A recent study in The Lancet Oncology showed that AI found 20 percent more cancers on mammogram screens than radiologists alone.
Published in The Lancet Oncology, the study analyzed the scans of 80,000 Swedish women with a moderate hereditary risk of breast cancer who had undergone a mammogram between April 2021 and July 2022. Half of these scans were read by AI and then a radiologist to double-check the findings. The second group of scans was read by two researchers without the help of AI. (Currently, the standard of care across Europe is to have two radiologists analyze a scan before diagnosing a patient with breast cancer.)
The study showed that the AI group detected cancer in 6 out of every 1,000 scans, while the radiologists detected cancer in 5 per 1,000 scans. In other words, AI found 20 percent more cancers than the highly-trained radiologists.
Scientists have been using MRI images (like the ones pictured here) to train artificial intelligence to detect cancers earlier and with more accuracy. Here, MIT's AI system, MIRAI, looks for patterns in a patient's mammograms to detect breast cancer earlier than ever before. news.mit.edu
But even though the AI was better able to pinpoint cancer on an image, it doesn’t mean radiologists will soon be out of a job. Dr. Laura Heacock, a breast radiologist at NYU, said in an interview with CNN that radiologists do much more than simply screening mammograms, and that even well-trained technology can make errors. “These tools work best when paired with highly-trained radiologists who make the final call on your mammogram. Think of it as a tool like a stethoscope for a cardiologist.”
AI is still an emerging technology, but more and more doctors are using them to detect different cancers. For example, researchers at MIT have developed a program called MIRAI, which looks at patterns in patient mammograms across a series of scans and uses an algorithm to model a patient's risk of developing breast cancer over time. The program was "trained" with more than 200,000 breast imaging scans from Massachusetts General Hospital and has been tested on over 100,000 women in different hospitals across the world. According to MIT, MIRAI "has been shown to be more accurate in predicting the risk for developing breast cancer in the short term (over a 3-year period) compared to traditional tools." It has also been able to detect breast cancer up to five years before a patient receives a diagnosis.
The challenges for cancer-detecting AI tools now is not just accuracy. AI tools are also being challenged to perform consistently well across different ages, races, and breast density profiles, particularly given the increased risks that different women face. For example, Black women are 42 percent more likely than white women to die from breast cancer, despite having nearly the same rates of breast cancer as white women. Recently, an FDA-approved AI device for screening breast cancer has come under fire for wrongly detecting cancer in Black patients significantly more often than white patients.
As AI technology improves, radiologists will be able to accurately scan a more diverse set of patients at a larger volume than ever before, potentially saving more lives than ever.
A child sits on the cracked earth, staring at the sun.
When Rattan Lal was awarded the Japan Prize for Biological Production, Ecology in April—the Asian equivalent of a Nobel—the audience at Tokyo's National Theatre included the emperor and empress. Lal's acceptance speech, however, was down-to-earth in the most literal sense.
Carbon, in its proper place, holds landscapes and ecosystems together.
"I'd like to begin, rather unconventionally, with the conclusion of my presentation," he told the assembled dignitaries. "And the conclusion is four words: In soil we trust."
That statement could serve as the motto for a climate crisis-fighting strategy that has gained remarkable momentum over the past five years or so—and whose rise to international prominence was reflected in that glittering award ceremony. Lal, a septuagenarian professor of soil science at Ohio State University, is one of the foremost exponents of carbon farming, an approach that centers on correcting a man-made, planetary chemical imbalance.
A Solution to Several Problems at Once?
The chemical in question is carbon. Too much of it in the atmosphere (in the form of carbon dioxide, a potent greenhouse gas) is the main driver of global heating. Too little of it in the soil is the bane of farmers in many parts of the world, and a threat to our ability to feed a ballooning global population. Advocates say agriculture can mitigate both problems—by adopting techniques that keep more soil carbon from escaping skyward, and draw more atmospheric carbon down into fields and pastures.
The potential impacts go beyond slowing climate change and boosting food production. "There are so many benefits," says Lal. "Water quality, drought, flooding, biodiversity—this is a natural solution for all these problems." That's because carbon, in its proper place, holds landscapes and ecosystems together. Plants extract it from the air and convert it into sugars for energy; they also transfer it to the soil through their roots and in the process of decomposition. In the ground, carbon feeds microbes and fungi that form the basis of complex food webs. It helps soil absorb and retain water, resist erosion, and hold onto nitrogen and phosphorous—keeping those nutrients from running off into waterways and creating toxic algal blooms.
