innovation Verhaert Masters in Innovation developed ‘Hai’: a digital demonstrator platform, based on user-centered Artificial Intelligence.
New platform Hai for safer behavior

After 3 months of lockdown, strong regulations, and economic struggle, we’re carefully going back to our “normal” life. It’s a challenge to find the right balance between the well-being and health of the population, and a steady recovery after this critical period. 

To provide an answer to this challenging situation, Verhaert developed a demonstrator of a digital platform that uses AI-based Computer Vision to extract essential metrics from any room or area. The ‘Hai’ platform can bring COVID-related safety awareness to the public, allowing them to make informed decisions. It’s not a surveillance system, but a tool to empower people with relevant data about a specific space and to nudge them in a positive way towards a safer behavior. 

Components of the AI system

The digital platform consists of 3 components:

  1. Cameras to record a live feed of the people present in a particular area, the people entering and leaving the place.
  2. An edge AI system to process the footage on-the-fly. The system extracts the number of people, how many of them wear face masks, and measures the physical distance between individuals.
  3. Online dashboard to display this information in a friendly and educational way. 

Let’s say you work at your desk and you want to get something from the cafeteria. On the dashboard, you can see whether or not you should wait a while until fewer people are present at that place.
Artificial Intelligence algorithms

Verhaert’s AILab trained the AI algorithms to calculate the number of people present in any space and detect how many of them are wearing face masks. What about the security and protection of private data? The cameras’ live feed never leaves the AI system. The edge AI device treats the information locally and only transfers processed and anonymous data to the dashboard. No human being sees, stores or transfers any images, safeguarding everyone’s identity and privacy.

Hai is about our health

The online platform is a tool to organize ourselves and our spaces, it doesn’t judge individuals. It allows us to access real-time information from anywhere to make informed consent whether or not to enter a room. Hai will display the total number of people in an area versus the maximum quantity allowed. Additionally, it creates a heat map of “close-encounters” (distance less than 1.5 meters) giving valuable information for cleaning, disinfecting, optimizing walking flows, and detecting bottlenecks.

Hai is about you

Hai will recognize in the near future  your gestures, so if you wave hello to the camera or raise a thumb, Hai will respond interactively. The digital platform has been created to demonstrate how AI technology can help us in managing our presence and common spaces better during COVID. Ensuring we all stay safe, not only at home.

– – – – – –


Since 1969, Verhaert Masters in Innovation has pioneered the field of product innovation. As a leading innovation group in integrated product development, Verhaert assists companies and entrepreneurs in the development and implementation of successful innovation processes. The group now has more than 200 employees with offices in Kruibeke, Gentbrugge, Kortrijk, Nivelles, Noordwijk, Utrecht and Aveiro.

For more information, please visit our website.

Nicky Sterck, Communicatie Verhaert Masters in Innovation
T +32 3 250 19 00 – M +32 491 24 98 64 – Jochem Grietens, Coordinator AILab at Verhaert Masters in Innovation
T +32 3 250 19 00 –

You can visit Verhaert at their website and follow them via their social media channels

This is a press release from the Verhaert Team

Deltaray keeps the momentum going

In June 2020, Flemish startup Deltaray launched their disruptive X-ray technology: 3D Xray equipment for 100% inspection of mission-critical mechanical parts. Since then, they’ve been making a splash.

Officially launched

From 15 to 17 June, they held an open house at Averana Hasselt, Deltaray’s automation partner, which was featured not only in the Gazet van Antwerpen but also garnered visual attention from Flemish television channel Kanaal Z.

Making waves

In the midst of the Covid-19 crisis, the Deltaray team has seen their hard work pay off with two recent accolades:

Belgian finalist for the TAFTIE e-pitch 16th of June : Deltaray
  • Just last week, the Tech Tour Photonics Programme announced Deltaray had been selected for their 2020 edition
    • Designed by entrepreneurs for startups developing tech solutions in the photonics field, the program includes a series of online sessions and a 2-day live event that would take place in September 2020 (date will be announced soon) in Eindhoven, The Netherlands.

As befits an exciting startup, the Deltaray team is actively looking ahead. We’ll be watching for new developments – stay tuned!

You can visit Deltaray’s website and follow them on LinkedIn

Covid-19 Innovation Leads to Prestigious Nomination for Flemish StartUp Edgise

Data News Awards for Excellence

Each year, Data News, Roularta Media’s ICT journal, presents its Awards for Excellence. Aimed at IT professionals, including CIOs, general managers, HR and Finance managers, the magazine has a strong focus on Belgian news, trends and opinions, making the awards prestigious within the Belgian IT and data world. This year, DSP Valley startup member Edgise has caught attention for their Covid-19 innovation. They are nominated for not one but two categories:

  • Artificial Intelligence Innovator of the Year
  • Belgian StartUp Company of the Year

We spoke to Edgise co-founder Nick Destrycker to find out a bit more about their nominations, what’s gotten them this far, and what they’re looking forward to.

