by UT Southwestern Medical Center

A typical histopathologic slide image of kidney cancer tissue (left) has significant intra-slide heterogeneity, illustrated by the false coloring in the middle panel with two distinct regions. The dramatic change in blood vessels across these regions is marked as a green overlay. Credit: UT Southwestern Medical Center

An artificial intelligence (AI)-based model developed by UT Southwestern Medical Center researchers can accurately predict which kidney cancer patients will benefit from anti-angiogenic therapy, a class of treatments that's only effective in some cases. Their findings, published in Nature Communications, could lead to viable ways to use AI to guide treatment decisions for this and other types of cancer.

"There's a real unmet need in the clinic to predict who will respond to certain therapies. Our work demonstrates that histopathological slides, a readily available resource, can be mined to produce state-of-the-art biomarkers that provide insight on which treatments might benefit which patients, " said Satwik Rajaram, Ph.D., Assistant Professor in the Lyda Hill Department of Bioinformatics and member of the Harold C. Simmons Comprehensive Cancer Center at UT Southwestern.

Dr. Rajaram co-led the study with Payal Kapur, M.D., Professor of Pathology and Urology and a co-leader of the Kidney Cancer Program (KCP) at the Simmons Cancer Center.

Every year, nearly 435, 000 people are diagnosed with clear cell renal cell carcinoma (ccRCC), making it the most common subtype of kidney cancer. When the disease metastasizes, anti-angiogenic therapies are often used for treatment. These drugs inhibit new blood vessels from forming in tumors, limiting access to molecules that fuel tumor growth. Although anti-angiogenic drugs are widely prescribed, fewer than 50% of patients benefit from them, Dr. Kapur explained, exposing many to unnecessary toxicity and financial burden.

No biomarkers are clinically available to accurately assess which patients are most likely to respond to anti-angiogenic drugs, she added, although a clinical trial conducted by Genentech suggested that the Angioscore (a test that assesses the expression of six blood vessel-associated genes) may have promise. However, this genetic test is expensive, is hard to standardize among clinics, and introduces delays in treatment. It also tests a limited part of the tumor, and ccRCC is quite heterogeneous, with variable gene expression in different regions of the cancer.

To overcome these challenges, Drs. Kapur and Rajaram and their colleagues at the KCP developed a predictive method using AI to assess histopathological slides—thinly cut tumor tissue sections stained to highlight cellular features. These slides are nearly always part of a patient's standard workup at diagnosis, and their images are increasingly available in electronic health records, said Dr. Rajaram, also Assistant Professor in the Center for Alzheimer's and Neurodegenerative Diseases and the Department of Pathology.

Using a type of AI based on deep learning, the researchers "trained" an algorithm using two sets of data: one that matched ccRCC histopathological slides with their corresponding Angioscore, and another that matched slides with a test they developed that assesses blood vessels in the tumor sections.

Importantly, unlike many deep learning algorithms that don't offer insight into their results, this approach is designed to be visually interpretable. Rather than producing a single number and directly predicting a response, it generates a visualization of the predicted blood vessels that correlates tightly with the RNA-based Angioscore. Patients with more blood vessels are more likely to respond to therapy; this approach allows users to understand how the model reached its conclusions.

When the researchers evaluated this approach using slides from more than 200 patients who weren't part of the training data—including those collected during the clinical trial that showed the potential value of Angioscore—it predicted which patients were most likely to respond to anti-angiogenic therapies nearly as well as Angioscore. The algorithm showed a responder will have a higher score than a non-responder 73% of the time compared to 75% with Angioscore.

The study authors suggest AI analysis of histopathological slides could eventually be used to help guide diagnostic, prognostic, and therapeutic decisions for a variety of conditions. They plan to develop a similar algorithm to predict which patients with ccRCC will respond to immunotherapy, another class of treatment that only some patients respond to.

More information: Jay Jasti et al, Histopathology based AI model predicts anti-angiogenic therapy response in renal cancer clinical trial, Nature Communications (2025). DOI: 10.1038/s41467-025-57717-6  Journal information: Nature Communications