Ramachandran Arivan, Kathavarayan Ramu Shivabalan
Postgraduate Institute of Medical Education and Research, Chandigarh, India.
Mahatma Gandhi Medical College and Research Institute, Puducherry, India.
JMIR Biomed Eng. 2021 Jun 2;6(2):e23808. doi: 10.2196/23808.
Ultrasound-based radiomic features to differentiate between benign and malignant breast lesions with the help of machine learning is currently being researched. The mean echogenicity ratio has been used for the diagnosis of malignant breast lesions. However, gray scale intensity histogram values as a single radiomic feature for the detection of malignant breast lesions using machine learning algorithms have not been explored yet.
This study aims to assess the utility of a simple convolutional neural network in classifying benign and malignant breast lesions using gray scale intensity values of the lesion.
An open-access online data set of 200 ultrasonogram breast lesions were collected, and regions of interest were drawn over the lesions. The gray scale intensity values of the lesions were extracted. An input file containing the values and an output file consisting of the breast lesions' diagnoses were created. The convolutional neural network was trained using the files and tested on the whole data set.
The trained convolutional neural network had an accuracy of 94.5% and a precision of 94%. The sensitivity and specificity were 94.9% and 94.1%, respectively.
Simple neural networks, which are cheap and easy to use, can be applied to diagnose malignant breast lesions with gray scale intensity values obtained from ultrasonogram images in low-resource settings with minimal personnel.
目前正在研究借助机器学习利用基于超声的放射组学特征来区分乳腺良恶性病变。平均回声率已用于乳腺恶性病变的诊断。然而，尚未探索将灰度强度直方图值作为使用机器学习算法检测乳腺恶性病变的单一放射组学特征。
本研究旨在评估一种简单的卷积神经网络利用病变灰度强度值对乳腺良恶性病变进行分类的效用。
收集了一个包含200个超声乳腺病变的开放获取在线数据集，并在病变上绘制感兴趣区域。提取病变的灰度强度值。创建一个包含这些值的输入文件和一个由乳腺病变诊断组成的输出文件。使用这些文件对卷积神经网络进行训练，并在整个数据集上进行测试。
训练后的卷积神经网络准确率为94.5%，精确率为94%。敏感性和特异性分别为94.9%和94.1%。
简单的神经网络成本低廉且易于使用，可应用于在低资源环境中以最少人员利用超声图像获得的灰度强度值来诊断乳腺恶性病变。