Government and private support for research into carbon-conscious agriculture is on the rise, and growing numbers of farmers are exploring such methods. How much difference these methods can make, however, remains a matter of debate. Lal sees carbon farming as a way to buy time until CO2 emissions can be brought under control. Skeptics insist that such projections are overly optimistic. Some allies, meanwhile, think Lal's vision is too timid. "Farming can actually fix the climate," says Tim LaSalle, co-founder of the Center for Regenerative Agriculture at California State University, Chico. "That should be our only focus."
Yet Can soil solve the climate crisis? may be not be the key question in assessing the promise of carbon farming, since it implies that action is worthwhile only if a solution is ensured. A more urgent line of inquiry might be: Can the climate crisis be solved without addressing soil?
A Chance Meeting Leads to the Mission of a Lifetime
Lal was among the earliest scientists to grapple with that question. Born in Pakistan, he grew up on a tiny subsistence farm in India, where his family had fled as refugees. The only one of his siblings who learned to read and write, he attended a local agricultural university, then headed to Ohio State on scholarship for his PhD. In 1982, he was working at the International Institute of Tropical Agriculture in Nigeria, trying to develop sustainable alternatives to Africa's traditional slash-and-burn farming, when a distinguished visitor dropped by: oceanographer Roger Revelle, who 25 years earlier had published the first paper warning that fossil fuel combustion could throw the climate dangerously off-kilter.
Rattan Lal, Distinguished University Professor of Soil Science at Ohio State, received the Japan Prize at a ceremony in April.
(Photo: Ken Chamberlain. CFAES.)
Lal showed Revelle the soil in his test plots—hard and reddish, like much of Africa's agricultural land. Then (as described in Kristin Ohlson's book The Soil Will Save Us), he led the visitor to the nearby forest, where the soil was dark, soft, and wriggling with earthworms. In the forest, the soil's carbon content was 2 to 3 percent; in Lal's plots, it had dwindled to 0.5 percent. When Revelle asked him where all that carbon had gone, Lal confessed he didn't know. Revelle suggested that much of it might have floated into the atmosphere, adding to the burden of greenhouse gases. "Since then," Lal told me, "I've been looking for ways to put it back."
Back at Ohio State, Lal found that the United States Department of Agriculture (USDA) and Environmental Protection Agency (EPA) were also interested in the connection between soil carbon and climate change. With a small group of other scientists, he began investigating the dimensions of the problem, and how it might be solved.
Comparing carbon in forested and cultivated soils around the globe, the researchers calculated that about 100 billion tons had vanished into the air since the dawn of agriculture 10,000 years ago. The culprits were common practices—including plowing, overgrazing, and keeping fallow fields bare—that exposed soil carbon to oxygen, transforming it into carbon dioxide. Yet the process could also be reversed, Lal and his colleagues argued. Although there was a limit to the amount of carbon that soil could hold, they theorized that it would be possible to sequester several billion tons of global CO2 emissions each year for decades before reaching maximum capacity.
Lal set up projects on five continents to explore practices that could help accomplish that goal, such as minimizing tillage, planting cover crops, and leaving residue on fields after harvest. He organized conferences, pumped out papers and books. As other researchers launched similar efforts, policymakers worldwide took notice.
But before long, recalls Colorado State University soil scientist Keith Paustian (a fellow carbon-farming pioneer, who served with Lal on the UN's International Panel on Climate Change), official attention "kind of faded away. The bigger imperative was to cut emissions." And because agriculture accounted for only about 13 percent of greenhouse gas pollution, Paustian says, the sectors that emitted the most—energy and transportation—got the bulk of funding.
A Movement on the Rise
In recent years, however, carbon farming has begun to look like an idea whose time has come. One factor is that efforts to reduce emissions haven't worked; in 2018 alone, global CO2 output rose by an estimated 2.7 percent, according to the Global Carbon Project. Last month, researchers from the Scripps Institute of Oceanography reported that atmospheric CO2—under 350 ppm when Lal began his quest—had reached 415 ppm, the highest in 3 million years. And with the world's population expected to approach 10 billion by 2050, the need for sustainable technologies to augment food production has grown increasingly pressing.
