Zhang Daqu, Dihge Looket, Bendahl Pär-Ola, Arvidsson Ida, Dustler Magnus, Ellbrant Julia, Gulis Kim, Hjärtström Malin, Ohlsson Mattias, Rejmer Cornelia, Schmidt David, Zackrisson Sophia, Edén Patrik, Rydén Lisa
Centre for Environmental and Climate Science, Computational Science for Health and Environment, Lund University, Lund, Sweden.
Department of Clinical Sciences, Division of Surgery, Lund University, Skåne University Hospital, Lund, Sweden.
NPJ Digit Med. 2025 Jul 10;8(1):425. doi: 10.1038/s41746-025-01831-8.
With the shift toward de-escalating surgery in breast cancer, prediction models incorporating imaging can reassess the need for surgical axillary staging. This study employed advancements in deep learning to comprehensively evaluate routine mammograms for preoperative lymph node metastasis prediction. Mammograms and clinicopathological data from 1265 cN0 T1-T2 breast cancer patients (primary surgery, no neoadjuvant therapy) were retrospectively collected from three Swedish institutions. Compared to models using only clinical variables, incorporating full-breast mammograms with preoperative clinical variables improved the ROC AUC from 0.690 to 0.774 (improvement: 0.001-0.154) in the independent test set. The combined model showed good calibration and, at sensitivity ≥90%, achieved a significantly better net benefit, and a sentinel lymph node biopsy reduction rate of 41.7% (13.0-62.6%). Our findings suggest that routine mammograms, particularly full-breast images, can enhance preoperative nodal status prediction. They may substitute key predictors such as pathological tumor size and multifocality, aiding patient stratification before surgery.
随着乳腺癌手术向降阶梯治疗的转变，结合影像学的预测模型可以重新评估腋窝手术分期的必要性。本研究利用深度学习的进展，全面评估常规乳腺钼靶片以预测术前淋巴结转移情况。回顾性收集了来自瑞典三个机构的1265例cN0 T1-T2期乳腺癌患者（初次手术，未接受新辅助治疗）的乳腺钼靶片和临床病理数据。在独立测试集中，与仅使用临床变量的模型相比，将全乳钼靶片与术前临床变量相结合，使ROC曲线下面积从0.690提高到0.774（提高幅度：0.001-0.154）。联合模型显示出良好的校准，在灵敏度≥90%时，实现了显著更好的净效益，前哨淋巴结活检减少率为41.7%（13.0-62.6%）。我们的研究结果表明，常规乳腺钼靶片，尤其是全乳图像，可以提高术前淋巴结状态的预测能力。它们可能替代病理肿瘤大小和多灶性等关键预测指标，有助于术前对患者进行分层。