A crumpled piece of paper on a sketch book of ideas

Innovation in Covid-19 lockdown

As with most of Europe, when Covid-19 came to Belgium in early 2020, lock down soon followed. Economic and business rhythm changes ensued in turn, as official health measures forced a rapid realignment of public spaces. Many companies saw business change in an instant, and Edgise was no exception. According to Nick, Edgise saw an immediate impact as projects stalled or were withdrawn.

Not to be discouraged, the team called upon the enterprising spirit that defines successful startups. As Nick puts it, they “started thinking about how we as a company could mean something to society.” With social distancing the order of the day, they quickly focused on the need to monitor occupancy rates in buildings, which they realized would be key to ending an almost total lock down.

As health officials around the world have continuously explained, the pandemic can be contained by limiting (large) gatherings and maximizing distance among people who don’t live together. Enforcing this means being able to tell whether a space is close to capacity. In other words, being able to tell how many people are in a given store, museum, office, or whatever building at any given time.

The Edgise team combined their engineering know-how with some edge AI — meaning it operates at the device level rather than continuously connecting to a remote server — to come up with a simple, privacy-proof solution. Enter their newest technology: “Telly.”

We started thinking about how we as a company could mean something to society.

Nick Destrycker, Co-founder Edgise

Telly to the rescue

As Nick explains, “Telly provides real-time overviews of how many people are present in buildings. It is a small device that can smartly count people without any privacy exposure. Via a small low-power camera and an intelligent AI algorithm, Telly can recognize people and detect their movements (in or out of the building). This all happens without recording the video images. Multiple Tellys can also be connected [to each other] if the building has multiple entrances or exits.”

Telly’s versatility, and by consequence its award-worthy Covid-19 innovation, comes from its ability to be smart and dumb at the same time. It’s smart because it’s using AI. This means that the cameras can harness artificial intelligence to also analyze the images they see. For example, far from just counting the number of people entering and exiting a building, Telly can be integrated with a voice or chat system to proactively send alerts about occupancy rates. It could also be used to detect whether someone is wearing a mask (or not).

Telly – Face mask detection

Wearing a face mask protects you and others from the spread of the coronavirus. But how do we encourage people to wear one? 😷Follow Telly for more updates and check the link in comments for more info 👇🏼

Geplaatst door Edgise op Dinsdag 16 juni 2020

Simultaneously, the system is “dumb” in the sense that it’s not storing or recognizing sensitive images. Edgise has cleverly avoided sensitive privacy issues by not recording the images and not integrating facial recognition technology. Telly can pick up whether you’re wearing a mask, but she’s not picking up who you are.

Where to from here

Currently, Telly is monitoring activity at 15 different locations, including both office and retail space. That’s absolutely just the beginning for Nick and his colleagues. “We see many opportunities for Telly in the future, both in retail and in office buildings, factories, other public buildings, etc., both today and in the future.”

And of course, there’s the awards to look forward to. Edgise is a strong competitor for both categories thanks to the innovative edge AI technology in Telly. The jury is currently deliberating and the winners will be highlighted in September 29th issue of Data News.

We’ll be staying tuned!

Visit Edgise at their website and follow them via their social media channels

What tangible benefits can AI technology provide for companies?

On 12 September 2019, the Artificial Intelligence Applied in Industry symposium at KU Leuven Campus De Nayer (Sint-Katelijne-Waver) addressed this question.

The symposiums centered on two main topics: analysis of time series data and applications of Deep Learning. More and more companies have started to collect more and more data; however, it is often not easy — especially for smaller companies — to derive useful conclusions from their data. Analysis of time series data (data collected over a specifically determined amount of time), is a key task for many companies, who wish to monitor their production or business processes in a (semi-)automated way. Deep Learning is the driving force behind recent innovations in computer vision, natural language processing, and many other domains. Both themes are directly relevant to today’s business needs.

Organized by the KU Leuven research groups Embedded and Artificially Intelligent Vision Engineering (EAVISE) and Declarative Languages and Artificial Intelligence (DTAI), the symposium presented results from two Technology Transfer (TETRA) projects: Intelligent Analysis of Time Series and Start to Deep Learn. Crucially, TETRA projects like these involve industrial-academic cooperation. Thus, a consortium of more than 20 industrial partners helped organize the symposium. In this case, a consortium of more than 20 industrial partners collaborated with KU Leuven. Both TETRA projects are funded by the Flemish Agency for Innovation and Entrepreneurship (VLAIO), ensuring that the most up-to-date technology is used to address the most industrially relevant use cases.

