How can AI help pathologists find metastases in breast cancer faster (and in an less expensive way)? And why are breast cancer tumors more likely to be more aggressive in pregnant women? Two new innovative studies from UMC Utrecht evolve around these questions. Researchers present the results today at the leading San Antonio Breast Cancer Symposium.
Today, the San Antonio Breast Cancer Symposium (5-9 December 2023) kicks off. From all over the world, cancer researchers are traveling to San Antonio in the United States. A selected few are invited to present the (first) results of their research. UMC Utrecht is well represented at the symposium. Here, we highlight two remarkable new studies by our researchers.
After a woman’s breast tumor is removed for breast cancer, often the sentinel lymph node is also removed. By doing so, the pathologist can check if the cancer has metastasized. That is, if breast cancer starts spreading, the tumor cells end up in that sentinel gland first, via the lymph fluid. That is why pathologists always carefully examine that tissue as well.
With about two-thirds of the patients, the pathologists have good news, because they have found no metastases in the sentinel gland. But to be really sure about this, pathologists take another look at sections (thin slices) of the glandular tissue. This time, they use additional staining, containing antibodies that recognize tumor-specific proteins.
“Because these antibodies have a color label, the tumor cells become clearly visible,” explains physician-researcher and clinical epidemiologist Carmen van Dooijeweert. “This way, you can clearly recognize possible tumor cells, which might have been missed during the first assessment, without the extra staining. Those extra stains are just quite expensive, about 25 euros per tissue section, of which we already do (at least) five per sentinel node. Also, sometimes multiple tissue blocks from multiple sentinel lymph nodes need to be viewed, and then the costs will rise even more rapidly. In addition, it is an intensive, time-consuming job for the pathologist.”
During the CONFIDENT-B trial, Carmen investigated whether AI can help to perform sentinel node tissue assessment more efficiently. Can it be done faster and – with rising healthcare costs in mind – less expensive, without risking missing tumor cells when omitting the extra staining?
“AI can be used in two ways: completely independent (‘independent AI’ – ed.) or as an assistant to the healthcare professional (‘AI assistance’ – ed.),” says Carmen. “With Independent AI, the algorithm decides completely independently whether something is a tumor or not. This is quite risky, because what if the algorithm is wrong? That raises all kinds of ethical and legal questions. How safe will it be then to start using the algorithm as soon as possible?”
Carmen and her team used the other form of artificial intelligence, AI assistance: the algorithm lends a helping hand, but you will still have take a look at the result yourself.
“Our algorithm – which we did not develop ourselves but we licensed it from a company – recognizes structures,” Carmen says. “It recognizes for the pathologist anything which doesn’t belong in a lymph node. The algorithm then puts a red, orange or yellow circle around it, depending on how suspicious the algorithm thinks the spot is.”
Those markings are a signal to pathologists that they will need to take a closer look at the encircled spots, but they then do so in a much more focused way and no longer need to look closely at the entire tissue piece.
For the trial, Carmen worked with two groups of sentinel nodes. For one group, the standard procedure was followed, and for the other group, AI was used first. For the AI group, Carmen let the algorithm run. Subsequently, the pathologists looked specifically at the circled spots. That final check could be done quite quickly by the pathologist, often without the need for expensive additional staining.
Conclusion after two weeks: less time was needed in the AI group to check the tissue, and it turned out to be much less expensive to work that way. “During the trial, we have already saved 3,000 euros in additional coloring. That can add up to tens of thousands of euros per year,” Carmen says.
The sum saved only increases bearing in mind that in some hospitals the expensive, extra staining is often used directly in order to work faster.
Of course, during the trial, extra checks with additional staining were done to ensure that the AI procedure is indeed safe: in all cases, no tumor cells were detected, and AI turned out to have done its work correctly. Furthermore, the participating pathologists all agreed that working with the algorithm makes their work more enjoyable.
Carmen: “Healthcare costs are skyrocketing, and there is a worldwide shortage of pathologists. Healthcare innovations are often expensive, but this innovation actually reduces healthcare costs. And AI allows pathologists to get on with their other important work faster. It shows that if you implement AI in a safe way, you’ll not only save money and time, but you’ll also immediately make pathologists’ work a lot more enjoyable.”
As a result of the CONFIDENT-B trial, the UMC Utrecht pathologists have started working with AI as a standard procedure with breast cancer, probably as the first in the world.
At the San Antonio symposium, PhD candidate Carsten Bakhuis will present two studies on breast cancer in pregnant women.
“At the beginning of the 20th century, an American surgeon already pointed out in an article that breast cancer tends to be more aggressive with pregnant women. Since then, many doctors have always been aware of this. But we are now really looking closely at whether and why this is really the case,” Carsten explains.
