Breast‐conserving surgery (BCS) combined with sentinel lymph node biopsy (SLNB) is a standard treatment for early‐stage breast cancer. However, surgical variability and patient discomfort under regional anesthesia present challenges for training programs and consistent clinical outcomes. To address this, we implemented a breast modular resection (BMR) surgical teaching course designed to deconstruct BCS + SLNB into standardized modules and evaluated its impact on training effectiveness and patient outcomes in the day surgery setting under regional anesthesia.

A total of 273 patients underwent BCS with SLNB between 2019 and 2022, performed by six attending breast surgeons. Patients were divided into a classical procedure resection group (n = 124) and a BMR group (n = 149). All surgeries were performed under regional anesthesia. Clinical and subjective outcome indicators, such as re‐excision rate, pain scores, cosmetic satisfaction, and hospital stay, were analyzed.

The BMR group showed significantly more favorable perioperative outcomes, including lower re‐excision rates (3.85% vs. 11.88%, p = 0.038), reduced intraoperative pain (p < 0.05), decreased seroma incidence (9.62% vs. 20.79%, p = 0.032), and enhanced breast symmetry satisfaction (p = 0.008). A substantially higher proportion of BMR patients were discharged on postoperative Day 1 (79.81% vs. 31.68%, p < 0.001), confirming the feasibility of safe, same‐day BCS + SLNB. There were no differences in long‐term complications or recurrence.

The BMR‐based teaching model improved surgical performance, standardized the technique, and enhanced the patient experience for BCS + SLNB under regional anesthesia. This structured modular approach provides a replaceable framework for surgical education and may facilitate broader adoption of day‐case breast cancer surgery without compromising oncologic safety or patient comfort.

Cyclin‐dependent kinase 4/6 (CDK4/6) inhibitors have become a cornerstone in the first‐line management of hormone receptor‐positive, human epidermal growth factor receptor 2‐negative (HR+/HER2−) advanced breast cancer. Despite their clinical efficacy, most patients eventually experience disease progression, and optimal treatment strategies following CDK4/6 inhibitor resistance remain unclear. Emerging evidence suggests that switching endocrine therapy (ET) while continuing cyclin inhibition may provide additional clinical benefit. Dalpiciclib, a selective CDK4/6 inhibitor, in combination with physician‐selected ET, represents a potential option in this setting. Concurrently, 16α‐[¹⁸F]fluoro‐17β‐estradiol ([¹⁸F]FES) PET/CT, a novel imaging modality targeting estrogen receptors (ER), enables non‐invasive, whole‐body assessment of ER expression in metastatic lesions, offering a personalized approach to treatment selection.

This is a prospective, single‐center, single‐arm Phase Ⅱ clinical trial evaluating the efficacy and safety of dalpiciclib plus ET in HR+/HER2− advanced breast cancer patients who progressed on prior CDK4/6 inhibitor therapy. Forty eligible patients with confirmed metastases and at least one [¹⁸F]FES‐positive lesion will be enrolled. Participants will receive dalpiciclib combined with ET as determined by the treating physician. The primary endpoint is progression‐free survival (PFS). Secondary endpoints include objective response rate (ORR), disease control rate (DCR), and overall survival (OS).

Beyond evaluating efficacy, this single‐center phase Ⅱ trial will provide practical insight into the feasibility of [¹⁸F]FES PET/CT‐guided patient selection, including standardized imaging workflows and multidisciplinary implementation in routine clinical research. Positive outcomes may support a personalized, imaging‐guided strategy to prolong disease control after prior CDK4/6 inhibitor progression.

Approved by the Ethics Committee of Peking Union Medical College Hospital (Approval number: K3629); registered at ClinicalTrials. gov (NCT05613270).

Sclerosing adenosis (SA) and breast cancer (BC) often exhibit overlapping clinical, imaging, and pathological characteristics, making them difficult to differentiate. SA may also coexist with BC (SA + BC), including ductal carcinoma in situ (SA‐DCIS) and invasive breast cancer (SA‐IBC), which complicates diagnosis even when core‐needle biopsy (CNB) suggests SA. This study aimed to develop interpretable AI‐based binary and ternary classification models that leverage clinical and imaging features to distinguish SA‐only from SA + BC and to further differentiate among SA‐only, SA‐DCIS, and SA‐IBC.

