Skip to Content

Steady as She Goes

When Steven Dubowsky saw the details of Massachusetts General Hospital’s (MGH) planned proton beam therapy center several years ago, he immediately realized that its high-tech robotic apparatus for positioning patients was not nearly precise enough.

Dubowsky, a robotics expert at MIT and an advisor to the MGH facility, spent the next two and half years solving the problem. By writing an elaborate algorithm that compensates for imprecision inherent in the equipment and designing an array of sensors to detect the different sizes and shapes of patients, Dubowsky and coworkers at MIT improved the system’s accuracy by an order of magnitude. When the MGH facility, which will treat patients with inoperable brain tumors, opens within the next year, it will use software for the patient positioning apparatus based on Dubowsky’s work.

Proton treatment is favored over conventional X-ray radiation in treating some tumors precisely because it can target cells far more accurately. “The goal [of the facility] is to point a beam of radiation at the tumor and avoid treating nearby material,” says Michael Goitein, MGH’s project director. At least three other dedicated proton centers are being built in the United States. “I’m sure they’ll use this or similar software,” says Goitein.

While the facility’s initial plans called for targeting the proton beam with an accuracy within a half-millimeter, Dubowsky says early tests confirmed his hunch: The system, which is being built by Ion Beam Applications, a Belgium-based company, was actually achieving accuracy no better than 5 millimeters.

Dubowsky holds his forefinger and thumb slightly apart. “That’s about 5 millimeters.” Then he closes the gap, nearly touching his finger to the thumb. “And that’s about 0.5 millimeters.” It’s not a huge difference. But it could be the difference between life and death.

Keep Reading

Most Popular

Large language models can do jaw-dropping things. But nobody knows exactly why.

And that's a problem. Figuring it out is one of the biggest scientific puzzles of our time and a crucial step towards controlling more powerful future models.

OpenAI teases an amazing new generative video model called Sora

The firm is sharing Sora with a small group of safety testers but the rest of us will have to wait to learn more.

Google’s Gemini is now in everything. Here’s how you can try it out.

Gmail, Docs, and more will now come with Gemini baked in. But Europeans will have to wait before they can download the app.

This baby with a head camera helped teach an AI how kids learn language

A neural network trained on the experiences of a single young child managed to learn one of the core components of language: how to match words to the objects they represent.

Stay connected

Illustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at customer-service@technologyreview.com with a list of newsletters you’d like to receive.