基于瘤周组织考虑的放射组学和深度学习在 DCE-MRI 上对乳腺良恶性病变的诊断。
Diagnosis of Benign and Malignant Breast Lesions on DCE-MRI by Using Radiomics and Deep Learning With Consideration of Peritumor Tissue.
机构信息
Department of Radiology, First Affiliate Hospital of Wenzhou Medical University, Wenzhou, China.
Department of Radiological Sciences, University of California, Irvine, California, USA.
出版信息
J Magn Reson Imaging. 2020 Mar;51(3):798-809. doi: 10.1002/jmri.26981. Epub 2019 Nov 1.
BACKGROUND
Computer-aided methods have been widely applied to diagnose lesions detected on breast MRI, but fully-automatic diagnosis using deep learning is rarely reported.
PURPOSE
To evaluate the diagnostic accuracy of mass lesions using region of interest (ROI)-based, radiomics and deep-learning methods, by taking peritumor tissues into consideration.
STUDY TYPE
Retrospective.
POPULATION
In all, 133 patients with histologically confirmed 91 malignant and 62 benign mass lesions for training (74 patients with 48 malignant and 26 benign lesions for testing).
FIELD STRENGTH/SEQUENCE: 3T, using the volume imaging for breast assessment (VIBRANT) dynamic contrast-enhanced (DCE) sequence.
ASSESSMENT
3D tumor segmentation was done automatically by using fuzzy-C-means algorithm with connected-component labeling. A total of 99 texture and histogram parameters were calculated for each case, and 15 were selected using random forest to build a radiomics model. Deep learning was implemented using ResNet50, evaluated with 10-fold crossvalidation. The tumor alone, smallest bounding box, and 1.2, 1.5, 2.0 times enlarged boxes were used as inputs.
STATISTICAL TESTS
The malignancy probability was calculated using each model, and the threshold of 0.5 was used to make a diagnosis.
RESULTS
In the training dataset, the diagnostic accuracy was 76% using three ROI-based parameters, 84% using the radiomics model, and 86% using ROI + radiomics model. In deep learning using the per-slice basis, the area under the receiver operating characteristic (ROC) was comparable for tumor alone, smallest and 1.2 times box (AUC = 0.97-0.99), which were significantly higher than 1.5 and 2.0 times box (AUC = 0.86 and 0.71, respectively). For per-lesion diagnosis, the highest accuracy of 91% was achieved when using the smallest bounding box, and that decreased to 84% for tumor alone and 1.2 times box, and further to 73% for 1.5 times box and 69% for 2.0 times box. In the independent testing dataset, the per-lesion diagnostic accuracy was also the highest when using the smallest bounding box, 89%.
DATA CONCLUSION
Deep learning using ResNet50 achieved a high diagnostic accuracy. Using the smallest bounding box containing proximal peritumor tissue as input had higher accuracy compared to using tumor alone or larger boxes.
LEVEL OF EVIDENCE
3 Technical Efficacy: Stage 2.
背景
计算机辅助方法已广泛应用于诊断乳腺 MRI 检测到的病变，但很少有使用深度学习进行全自动诊断的报道。
目的
通过考虑肿瘤周围组织，评估基于感兴趣区域（ROI）、放射组学和深度学习方法对肿块病变的诊断准确性。
研究类型
回顾性。
人群
共有 133 名经组织学证实的 91 例恶性和 62 例良性肿块病变患者用于训练（74 名患者中有 48 例恶性和 26 例良性病变用于测试）。
场强/序列：3T，使用容积成像乳腺评估（VIBRANT）动态对比增强（DCE）序列。
评估
使用模糊 C 均值算法结合连通分量标记自动进行 3D 肿瘤分割。为每个病例计算了 99 个纹理和直方图参数，并使用随机森林选择了 15 个参数来构建放射组学模型。使用 ResNet50 实现深度学习，使用 10 折交叉验证进行评估。分别使用肿瘤本身、最小边界框以及放大 1.2、1.5、2.0 倍的方框作为输入。
统计检验
使用每个模型计算恶性概率，并使用 0.5 作为诊断阈值。
结果
在训练数据集中，使用三种基于 ROI 的参数的诊断准确率为 76%，使用放射组学模型的诊断准确率为 84%，使用 ROI+放射组学模型的诊断准确率为 86%。在基于切片的深度学习中，肿瘤本身、最小边界框和 1.2 倍方框的接收器工作特征（ROC）曲线下面积（AUC）相当（AUC=0.97-0.99），显著高于 1.5 倍和 2.0 倍方框（AUC=0.86 和 0.71，分别）。对于每个病变的诊断，使用最小边界框可获得最高的 91%准确率，其次是肿瘤本身（84%）和 1.2 倍方框（84%），然后是 1.5 倍方框（73%）和 2.0 倍方框（69%）。在独立的测试数据集，使用最小边界框时，病变的诊断准确率也是最高的，为 89%。
数据结论
使用 ResNet50 的深度学习达到了很高的诊断准确率。与仅使用肿瘤或更大的方框相比，使用包含肿瘤周围近端组织的最小边界框作为输入具有更高的准确性。
证据水平
3 级技术功效：2 级。
Zotero 插件