Today, carbon-conscious methods are central to the burgeoning movement known as "regenerative agriculture," which also embraces other practices aimed at improving soil health and farming in an ecologically sound (though not always strictly organic) manner. In the United States, the latest Farm Bill includes $25 million to incentivize soil-based carbon sequestration. State and local governments across the country are supporting such efforts, as are at least a dozen nonprofits. The Department of Energy's Advanced Projects Research Agency (ARPA-e) is working to develop crops and technologies aimed at increasing soil carbon accumulation by 50 percent. General Mills recently announced plans to advance regenerative farming on 1 million acres by 2030, and many smaller companies have made their own commitments.
The toughest challenge, Lal suggests, may be persuading farmers to change their ways.
Internationally, the biggest initiative is the French-led "4 per 1,000" initiative, which aims to increase the amount of carbon in the soil of farms and rangelands worldwide by 0.4 percent per year—a rate that the project's website contends would "halt the increase of CO2 (carbon dioxide) concentration in the atmosphere related to human activities."
Given the current pace of research, Lal believes that goal—which equates to sequestering 3.6 billion tons of CO2 annually, or 10 percent of global emissions—is doable. The toughest challenge, he suggests, may be persuading farmers to change their ways. Although carbon farming can reduce costs for chemical inputs such as herbicides and fertilizers, while building rich topsoil, agriculturalists tend to be a conservative lot.
And getting low-income farmers to leave crop residue on fields, instead of using it for fuel or animal feed, will require more than speeches about melting glaciers. Lal proposes a $16 per acre subsidy, totaling $64 billion for the world's 4 billion acres of cropland. "That's not a very large amount," he says, "if you're investing in the health of the planet."
Experimental Methods Attract Supporters and Skeptics
Some experts question whether enough CO2 can be stashed in the soil to prevent the rise in average global temperature from surpassing the 2º C mark—set by the 2016 Paris Agreement as the limit beyond which climate change would become catastrophic. But others insist that carbon farming's goal should be to reverse climate change, not just to put it on pause.
"That's the only way out of this predicament," says Tim LaSalle, whose Center for Regenerative Agriculture supports the use of experimental methods ranging from multi-species cover cropping to fungal-dominant compost solutions. Using such techniques, a few researchers and farmers claim to be able to transfer carbon to the soil at rates many times higher than with established practices. Although several of these methods have yet to be documented in peer-reviewed studies, LaSalle believes they point the way forward. "We can't fix the climate, or even come close to it, using Rattan's numbers," he says, referring to Lal. "If we can replicate these experiments, we can fix it."
Even scientists sympathetic to regenerative ag warn that relying on unproven techniques is risky. "Some of these claims are beyond anything we've seen in agricultural science," says Andrew McGuire, an agronomist at Washington State University. "They could be right, but extraordinary claims require extraordinary evidence."
Still, the assorted methods currently being tested—which also include amending soil with biochar (made by heating agricultural wastes with minimal oxygen), planting long-rooted perennial crops instead of short-rooted annuals, and deploying grazing animals in ways that enrich soil rather than depleting it—offer a catalogue of hope at a time when environmental despair is all too tempting.
Last October, the National Academy of Sciences, Engineering, and Medicine issued a report acknowledging that it was too late to stave off apocalyptic overheating just by reducing CO2 emissions; removing carbon from the atmosphere would be necessary as well. The document laid out several options for doing so—most of which, it cautioned, had serious limitations.
"Soil is a bridge to the future. We can't do without it."
One possibility was planting more forests. To absorb enough carbon dioxide, however, trees might have to replace areas of farmland, reducing the food supply. Another option was creating biomass plantations to fuel power plants, whose emissions would be stored underground. But land use would be a problem: "You'd need to cover an area the size of India," explains Paustian, who was a co-author of the report. Yet another alternative was direct-air capture, in which chemical processes would be used to extract CO2 from the air. The technology was still in its infancy, though—and the costs and power requirements would likely be astronomical.
The report took up agriculture-based methods on page 95. Those needed further research as well, the authors wrote, to determine which approaches would be most effective. But of all the alternatives, this one seemed the least problematic. "Soil carbon is probably what you can do first, cheapest, and with the most additional co-benefits," says Paustian. "If we can make progress in that area, it's a huge advantage."
In any case, he and other researchers agree, we have little choice but to try. "Soil is a bridge to the future," Lal says. "We can't do without it."