(Press-News.org) Artificial intelligence (AI) and machine learning tools have received a lot of attention recently, with the majority of discussions focusing on proper use. However, this technology has a wide range of practical applications, from predicting natural disasters to addressing racial inequalities and now, assisting in cancer surgery.
A new clinical and research partnership between the UNC Department of Surgery, the Joint UNC-NCSU Department of Biomedical Engineering, and the UNC Lineberger Comprehensive Cancer Center has created an AI model that can predict whether or not cancerous tissue has been fully removed from the body during breast cancer surgery. Their findings were published in Annals of Surgical Oncology.
“Some cancers you can feel and see, but we can’t see microscopic cancer cells that may be present at the edge of the tissue removed. Other cancers are completely microscopic,” said senior author Kristalyn Gallagher, DO, section chief of breast surgery in the Division of Surgical Oncology and UNC Lineberger member. “This AI tool would allow us to more accurately analyze tumors removed surgically in real-time, and increase the chance that all of the cancer cells are removed during the surgery. This would prevent the need to bring patients back for a second or third surgery.”
During surgery, the surgeon will resect the tumor (also referred to as a specimen) and take a small amount of surrounding healthy tissue in an attempt to remove all of the cancer in the breast. The specimen is then photographed using a mammography machine and reviewed by the team to make sure the area of abnormality was removed. It is then sent to pathology for further analysis.
The pathologist can determine whether cancer cells extend to the specimen's outer edge, or pathological margin. If cancer cells are present on the edge of the tissue removed, there is a chance that additional cancer cells still remain in the breast. The surgeon might have to perform additional surgery to remove additional tissue to ensure the cancer has been completely removed. However, this can take up to a week after surgery to process fully, while specimen mammography, or photographing the specimen with an X-ray, can be done immediately in the operating room.
To "teach" their AI model what positive and negative margins look like, researchers used hundreds of these specimen mammogram images, matched with the final specimen reports from pathologists. To help their model, the researchers also gathered demographic data from patients, such as age, race, tumor type, and tumor size.
After calculating the model’s accuracy in predicting pathologic margins, researchers compared that data to the typical accuracy of human interpretation and discovered that the AI model performed as well as humans, if not better.
“It is interesting to think about how AI models can support doctor’s and surgeon’s decision making in the operating room using computer vision,” said first author Kevin Chen, MD, general surgery resident in the Department of Surgery. “We found that the AI model matched or slightly surpassed humans in identifying positive margins.”
According to Gallagher, the model can be especially helpful in discerning margins in patients that have higher breast density. On mammograms, higher density breast tissue and tumors appear as a bright white color, making it difficult to discern where the cancer ends and the healthy breast tissue begins.
Similar models could also be especially helpful for hospitals with fewer resources, which may not have the specialist surgeons, radiologists, or pathologists on hand to make a quick, informed decision in the operating room.
“It is like putting an extra layer of support in hospitals that maybe wouldn't have that expertise readily available,” said Shawn Gomez, EngScD, professor of biomedical engineering and pharmacology and co-senior author on the paper. “Instead of having to make a best guess, surgeons could have the support of a model trained on hundreds or thousands of images and get immediate feedback on their surgery to make a more informed decision.”
Since the model is still in its early stages, researchers will keep adding more pictures taken by more patients and different surgeons. The model will need to be validated in further studies before it can be used clinically. Researchers anticipate that the accuracy of their models will increase over time as they learn more about the appearance of normal tissue, tumors, and margins.
END
A new AI model has been developed to improve accuracy of breast cancer tumor removal
2023-09-25
[Attachments] See images for this press release:
ELSE PRESS RELEASES FROM THIS DATE:
Finding the balance: Opioids and pain control after surgery
2023-09-25
ROCHESTER, Minn. — In a recent Mayo Clinic study, researchers found that most patients prescribed fewer opioids after surgery were able to maintain satisfactory comfort levels without requiring more prescription refills later.
Under new evidence-based guidelines, patients undergoing various surgeries received fewer opioid pills, and 88% reported feeling "very" or "somewhat" satisfied with their pain management.
Researchers worked with the Mayo Clinic Survey Research Center to survey patients undergoing a range of elective surgeries. The survey investigated their post-surgery experiences, overall pain management approach and opioid use.
The study’s ...
UC Irvine scientists reveal what fuels wildfires in Sierra Nevada Mountains
2023-09-25
Irvine, Calif., Sept. 25, 2023 — Wildfires in California, exacerbated by human-driven climate change, are getting more severe. To better manage them, there’s a growing need to know exactly what fuels the blazes after they ignite. In a study published in Environmental Research Letters, Earth system scientists at the University of California, Irvine report that one of the chief fuels of wildfires in California’s Sierra Nevada mountains is the decades-old remains of large trees.
