Deep learning-based spatiotemporal estimation of lesion changes for patient-level assessment of breast cancer lung metastases on longitudinal CT.
Authors
Affiliations (10)
Affiliations (10)
- School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China.
- Department of Breast Surgery, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, Beijing, China.
- Department of Electronic Engineering, Tsinghua University, Beijing, Beijing, China.
- Department of Radiology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, Beijing, China.
- Department of Radiology, Xiangya Hospital, Central South University, Changsha, Hunan, China.
- Department of Breast Diseases, Shanxi Provincial Hospital of Traditional Chinese Medicine, Taiyuan, Shanxi, China.
- Department of Breast Oncology, Peking University Cancer Hospital Inner Mongolia Hospital, Saihan District, Hohhot, China.
- Department of Breast and Thyroid Surgery, Liuzhou People's Hospital, Liuzhou, Guangxi, China.
- Department of Radiology, Liuzhou People's Hospital, Liuzhou, Guangxi, China.
- Department of Radiology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, Beijing, China. [email protected].
Abstract
Clinical management of breast cancer lung metastasis is challenging because of the complexity of dynamic lesion assessment. Traditional methods based on RECIST1.1 rely on size measurement, and existing studies require image registration and are limited to lesion-level assessment. In this study, we proposed a patient-level spatiotemporal assessment framework without registration to comprehensively analyze multiple lesions evolvement based on longitudinal CT images. Our method considers metastatic lesions that vary in size and often overlap with complex structures such as blood vessels and bones, and avoids potential registration errors. Our method outperforms state-of-the-art methods on both the Peking Union Medical College Hospital breast cancer lung metastasis dataset and the publicly available dataset. The model also showed excellent performance in a multicenter validation across four medical centers. We established a patient-level metastatic breast cancer assessment framework, providing a practical solution for longitudinal treatment monitoring.