Annals of Surgical Oncology最新文献

Background: Endocrine prevention is a well-established preventative strategy for women with high-risk lesions (HRL). The objective of the study was to evaluate factors associated with endocrine prevention adherence in this patient population.

Patients and methods: We performed a retrospective cohort study of all women referred for atypical ductal and lobular hyperplasia (ADH/ALH) and lobular carcinoma in situ (LCIS) between 2019 and 2025. Data pertaining to eligibility, initiation, and adherence to endocrine prevention were extracted with univariate analyses performed to evaluate factors associated with adherence.

Results: Among 200 female patients with HRL, 112 (56%) had ADH, 72 (36%) had ALH, and 16 (8%) had classical LCIS. The median age was 55 years (IQR 50-62 years), with 126 (63%) patients accepting a prescription for endocrine prevention. Low-dose tamoxifen was the most common regimen prescribed (65.1%), compared with regular-dose tamoxifen (13.5%), raloxifene (16.7%), and aromatase inhibitors (4.8%). At a median follow-up of 37 months (IQR 18-49 months), 83 of 126 women (65.9%) initiated endocrine prevention and 72 (57.1%) remained adherent. Age (67.7% 51-60 years versus 47.1% < 50 years, p = 0.046), family history of breast cancer (71.0% vs. 52.6%, p = 0.048), and awareness of endocrine prevention (75.0% vs. 52.0%, p = 0.03) were significantly associated with adherence. Of 50 patients who initiated tamoxifen 5 mg, 46 (92%) remained adherent, and of 13 women who completed at least 3 years of therapy, 9 (69.2%) elected to complete a total 5 year course of low-dose tamoxifen.

Conclusions: Adherence to endocrine prevention is high in women who initiate medication, with few discontinuing due to side effects.

Background: Fibroepithelial breast lesions, including fibroadenomas and phyllodes tumors (PTs), can be difficult to classify on needle biopsy. Misclassification may result in unnecessary excisions of benign fibroadenomas or delays and repeat operations for borderline/malignant PTs. Artificial Intelligence for Fibroepithelial Lesion Evaluation and Extrication Technology (AI-FLEET) is a multi-stage program designed to improve diagnostic accuracy and reduce inconclusive preoperative assessments by integrating radiologic, pathologic, and clinical data.

Patients and methods: In this first phase, we retrospectively analyzed patients with histologically confirmed PTs. Borderline and malignant PTs were grouped together owing to similarities in margin management and the limited number of cases. Models were trained to distinguish benign from borderline/malignant PTs using ultrasound images and clinical variables (age, body mass index (BMI), race/ethnicity, menopausal status, echogenicity, and tumor size). Multiple convolutional and attention-based encoders were evaluated using subject-stratified five-fold cross-validation.

Results: The cohort included 81 patients (65 benign, 16 borderline/malignant PTs) with 1638 ultrasound images. The multimodal ConvNeXt model achieved an accuracy of 0.91 (AUC 0.94), while the multimodal ResNet18 achieved an accuracy of 0.92 (AUC 0.94). Other multimodal architectures showed lower performance. Ultrasound-only and clinical-only models reached AUCs of 0.89 and 0.78, respectively. Saliency analyses identified intratumoral heterogeneity as an important predictive feature.

Conclusions: Multimodal deep learning models combining ultrasound and clinical factors achieved high accuracy in differentiating benign from borderline/malignant PTs, demonstrating the feasibility of AI-assisted assessment of fibroepithelial lesions. Phase II will expand this work by incorporating histopathology and fibroadenoma cases to further enhance radiologic-pathologic integration.