用CNN分析乳腺钼靶片，自动区分正常与异常肿块
Computer Aided Detection and Classification of mammograms using Convolutional Neural Network
- 基于CNN提取钼靶图像中的肿块特征
- 在DDSM数据集上实现920例异常、460例正常的分类
- 可辅助医生早期发现乳腺癌，适合医学影像研究者
乳腺癌是女性死亡的主要原因之一，仅次于肺癌。通过乳腺钼靶成像早期检测乳腺癌可显著提高患者生存率。目前，利用钼靶影像进行计算机辅助检测已被视为关键步骤。研究人员提出了多种自动检测早期肿瘤的方法。早期乳腺癌症状包括肿块和微钙化。由于肿瘤形状、大小和位置差异大，从正常组织中提取异常区域具有挑战性。机器学习有助于提升诊断准确性，其中深度学习或神经网络可有效区分正常与异常乳腺组织。本研究采用卷积神经网络（CNN）对乳腺钼靶图像中的肿块进行分类，判断其为正常或异常。实验使用DDSM数据集，包含约460张正常乳腺图像和920张异常乳腺图像。
原文摘要 · Abstract (English)
Breast cancer is one of the most major causes of death among women, after lung cancer. Breast cancer detection advancements can increase the survival rate of patients through earlier detection. Breast cancer that can be detected by using mammographic imaging is now considered crucial step for computer aided systems. Researchers have explained many techniques for the automatic detection of initial tumors. The early breast cancer symptoms include masses and micro-calcifications. Because there is the variation in the tumor shape, size and position it is difficult to extract abnormal region from normal tissues. So, machine learning can help medical professionals make more accurate diagnoses of the disease whereas deep learning or neural networks are one of the methods that can be used to distinguish regular and irregular breast identification. In this study the extraction method for the classification of breast masses as normal and abnormal we have used is convolutional neural network (CNN) on mammograms. DDSM dataset has been used in which nearly 460 images are of normal and 920 of abnormal breasts.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。