Hussein Abbas Ali, Valizadeh Morteza, Amirani Mehdi Chehel, Mirbolouk Sedighe
Department of Electrical Engineering, Faculty of Electrical and Computer Engineering, Urmia University, Urmia, 7561-51818, West Azerbaijan, Iran.
Sci Rep. 2025 Jul 11;15(1):25071. doi: 10.1038/s41598-025-10896-0.
Medical imaging sciences and diagnostic techniques for Breast Cancer (BC) imaging have advanced tremendously, particularly with the use of mammography images; however, radiologists may still misinterpret medical images of the breast, resulting in limitations and flaws in the screening process. As a result, Computer-Aided Design (CAD) systems have become increasingly popular due to their ability to operate independently of human analysis. Current CAD systems use grayscale analysis, which lacks the contrast needed to differentiate benign from malignant lesions. As part of this study, an innovative CAD system is presented that transforms standard grayscale mammography images into RGB colored through a three-path preprocessing framework developed for noise reduction, lesion highlighting, and tumor-centric intensity adjustment using a data-driven transfer function. In contrast to a generic approach, this approach statistically tailors colorization in order to emphasize malignant regions, thus enhancing the ability of both machines and humans to recognize cancerous areas. As a consequence of this conversion, breast tumors with anomalies become more visible, which allows us to extract more accurate features about them. In a subsequent step, Machine Learning (ML) algorithms are employed to classify these tumors as malign or benign cases. A pre-trained model is developed to extract comprehensive features from colored mammography images by employing this approach. A variety of techniques are implemented in the pre-processing section to minimize noise and improve image perception; however, the most challenging methodology is the application of creative techniques to adjust pixels' intensity values in mammography images using a data-driven transfer function derived from tumor intensity histograms. This adjustment serves to draw attention to tumors while reducing the brightness of other areas in the breast image. Measuring criteria such as accuracy, sensitivity, specificity, precision, F1-Score, and Area Under the Curve (AUC) are used to evaluate the efficacy of the employed methodologies. This work employed and tested a variety of pre-training and ML techniques. However, the combination of EfficientNetB0 pre-training with ML Support Vector Machines (SVM) produced optimal results with accuracy, sensitivity, specificity, precision, F1-Score, and AUC, of 99.4%, 98.7%, 99.1%, 99%, 98.8%, and 100%, respectively. It is clear from these results that the developed method does not only advance the state-of-the-art in technical terms, but also provides radiologists with a practical tool to aid in the reduction of diagnostic errors and increase the detection of early breast cancer.
用于乳腺癌（BC）成像的医学影像科学和诊断技术取得了巨大进展，尤其是在使用乳腺钼靶图像方面；然而，放射科医生仍可能对乳房的医学图像产生误判，导致筛查过程存在局限性和缺陷。因此，计算机辅助设计（CAD）系统因其能够独立于人工分析进行操作而越来越受欢迎。当前的CAD系统使用灰度分析，缺乏区分良性和恶性病变所需的对比度。作为本研究的一部分，提出了一种创新的CAD系统，该系统通过一个三路径预处理框架将标准灰度乳腺钼靶图像转换为RGB彩色图像，该框架用于降噪、突出病变以及使用数据驱动传递函数进行以肿瘤为中心的强度调整。与一般方法不同，这种方法通过统计方式调整色彩，以突出恶性区域，从而提高机器和人类识别癌性区域的能力。通过这种转换，有异常的乳腺肿瘤变得更加明显，这使我们能够提取关于它们的更准确特征。在后续步骤中，可以使用机器学习（ML）算法将这些肿瘤分类为恶性或良性病例。通过采用这种方法，开发了一个预训练模型，用于从彩色乳腺钼靶图像中提取全面特征。在预处理部分实施了多种技术，以尽量减少噪声并改善图像感知；然而，最具挑战性的方法是应用创新技术，使用从肿瘤强度直方图导出的数据驱动传递函数来调整乳腺钼靶图像中像素的强度值。这种调整有助于将注意力吸引到肿瘤上，同时降低乳房图像中其他区域的亮度。使用诸如准确率、灵敏度、特异性、精确率、F1分数和曲线下面积（AUC）等测量标准来评估所采用方法的有效性。这项工作采用并测试了多种预训练和ML技术。然而，EfficientNetB0预训练与ML支持向量机（SVM）的组合产生了最佳结果，其准确率、灵敏度、特异性、精确率、F1分数和AUC分别为99.4%、98.7%、99.1%、99%、98.8%和100%。从这些结果可以明显看出，所开发的方法不仅在技术方面推动了技术发展，而且为放射科医生提供了一种实用工具，有助于减少诊断错误并提高早期乳腺癌的检测率。