The event started with dr. Jan Van Haaren, head of Data & Analytics at SciSports, discussing the development of a new football performance metric. While previous metrics focused exclusively on technical and physical aspects, his team has come up with a new method that also addresses the mental pressure under which a player has to perform. They developed a machine learning model to estimate how much mental pressure the player possessing the ball experiences using a combination of match context features and the current game state. Given the extreme pressure put on top players, it can provide football clubs with a significant competitive advantage, using machine learning models to provide actionable insights for football clubs. He succinctly set the theme of the day: artificial intelligence and intelligent analysis benefits for real-life companies and situations.

Added value from temporal data

First on the agenda were results from the TETRA project Intelligent Analysis of Time Series, which ran from October 2017 to September 2019 and helped companies to derive added value from temporal data. The researchers investigated a number of case studies, aimed at a number of specific sectors, including machine manufacturing/maintenance, providers of complex ICT infrastructure and services. They attempted to use existing technology to analyze analogue, discrete and spatiotemporal time series. At the symposium, they presented results from three different case studies.

  • oXya – Automated detection of anomalies in SAP
    The first talk presented a collaboration between KU Leuven and oXya, an international company specializing in custom-made SAP solutions for other companies. As part of the project’s user group, oXya wants to automate the process of detecting anomalies in SAP server transactions for easier maintenance and faster response times. For this, KU Leuven researchers developed a framework that trains several models of the expected system behavior, and raises an alarm when the expected results differ significantly from the measured values.
  • TenForce – leveraging past audits to predict future performance
    TenForce helps customers in the utility sector audit maintenance sites. For them, the KU Leuven teams devised a system to optimize inspection rounds by leveraging past audits to predict future subcontractor performance. The system uses a Bayesian Network to model an audit, which is then used to generate a distribution over possible audit outcomes by means of Monte Carlo simulation. These distributions allow one to rank the open sites according to expected performance.
  • Skyline Communications – Alarm sequence similarities
    Skyline Communications specializes in network management and operational support for broadcast, telco, cable, satellite and mobile industries. One of their key challenges is to handle the large number of alarms that may occur, due to, e.g., poorly configured customer thresholds or cascading alerts. The KU Leuven researchers investigated a method for finding similarities between different sequences of alarms, based on graph isomorphism algorithms.

Deep learning technology for local companies

The second part of the symposium concerned the ongoing TETRA project Start To Deep Learn. The aim of this project, which runs from September 2018 to October 2020, is to facilitate local companies in the adoption of deep learning technology through hands-on workshops, seminars and real-life use cases on computer vision and AI. Again, participants showcased three case studies.

  • Colruyt – occupancy degree and privacy
    The first case study was conducted in collaboration with Colruyt. Like many modern companies, Colruyt allows employees to reserve meeting rooms and flex-desks. To ensure that these resources are used effectively, they want to monitor their occupancy, while still respecting their employees’ privacy.  The KU Leuven researchers have proposed an approach to detect occupancy degrees on low-resolution omnidirectional video. To safeguard privacy, they are processing the data locally on an embedded platform and at reduced image resolution, achieving high accuracy for resolutions as low as 32px.
    side-by-side of high resolution and low resolution images of people in a room showing the AI recognition of human shapes
  • Reliability computer vision systems
    The second case study focused on the reliability of computer vision systems. Thanks to recent advances, computer vision is now routinely used in safety-critical applications. However, targeted attacks might be able to deceive such a system. Researchers are exploring this vulnerability by designing a specific patch that a person can hold in front of his or her torso to become undetectable by a state-of-the-art deep learning vision system. Using a method similar to training a neural network, they have already been able to automatically generate such an adversarial patch.
    two young men standing next to each other, one with a colorful panel at his torso. The AI only recognizes the man without the panel as a person.
  • Eurofins – Rapid, automated image comparison
    The company Eurofins came to the research groups needing to develop a method for fast image comparison, for use in their newest digital TV testing solution. The solution involves testing the functionality of on-screen displays of new TVs image against the image from a camera pointed towards the TV. The KU Leuven teams compared several older image comparison techniques against Deep Learning, and found that the latter clearly outperformed the others, even without training.

Tangible benefits of AI research is a win-win

Ultimately, the symposium presented several successful instances of academic-industrial cooperation through funding schemes like these VLAIO-funded TETRA projects. The cases convincingly demonstrated the added value of such collaborations, both for companies (access to state-of-the-art science and technology) and researchers (access to real-world problems and datasets).

Moreover, the presentations illustrated diverse tangible benefits of using AI for companies. For example, Eurofins has already commercially implemented the findings of their case – that AI image comparison vastly outperforms surpasses previously used testing methods. The researchers demonstrated that companies can already use Deep Learning and intelligent analysis for efficiency monitoring, detecting SAP anomalies, and work planning based on previous performance. These are not just promises of technology to come, but evincible, realizable implementations from which companies could immediately profit.

Find out more and watch a short video of the symposium here.