Vogl Wolf-Dieter, Pinker Katja, Helbich Thomas H, Bickel Hubert, Grabner Günther, Bogner Wolfgang, Gruber Stephan, Bago-Horvath Zsuzsanna, Dubsky Peter, Langs Georg
Computational Imaging Research Laboratory, Department of Biomedical Imaging and Image-guided Therapy, Medical University Vienna, Waehringer Guertel 18-20, 1090, Vienna, Austria.
Division of Molecular and Gender Imaging, Department of Biomedical Imaging and Image-guided Therapy, Medical University Vienna, 1090, Vienna, Austria.
Eur Radiol Exp. 2019 Apr 27;3(1):18. doi: 10.1186/s41747-019-0096-3.
Multiparametric positron emission tomography/magnetic resonance imaging (mpPET/MRI) shows clinical potential for detection and classification of breast lesions. Yet, the contribution of features for computer-aided segmentation and diagnosis (CAD) need to be better understood. We proposed a data-driven machine learning approach for a CAD system combining dynamic contrast-enhanced (DCE)-MRI, diffusion-weighted imaging (DWI), and F-fluorodeoxyglucose (F-FDG)-PET.
The CAD incorporated a random forest (RF) classifier combined with mpPET/MRI intensity-based features for lesion segmentation and shape features, kinetic and spatio-temporal texture features, for lesion classification. The CAD pipeline detected and segmented suspicious regions and classified lesions as benign or malignant. The inherent feature selection method of RF and alternatively the minimum-redundancy-maximum-relevance feature ranking method were used.
In 34 patients, we report a detection rate of 10/12 (83.3%) and 22/22 (100%) for benign and malignant lesions, respectively, a Dice similarity coefficient of 0.665 for segmentation, and a classification performance with an area under the curve at receiver operating characteristics analysis of 0.978, a sensitivity of 0.946, and a specificity of 0.936. Segmentation but not classification performance of DCE-MRI improved with information from DWI and FDG-PET. Feature ranking revealed that kinetic and spatio-temporal texture features had the highest contribution for lesion classification. F-FDG-PET and morphologic features were less predictive.
Our CAD enables the assessment of the relevance of mpPET/MRI features on segmentation and classification accuracy. It may aid as a novel computational tool for exploring different modalities/features and their contributions for the detection and classification of breast lesions.
多参数正电子发射断层扫描/磁共振成像（mpPET/MRI）在乳腺病变的检测和分类方面显示出临床潜力。然而，对于计算机辅助分割和诊断（CAD）的特征贡献需要更好地理解。我们提出了一种数据驱动的机器学习方法，用于结合动态对比增强（DCE）-MRI、扩散加权成像（DWI）和氟代脱氧葡萄糖（F-FDG）-PET的CAD系统。
该CAD系统采用随机森林（RF）分类器，结合基于mpPET/MRI强度的特征进行病变分割，并结合形状特征、动力学和时空纹理特征进行病变分类。CAD流程检测并分割可疑区域，并将病变分类为良性或恶性。使用了RF的固有特征选择方法以及最小冗余最大相关特征排序方法。
在34例患者中，我们报告良性病变的检测率为10/12（83.3%），恶性病变的检测率为22/22（100%），分割的骰子相似系数为0.665，在接受者操作特征分析中分类性能的曲线下面积为0.978，灵敏度为0.946，特异性为0.936。DCE-MRI的分割性能而非分类性能随着DWI和FDG-PET信息的加入而提高。特征排序显示，动力学和时空纹理特征对病变分类的贡献最大。F-FDG-PET和形态学特征的预测性较低。
我们的CAD系统能够评估mpPET/MRI特征对分割和分类准确性的相关性。它可能有助于作为一种新型计算工具，用于探索不同模态/特征及其对乳腺病变检测和分类的贡献。
