Cancer: How AI architects are constructing the future of radiotherapy

A quantum leap in cancer treatment? Artificial intelligence (AI) could optimize the planning process for radiation therapy and reduce waiting times for patients from weeks to just hours. Read how concept designer Fernando Vega and team aim to achieve this goal – in part seven of our #Futureshaper series.

 8 min
Katja Gäbelein
Published on 10. Juli 2023

Whether waiting for an appointment with a specialist physician, or for medication that you've ordered, or to finally hear your name called in the waiting room: long waits for medical care – or anything, really – are annoying. In some cases, though, waiting can prove life-threatening. This is the case when cancer patients have to wait to begin radiation therapy that they urgently need.

Radiotherapy1 to treat cancer is a complex process, involving a number of different steps and technologies. Planning radiation treatment takes a long time – currently about two weeks, from when therapy is prescribed until treatment actually starts. "When it comes to cancer, time is a crucial factor. It can make the difference between life and death in some cases," Fernando Vega notes earnestly.

A method for treating cancer by applying ionizing radiation to destroy cancer cells. It can hinder cell division or kill the cancer cells outright, thereby reducing the size of malignant tumors or fully destroying them.
A close-up photo of part of Fernando Vega's face, showing a section of his glasses, one eye, and part of his nose against a light-blue background.
He and his colleagues have taken up the fight against waiting time. While AI-trained large language models are on the cusp of revolutionizing the conversational interaction between humans and machines, Vega and his team are collaborating closely with clinical partners to bring about an AI revolution of an entirely different, less visible sort.

Slightly low-angle portrait shot of Fernando Vega taken from the side. Orange-colored ceiling lighting is visible in the background, slightly out of focus.

Vega sits, focused on this computer, with multiple monitors displaying CT, PET-CT and MRI scans of a cancer patient. The tumor growing in the left half of a patient's brain shows brightly visible and distinctly contrasted on the screens.

A medical imaging technology that combines positron emission tomography (PET) with computed tomography (CT) for the purpose of generating detailed images of metabolic activities and anatomical structures in the body.

Fernando Vega, who originally hails from Colombia, is a computer scientist and specialist in medical imaging and software applications. At Siemens Healthineers, he leads Software & Concept Definition at the “Cancer Therapy Imaging" unit of the Varian Business Area. "One question we ask ourselves is: How can we optimize and speed up the entire radiation therapy planning and delivery workflow – with the help of AI?"

This is the question that Vega and a large team of colleagues from various business areas are jointly seeking to answer. While Siemens Healthineers already offers a comprehensive portfolio of equipment and systems for radiotherapy, AI integration is poised to soon make much more possible.

Following the merger in April 2021, one sector the Varian Business Area has been focusing on within the framework of the company’s Comprehensive Cancer Care strategy is the development of AI. Their objective: to create a world without fear of cancer.
What exactly can AI improve in the workflow? To understand this, we need to examine the process as it works today: Vega explains that, basically, from the point in time when radiotherapy is prescribed until radiation treatment begins, four steps are needed.

Are you also interested in joining our enthusiastic team?

Visit our career portal

In this first step, the radiation oncologist2 examines the findings to date and discusses the potential benefits, risks and type of radiation with the cancer patient.

Radiation oncologists are physicians who specialize in the treatment of cancer by radiotherapy. They plan and manage radiation treatment while closely collaborating with other medical specialists.

The radiation oncologist enters this information into an oncology information system. The physician's scheduling staff then coordinate with the patient to set up an imaging appointment, as highly precise medical images provide the basis for subsequent treatment. Ideally, an appointment is scheduled for the patient within a few days. This completes the first step in the process. 

Vega then outlines how the scenario would play out in the workflow improved by AI. The initial substeps of consulting with the patient, prescribing radiation therapy, and data input in the information system would remain the same. However, the follow-up appointment scheduling would be controlled by AI in the oncology information system. Vega explains: "The AI would already know exactly what type of scan the patient needs based on the stored information, and could also see which suitable scanner is available the soonest. This could reduce waiting times."

Oncology information systems such as ARIA OIS serve to document the treatment cycles of patients receiving radiotherapy. This enables medical personnel to plan their workflows.
Read more at:
Compared to today's process, the second step – imaging as the basis for radiation planning – would also benefit from using AI.
Oncology information systems such as ARIA OIS serve to document the treatment cycles of patients receiving radiotherapy. This enables medical personnel to plan their workflows.
Read more at:
The third step comprises creating a three-dimensional radiation plan – the most complex and time-intensive operation within the process. Cancer patients today have to wait several days for this to happen. In meticulously detailed work, a team of medical experts generate a digital simulation in a sort of "ping-ponging" of activities.

Part of the planning process consists of what's called contouring – a complex and time-consuming step. On the generated medical images (i.e. the CT, PET-CT and/or MRI scans), the area to be treated – such as the tumors – are delineated from the surrounding healthy tissue. The organs-at-risk  (OARs, for short) which need to be protected during the radiation treatment are clearly identified. 

Vega explains that, in standard clinical practice depending on the given country or hospital, this contouring of the OARs is performed by resident physicians of the radiation oncology department, medical technical radiology assistants (MTRA), medical physicists3, or medical dosimetrists. However, this manual process is susceptible to error. Automatic contouring could already lead to improvements today, providing automated contouring of the OARs.

They are experts in medical physics and work closely together with radiologists and radiation oncologists to optimize medical imaging and radiation therapy.
Radiation planning can only proceed once the OARs have been contoured: As Vega explains, "patients have to deal with waiting times in this phase as well." The radiation oncologist now takes the reins again, reviewing the organ contouring, subsequently defining the areas to be treated (such as the tumors), and then ultimately approving the digital anatomy of the patient for dosimetric planning.