We retrospectively analyzed a cohort of 726 patients with SA (January 2006 to December 2021), comprising 537 SA‐only and 189 SA + BC cases (90 SA‐DCIS, 99 SA‐IBC). Multiple machine learning algorithms—logistic regression, support vector machine, decision tree, XGBoost, and random forest—were compared using AUC, accuracy, F1‐score, and C‐index. Model interpretability was assessed with SHAP to elucidate feature contributions and identify key predictors. Additionally, we incorporated an independent external validation cohort consisting of 113 patients to verify the model's effectiveness.

XGBoost consistently outperformed other algorithms in both tasks. Eight features emerged as most informative: age, ultrasound BI‐RADS category, maximum and minimum ultrasound diameters, ultrasound margin characteristics, biopsy procedure, mammographic density, and microcalcifications. For binary classification (SA‐only vs. SA + BC), XGBoost achieved an AUC of 0.925, accuracy of 0.883, and C‐index of 0.844. For ternary classification (SA‐only, SA‐DCIS, SA‐IBC), the model achieved an AUC of 0.888, accuracy of 0.811, and C‐index of 0.813. Age, ultrasound BI‐RADS, and minimum lesion diameter were consistently top predictors. We further proposed a three‐tier interpretability framework (global, cohort‐level; local, subgroup‐level; and individual, case‐level) to facilitate clinical translation.

Given the substantial risk of coexisting of SA with DCIS or IBC, and the potential for CNB to underestimate disease due to limited sampling, lesions diagnosed as SA on CNB should be evaluated with additional modalities before determining the need for surgical excision. The proposed interpretable AI model enhances discrimination between SA‐only and SA with concomitant breast cancer (SA + BC), thereby supporting more informed clinical decision‐making in breast disease management.

To conduct a systematic analysis of a clinical surgery theoretical examination based on knowledge points, thereby providing a reference for establishing a scientific and comprehensive test paper analysis system.

Using the difficulty coefficient (P-value) and discrimination index (D-value) as indicators, a detailed evaluation was performed on 6 question types and 40 knowledge points from the Clinical Comprehensive Course: Surgery examination for the 2023 clinical medicine pilot class at Peking Union Medical College. Data were visualized using frequency distribution charts, radar charts, and scatter plots.

A total of 23 examination papers were collected. The students' average score was 78.63±7.58, with a pass rate of 100%. The overall examination difficulty was relatively low (P=0.79), and the overall discrimination was poor (D=0.15). Among the 40 knowledge points, 2 (5.0%) were difficult, 9 (22.5%) were moderately difficult, and 29 (72.5%) were relatively easy. Regarding discrimination, 3 (7.5%) knowledge points showed excellent discrimination, 8 (20.0%) demonstrated good or acceptable discrimination, and 29 (72.5%) had relatively poor discrimination. Some knowledge points [e.g., "Benign Prostatic Hyperplasia" (P=0.26, D=-0.17)] presented issues of high difficulty coupled with poor discrimination. A considerable number of knowledge points require corresponding adjustments.

Knowledge-point-based test paper analysis can provide references for optimizing question type design, thereby enhancing the scientific nature of assessments and offering a basis for teaching improvements.

To compare the clinical efficacy of intralesional corticosteroid injection combined with topical corticosteroids versus topical corticosteroids alone in patients with idiopathic granulomatous mastitis (IGM).

Patients diagnosed with IGM and treated at the Breast Surgery Department of Peking Union Medical College Hospital between October 2016 and March 2018 were retrospectively analyzed. Based on treatment modalities, patients were divided into an injection group (receiving intralesional corticosteroid injections plus topical corticosteroids) and a control group (receiving topical corticosteroids alone). Clinical outcomes and recurrence rates were compared between the two groups.

Seventy-eight patients meeting the inclusion and exclusion criteria were enrolled, with 51 in the injection group and 27 in the control group. The median age was 35 years (range: 22-45). The maximum lesion diameter was 8.7±2.9 cm in the injection group and 7.1±2.7 cm in the control group. Compared with the control group, the injection group showed a significantly shorter time to half remission(2.8±0.9 weeks vs. 4.2±1.3 weeks, P < 0.001) and a shorter time to complete remission(8.8±2.5 weeks vs. 10.1±2.7 weeks, P=0.043). During a follow-up period of 74 months, recurrence occurred in 2 patients in the injection group (1 ipsilateral and 1 contralateral) and 1 patient in the control group (contralateral).

Compared with topical corticosteroid monotherapy, the combina-tion of intralesional corticosteroid injection and topical corticosteroids provides faster symptom control and shorter treatment duration while maintaining high efficacy and low long-term recurrence rates, offering a more effective therapeutic option for IGM patients.