- Press Release Distribution

Deep learning reveals valuable clues about kidney cancer in pathology slides

AI models uncover patterns across two-dimensional images of tumor samples that could help predict response to immunotherapy.

( A team of Dana-Farber researchers has identified a potential new way to assess clinically valuable features of clear cell renal cell carcinoma (ccRCC), a form of kidney cancer, using image processing with deep learning. Their AI-based assessment tool evaluates two-dimensional pictures of a tumor sample on a pathology slide and identifies previously underappreciated features, such as tumor microheterogeneity, that could help predict whether a tumor will respond to immunotherapy.

Their results suggest that pathology slides contain important biological information about ccRCC tumors – and possibly all types of tumors – that could be valuable for understanding more about the biology of the cancer.

The work, which is described in Cell Reports Medicine, is part of a broader effort at Dana-Farber to use AI in biologically grounded ways to transform cancer care and cancer discovery.

“This is an example of the growing convergence of AI and cancer biology,” says co-senior author Eliezer Van Allen, MD, Chief of the Division of Population Sciences at Dana-Farber. “It represents a major opportunity to measure key features of the tumor and its immune microenvironment at the same time. These measures could help drive not only biological discovery but also potentially guide cancer care.”

Renal cell carcinoma is among the 10 most common cancers worldwide. The clear cell subtype (ccRCC) accounts for 75-80% of metastatic cases. Some tumors are sensitive to immune checkpoint inhibitors (ICIs), but so far there are no measures that predict whether a ccRCC tumor will respond to immunotherapy with an ICI.

“We wanted to know what a tumor that responds to immunotherapy looks like,” says first author Jackson Nyman, PhD, who was a graduate student in Van Allen’s lab and is now at PathAI. “Is there anything in the pathology slide that might give us clues about what is different about the tumors?”

As part of diagnosis, pathologists analyze pathology slides of tumor samples that have been stained to reveal the structures of cells. A routine measure is nuclear grade, which indicates how far tumor cells deviate from normal cells.

Nyman, who collaborated with Van Allen, Dana-Farber pathologist Sabina Signoretti, MD, and Toni Choueiri, MD, Director of the Lank Center for Genitourinary Oncology at Dana-Farber, on the project, first trained an AI model to assess a tumor’s nuclear grade. The AI model was not only able to assess nuclear grade, but also to identify differences in grade across a tumor sample.

The finding inspired the team to expand their deep learning model to quantify tumor microheterogeneity and immune properties, such as immune infiltration, across the slide. Tumor microheterogeneity is a measure of how much the nuclear grade varies across the slide. Immune infiltration is a measure of how deeply lymphocytes, the warriors of the immune system, have penetrated the tumor. These measures are possible for pathologists to complete, but far too time-consuming to do routinely.

When they assessed a set of ccRCC pathology slides with their AI model, they saw that some tumors were markedly homogeneous while others had many different nuclear grades in many different patterns. They could also see that in some tumors, lymphocytes were present while others lacked substantial infiltration.

“There was a visual difference in some patient images versus others that had not been obvious before,” says Nyman. “We wondered if certain patterns might be predictive of a response to immunotherapy.”

To answer this question, the team used the AI-based tool to assess pathology slides of tumors from patients who were part of the CheckMate 025 randomized phase 3 clinical trial. The trial tested monotherapy with an ICI or an mTOR inhibitor in patients with ccRCC who had been previously treated with standard therapy.

They found that features such as tumor microheterogeneity and immune infiltration were associated with improved overall survival among patients taking immune checkpoint inhibitors. The tumors that responded to ICIs had both higher levels of tumor microheterogeneity and denser infiltration of lymphocytes in high-grade regions.

“These signals are hiding in plain sight,” says Van Allen. “They are just hard for pathologists to practically measure on individual slides. With AI, we have a scalable way to potentially squeeze a lot more information out of these slides.”

The tool is not ready for clinical use, but as a next step, the team is testing it in an ongoing clinical trial involving combination immunotherapy as first-line treatment in patients with ccRCC. The team also plans to explore whether these visual clues in pathology slides are related to molecular features of the tumor, such as alterations in genes.

“The use of deep learning strategies to identify tumor and microenvironmental features from histopathology slides and determine their relationship to molecular and clinical states may have value across tumor types and therapeutic modalities,” says Van Allen.

