Hierarchical diagnosis of breast phyllodes tumors enabled by deep learning of ultrasound images: a retrospective multi-center study.
Authors
Affiliations (22)
Affiliations (22)
- 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.
- Taizhou Key Laboratory of Minimally Invasive Interventional Therapy & Artificial Intelligence, Taizhou Branch of Zhejiang Cancer Hospital (Taizhou Cancer Hospital), Taizhou, Zhejiang, China.
- Center of Intelligent Diagnosis and Therapy (Taizhou), Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences, Taizhou, Zhejiang, China.
- Interventional Medicine and Engineering Research Center, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences, Hangzhou, Zhejiang, China.
- Postgraduate training base Alliance of Wenzhou Medical University (Zhejiang Cancer Hospital), Hangzhou, Zhejiang, China.
- Department of Ultrasound, Lishui People's Hospital, Lishui, Zhejiang, China.
- Department of Ultrasound, Zhejiang Xiaoshan Hospital, Hangzhou, Zhejiang, China.
- Department of Ultrasound, The Affiliated Dongyang Hospital of Wenzhou Medical University, Dongyang, Zhejiang, China.
- Department of Ultrasound in Medicine, Affiliated Sir Run Run Shaw Hospital of Zhejiang University School of Medicine, Hangzhou, Zhejiang, China.
- Department of Ultrasound, Ruijin Hospital, Shanghai Jiaotong University School of Medicine, No.197, Ruijin 2nd Road, Huangpu District, Shanghai, Zhejiang, 200025, China. [email protected].
- Wenling Institute of Big Data and Artificial Intelligence Institute in Medicine, No.18, Civic Avenue, Wenling, Taizhou, Zhejiang, 317502, China. [email protected].
- Taizhou Key Laboratory of Minimally Invasive Interventional Therapy & Artificial Intelligence, Taizhou Branch of Zhejiang Cancer Hospital (Taizhou Cancer Hospital), Taizhou, Zhejiang, China. [email protected].
- Center of Intelligent Diagnosis and Therapy (Taizhou), Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences, Taizhou, Zhejiang, China. [email protected].
- Wenling Institute of Big Data and Artificial Intelligence Institute in Medicine, No.18, Civic Avenue, Wenling, Taizhou, Zhejiang, 317502, China. [email protected].
- Taizhou Key Laboratory of Minimally Invasive Interventional Therapy & Artificial Intelligence, Taizhou Branch of Zhejiang Cancer Hospital (Taizhou Cancer Hospital), Taizhou, Zhejiang, China. [email protected].
- Center of Intelligent Diagnosis and Therapy (Taizhou), Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences, Taizhou, Zhejiang, China. [email protected].
- Department of Diagnostic Ultrasound Imaging & Interventional Therapy, Zhejiang Cancer Hospital, No.1 East Banshan Road, Gongshu District, Hangzhou, Zhejiang, 310022, China. [email protected].
- Wenling Institute of Big Data and Artificial Intelligence Institute in Medicine, No.18, Civic Avenue, Wenling, Taizhou, Zhejiang, 317502, China. [email protected].
- Taizhou Key Laboratory of Minimally Invasive Interventional Therapy & Artificial Intelligence, Taizhou Branch of Zhejiang Cancer Hospital (Taizhou Cancer Hospital), Taizhou, Zhejiang, China. [email protected].
- Center of Intelligent Diagnosis and Therapy (Taizhou), Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences, Taizhou, Zhejiang, China. [email protected].
- Interventional Medicine and Engineering Research Center, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences, Hangzhou, Zhejiang, China. [email protected].
Abstract
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.