Neural network and multi-fractal dimension features for breast cancer classification from ultrasound images
Neural network and multi-fractal dimension features for breast cancer classification from ultrasound images
复制标题
DOI：
10.1016/j.compeleceng.2018.01.033
复制
发表时间：
2018-08-01
影响因子：
4.3
通讯作者：
Mostafa, Salama A.
中科院分区：
文献类型：
--
作者：
Mohammed, Mazin Abed;Al-Khateeb, Belal;Mostafa, Salama A.
乳腺癌被认为是临床实践中最具威胁的问题之一。然而，现有的乳腺癌诊断方法面临着复杂性、成本、人为依赖性和不准确的问题。最近，已经开发了许多计算机化和跨学科系统，以避免量化和诊断中的人为错误。可以进一步改进计算机化系统，以优化乳腺肿瘤识别的效率。当前的论文提出了使用多重分形维度和反向传播神经网络从超声图像中自动表征乳腺癌的努力。在这项研究中，总共检查了 184 幅乳腺超声图像（72 幅异常（肿瘤病例）和 112 幅正常病例）。采用了各种设置来实现确诊病例阳性率和阴性率之间的良好平衡。所得结果具有较高的准确率（82.04%）、灵敏度（79.39%）和特异度（84.75%）。 (C) 2018 Elsevier Ltd. 保留所有权利。
Breast cancer is considered to be one of the most threatening issues in clinical practice. However, existing breast cancer diagnosis methods face questions of complexity, cost, human-dependency, and inaccuracy. Recently, many computerized and interdisciplinary systems have been developed to avoid human errors in both quantification and diagnosis. A computerized system can be further improved to optimize the efficiency of breast tumour identification. The current paper presents an effort to automate characterization of breast cancer from ultrasound images using multi-fractal dimensions and backpropagation neural networks. In this study, a total of 184 breast ultrasound images (72 abnormal (tumour cases) and 112 normal cases) were examined. Various setups were employed to achieve a decent balance between positive and negative rates of the diagnosed cases. The obtained results manifested in high rates of precision (82.04%), sensitivity (79.39%), and specificity (84.75%). (C) 2018 Elsevier Ltd. All rights reserved.