Mode
Text Size
Log in / Sign up

Radiomics features predict equivocal HER2 status in breast cancer patients with high accuracyNew mammography tool may predict hard to read breast cancer results

AI-generated summary of the cited source, checked by automated accuracy review. How we work

Key Takeaway
Consider using radiomics features for preoperative prediction of equivocal HER2 status in breast cancer.

This cohort study included 131 breast cancer patients with equivocal HER2 (IHC 2+) status. The researchers assessed intra- and peritumoral radiomics features derived from contrast-enhanced mammography. The primary outcome was the prediction of equivocal HER2 status.

In the internal test cohort, the nomogram showed optimal predictive performance compared to a radiomics model and a clinical model. The area under the curve was 0.893 for n=22 patients. In the prospective test cohort, the nomogram again showed optimal predictive performance compared to the other models. The area under the curve was 0.840 for n=25 patients. P-values or confidence intervals were not reported for these results.

Safety data, adverse events, discontinuations, and tolerability were not reported. The study had no reported limitations regarding study design or population. Funding or conflicts of interest were not reported. The practice relevance indicates that the nomogram has the potential to predict equivocal HER2 (IHC 2+) status of breast cancer preoperatively.

A new tool from contrast-enhanced mammography may help doctors predict a confusing breast cancer result before surgery. This could spare some women from waiting, worrying, and getting extra biopsies.

Breast cancer treatment often depends on a marker called HER2. Some tumors are clearly positive or negative. Others sit in a gray zone called equivocal. That means the standard test is not sure. Doctors call this IHC 2 plus. It is frustrating for patients and can delay care.

Many women with equivocal results need a second test called FISH. That test can take days or weeks. It can also mean another biopsy. Not every hospital can run it quickly. The result is more waiting and more stress.

But here is the twist. A new look at mammography images may help. Contrast-enhanced mammography, or CEM, uses a special dye to light up tumors. It shows more detail than a standard mammogram. Researchers found that patterns in and around a tumor on CEM can hint at HER2 status.

Think of a tumor as a house. The inside of the house is the intratumoral area. The yard around it is the peritumoral area. The dye acts like a floodlight. It shows how the tumor feeds and how the tissue around it reacts. Some patterns suggest a tumor is more likely to be HER2 positive. Others suggest it is not.

The study included 131 breast cancer patients with equivocal HER2 results. They were split into three groups for training and testing. Researchers extracted patterns from the tumor and the area around it on CEM images. They used smart computer methods to pick the most useful patterns. Then they built a simple tool called a nomogram. This tool combines those patterns with basic clinical facts, like tumor size.

The nomogram performed well. In the internal test group, it had an AUC of 0.893. In the prospective test group, it had an AUC of 0.840. AUC is a score from 0 to 1. A score near 1 means the tool is good at telling two groups apart. The tool also showed good calibration and decision curve results. That means its predictions matched real outcomes and helped guide decisions.

This does not mean this tool is available in your hospital today.

The study suggests that CEM patterns could help doctors decide who needs a second test and who might not. It could shorten the path to a clear answer. It might reduce the number of repeat biopsies. It could also help teams plan surgery sooner.

An expert perspective is not included in the abstract. Still, this work fits a growing trend. Radiologists are using computer-based image analysis to support clinical decisions. The goal is not to replace doctors. It is to give them better tools to care for patients.

What does this mean for you right now. If you have an equivocal HER2 result, ask your care team about CEM. Not every center offers it yet. It is not a substitute for standard testing. It is a possible aid to help guide next steps. Talk with your doctor about whether it might fit your situation.

The study has limits. It included a small number of patients. The tool needs larger, multi-center trials. It also needs testing in real-world clinics over time. Not every tumor looks the same, and not every hospital uses the same equipment.

What happens next. Researchers will likely test this nomogram in more patients and more hospitals. They will compare it to standard care and see if it truly shortens time to treatment. If results hold, the tool could be built into CEM software. That could make it easier for doctors to use in daily practice.

Study Details

Study typeCohort
EvidenceLevel 3
PublishedApr 2026
View Original Abstract ↓
ObjectiveIdentification of Human epidermal growth factor receptor 2 (HER2) status is significant for the treatment and prognosis of breast cancer patients. The study aimed to evaluate the equivocal HER2 (IHC 2+) status of breast cancer using intra- and peritumoral radiomics features of contrast-enhanced mammography (CEM).MethodsA total of 131 breast cancer patients with equivocal HER2 (IHC 2+) status of breast cancer were enrolled in the study and divided into training (n=84), internal test (n=22) and prospective test (n=25) cohorts. Radiomics features were extracted from intratumoral and peritumoral regions on CEM and were selected using low variance and least absolute shrinkage and selection operator regression (LASSO). Five radiomics signatures were established based on different intratumoral and peritumoral regions. The nomogram was constructed using the selected signatures and clinical factors by logistic regression analysis. Its predictive performance was compared with the radiomics model and the clinical model. The area under the receiver operator characteristic curve (AUC), sensitivity, specificity, accuracy, the calibration curve, and decision curve analysis (DCA) were used to evaluate predictive performance of the models.ResultsThe intratumoral signature, 5mm-peritumoral signature, and tumor diameter were used to establish nomogram. Compared to the radiomics model and the clinical model, the nomogram achieved optimal predictive performance, with an AUC of 0.893 in the internal test cohort and an AUC of 0.840 in the prospective test cohort. The calibration curves and DCA showed favorable predictive performance of the nomogram.ConclusionsThe nomogram incorporated the intratumoral and peritumoral radiomics signatures of CEM and clinical risk variables has the potential to predict equivocal HER2 (IHC 2+) status of breast cancer preoperatively.
Free Newsletter

Clinical research that matters. Delivered to your inbox.

Join thousands of clinicians and researchers. No spam, unsubscribe anytime.