【摘要】 目的探讨超声图像去噪后增强算法对乳腺肿块良恶性检测与分类的价值。方法选用211例603幅乳腺肿块超声图片(良性109例,恶性102例)进行去噪后增强处理,以手术病理结果作为金标准,对乳腺肿块原始图片和处理后图片进行分析,来区分乳腺肿块的良、恶性。利用ROC曲线下面积表现去噪后增强前后的诊断性能,计算超声诊断的准确率。结果通过去噪后增强算法处理后,使腺体和周围组织能分离,突出了腺体和病灶的部位,细节显示更加清晰,超声与病理诊断的各项指标符合率明显提高,准确率提高至92.73%,原片与处理后图片ROC曲线下面积二者之间差异有显著性统计学意义(P<0.001)。结论新的超声图像去噪后增强算法可明显地改善了图像质量,提高了乳腺肿块的正确诊断率。更多还原

【Abstract】 Objective To evaluate the performance of a computerized detection and classification with breast Ultrasound (US) images using the algorithm of enhancement after speckle reduction. Methods A total of 603 US images of 211 cases were analyzed including 109 benign lesions and 102 malignant lesions. The original and processed images were assessed by radiologists using double blind method. The pathological results were regarded as the golden standard. The diagnostic accuracy was calculated by the areas under the receiver operating characteristic (ROC) curves. Results By enhancement after speckle reduction, the fine details of breast lesion features were preserved by the proposed approaches without noise amplification and overenhancement. The diagnostic accuracy was raised to 92.73% obviously, and there were significant differences in the areas under ROC curve between the original breast lesions and processed ones on ultrasound images (P<0. 001). Conclusions The novel algorithm of enhancement after speckle reduction can improve the quality of breast ultrasound images and increase the diagnostic accuracy in differentiating benign and malignant breast lesions.更多还原