Yan Yuqi, Liu Yuanzhen, Wang Yao, Jiang Tian, Xie Jiayu, Zhou Yahan, Liu Xin, Yan Meiying, Zheng Qiuqing, Xu Haifei, Chen Jinxiao, Sui Lin, Chen Chen, Ru RongRong, Wang Kai, Zhao Anli, Li Shiyan, Zhu Ying, Zhang Yang, Wang Vicky Yang, Xu Dong
Department of Diagnostic Ultrasound Imaging & Interventional Therapy, Zhejiang Cancer Hospital, No.1 East Banshan Road, Gongshu District, Hangzhou, Zhejiang, 310022, China.
Wenling Institute of Big Data and Artificial Intelligence Institute in Medicine, No.18, Civic Avenue, Wenling, Taizhou, Zhejiang, 317502, China.
Cancer Imaging. 2025 May 8;25(1):61. doi: 10.1186/s40644-025-00879-9.
Phyllodes tumors (PTs) are rare breast tumors with high recurrence rates, current methods relying on post-resection pathology often delay detection and require further surgery. We propose a deep-learning-based Phyllodes Tumors Hierarchical Diagnosis Model (PTs-HDM) for preoperative identification and grading.
Ultrasound images from five hospitals were retrospectively collected, with all patients having undergone surgical pathological confirmation of either PTs or fibroadenomas (FAs). PTs-HDM follows a two-stage classification: first distinguishing PTs from FAs, then grading PTs into benign or borderline/malignant. Model performance metrics including AUC and accuracy were quantitatively evaluated. A comparative analysis was conducted between the algorithm's diagnostic capabilities and those of radiologists with varying clinical experience within an external validation cohort. Through the provision of PTs-HDM's automated classification outputs and associated thermal activation mapping guidance, we systematically assessed the enhancement in radiologists' diagnostic concordance and classification accuracy.
A total of 712 patients were included. On the external test set, PTs-HDM achieved an AUC of 0.883, accuracy of 87.3% for PT vs. FA classification. Subgroup analysis showed high accuracy for tumors < 2 cm (90.9%). In hierarchical classification, the model obtained an AUC of 0.856 and accuracy of 80.9%. Radiologists' performance improved with PTs-HDM assistance, with binary classification accuracy increasing from 82.7%, 67.7%, and 64.2-87.6%, 76.6%, and 82.1% for senior, attending, and resident radiologists, respectively. Their hierarchical classification AUCs improved from 0.566 to 0.827 to 0.725-0.837. PTs-HDM also enhanced inter-radiologist consistency, increasing Kappa values from - 0.05 to 0.41 to 0.12 to 0.65, and the intraclass correlation coefficient from 0.19 to 0.45.
PTs-HDM shows strong diagnostic performance, especially for small lesions, and improves radiologists' accuracy across all experience levels, bridging diagnostic gaps and providing reliable support for PTs' hierarchical diagnosis.
叶状肿瘤（PTs）是罕见的乳腺肿瘤，复发率高，目前依赖切除后病理的方法往往会延迟诊断，且需要进一步手术。我们提出一种基于深度学习的叶状肿瘤分级诊断模型（PTs-HDM）用于术前识别和分级。
回顾性收集来自五家医院的超声图像，所有患者均经过手术病理确诊为PTs或纤维腺瘤（FAs）。PTs-HDM采用两阶段分类：首先区分PTs和FAs，然后将PTs分为良性或交界性/恶性。对包括AUC和准确率在内的模型性能指标进行定量评估。在外部验证队列中，对该算法与不同临床经验的放射科医生的诊断能力进行了比较分析。通过提供PTs-HDM的自动分类输出和相关的热激活映射指导，我们系统地评估了放射科医生诊断一致性和分类准确率的提高。
共纳入712例患者。在外部测试集上，PTs-HDM在PT与FA分类中的AUC为0.883，准确率为87.3%。亚组分析显示，对于<2cm的肿瘤，准确率较高（90.9%）。在分级分类中，该模型的AUC为0.856，准确率为80.9%。在PTs-HDM的辅助下，放射科医生的表现有所改善，高级、主治和住院放射科医生的二元分类准确率分别从82.7%、67.7%和64.2%提高到87.6%、76.6%和82.1%。他们的分级分类AUC从0.566提高到0.827，再到0.725至0.837。PTs-HDM还提高了放射科医生之间的一致性，将Kappa值从-0.05提高到0.41，再到0.12至0.65，组内相关系数从0.19提高到0.45。
PTs-HDM显示出强大的诊断性能，尤其是对小病变，并且提高了所有经验水平放射科医生的准确率，弥合了诊断差距，为PTs的分级诊断提供了可靠支持。
