Balaguer-Montero Maria, Marcos Morales Adrià, Ligero Marta, Zatse Christina, Leiva David, Atlagich Luz M, Staikoglou Nikolaos, Viaplana Cristina, Monreal Camilo, Mateo Joaquin, Hernando Jorge, García-Álvarez Alejandro, Salvà Francesc, Capdevila Jaume, Elez Elena, Dienstmann Rodrigo, Garralda Elena, Perez-Lopez Raquel
Radiomics Group, Vall d'Hebron Institute of Oncology (VHIO), 08035 Barcelona, Spain.
Radiomics Group, Vall d'Hebron Institute of Oncology (VHIO), 08035 Barcelona, Spain; Else Kroener Fresenius Center for Digital Health, Medical Faculty Carl Gustav Carus, TUD Dresden University of Technology, 01307 Dresden, Germany.
Cell Rep Med. 2025 Apr 15;6(4):102032. doi: 10.1016/j.xcrm.2025.102032. Epub 2025 Mar 20.
Liver tumors, whether primary or metastatic, significantly impact the outcomes of patients with cancer. Accurate identification and quantification are crucial for effective patient management, including precise diagnosis, prognosis, and therapy evaluation. We present SALSA (system for automatic liver tumor segmentation and detection), a fully automated tool for liver tumor detection and delineation. Developed on 1,598 computed tomography (CT) scans and 4,908 liver tumors, SALSA demonstrates superior accuracy in tumor identification and volume quantification, outperforming state-of-the-art models and inter-reader agreement among expert radiologists. SALSA achieves a patient-wise detection precision of 99.65%, and 81.72% at lesion level, in the external validation cohorts. Additionally, it exhibits good overlap, achieving a dice similarity coefficient (DSC) of 0.760, outperforming both state-of-the-art and the inter-radiologist assessment. SALSA's automatic quantification of tumor volume proves to have prognostic value across various solid tumors (p = 0.028). SALSA's robust capabilities position it as a potential medical device for automatic cancer detection, staging, and response evaluation.
肝脏肿瘤，无论是原发性还是转移性，都会对癌症患者的预后产生重大影响。准确识别和量化对于有效的患者管理至关重要，包括精确诊断、预后评估和治疗评估。我们展示了SALSA（肝脏肿瘤自动分割与检测系统），这是一种用于肝脏肿瘤检测和勾勒的全自动工具。基于1598例计算机断层扫描（CT）和4908个肝脏肿瘤开发的SALSA，在肿瘤识别和体积量化方面表现出卓越的准确性，优于现有最先进的模型以及专家放射科医生之间的阅片者一致性。在外部验证队列中，SALSA在患者层面的检测精度达到99.65%，在病灶层面达到81.72%。此外，它表现出良好的重叠性，骰子相似系数（DSC）为0.760，优于现有最先进技术和放射科医生之间的评估。SALSA对肿瘤体积的自动量化在各种实体瘤中被证明具有预后价值（p = 0.028）。SALSA强大的功能使其成为一种潜在的用于癌症自动检测、分期和反应评估的医疗设备。
