Faculty of Biomedical Engineering, Amirkabir University of Technology, Tehran, Iran.
Faculty of Medical Sciences & Technologies, Science & Research Branch, Islamic Azad University, Tehran, Iran.
J Ultrasound Med. 2024 Nov;43(11):2129-2145. doi: 10.1002/jum.16542. Epub 2024 Aug 14.
One of the most promising adjuncts for screening breast cancer is ultrasound (US) radio-frequency (RF) time series. It has the superiority of not requiring any supplementary equipment over other methods. This research aimed to propound a machine learning (ML) approach for automatically classifying benign, probably benign, suspicious, and malignant breast lesions based on the features extracted from the accumulated US RF time series.
In this article, 220 data of the aforementioned categories, recorded from 118 patients, were analyzed. The dataset, named RFTSBU, was registered by a SuperSonic Imagine Aixplorer medical/research system equipped with a linear transducer. The regions of interest (ROIs) of the B-mode images were manually selected by an expert radiologist before computing the suggested features. Regarding time, frequency, and time-frequency domains, 291 various features were extracted from each ROI. Finally, the features were classified by a pioneering technique named the reference classification method (RCM). Furthermore, the Lee filter was applied to evaluate the effectiveness of reducing speckle noise on the outcomes.
The accuracy of two-class, three-class, and four-class classifications were respectively calculated 98.59 ± 0.71%, 98.13 ± 0.69%, and 96.10 ± 0.66% (considering 10 repetitions) while support vector machine (SVM) and K-nearest neighbor (KNN) classifiers with 5-fold cross-validation were utilized.
This article represented the proposed approach, named CCRFML, to distinguish between breast lesions based on registered in vivo RF time series employing an ML framework. The proposed method's impressive level of classification accuracy attests to its capability of effectively assisting medical professionals in the noninvasive differentiation of breast lesions.
筛查乳腺癌最有前途的辅助手段之一是超声（US）射频（RF）时间序列。它具有优于其他方法的优势，不需要任何额外的设备。本研究旨在提出一种基于从积累的 US RF 时间序列中提取的特征自动分类良性、可能良性、可疑和恶性乳腺病变的机器学习（ML）方法。
在本文中，分析了来自 118 名患者的上述类别的 220 个数据。该数据集命名为 RFTSBU，由配备线性换能器的 SuperSonic Imagine Aixplorer 医疗/研究系统记录。在计算建议的特征之前，由一位专家放射科医生手动选择 B 模式图像的感兴趣区域（ROI）。关于时间、频率和时频域，从每个 ROI 提取了 291 种不同的特征。最后，使用一种名为参考分类方法（RCM）的开创性技术对特征进行分类。此外，应用 Lee 滤波器评估减少斑点噪声对结果的有效性。
在考虑 10 次重复的情况下，两分类、三分类和四分类的准确率分别计算为 98.59±0.71%、98.13±0.69%和 96.10±0.66%，同时使用支持向量机（SVM）和 K-最近邻（KNN）分类器进行 5 折交叉验证。
本文提出了一种基于 ML 框架，使用注册的体内 RF 时间序列区分乳腺病变的方法，称为 CCRFML。该方法的分类精度令人印象深刻，证明了它能够有效地协助医学专业人员进行非侵入性的乳腺病变区分。
