School of Computer Science and Technology, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, China.
Department VI of Radiation Oncology, Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical Sciences, Jinan 250117, China.
Comput Math Methods Med. 2020 Apr 7;2020:6913418. doi: 10.1155/2020/6913418. eCollection 2020.
The objective of this study is to investigate the use of texture analysis (TA) of magnetic resonance image (MRI) enhanced scan and machine learning methods for distinguishing different grades in breast invasive ductal carcinoma (IDC). Preoperative prediction of the grade of IDC can provide reference for different clinical treatments, so it has important practice values in clinic.
Firstly, a breast cancer segmentation model based on discrete wavelet transform (DWT) and -means algorithm is proposed. Secondly, TA was performed and the Gabor wavelet analysis is used to extract the texture feature of an MRI tumor. Then, according to the distance relationship between the features, key features are sorted and feature subsets are selected. Finally, the feature subset is classified by using a support vector machine and adjusted parameters to achieve the best classification effect.
By selecting key features for classification prediction, the classification accuracy of the classification model can reach 81.33%. 3-, 4-, and 5-fold cross-validation of the prediction accuracy of the support vector machine model is 77.79%~81.94%.
The pathological grading of IDC can be predicted and evaluated by texture analysis and feature extraction of breast tumors. This method can provide much valuable information for doctors' clinical diagnosis. With further development, the model demonstrates high potential for practical clinical use.
本研究旨在探讨磁共振成像（MRI）增强扫描的纹理分析（TA）和机器学习方法在鉴别乳腺浸润性导管癌（IDC）不同分级中的应用。术前预测 IDC 的分级可为不同的临床治疗提供参考，因此在临床上具有重要的实用价值。
首先，提出了一种基于离散小波变换（DWT）和 -means 算法的乳腺癌分割模型。其次，进行 TA，并使用 Gabor 小波分析提取 MRI 肿瘤的纹理特征。然后，根据特征之间的距离关系，对特征进行排序并选择特征子集。最后，使用支持向量机对特征子集进行分类，并调整参数以达到最佳分类效果。
通过对分类预测进行关键特征选择，分类模型的分类准确率可达 81.33%。支持向量机模型的 3 倍、4 倍和 5 倍交叉验证预测准确率为 77.79%~81.94%。
通过对乳腺肿瘤的纹理分析和特征提取，可以预测和评估 IDC 的病理分级。该方法可为医生的临床诊断提供有价值的信息。随着进一步的发展，该模型具有很高的实际临床应用潜力。
