Deep Learning Classification of Breast Cancer Tissue from Terahertz Imaging Through Wavelet Synchro-Squeezed Transformation and Transfer Learning.
Deep Learning Classification of Breast Cancer Tissue from Terahertz Imaging Through Wavelet Synchro-Squeezed Transformation and Transfer Learning.
复制标题
DOI：
10.1007/s10762-021-00839-x
复制
发表时间：
2022-01
期刊：
影响因子：
--
通讯作者：
中科院分区：
文献类型：
--
作者：
太赫兹成像和光谱学是一项令人兴奋的技术，有可能为医学成像提供见解。先前的研究已经利用统计推断来对太赫兹图像中的组织区域进行分类。迄今为止，这些方法已经表明，分割问题是具有挑战性的新鲜组织的图像和肿瘤侵入肌肉区域。人工智能，特别是机器学习和深度学习，已被证明可以提高某些医学成像挑战的性能。本文以该文献为基础，修改了一套深度学习方法，以应对对新鲜切除的小鼠异种移植组织的太赫兹成像和光谱学捕获的图像的组织区域进行分类的挑战。我们的方法是通过小波同步压缩变换（WSST）的图像进行预处理，将每个太赫兹像素的时间序列太赫兹数据转换为频谱图。频谱图被用作深度卷积神经网络的输入张量，用于逐像素分类。基于每个像素的分类结果，得到癌组织分割图。在实验中，我们采用留一样本交叉验证策略，并使用多个指标，如准确性，精度，交集和大小来评估我们选择的网络和结果。该实验的结果表明，与统计方法相比，分类准确性有所提高，异种移植肿瘤中肌肉和癌性区域之间的分割有所改善，并确定了改善成像和分类方法的区域。
Terahertz imaging and spectroscopy is an exciting technology that has the potential to provide insights in medical imaging. Prior research has leveraged statistical inference to classify tissue regions from terahertz images. To date, these approaches have shown that the segmentation problem is challenging for images of fresh tissue and for tumors that have invaded muscular regions. Artificial intelligence, particularly machine learning and deep learning, has been shown to improve performance in some medical imaging challenges. This paper builds on that literature by modifying a set of deep learning approaches to the challenge of classifying tissue regions of images captured by terahertz imaging and spectroscopy of freshly excised murine xenograft tissue. Our approach is to preprocess the images through a wavelet synchronous-squeezed transformation (WSST) to convert time-sequential terahertz data of each THz pixel to a spectrogram. Spectrograms are used as input tensors to a deep convolution neural network for pixel-wise classification. Based on the classification result of each pixel, a cancer tissue segmentation map is achieved. In experimentation, we adopt leave-one-sample-out cross-validation strategy, and evaluate our chosen networks and results using multiple metrics such as accuracy, precision, intersection, and size. The results from this experimentation demonstrate improvement in classification accuracy compared to statistical methods, an improvement to segmentation between muscle and cancerous regions in xenograft tumors, and identify areas to improve the imaging and classification methodology.
登录
查看更多内容
DOI：
10.1148/rg.2017160130
发表时间：
2017-03
期刊：
Radiographics : a review publication of the Radiological Society of North America, Inc
影响因子：
--
作者：
Erickson BJ;Korfiatis P;Akkus Z;Kline TL
通讯作者：
Kline TL
影响因子：
3.7
作者：
Araújo T;Aresta G;Castro E;Rouco J;Aguiar P;Eloy C;Polónia A;Campilho A
通讯作者：
Campilho A
影响因子：
2.4
作者：
Bowman, Tyler;Vohra, Nagma;El-Shenawee, Magda
通讯作者：
El-Shenawee, Magda
影响因子：
3.5
作者：
Brun, M-A;Formanek, F.;Eishii, Y.
通讯作者：
Eishii, Y.
影响因子：
2.5
作者：
Daubechies, Ingrid;Lu, Jianfeng;Wu, Hau-Tieng
通讯作者：
Wu, Hau-Tieng