The medical physicist – and thus the patient as well – is meanwhile waiting. Only once the OARs and target areas have been clearly defined and approved can the medical physicist begin calculating the exact dose of the individual radiation sessions in what is termed the fractionation. 

This dosimetry plan, too, must in turn then receive the "blessing" of the radiation oncologist. "What's more, these physicians are generally very busy in their daily clinical routines, and often difficult to reach," Vega adds. Yet, this step must also be completed before the patient can finally be brought in to begin radiation treatment.

Senior AI research scientist Chloé Audigier is conducting research aimed at creating a digital twin of the human liver. Such models can help physicians simulate multiple treatment options.

Read more
So, what could our research scientists improve by way of the envisaged AI-supported workflow? "We could shorten the waiting times for everyone involved to an absolute minimum, and custom-tailor radiotherapy more individually to each patient," says Vega.

AI can improve the coordination between the planning steps. Errors in contouring can be reduced by optimally setting the scanners in advance to the needs of each patient and the therapy to be applied. In addition, more precise information for planning can be gleaned from the personalized imaging, for example on tumor movement, tumor cell spread, and the likelihood of therapy proving successful.

Senior AI research scientist Chloé Audigier is conducting research aimed at creating a digital twin of the human liver. Such models can help physicians simulate multiple treatment options.

Read more

Based on the results of precise automated contouring, planning software could automatically calculate the correct dose plan for radiotherapy. The AI-controlled oncology information system that supports all steps across the entire process could notify the radiation oncologist automatically that the plans are ready for final review. 

The team in charge of planning the radiation treatment would be informed in real time by the information system of which radiation planning has been completed. Considering the available systems and personnel, it could assign each patient the earliest possible appointment to begin treatment. In the overall process of preparing radiotherapy plans, this would reduce not only the "ping-ponging" of activities and thus the waiting times, but also any potential sources of error.

The RapidPlan software program utilizes existing treatment plans on the basis of machine learning to automatically generate optimized radiotherapy planning.
Read more
Whole body photo of Fernando Vega from a bird's-eye view. He stands with his arms folded across his chest, smiling as he looks upward. Strikingly patterned tiled flooring can be seen in the background. A quotation from Vega is overlayed across the image: "For me, it's a dream come true that I have the privilege to help work on these solutions."

Vega then explains today's current workflow for the fourth step in the whole process: the actual radiation treatment. The tumor is treated with X-rays using a linear accelerator (LINAC). The objective is to kill the cancer cells and prevent further cell division from occurring. The treatment appointments at which dose fractions are administered are generally scheduled over multiple weeks.

LINACs use electricity to generate, among other things, high-energy X-rays. This radiation can be used for a broad range of purposes. One of the most widely used applications is in the treatment of cancer by killing cancer cells.

How could AI improve the workflow of the actual radiation treatment? "In cases of lung cancer, for instance, the tumors could be identified automatically in the image and the radiation predictively adjusted in real time to the patient's breathing movements. This could give us even more precise results," Vega explains.

Direct i4D serves to prevent motion artefacts during CT scanning – which enables more precise planning of radiotherapy. Click on the following link to read more about how #Futureshaper Christian Hofmann and his team developed the algorithmic solution for this purpose.

Read more

Summing it all up: Radiotherapy planning today is marked by significant loss of time because the medical team has to coordinate various systems and workflows. The process takes on average several weeks.

Vega says that if all of these systems could in future think "as one" thanks to AI, there would be practically no unnecessary waiting times: "Our vision is to shorten the wait to a just few hours between when radiotherapy is prescribed and actual radiation treatment begins."

LINACs use electricity to generate high-energy X-rays or eletron beams. This radiation can be used for a broad range of purposes. One of the most widely used applications is in the treatment of cancer by killing cancer cells.

What's more, AI would enable all therapy to be custom-tailored more individually to each patient, leading to better treatment results – and thus, combined with the time savings, helping people live longer. 

It would also benefit daily clinical routines, as AI can accelerate repetitive, recurring tasks. This can ease the burden on clinical staff and help cut costs by enhancing efficiency.

One thing is clear: an undertaking like this, that comprises so many work steps and different devices and systems, cannot be done by one person. As Fernando Vega – who very soon needs to join a video call with his international colleagues – knows well, it takes many keen minds.

Are you, too, interested in joining our highly motivated team? Come visit us at the Career Portal of Siemens Healthineers.

Career Portal

"We still have a long way to go until we will be able to implement the full vision on our devices and systems." Vega is well aware of this fact – especially considering that the predevelopment project would need to be scalable. Moving forward, additional areas such as imaging for early cancer detection and laboratory diagnostics could be integrated into the AI-optimized workflow. The objective of all this is to establish a solid, networked solution for cancer centers that enable comprehensive, full-service care along the entire cancer treatment pathway – from early detection to follow-up care.

In any case, the inveterate innovator Fernando Vega, who even listens to audio books about AI while jogging after work, is fascinated by artificial intelligence and the potential it holds for the future. Yet, all the while remaining circumspect:

© Photos: Markus Ulbrich
© Video: Lisa Fiedler (camera, editing); Markus Ulbrich (camera); Cagdas Cubuk (camera, sound); Katja Gäbelein (concept, direction) 
© Motion Graphics: Viola Wolfermann

By Katja Gäbelein

Katja Gäbelein works as an editor in corporate communications at Siemens Healthineers, and specializes in technology and innovation topics. She writes for text and film media. 

Assistant editor: Guadalupe Sanchez