Medical Physics Graduate Program, Duke Kunshan University, Kunshan, Jiangsu 215316, People's Republic of China.
Department of Radiation Oncology, Duke University, Durham, NC, 27710, United States of America.
Phys Med Biol. 2023 Sep 13;68(18). doi: 10.1088/1361-6560/acf10d.
To develop a deep ensemble learning (DEL) model with radiomics spatial encoding execution for improved glioma segmentation accuracy using multi-parametric magnetic resonance imaging (mp-MRI).This model was developed using 369 glioma patients with a four-modality mp-MRI protocol: T1, contrast-enhanced T1 (T1-Ce), T2, and FLAIR. In each modality volume, a 3D sliding kernel was implemented across the brain to capture image heterogeneity: 56 radiomic features were extracted within the kernel, resulting in a fourth-order tensor. Each radiomic feature can then be encoded as a 3D image volume, namely a radiomic feature map (RFM). For each patient, all RFMs extracted from all four modalities were processed using principal component analysis for dimension reduction, and the first four principal components (PCs) were selected. Next, a DEL model comprised of four U-Net sub-models was trained for the segmentation of a region-of-interest: each sub-model utilizes the mp-MRI and one of the four PCs as a five-channel input for 2D execution. Last, four softmax probability results given by the DEL model were superimposed and binarized using Otsu's method as the segmentation results. Three DEL models were trained to segment the enhancing tumor (ET), tumor core (TC), and whole tumor (WT), respectively. The segmentation results given by the proposed ensemble were compared to the mp-MRI-only U-Net results.All three radiomics-incorporated DEL models were successfully implemented: compared to the mp-MRI-only U-net results, the dice coefficients of ET (0.777 → 0.817), TC (0.742 → 0.757), and WT (0.823 → 0.854) demonstrated improvement. The accuracy, sensitivity, and specificity results demonstrated similar patterns.The adopted radiomics spatial encoding execution enriches the image heterogeneity information that leads to the successful demonstration of the proposed DEL model, which offers a new tool for mp-MRI-based medical image segmentation.
为了提高基于多参数磁共振成像（mp-MRI）的脑胶质瘤分割精度，开发了一种具有放射组学空间编码执行功能的深度集成学习（DEL）模型。该模型使用 369 名具有四模态 mp-MRI 方案（T1、对比增强 T1（T1-Ce）、T2 和 FLAIR）的脑胶质瘤患者进行开发。在每个模态体积中，通过大脑实现了 3D 滑动核，以捕获图像异质性：在核内提取了 56 个放射组学特征，产生了四阶张量。然后可以将每个放射组学特征编码为 3D 图像体积，即放射组学特征图（RFM）。对于每个患者，从所有四个模态中提取的所有 RFMs 都使用主成分分析进行降维处理，并选择前四个主成分（PCs）。接下来，使用四个 U-Net 子模型组成的 DEL 模型对感兴趣区域进行分割：每个子模型使用 mp-MRI 和四个 PC 之一作为五个通道输入进行 2D 执行。最后，DEL 模型给出的四个 softmax 概率结果通过 Otsu 方法进行叠加和二值化作为分割结果。三个 DEL 模型分别用于分割增强肿瘤（ET）、肿瘤核心（TC）和全肿瘤（WT）。与仅基于 mp-MRI 的 U-Net 结果相比，所提出的集合给出的分割结果。所有三个包含放射组学的 DEL 模型都成功实施：与仅基于 mp-MRI 的 U-Net 结果相比，ET（0.777→0.817）、TC（0.742→0.757）和 WT（0.823→0.854）的骰子系数有所提高。准确性、敏感性和特异性结果表现出相似的模式。所采用的放射组学空间编码执行丰富了图像异质性信息，这导致了所提出的 DEL 模型的成功演示，为基于 mp-MRI 的医学图像分割提供了新工具。
