# Intra-tumor and peritumoral radiomics and deep learning based on ultrasound for differentiating fibroadenoma and phyllodes tumor: a multicenter study

## TL;DR

This study uses ultrasound imaging and machine learning to accurately distinguish fibroadenomas from phyllodes tumors and classify the latter into subtypes, reducing the need for biopsies.

## Contribution

The novel contribution is a combined intra-tumoral and peritumoral radiomics-deep learning model that achieves high accuracy in differentiating and subtyping breast tumors using ultrasound.

## Key findings

- The integrated model achieved 96% accuracy in differentiating fibroadenomas from phyllodes tumors.
- Peritumoral analysis at 8mm expansion significantly improved model performance.
- The model reduced unnecessary biopsies by 11.7% overall.

## Abstract

To develop and validate an integrated intra-tumoral (ITR) and peritumoral (PTR) radiomics-deep learning model based on ultrasound (US) imaging for accurately differentiating fibroadenomas (FA) from phyllodes tumors (PT) and further classifying PT into benign, borderline, and malignant subtypes.

This multicenter retrospective study enrolled 300 patients (141 FA, 159 PT) from three institutions. US images were analyzed using manual segmentation of ITR and PTR (4mm, 8mm, 12mm, 16mm expansions). A total of 114 radiomics features were extracted per region using PyRadiomics. Five deep learning models (CNN, MLP, ViT, GAN, RNN) and six machine learning classifiers were evaluated. Optimal features were selected via LASSO and Boruta algorithms. Integrated models combining radiomics (ITR ± PTR) with clinical factors (diameter, Bi-RADS) were developed. Performance was assessed using AUC, accuracy, sensitivity, specificity, F1-score, and biopsy reduction rate. Internal validation used a 7:3 random split stratified by center and pathology. External validation was performed on a per-center hold-out basis.

The combined model (ITR + 8mm PTR + clinical) achieved the highest performance for FA/PT differentiation (AUC: 0.960; accuracy: 96.0%; sensitivity: 96.0%; specificity: 94.5%). For PT subtyping (benign/borderline/malignant), the model attained an AUC of 0.874 (accuracy: 77.2%). The integrated model significantly reduced unnecessary biopsy rates by 11.7% overall (18.1% for PT cases). Peritumoral analysis (8mm PTR) contributed critically to model performance, likely capturing stromal interactions at the tumor periphery.

Integrating intra-tumoral, peritumoral (8mm), and clinical US radiomics features enables highly accurate non-invasive differentiation of FA and PT and stratification of PT subtypes. This approach reduces diagnostic ambiguity in Bi-RADS 4 lesions and decreases unnecessary biopsies, demonstrating significant clinical utility for precision diagnosis of breast fibroepithelial tumors.