Development of intuitionistic fuzzy special embedded convolutional neural network for mammography enhancement

This article proposes a novel mammogram enhancement approach using adaptive intuitionistic fuzzy special set (IFSS) with deep convolutional neural network (called MECNNIFS) for visual interpretation of mammography lesions, lumps, and abnormal cells in low‐dose X‐ray images. The proposed MECNNIFS scheme utilizes the membership grade modification by IFSS on low‐dose X‐ray images (mammography). The suggested model attempts to increase the underexposed and abnormal structural regions such as breast lesions, lumps, and nodules on the mammogram. The proposed algorithm initially separates mammograms using convolutional neural networks (CNNs) into foreground and background areas and then fuzzifies the image by intuitionistic fuzzy set theory. Low‐level features of a mammogram of the adjacent part are integrated with CNN in pixel classification during the separation task stage to improve the performance. Hyperbolic regularization and hesitant score have been applied on fuzzy plane to quantify the uncertainty and fuzziness in spatial domain for the proposed contrast enhancement. Finally, an enhanced mammogram is acquired through the process of defuzzification. The results show better quality and performance for improvement of contrast and visual quality in mammograms compared with other state‐of‐the‐art methods.     

On the concept of best achievable compression ratio for lossy image coding

The trade-off between image fidelity and coding rate is reached with several techniques, but all of them require an ability to measure distortion. The problem is that finding a general enough measure of perceptual quality has proven to be an elusive goal. Here, we propose a novel technique for deriving an optimal compression ratio for lossy coding based on the relationship between information theory and the problem of testing hypotheses. The best achievable compression ratio determines a boundary between achievable and non-achievable regions in the trade-off between source fidelity and coding rate. The resultant performance bound is operational in that it is directly achievable by a constructive procedure, as suggested in a theorem that states the relationship between the best achievable compression ratio and the Kullback-Leibler information gain. As an example of the proposed technique, we analyze the effects of lossy compression at the best achievable compression ratio on the identification of breast cancer microcalcifications.     

基于多尺度空间滤波和l1范数最近邻分类的乳腺图像微钙化点检测

钙化信息是乳腺癌早期诊断的一个重要依据,针对钙化点检测检出率较低和假阳性较高的问题,提出一种基于多尺度空间滤波和l1范数最近邻分类的乳腺图像微钙化点检测算法.首先利用多尺度空间滤波方法得到原图像的多尺度显著特征图,然后通过基于人眼视觉特性的钙化点分割方法得到粗检测钙化点的二值图像,并送入l1范数最近邻分类器去除假阳性点...     

乳腺X线图像的增强与噪声抑制研究

提出了一种基于多尺度几何分析的乳腺X线图像增强与噪声抑制的新方法.首先对乳腺X线图像进行非下采样Contourlet变换分解,得到相应尺度和子带信息;然后根据变换系数的统计特性,应用广义高斯混合模型对其进行建模,并在此基础上引入贝叶斯分类方法将建模后的系数分为强弱边缘及噪声;再根据各个子带系数的类别属性,分别设计相应的非线性映射函数来对不同的系数进行自适应增强和抑制;最后采用增强和抑制后的系数对原图像进行重构,从而得到凸显病变区域特征的增强图像.实验结果表明,该方法具有良好的实用性和鲁棒性.     

