Diffusion Histology Imaging Combining Diffusion Basis Spectrum Imaging (DBSI) and Machine Learning Improves Detection and Classification of Glioblastoma Pathology.
Diffusion Histology Imaging Combining Diffusion Basis Spectrum Imaging (DBSI) and Machine Learning Improves Detection and Classification of Glioblastoma Pathology.
复制标题
DOI：
10.1158/1078-0432.ccr-20-0736
复制
发表时间：
2020-10-15
期刊：
影响因子：
--
通讯作者：
Song SK
中科院分区：
文献类型：
--
作者：
Ye Z;Price RL;Liu X;Lin J;Yang Q;Sun P;Wu AT;Wang L;Han RH;Song C;Yang R;Gary SE;Mao DD;Wallendorf M;Campian JL;Li JS;Dahiya S;Kim AH;Song SK
胶质母细胞瘤（GBM）是最致命的癌症之一，无法治愈。虽然常规MRI已被广泛用于临床检查GBM，但用于改善诊断、手术计划和治疗评价的肿瘤组织病理学的准确神经影像学评估在GBM的临床管理中仍然是未满足的需求。我们采用一种新的扩散组织学成像（DHI）方法，结合扩散基础光谱成像（DBSI）和机器学习，检测，区分和量化GBM中的高细胞性，肿瘤坏死和肿瘤浸润区域。Gd增强T1W或高信号FLAIR不能反映GBM患者肿瘤的形态学复杂性。与表观扩散系数（ADC）与肿瘤细胞数增加呈负相关的传统观点相反，我们证明了ADC与胶质母细胞瘤标本中组织学证实的肿瘤细胞数之间的不一致，而DBSI衍生的限制性各向同性扩散分数与相同标本中的肿瘤细胞数呈正相关。通过将DBSI指标作为监督机器学习算法的分类器，我们准确地预测了高肿瘤细胞数、肿瘤坏死和肿瘤浸润，准确率分别为87.5%、89.0%和93.4%。我们的研究结果表明，DHI可以作为一个有利的替代目前的神经影像学技术在指导活检或手术，以及监测治疗反应，在胶质母细胞瘤的治疗。
Glioblastoma (GBM) is one of the deadliest cancers with no cure. While conventional MRI has been widely adopted to examine GBM clinically, accurate neuroimaging assessment of tumor histopathology for improved diagnosis, surgical planning, and treatment evaluation remains an unmet need in the clinical management of GBMs. We employ a novel Diffusion Histology Imaging (DHI) approach, combining diffusion basis spectrum imaging (DBSI) and machine learning, to detect, differentiate, and quantify areas of high cellularity, tumor necrosis, and tumor infiltration in GBM. Gd-enhanced T1W or hyper-intense FLAIR failed to reflect the morphological complexity underlying tumor in GBM patients. Contrary to the conventional wisdom that apparent diffusion coefficient (ADC) negatively correlates with increased tumor cellularity, we demonstrate disagreement between ADC and histologically confirmed tumor cellularity in glioblastoma specimens, whereas DBSI-derived restricted isotropic diffusion fraction positively correlated with tumor cellularity in the same specimens. By incorporating DBSI metrics as classifiers for a supervised machine learning algorithm, we accurately predicted high tumor cellularity, tumor necrosis, and tumor infiltration with 87.5%, 89.0% and 93.4% accuracy, respectively. Our results suggest that DHI could serve as a favorable alternative to current neuroimaging techniques in guiding biopsy or surgery as well as monitoring therapeutic response in the treatment of glioblastoma.