Medical device giant Philips made a series of announcements this week at the Radiological Society of North America's annual meeting in Chicago, the most notable of which were the launch of a new CT machine and the development of a new helium-free MRI system.
Shez Partovi, Chief Innovation and Strategy Officer of Philips, said that the company’s new CT system, called Verida, is the world’s first energy spectrum CT system driven entirely by artificial intelligence. He explained that CT scanners use spectral detectors to capture multiple X-ray energy levels in each scan, and artificial intelligence is built directly into the imaging chain to improve clarity and reduce noise.
In his view, the key innovation is that the AI is built directly into the CT detector hardware, rather than just applied to the image after it is formed.
“As soon as the X-ray beam hits the patient, the AI says, ‘How do I optimize the signal and remove the noise and graininess?’ That’s the core of this machine, which is why we say it’s AI-powered end-to-end,” Partovi said.
He added that this end-to-end design means AI is involved in every step – from signal capture to patient positioning to correcting movements, such as the beating of the heart.
Philips plans to launch the new machine in select markets in 2026.
One of the other notable machines the company showed off during the conference was the BlueSeal Horizon MRI system, an upgraded version of last year's BlueSeal MRI model. Unlike the 1.5 T version due out in 2024, Horizon is a 3 T system, meaning it offers double the magnetic field strength. This means it can produce more detailed images and scan three times faster, Partovi said.
He also noted that the model, still in development, is helium-free, meaning its magnets are permanently sealed and don't require expensive helium refills or quenching tubes. This reduces operating costs and the complexity of installing scanners in hospitals.
Traditional MRI magnets typically require nearly 400 gallons of liquid helium to effectively cool the magnet's coils so they remain superconducting. Partovi noted that this makes MRI machines very heavy—which is why most of them are located on the first floor or basement of hospitals.
“Now they can be anywhere,” he declared.
Like the artificial intelligence in Verida CT machines, BlueSeal Horizon embeds artificial intelligence directly into the signal acquisition stage of MRI, not just the image. To achieve better image quality, the AI is designed to optimize the raw signal in real time as the magnet generates it from the body, Partovi explained.
By integrating AI at the hardware level and addressing operational barriers such as helium dependence, Philips not only seeks to improve image quality but also aims to make high-quality imaging more accessible and practical for hospitals, he said.
Photo: Milos Ruzicka, Getty Images