About Dana-Farber Cancer Institute

Dana-Farber Cancer Institute is one of the world’s leading centers of cancer research and treatment. Dana-Farber’s mission is to reduce the burden of cancer through scientific inquiry, clinical care, education, community engagement, and advocacy. Dana-Farber is a federally designated Comprehensive Cancer Center and a teaching affiliate of Harvard Medical School.

We provide the latest treatments in cancer for adults through Dana-Farber Brigham Cancer Center and for children through Dana-Farber/Boston Children’s Cancer and Blood Disorders Center. Dana-Farber is the only hospital nationwide with a top 5 U.S. News & World Report Best Cancer Hospital ranking in both adult and pediatric care.

As a global leader in oncology, Dana-Farber is dedicated to a unique and equal balance between cancer research and care, translating the results of discovery into new treatments for patients locally and around the world, offering more than 1,100 clinical trials. 




Poor oral health could lessen survival from head and neck cancer

Poor oral health could lessen survival from head and neck cancer
An international study has revealed strong associations between oral health and survival among people diagnosed with head and neck cancer. Specifically, better oral health, as evidenced by the number of natural teeth and dental visits prior to the time of diagnosis, was associated with increased survival. Importantly, those who had more frequent dental visits were more likely to have their cancer diagnosed at an earlier, and less deadly, stage of the disease than those who had few or no dental visits. The study, by researchers at UNC Lineberger ...

Interventions for physical capacity and quality of life in adults with post–COVID-19 condition

About The Study: The findings of this systematic review and meta-analysis suggest that rehabilitation interventions in adults with post–COVID-19 condition are associated with improvements in functional exercise capacity, dyspnea, and quality of life, with a high probability of improvement compared with the current standard care. The certainty of evidence was moderate for functional exercise capacity and quality of life and low for other outcomes. Authors: Dimitra V. Pouliopoulou, M.Sc., of Western University in London, Ontario, Canada, is the corresponding author. To access the embargoed study: Visit our For The Media website at this link ...

Premenstrual disorders, timing of menopause, and severity of vasomotor symptoms

About The Study: In this study of 3,635 female participants in the U.S., premenstrual disorders (PMDs) were associated with increased risks of early menopause and moderate or severe vasomotor symptoms (VMS). PMDs may be indicative of underlying physiology linked to early menopause and VMS, suggesting a phenotype observable during the reproductive years that may allow clinicians to target women at risk of earlier menopause and subsequent health risks later in the life course. Authors: Yihui Yang, M.P.H., and Donghao Lu, M.D., Ph.D., of the Karolinska Institutet in Stockholm, Sweden are the corresponding authors. To ...

Study finds two antibiotics for children with sinusitis equally effective, but one had fewer side effects

Brigham researchers found that patients prescribed amoxicillin-clavulanate had higher rates of gastrointestinal symptoms and yeast infections than those prescribed amoxicillin Acute sinusitis is one of the most common causes for children to be put on antibiotic medications, with patients in the United States filing nearly 5 million antibiotic prescriptions every year to treat the condition. The drugs amoxicillin and amoxicillin-clavulanate make up most of those prescriptions, but there is a lack of consensus on which should be first-line ...

Women given new insight into blood clot risk

New research from Queen Mary University of London, published in iScience, shows an increased risk of blood clots in women who have any combination of a particular gene mutation, oestrogen use, or common medical conditions – specifically: obesity, high blood pressure, high cholesterol, and kidney disease. Women with the Factor V Leiden (FVL) gene mutation who had been prescribed oestrogen had more than double the risk of blood clotting compared to women who did not have this mutation. And almost 20% of the women who carry FVL, ...

A mysterious blue molecule will help make better use of light energy

A mysterious blue molecule will help make better use of light energy
Researchers at IOCB Prague are the first to describe the causes of the behavior of one of the fundamental aromatic molecules, which fascinates the scientific world not only with its blue color but also with other unusual properties – azulene. Their current undertaking will influence the foundations of organic chemistry in the years to come and in practice will help harness the maximum potential of captured light energy. The article appeared in the Journal of the American Chemical Society (JACS). Azulene has piqued the ...

