Pawan S J, Rich Joseph, Le Jonathan, Yi Ethan, Triche Timothy, Goldkorn Amir, Duddalwar Vinay
Department of Radiology, Keck School of Medicine of the University of Southern California, Los Angeles, California, USA.
Radiomics lab, Keck School of Medicine of the University of Southern California, Los Angeles, California, USA.
iRadiology. 2024 Dec;2(6):527-538. doi: 10.1002/ird3.99. Epub 2024 Sep 26.
The skeletal system is the most common site of metastatic prostate cancer, and these lesions are associated with poor outcomes. Diagnosing these osseous metastatic lesions relies on radiologic imaging, making early detection, diagnosis, and monitoring crucial for clinical management. However, the literature lacks a detailed analysis of various approaches and future directions. To address this gap, we present a scoping review of quantitative methods from diverse domains, including radiomics, machine learning, and deep learning, applied to imaging analysis of prostate cancer with clinical insights. Our findings highlight the need for developing clinically significant methods to aid in the battle against prostate bone metastasis.
骨骼系统是转移性前列腺癌最常见的部位,这些病变与不良预后相关。诊断这些骨转移性病变依赖于放射影像学检查,因此早期检测、诊断和监测对临床管理至关重要。然而,文献中缺乏对各种方法和未来方向的详细分析。为了填补这一空白,我们对来自不同领域(包括放射组学、机器学习和深度学习)的定量方法进行了一项范围综述,这些方法应用于前列腺癌的影像学分析并提供临床见解。我们的研究结果强调了开发具有临床意义的方法以助力对抗前列腺骨转移的必要性。