Tang Leonardo, Wu Tianhe, Hu Ranliang, Gu Quanquan, Yang Xiaofeng, Mao Hui
Department of Radiology and Imaging Sciences, Emory University School of Medicine, Atlanta, GA, USA.
Department of Radiation Oncology, Emory University School of Medicine, Atlanta, GA, USA.
Quant Imaging Med Surg. 2024 Apr 3;14(4):2774-2787. doi: 10.21037/qims-23-1471. Epub 2024 Mar 28.
Magnetic resonance imaging (MRI) is a primary non-invasive imaging modality for tumor segmentation, leveraging its exceptional soft tissue contrast and high resolution. Current segmentation methods typically focus on structural MRI, such as T-weighted post-contrast-enhanced or fluid-attenuated inversion recovery (FLAIR) sequences. However, these methods overlook the blood perfusion and hemodynamic properties of tumors, readily derived from dynamic susceptibility contrast (DSC) enhanced MRI. This study introduces a novel hybrid method combining density-based analysis of hemodynamic properties in time-dependent perfusion imaging with deep learning spatial segmentation techniques to enhance tumor segmentation.
First, a U-Net convolutional neural network (CNN) is employed on structural images to delineate a region of interest (ROI). Subsequently, Hierarchical Density-Based Scans (HDBScan) are employed within the ROI to augment segmentation by exploring intratumoral hemodynamic heterogeneity through the investigation of tumor time course profiles unveiled in DSC MRI.
The approach was tested and evaluated using a cohort of 513 patients from the open-source University of Pennsylvania glioblastoma database (UPENN-GBM) dataset, achieving a 74.83% Intersection over Union (IoU) score when compared to structural-only segmentation. The algorithm also exhibited increased precision and localized predictions of heightened segmentation boundary complexity, resulting in a 146.92% increase in contour complexity (ICC) compared to the reference standard provided by the UPENN-GBM dataset. Importantly, segmenting tumors with the developed new approach uncovered a negative correlation of the tumor volume with the scores in the Karnofsky Performance Scale (KPS) clinically used for assessing the functional status of patients (-0.309), which is not observed with the prevailing segmentation standard.
This work demonstrated that including hemodynamic properties of tissues from DSC MRI can improve existing structural or morphological feature-based tumor segmentation techniques with additional information on tumor biology and physiology. This approach can also be applied to other clinical indications that use perfusion MRI for diagnosis or treatment monitoring.
磁共振成像（MRI）凭借其出色的软组织对比度和高分辨率，是肿瘤分割的主要非侵入性成像方式。当前的分割方法通常专注于结构MRI，如T加权对比增强或液体衰减反转恢复（FLAIR）序列。然而，这些方法忽略了肿瘤的血流灌注和血流动力学特性，而这些特性可从动态对比增强（DSC）MRI中轻易获得。本研究引入了一种新颖的混合方法，将基于密度的时间依赖性灌注成像血流动力学特性分析与深度学习空间分割技术相结合，以增强肿瘤分割。
首先，在结构图像上使用U-Net卷积神经网络（CNN）来勾勒感兴趣区域（ROI）。随后，在ROI内采用基于密度的分层扫描（HDBScan），通过研究DSC MRI中揭示的肿瘤时间进程曲线，探索肿瘤内血流动力学异质性，以增强分割效果。
该方法在来自宾夕法尼亚大学胶质母细胞瘤数据库（UPENN-GBM）开源数据集的513名患者队列中进行了测试和评估，与仅基于结构的分割相比，实现了74.83%的交并比（IoU）分数。该算法还表现出更高的精度和对分割边界复杂性增加的局部预测，与UPENN-GBM数据集提供的参考标准相比，轮廓复杂性（ICC）增加了146.92%。重要的是，用开发的新方法分割肿瘤发现，肿瘤体积与临床上用于评估患者功能状态的卡氏功能状态评分（KPS）之间存在负相关（-0.309），而现有的分割标准未观察到这种相关性。
这项工作表明，纳入DSC MRI的组织血流动力学特性可以利用肿瘤生物学和生理学的额外信息改进现有的基于结构或形态特征的肿瘤分割技术。这种方法也可应用于其他使用灌注MRI进行诊断或治疗监测的临床适应症。
