Suppr超能文献

基于稀疏曲波系数的局部二值模式描述子在减少 mammograms 中的假阳性。

Local Binary Patterns Descriptor Based on Sparse Curvelet Coefficients for False-Positive Reduction in Mammograms.

机构信息

Department of Electronics and Telecommunication, SVERI's College of Engineering, Pandharpur, Solapur, Maharashtra, India.

Department of Electronics and Telecommunication Engg., S.G.G.S.I.E. & T, Nanded, Maharashtra, India.

出版信息

J Healthc Eng. 2018 Sep 25;2018:5940436. doi: 10.1155/2018/5940436. eCollection 2018.

Abstract

Breast Cancer is the most prevalent cancer among women across the globe. Automatic detection of breast cancer using Computer Aided Diagnosis (CAD) system suffers from false positives (FPs). Thus, reduction of FP is one of the challenging tasks to improve the performance of the diagnosis systems. In the present work, new FP reduction technique has been proposed for breast cancer diagnosis. It is based on appropriate integration of preprocessing, Self-organizing map (SOM) clustering, region of interest (ROI) extraction, and FP reduction. In preprocessing, contrast enhancement of mammograms has been achieved using Local Entropy Maximization algorithm. The unsupervised SOM clusters an image into number of segments to identify the cancerous region and extracts tumor regions (i.e., ROIs). However, it also detects some FPs which affects the efficiency of the algorithm. Therefore, to reduce the FPs, the output of the SOM is given to the FP reduction step which is aimed to classify the extracted ROIs into normal and abnormal class. FP reduction consists of feature mining from the ROIs using proposed local sparse curvelet coefficients followed by classification using artificial neural network (ANN). The performance of proposed algorithm has been validated using the local datasets as TMCH (Tata Memorial Cancer Hospital) and publicly available MIAS (Suckling et al., 1994) and DDSM (Heath et al., 2000) database. The proposed technique results in reduction of FPs from 0.85 to 0.02 FP/image for MIAS, 4.81 to 0.16 FP/image for DDSM, and 2.32 to 0.05 FP/image for TMCH reflecting huge improvement in classification of mammograms.

摘要

乳腺癌是全球女性最常见的癌症。使用计算机辅助诊断 (CAD) 系统自动检测乳腺癌会出现假阳性 (FP)。因此,减少 FP 是提高诊断系统性能的挑战性任务之一。在本工作中,提出了一种新的 FP 减少技术用于乳腺癌诊断。它基于预处理、自组织映射 (SOM) 聚类、感兴趣区域 (ROI) 提取和 FP 减少的适当集成。在预处理中,使用局部最大熵算法实现了乳腺 X 线照片的对比度增强。无监督的 SOM 将图像聚类为若干段,以识别癌症区域并提取肿瘤区域(即 ROI)。然而,它也会检测到一些 FP,这会影响算法的效率。因此,为了减少 FP,将 SOM 的输出提供给 FP 减少步骤,该步骤旨在将提取的 ROI 分类为正常和异常类。FP 减少包括使用提出的局部稀疏曲波系数从 ROI 中进行特征挖掘,然后使用人工神经网络 (ANN) 进行分类。使用本地数据集 TMCH(塔塔纪念癌症医院)以及公开可用的 MIAS(Suckling 等人,1994 年)和 DDSM(Heath 等人,2000 年)数据库验证了所提出算法的性能。所提出的技术将 MIAS 的 FP 从 0.85 减少到 0.02 FP/图像,将 DDSM 的 FP 从 4.81 减少到 0.16 FP/图像,将 TMCH 的 FP 从 2.32 减少到 0.05 FP/图像,这反映了对乳腺 X 线照片分类的巨大改进。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/907b/6178513/d0cf5b1af49b/JHE2018-5940436.001.jpg

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验