Deeply supervised U‐Net for mass segmentation in digital mammograms

Mass detection is a critical process in the examination of mammograms. The shape and texture of the mass are key parameters used in the diagnosis of breast cancer. To recover the shape of the mass, semantic segmentation is found to be more useful rather than mere object detection (or) localization. The main challenges involved in the mass segmentation include: (a) low signal to noise ratio (b) indiscernible mass boundaries, and (c) more false positives. These problems arise due to the significant overlap in the intensities of both the normal parenchymal region and the mass region. To address these challenges, deeply supervised U‐Net model (DS U‐Net) coupled with dense conditional random fields (CRFs) is proposed. Here, the input images are preprocessed using CLAHE and a modified encoder‐decoder‐based deep learning model is used for segmentation. In general, the encoder captures the textual information of various regions in an input image, whereas the decoder recovers the spatial location of the desired region of interest. The encoder‐decoder‐based models lack the ability to recover the non‐conspicuous and spiculated mass boundaries. In the proposed work, deep supervision is integrated with a popular encoder‐decoder model (U‐Net) to improve the attention of the network toward the boundary of the suspicious regions. The final segmentation map is also created as a linear combination of the intermediate feature maps and the output feature map. The dense CRF is then used to fine‐tune the segmentation map for the recovery of definite edges. The DS U‐Net with dense CRF is evaluated on two publicly available benchmark datasets CBIS‐DDSM and INBREAST. It provides a dice score of 82.9% for CBIS‐DDSM and 79% for INBREAST.     

A logic filter for tumor detection on mammograms

This paper presents a novel approach for detection of suspicious regions in digitized mammograms,The edges of the suspicious region in mammogram are enhanced using an improved logic filter.The result of further image processing gives a gray-level histogram with distinguished characteristics,which facilitates the segmentation of the suspicious masses,The experiment results based on 25 digital sample mammograms,which are definitely diagnosed,are analyzed and evaluated briefly.     

基于解剖学特征的乳腺X线图像胸肌分割

提出了基于解剖学特征(纹理特征和形状特征)的乳腺X线图像胸肌区域分割方法. 融合边缘信息到谱聚类算法得到过分割图像. 根据区域的亮度分布和胸肌的三角形状特征,提出区域聚合算法, 从过分割图像中识别出胸肌边缘.该方法在322幅mini-MIAS (Mammographic image analysis society)乳腺图像和50幅北京大学人民医院乳腺中心乳腺图像上进行验证, 实验结果表明,该方法对不同大小、形状和亮度的胸肌分割具有较强的鲁棒性.     

基于形状选择性滤波和自适应背景抑制的乳腺钙化图像增强算法

钙化信息是乳腺癌早期诊断的一个重要依据,针对乳腺图像钙化信息受背景组织以及噪声影响而可视性差的问题,提出一种基于形状选择性滤波和自适应背景抑制的乳腺钙化图像增强算法。首先利用形状选择性滤波器提取出潜在非线状钙化信息,将钙化图像分为前景和背景区域;然后对背景信息的对比度进行自适应抑制,同时对前景钙化信息进行对比度增强处理,最后达到有选择地实现乳腺钙化图像中关键信息的可视化增强。实验结果表明,该方法可有针对的选择钙化区域进行对比度增强,同时可有效抑制背景图像中血管、组织等正常区域对钙化区域的影响。     

Automated Deep Learning Empowered Breast Cancer Diagnosis Using Biomedical Mammogram Images

Biomedical image processing is a hot research topic which helps to majorly assist the disease diagnostic process. At the same time, breast cancer becomes the deadliest disease among women and can be detected by the use of different imaging techniques. Digital mammograms can be used for the earlier identification and diagnostic of breast cancer to minimize the death rate. But the proper identification of breast cancer has mainly relied on the mammography findings and results to increased false positives. For resolving the issues of false positives of breast cancer diagnosis, this paper presents an automated deep learning based breast cancer diagnosis (ADL-BCD) model using digital mammograms. The goal of the ADL-BCD technique is to properly detect the existence of breast lesions using digital mammograms. The proposed model involves Gaussian filter based pre-processing and Tsallis entropy based image segmentation. In addition, Deep Convolutional Neural Network based Residual Network (ResNet 34) is applied for feature extraction purposes. Specifically, a hyper parameter tuning process using chimp optimization algorithm (COA) is applied to tune the parameters involved in ResNet 34 model. The wavelet neural network (WNN) is used for the classification of digital mammograms for the detection of breast cancer. The ADL-BCD method is evaluated using a benchmark dataset and the results are analyzed under several performance measures. The simulation outcome indicated that the ADL-BCD model outperforms the state of art methods in terms of different measures.