Djuričić Goran J, Rajković Nemanja, Milošević Nebojša, Sopta Jelena P, Borić Igor, Dučić Siniša, Apostolović Milan, Radulovic Marko
Department of Radiology, University Children's Hospital, School of Medicine, University of Belgrade, Belgrade, 11000, Serbia.
Department of Biophysics, School of Medicine, University of Belgrade, Belgrade, 11000, Serbia.
Biomark Med. 2021 Aug;15(12):929-940. doi: 10.2217/bmm-2020-0876. Epub 2021 Jul 8.
This study aimed to improve osteosarcoma chemoresponsiveness prediction by optimization of computational analysis of MRIs. Our retrospective predictive model involved osteosarcoma patients with MRI scans performed before OsteoSa MAP neoadjuvant cytotoxic chemotherapy. We found that several monofractal and multifractal algorithms were able to classify tumors according to their chemoresponsiveness. The predictive clues were defined as morphological complexity, homogeneity and fractality. The monofractal feature CV for Λ'(G) provided the best predictive association (area under the ROC curve = 0.88; p <0.001), followed by Y-axis intersection of the regression line for box fractal dimension, r² for FD and tumor circularity. This is the first full-scale study to indicate that computational analysis of pretreatment MRIs could provide imaging biomarkers for the classification of osteosarcoma according to their chemoresponsiveness.
本研究旨在通过优化磁共振成像（MRI）的计算分析来改善骨肉瘤化疗反应性预测。我们的回顾性预测模型纳入了在骨肉瘤MAP新辅助细胞毒性化疗前进行MRI扫描的骨肉瘤患者。我们发现，几种单分形和多分形算法能够根据肿瘤的化疗反应性对其进行分类。预测线索被定义为形态复杂性、同质性和分形性。Λ'(G)的单分形特征CV提供了最佳的预测关联（ROC曲线下面积=0.88；p<0.001），其次是盒维数回归线的Y轴截距、FD的r²以及肿瘤圆形度。这是第一项全面研究，表明预处理MRI的计算分析可为根据骨肉瘤化疗反应性进行分类提供影像生物标志物。