“Our findings support the idea that large-diameter fuel build-up is ...
US Department of Energy Office of Science awards $115M for High Rigidity Spectrometer project at FRIB
2023-09-25
Images
EAST LANSING, Mich. – The U.S. Department of Energy Office of Science, or DOE-SC, has awarded $115 million for the High Rigidity Spectrometer, or HRS, project at the Facility for Rare Isotope Beams, or FRIB, at Michigan State University.
The HRS instrument will enable scientists to characterize the properties of isotopes that are created in rare-isotope reactions produced at about 50% of the speed of light. With the ability to measure properties such as the mass, charge and velocity of rare isotopes produced in those conditions, HRS will be a centerpiece experimental instrument ...
Algorithm would predict disease relapses
2023-09-25
A University of Texas at Arlington research team has received a $450,000 grant from the National Institute of General Medical Sciences to use statistical machine learning to review patient data and better predict which patients will need additional treatments.
“With recent advances in screening, diagnosis and treatment, many diseases like cancer or cardiovascular disease can be identified in an early stage,” said Suvra Pal, associate professor of statistics in the Department of Mathematics. “Fortunately, a significant proportion of patients living ...
Exercise-mimicking drug sheds weight, boosts muscle activity in mice
2023-09-25
A brand-new kind of drug, tested in mice, shows promising new results that could lead to the development of a new weight-loss drug that mimics exercise.
The new compound, developed and tested by a University of Florida professor of pharmacy and his colleagues, leads obese mice to lose weight by convincing the body’s muscles that they are exercising more than they really are, boosting the animals’ metabolism.
It also increases endurance, helping mice run nearly 50% further than they could before. All without the mice lifting ...
Did life exist on Mars? Other planets? With AI's help, we may know soon
2023-09-25
Scientists have discovered a simple and reliable test for signs of past or present life on other planets – “the holy grail of astrobiology.”
In the journal Proceedings of the National Academy of Sciences, a seven-member team, funded by the John Templeton Foundation and led by Jim Cleaves and Robert Hazen of the Carnegie Institution for Science, reports that, with 90% accuracy, their artificial intelligence-based method distinguished modern and ancient biological samples from those of abiotic origin.
“This routine analytical method has the potential to revolutionize ...
Wind energy projects in North America are more likely to be opposed by white, wealthy communities
2023-09-25
(Santa Barbara, Calif.) — Wind energy is, by far, the most common type of clean energy. And transitioning to clean energy is critical to addressing the climate crisis. Yet local opposition poses a significant barrier to the deployment of wind energy projects.
A study published in Proceedings of the National Academy of Sciences (PNAS) by researchers from UC Santa Barbara, the University of Michigan and Gallup Inc. examined wind energy projects throughout the United States and Canada to determine how common opposition is and what factors predict it. The study found that nearly one in five projects faced opposition ...
Naming and shaming can be effective to get countries to act on climate
2023-09-25
Enforcement is one of the biggest challenges to international cooperation on mitigating climate change in the Paris Agreement. The agreement has no formal enforcement mechanism; instead, it is designed to be transparent so countries that fail to meet their obligations will be named and thus shamed into changing behavior. A new study from the University of California San Diego's School of Global Policy and Strategy shows that this naming-and-shaming mechanism can be an effective incentive for many countries to uphold their pledges ...
Scientists develop method of identifying life on other worlds
2023-09-25
Humankind is looking for life on other planets, but how will we recognise it when we see it? Now a group of US scientists have developed an artificial-intelligence-based system which gives 90% accuracy in discovering signs of life.
The work was presented to scientists for the first time at the Goldschmidt Geochemistry Conference in Lyon on Friday 14th July, where it received a positive reception from others working in the field. The details have now been published in the peer-reviewed journal PNAS (see notes for details).
Lead researcher Professor Robert Hazen, of the Carnegie Institution’s Geophysical ...
Caribbean parrots thought to be endemic are actually relicts of millennial-scale extinction
2023-09-25
In a new study published in PNAS, researchers have extracted the first ancient DNA from Caribbean parrots, which they compared with genetic sequences from modern birds. Working with fossils and archaeological specimens, they showed that two species thought to be endemic to particular islands were once more widespread and diverse. The results help explain how parrots rapidly became the world’s most endangered group of birds, with 28% of all species considered to be threatened. This is especially true for parrots that inhabit islands.
On ...