To properly study breast cancer during pregnancy, UMC Utrecht set up a national cohort. “In this, we have collected pathology reports and treatment data from pregnant women with breast cancer, and also from women with breast cancer within one year of delivery,” Carsten says. “We also supplemented the cohort with data from women with interrupted pregnancies, such as miscarriages or abortions. The cohort consists of 787 women, ranging from 1988 up to 2022.”
By closely studying the cohort data, the researchers have found out that breast cancer in pregnant women does indeed tend to behave more aggressively. Now, the researchers hope to find out why. Carsten is therefore now focusing in particular on the genetic composition of the tumor cells. In other words: what processes take place in the DNA of the cells, turning them into a tumor? At the congress in San Antonio, he is now presenting the first results of two projects he has conducted using the cohort.
One of Carsten’s studies revolves around so-called ‘hypoxia’: lack of oxygen at the cellular level.
Carsten: “A tumor cell divides and grows and therefore needs a lot of oxygen and nutrients. These are transported via the blood vessels. For this reason, a growing tumor creates extra blood vessels. But if this all needs to happen quickly, the blood vessels cannot always keep up.”
As a result, less oxygen reaches the tumor cells. This occurs more often in relatively aggressive breast tumors. Hypoxia is twice as common in tumors with pregnant women, Carsten has concluded. So, this is indeed a sign that with pregnant women, these aggressive forms of breast cancer are relatively more common.
But why are these breast cancer tumors in women actually more aggressive? “We don’t know that exactly yet, but we have some ideas,” Carsten explains. “First of all, we think that pregnancy hormones have something to do with it. During pregnancy, several hormone levels rise sharply. When non-pregnant women have breast cancer, these particular hormones already influence the tumor cells. And we believe that these higher hormone levels may have an even stronger effect on tumors in pregnant women.
Furthermore, the researchers suspect that the immune system plays a significant role. Carsten: “During pregnancy, women’s immune systems work more selectively, to ensure that the unborn child is not seen as an invader. As a result, the immune system may also slown down detecting and fighting tumors, but that still needs to be studied more closely.”
The second study presented by Carsten focuses on the following question: do the nature and prognosis of breast cancer differ depending on whether the disease is diagnosed in the first, second or third trimester? The revealing answer: yes, this is indeed the case, because tumors are less aggressive when detected in the first trimester.
Could that be because the tumor is then ‘less old’ and has not had the opportunity yet to become bigger? “No, because we have really been focusing on the biological aggressiveness of the tumor. In fact, the degree of aggression is already fixed when the tumor comes into existence,” Carsten says. “A grade 3 tumor (most aggressive variant – ed.) has always been biologically more aggressive, and thus will not become much more aggressive over time.”
But what then causes this greater aggressiveness of breast cancer detected in the second and third trimesters? “We are quite certain that tumors diagnosed in the first trimester, must have arisen before pregnancy. Some tumors can take several years to reach a certain size,” Carsten explains.
Other, more aggressive tumors, need a much shorter time to develop. “And if these, more aggressive tumors are also exposed to higher hormone levels during pregnancy, the tumor cells start dividing even faster. The latter might well be the case with second- and third-trimester tumors.”
During pregnancy, women’s breasts change constantly. Mammary glands grow, the breasts are more sensitive et cetera. Isn’t it very difficult to recognize breats cancer with pregnant women in time?
Carsten: “What we regularly see with our patients is that they have been told by their family doctor or maternity nurse: ‘It’s probably a clogged mammary gland.’ Healthcare professionals are less likely to think of breast cancer in pregnant women, and then don’t immediately send them on for further testing.”
To create awareness, Carsten and some colleagues recently wrote an article in the Dutch magazine Nederlands Tijdschrift voor Geneeskunde. “Our message: remain critical and objective when a pregnant woman comes to you with breast problems. She should also be evaluated seriously, just like someone without a (recent) pregnancy. With almost all pregnant women, it will turn out to be harmless but it is important not to miss that one patient that indeed has cancer. Just because breast cancer behaves so aggressively during and shortly after pregnancy, it is all the more important to detect the disease as early as possible.”
This Thursday (7 September 2023), Anne May, professor of clinical epidemiology of cancer survivorship (UMC Utrecht), will present the first results of the PREFERABLE-EFFECT trial. This is a large, international study coordinated by the Julius Center of UMC Utrecht.
Central question of this research: can physical training help metastatic breast cancer patients to suffer less from the symptoms of the disease and side effects of treatments?
UMC Utrecht collaborated for this trial with healthcare centers from five European countries and Australia. The Netherlands Cancer Institute is, for instance, one of the consortium partners.
An extensive article on the first results of PREFERABLE-EFFECT will appear on this website on Thursday, 7 December.
