Feng Cuixia, Zhao Hulin, Li Yueer, Cheng Zhibiao, Wen Junhai
Department of Biomedical Engineering, School of Life Science, Beijing Institute of Technology, Beijing, China.
The Sixth Medical Center of PLA General Hospital, Beijing, China.
Med Phys. 2021 Feb;48(2):912-925. doi: 10.1002/mp.14646. Epub 2020 Dec 21.
Focal cortical dysplasia (FCD) is a malformation of cortical development that often causes pharmacologically intractable epilepsy. However, FCD lesions are frequently characterized by minor structural abnormalities that can easily go unrecognized, making diagnosis difficult. Therefore, many epileptic patients have had pathologically confirmed FCD lesions that appeared normal in pre-surgical fluid-attenuated inversion recovery (FLAIR) magnetic resonance (MR) studies. Such lesions are called "FLAIR-negative." This study aimed to improve the detection of histopathologically verified FCD in a sample of patients without visually appreciable lesions.
The technique first extracts a series of features from a FLAIR image. Then, three naive Bayesian classifiers with probability (NBCP) are trained based on different numbers of feature maps to classify voxels as lesional or healthy voxels and assign the lesions a probability of correct classification. This method classifies the three-dimensional (3D) images of all patients using leave-one-out cross-validation (LOOCV). Finally, the 3D lesion probability map, including epileptogenic lesions, is obtained by removing false-positive voxel outliers using the morphological method. The performance of the NBCP was assessed for quantitative analysis by specificity, accuracy, recall, precision, and Dice coefficient in subject-wise, lesion-wise, and voxel-wise manners.
The best detection results were obtained by using four features: cortical thickness, symmetry, K-means, and modified texture energy. There were eight lesions in seven patients. The subject-wise sensitivity of the proposed method was 85.71% (6/7). Seven out of eight lesions were detected, so the lesion-wise sensitivity was 87.50% (7/8). No significant differences in effectiveness were found between automated lesion detection using four features and lesion detection using manual segmentation, as voxels were quantitatively analyzed in terms of specificity (mean ± SD = 99.64 ± 0.13), accuracy (mean ± SD = 99.62 ± 0.14), recall (mean ± SD = 73.27 ± 26.11), precision (mean ± SD = 11.93 ± 8.16), and Dice coefficient (mean ± SD = 22.82 ± 15.57).
We developed a novel automatic voxel-based method to improve the detection of FCD FLAIR-negative lesions. To the best of our knowledge, this study is the first to detect FCD lesions that appear normal in pre-surgical 3D high-resolution FLAIR images alone with a limited number of radiomics features. We optimized the algorithm and selected the best prior probability to improve the detection. For non-temporal lobe epilepsy (non-TLE) patients, lesions could be accurately located, although there were still false-positive areas.
局灶性皮质发育不良（FCD）是一种皮质发育畸形，常导致药物难治性癫痫。然而，FCD病变的特征通常是轻微的结构异常，很容易被忽视，这使得诊断困难。因此，许多癫痫患者在术前液体衰减反转恢复（FLAIR）磁共振（MR）研究中，其病变在病理上已得到证实，但在影像学上却表现正常。这种病变被称为“FLAIR阴性”。本研究旨在提高在无明显可视病变的患者样本中对经组织病理学证实的FCD的检测能力。
该技术首先从FLAIR图像中提取一系列特征。然后，基于不同数量的特征图训练三个带概率的朴素贝叶斯分类器（NBCP），以将体素分类为病变体素或健康体素，并为病变分配正确分类的概率。该方法使用留一法交叉验证（LOOCV）对所有患者的三维（3D）图像进行分类。最后，通过形态学方法去除假阳性体素异常值，获得包括致痫病变在内的3D病变概率图。通过在受试者层面、病变层面和体素层面的特异性、准确性、召回率、精确率和Dice系数对NBCP的性能进行评估，以进行定量分析。
使用皮质厚度、对称性、K均值和改进的纹理能量这四个特征获得了最佳检测结果。7例患者中有8个病变。所提方法在受试者层面的敏感性为85.71%（6/7）。8个病变中的7个被检测到，因此在病变层面的敏感性为87.50%（7/8）。在使用四个特征的自动病变检测和使用手动分割的病变检测之间，未发现有效性的显著差异，因为在特异性（均值±标准差=99.64±0.13）、准确性（均值±标准差=99.62±0.14）、召回率（均值±标准差=73.27±26.11）、精确率（均值±标准差=11.93±8.16）和Dice系数（均值±标准差=22.82±15.57）方面对体素进行了定量分析。
我们开发了一种基于体素的新型自动方法，以改进对FCD FLAIR阴性病变的检测。据我们所知，本研究是首次仅使用有限数量的影像组学特征，在术前3D高分辨率FLAIR图像中检测出看似正常的FCD病变。我们优化了算法并选择了最佳先验概率以提高检测能力。对于非颞叶癫痫（non-TLE）患者，尽管仍有假阳性区域，但病变能够被准确定位。