New research unveils pseudomonas cyclic lipopeptide medpeptin’s role in modulating plant immunity

New research unveils pseudomonas cyclic lipopeptide medpeptin’s role in modulating plant immunity
A groundbreaking research study conducted by Hai-Lei Wei's research team at the Chinese Academy of Agricultural Sciences in China has revealed significant insights into the biosynthesis and modulation of plant immunity by a novel cyclic lipopeptide called medpeptin, produced by Pseudomonas mediterranea. The findings, published in Engineering, shed light on the intricate structure–function interactions of cyclic lipopeptides (CLPs) and open new avenues for the development of plant disease resistance strategies. CLPs, multifunctional secondary metabolites produced by various bacteria, have emerged as key elicitors of plant ...

The MIT Press announces the Open Encyclopedia of Cognitive Science, a paradigm shift in open access reference works

The MIT Press announces the Open Encyclopedia of Cognitive Science, a paradigm shift in open access reference works
For over a generation, the MIT Encyclopedia of the Cognitive Sciences has been an essential resource for researchers and students of cognitive science and neuroscience. Today, the MIT Press proudly announces its intellectual successor—the Open Encyclopedia of Cognitive Science (OECS), a dynamic and openly accessible web reference poised to guide the next generation of exploration. Thanks to generous funding from James S. McDonnell Foundation and the Allen Institute for AI, the first set of articles will be published in 2024. In ...

Exercise boosts anti-cancer immunity and reduces inflammation in Lynch Syndrome patients

Exercise boosts anti-cancer immunity and reduces inflammation in Lynch Syndrome patients
HOUSTON ― Regular and intense aerobic exercise may reduce the risk of colorectal cancer in patients with Lynch Syndrome (LS) by improving the immune system's ability to detect and remove potentially harmful cells, according to researchers at The University of Texas MD Anderson Cancer Center.   The findings, published today in Clinical Cancer Research, revealed that LS carriers participating in a high-intensity training (HIIT) regimen saw a reduction of the inflammatory marker prostaglandin E2 (PGE2) in both the colon and the blood. Researchers ...

COVID-infected adults with 4 or more underlying diseases or advanced age, face higher risk of ICU stay, death

Whether vaccinated or not, having at least four disease risk factors put adults hospitalized due to COVID-19 at higher risk for critical outcomes, according to a 10-state study from the Centers for Disease Control and Prevention’s (CDC’s) VISION Network. The study describes the characteristics of adults hospitalized with COVID-19 from June 2021 through March 2023 and enumerates their risk factors for critical outcomes, defined as intensive care unit (ICU) admission and/or in-hospital death. It ...


Polymer research aims to expand possibilities in sensor technology

New therapeutic avenues in bone repair

Socioeconomic status transition throughout life and risk of dementia

Climbing the social ladder slows dementia, Japanese study reveals

Researchers discover hidden step in dinosaur feather evolution

Studies reveal cell-by-cell changes caused when pig hearts and kidneys are transplanted into humans

SRI earns FDA Orphan Drug Designation for pancreatic cancer

A new gene-editing system tackles complex diseases

Tracking down toxic metals from tobacco smoke

Clarifying the cellular mechanisms underlying periodontitis with an improved animal model

Age, race impact AI performance on digital mammograms

SwRI leads courses at 2024 Society of Tribologists & Lubrication Engineers Annual Meeting

Hope for a cure for visceral leishmaniasis, an often fatal infectious disease

How AI helps programming a quantum computer

New research reveals that prehistoric seafloor pockmarks off the California coast are maintained by powerful sediment flows

AI can help improve ER admission decisions, Mount Sinai study finds

Matcha mouthwash inhibits bacteria that causes periodontitis

Oncology events in Poland solidify collaboration with NCCN

City of Hope awarded $5.4 million CIRM grant to create a stem cell laboratory and expand access to state-of-the-art disease models and technology among a diverse scientific community

Meeting preview: Hot topics at NUTRITION 2024

Study models how ketamine’s molecular action leads to its effects on the brain

A diaspora-based model of human migration

Black and Hispanic Americans experience wider temperature swings

Gamers say they hate ‘smurfing,’ but admit they do it

How immune cells recognize the abnormal metabolism of cancer cells

How plants mate for life and repel other suitors

3D printing robot uses AI machine learning for US Army research

Ruptured Achilles tendon shows faster repair amid plasma irradiation treatment

Screen time not the main factor making parent-child interactions worse, study finds

Improving the effectiveness of earthquake early warning systems

[] Deep learning reveals valuable clues about kidney cancer in pathology slides
AI models uncover patterns across two-dimensional images of tumor samples that could help predict response to immunotherapy.