Development and Clinical Application of Deep Learning-Based Prospective Pathology Foundation Models
试验速览
- 阶段
- 不适用
- 状态
- 招募中
- 入组人数
- 2,000
- 试验地点
- 2
- 主要终点
- Area under ROC curve (AUC)
研究概览
简要总结
Histopathology remains the gold standard for disease diagnosis, yet faces challenges including pathologist shortages and diagnostic model limitations. This underscores the critical need to develop deep learning-based pathology foundation models integrating prospective imaging and clinical data. Such models would enhance diagnostic accuracy and efficiency, enabling tumor grading, histo-molecular classification, and intelligent chemotherapy guidance - ultimately optimizing clinical workflows. However, a critical gap remains: the absence of prospectively validated, pan-disease pathology foundation models. Developing clinically validated models is therefore imperative.
研究设计
- 研究类型
- Observational
- 观察模型
- Cohort
- 时间视角
- Prospective
入排标准
- 年龄范围
- 18 Years 至 75 Years（Adult, Older Adult）
- 性别
- All
- 接受健康志愿者
- 否
入选标准
- •Aged 18-75 years old.
- •Patients with complete pathological slides and clinical information.
排除标准
- •1.Patients with missing data or specimens not meeting quality control requirements for analysis.
研究组 & 干预措施
QFSH external validation dataset
1000 slides from 1000 eligible individuals were obtained in the Qianfoshan Hospital (QFSH, Jinan, China) between January 2020 and July 2025, which was used to validate the pathology foundation models.
Prospective validation datasets
We conducted a prospective validation study to compare the diagnostic performance among pathologists, our pathology foundation model, and pathologist-with-AI-assisted diagnosis. This study was initiated on August 28, 2025 at Nanfang Hospital, Southern Medical University, The First Affiliated Hospital, Zhejiang University School of Medicine, The First Affiliated Hospital of Zhengzhou University, Zhujiang Hospital, Southern Medical University, Zhongshan People's Hospital, The First Affiliated Hospital of Shantou University Medical College, and Xijing Hospital, Fourth Military Medical University.
Randomized controlled trial
We conducted a prospective randomized controlled trial to compare the diagnostic performance among pathologists, the pathology foundation model, and pathologist-with-model-assisted diagnosis at Nanfang Hospital of Southern Medical University (NFHSMU).The trial commenced data collection on August 28, 2025 to establish the NFHSMU randomized controlled trial dataset. Following quality control, the slides were randomly allocated (1:1:1 ratio) into three groups:Model-only group/Pathologist-only group/Model-assisted pathologist group.
结局指标
主要结局
Area under ROC curve (AUC)
时间窗: Diagnostic evaluation will be performed within 1 week when the WSIs are obtained
Area under the curve
次要结局
- Sensitivity(Diagnostic evaluation will be performed within 1 week when the WSIs are obtained)
- Specificity(Diagnostic evaluation will be performed within 1 week when the WSIs are obtained)