Researchers headed by a team at Northwestern University Feinberg School of Medicine have developed an artificial intelligence tool that could make it possible to spare breast cancer patients unnecessary chemotherapy by using a more precise method of predicting outcomes. In their reported study, the team used a deep learning approach to generate a Histomic Prognostic Signature (HiPS) risk score that was better than evaluations performed by expert pathologists at predicting the future course of an individual’s disease.

The new AI tool was able to identify breast cancer patients who are currently classified as high or intermediate risk but who become long-term survivors. For these patients the duration or intensity of chemotherapy could feasibly be reduced, which is important, as chemotherapy is associated with unpleasant, and potentially harmful side effects such as nausea or, more rarely, damage to the heart.

The study is the first to use AI for comprehensive evaluation of both the cancerous and non-cancerous elements of invasive breast cancer, and showed that patterns of non-cancerous cells are important in predicting outcomes. “Our study demonstrates the importance of non-cancer components in determining a patient’s outcome,” said Lee Cooper, PhD, associate professor of pathology at Northwestern University Feinberg School of Medicine. “The importance of these elements was known from biological studies, but this knowledge has not been effectively translated to clinical use.”

Cooper is a co-corresponding author of the team’s published paper in Nature Medicine, titled “A population-level digital histologic biomarker for enhanced prognosis of invasive breast cancer.” In their paper, the authors stated, “We show that the HiPS score is a strong, independent predictor of survival outcomes in nonmetastatic ER+ and HER2+ cancers, and that it is concordant with known epidemiologic and genomic risk profiles.”

Breast cancer is the most common malignancy worldwide, and is “… a heterogeneous disease with variable survival outcomes that depend on tumor biology, therapeutic regimen, and socioeconomic determinants of health,” the authors noted. About one in eight U.S. women will receive a breast cancer diagnosis in their lifetime.

Currently, pathologists evaluate cancerous cells in a patient’s tissue to determine treatment. This evaluation includes reviewing the cancerous tissue to determine how abnormal it appears. The process, known as grading, focuses on the appearance of cancer cells and has remained largely unchanged for decades. The grade, determined by the pathologists, is used to help determine what treatment a patient will receive. “Intrinsic subtype can be determined by gene expression profiling or approximated using assessment of the estrogen receptor (ER), progesterone receptor (PR), or the human epidermal growth factor receptor 2 (HER2) expression based on immunohistochemistry (IHC) or in situ hybridization (ISH)” the team continued.

However, they noted, “Pathologists grade the microscopic appearance of breast tissue using the Nottingham criteria, which are qualitative and do not account for noncancerous elements within the tumor microenvironment.” Yet many studies of breast cancer biology have shown that the non-cancerous cells, including cells from the immune system and cells that provide form and structure for the tissue, can play an important role in sustaining or inhibiting cancer growth.

For their study, Cooper and colleagues built an AI model to evaluate breast cancer tissue from digital images that measures the appearance of both cancerous and non-cancerous cells, as well as interactions between them.

“These patterns are challenging for a pathologist to evaluate as they can be difficult for the human eye to categorize reliably,” said Cooper, also a member of the Robert H. Lurie Comprehensive Cancer Center of Northwestern University. “The AI model measures these patterns and presents information to the pathologist in a way that makes the AI decision-making process clear to the pathologist.”

The AI system analyzes 26 different properties of a patient’s breast tissue to generate an overall prognostic score. The system also generates individual scores for the cancer, immune and stromal cells to explain the overall score to the pathologist. For example, in some patients, a favorable prognosis score may be due to properties of their immune cells, where for others it may be due to properties of their cancer cells. This information could be used by a patient’s care team in creating an individualized treatment plan.

To train the AI model the scientists required hundreds of thousands of human-generated annotations of cells and tissue structures within digital images of patient tissues. To achieve this they created an international network of medical students and pathologists across several continents. These volunteers provided this data through a website over the course of several years to make it possible for the AI model to reliably interpret images of breast cancer tissue.

“A key advantage of HiPS is interpretability and transparency, being composed of features that correspond to recognizable, well-established biological entities,” the team wrote. “This enabled us to investigate the biological phenomena underlying HiPS by correlating morphology with pathology reports, messenger RNA (mRNA) expression data, and inferred pathway activations and cell abundance using genomic deconvolution method.”

The study was conducted in collaboration with the American Cancer Society (ACS), which created a unique dataset of breast cancer patients through their Cancer Prevention Studies. This dataset has representation of patients from over 423 U.S. counties, many who received a diagnosis or care at community medical centers. This is important, because most studies typically use data from large academic medical centers which represent only a portion of the U.S. population. As part of their collaboration, Northwestern developed the AI software, while scientists at the ACS and National Cancer Institute provided expertise on breast cancer epidemiology and clinical outcomes.

“Quantitative HiPS features were developed in a hypothesis-driven manner to quantify distinct biological phenomena,” the investigators reported. Their study found that HiPS consistently outperformed pathologists in predicting survival outcomes, independent of tumor–node–metastasis stage and other variables. “…  we exceeded expert performance using established grading criteria. This success is partly driven by capturing stromal, immune, and spatial clustering features not typically assessed.”

Moreover, the team pointed out, “… we exceeded human performance even when we limited our analysis to epithelial morphology. These gains may be due to the quantitative nature of HiPS compared with visual estimates.”

Adoption of the new model could provide patients diagnosed with breast cancers with a more accurate estimate of the risk associated with their disease, empowering them to make informed decisions about their clinical care, Cooper said. Additionally, the model may help in assessing therapeutic response, allowing treatment to be escalated or de-escalated depending on how the microscopic appearance of the tissue changes over time. For example, the tool may be able to recognize the effectiveness of a patient’s immune system in targeting the cancer during chemotherapy, which could be used to reduce the duration or intensity of chemotherapy.

“We also hope that this model could reduce disparities for patients who are diagnosed in community settings,” Cooper said. “These patients may not have access to a pathologist who specializes in breast cancer, and our AI model could help a generalist pathologist when evaluating breast cancers.” And while noting limitations of their study, the authors wrote, “In conclusion, HiPS is a robustly validated biomarker to support pathologists and improve patient prognosis.”

Next, the scientists will evaluate this model prospectively to validate it for clinical use. This coincides with the transition to using digital images for diagnosis at Northwestern Medicine, which will happen over the next three years.

The scientists also are working to develop models for more specific types of breast cancers like triple-negative or HER2-positive. Invasive breast cancer encompasses several different categories, and the important tissue patterns may vary across these categories. “This will improve our ability to predict outcomes and will provide further insights into the biology of breast cancers,” Cooper said.

Previous articleAC Current Limiters
Next articleAdvanced Method for High-Resolution Spatial Proteomics