High-risk breast lesions: a combined intratumoral and peritumoral radiomics nomogram model to predict pathologic upgrade and reduce unnecessary surgical excision
2024

Predicting Upgrades in High-Risk Breast Lesions with a Radiomics Model

Sample size: 138 publication 10 minutes Evidence: high

Author Information

Author(s): Liao Tingting, Yang Yuting, Lin Xiaohui, Ouyang Rushan, Deng Yaohong, Ma Jie

Primary Institution: Shenzhen People’s Hospital, The Second Clinical Medical College of Jinan University

Hypothesis

Can a nomogram combining intratumoral and peritumoral radiomics predict the pathological upgrade of high-risk breast lesions?

Conclusion

The nomogram effectively predicts postoperative pathological upgrades in high-risk breast lesions, aiding in clinical decision-making.

Supporting Evidence

  • The nomogram achieved an AUC of 0.914 in the training set and 0.867 in the validation set.
  • Specificity and accuracy were 85.1% and 82.3% during training, and 66.7% and 76.2% during validation.
  • Multivariate analysis identified maximum lesion diameter, Ki-67, and background parenchymal enhancement as independent predictors.

Takeaway

This study created a tool that helps doctors figure out if certain breast lumps might turn into cancer, so they can avoid unnecessary surgeries.

Methodology

The study used a retrospective design with 138 patients, dividing them into training and validation sets, and developed a nomogram based on radiomics features from MRI.

Potential Biases

Selection bias may affect the generalizability of the findings.

Limitations

The study is limited by its single-center design and the potential for selection bias.

Participant Demographics

All participants were female, aged 25 to 83 years, with various types of high-risk breast lesions.

Statistical Information

P-Value

<0.001

Confidence Interval

95% CI for AUC values reported

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.3389/fonc.2024.1479565

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication