Convex Non-Negative Matrix Factorization for Brain Tumor Delimitation from MRSI Data

BackgroundPattern Recognition techniques can provide invaluable insights in the field of neuro-oncology. This is because the clinical analysis of brain tumors requires the use of non-invasive methods that generate complex data in electronic format. Magnetic Resonance (MR), in the modalities of spectroscopy (MRS) and spectroscopic imaging (MRSI), has been widely applied to this purpose. The heterogeneity of the tissue in the brain volumes analyzed by MR remains a challenge in terms of pathological area delimitation. Methodology/Principal FindingsA pre-clinical study was carried out using seven brain tumor-bearing mice. Imaging and spectroscopy information was acquired from the brain tissue. A methodology is proposed to extract tissue type-specific sources from these signals by applying Convex Non-negative Matrix Factorization (Convex-NMF). Its suitability for the delimitation of pathological brain area from MRSI is experimentally confirmed by comparing the images obtained with its application to selected target regions, and to the gold standard of registered histopathology data. The former showed good accuracy for the solid tumor region (proliferation index (PI)>30%). The latter yielded (i) high sensitivity and specificity in most cases, (ii) acquisition conditions for safe thresholds in tumor and non-tumor regions (PI>30% for solid tumoral region; ≤5% for non-tumor), and (iii) fairly good results when borderline pixels were considered. Conclusions/SignificanceThe unsupervised nature of Convex-NMF, which does not use prior information regarding the tumor area for its delimitation, places this approach one step ahead of classical label-requiring supervised methods for discrimination between tissue types, minimizing the negative effect of using mislabeled voxels. Convex-NMF also relaxes the non-negativity constraints on the observed data, which allows for a natural representation of the MRSI signal. This should help radiologists to accurately tackle one of the main sources of uncertainty in the clinical management of brain tumors, which is the difficulty of appropriately delimiting the pathological area.背景 模式识别技术可为神经肿瘤学领域提供极具价值的研究洞见。脑肿瘤的临床分析需采用无创方法生成电子化格式的复杂数据，这一需求使得该类技术的应用具备重要意义。磁共振光谱（Magnetic Resonance Spectroscopy, MRS）与磁共振光谱成像（Magnetic Resonance Spectroscopic Imaging, MRSI）已被广泛应用于该研究场景。但经MR扫描分析的脑组织体积内存在组织异质性，这仍是病理区域划定过程中的一大挑战。 方法学与主要研究结果 本研究针对7只脑肿瘤模型小鼠开展了临床前实验，采集了脑组织的成像与光谱信息。本文提出一种方法，通过应用凸非负矩阵分解（Convex Non-negative Matrix Factorization, Convex-NMF）从上述信号中提取组织类型特异性源信号。将应用该方法后得到的图像与选定的目标区域及配准后的组织病理学金标准数据进行对比，实验证实了该方法在基于MRSI划定病理脑区域中的适用性。实验结果显示，该方法在实体瘤区域（增殖指数（Proliferation Index, PI）>30%）的划分精度良好。进一步分析表明：(i) 多数场景下具备较高的灵敏度与特异性；(ii) 可确定肿瘤与非肿瘤区域的安全阈值采集条件（实体瘤区域PI>30%，非肿瘤区域PI≤5%）；(iii) 当纳入边界像素进行分析时，亦能取得较为理想的结果。 结论与意义 凸非负矩阵分解具备无监督特性，在划定肿瘤区域时无需使用肿瘤区域的先验信息，这使得该方法优于传统依赖标签的监督式组织类型区分方法，最大限度降低了使用标记错误体素带来的负面影响。此外，凸非负矩阵分解还放宽了对观测数据的非负约束，可自然表征MRSI信号。该方法将帮助放射科医生精准应对脑肿瘤临床管理中的一项核心不确定性来源——即难以准确划定病理区域的问题。