Ultrasound is the second most used modality in medical imaging. It is cost effective, hazardless, portable and implemented routinely in numerous clinical procedures. Nonetheless, image quality is characterized by granulated appearance, poor SNR and speckle noise. Specific for malignant tumors, the margins are blurred and indistinct. Thus, there is a great need for improving ultrasound image quality. We hypothesize that this can be achieved by translation into a more realistic anatomic display, using neural networks. In order to achieve this goal, the preferable approach would be to use a set of paired images. However, this is practically impossible in our case. Therefore, CycleGAN was used, to learn each domain properties separately and enforce cross domain cycle consistency. The two datasets which were used for training the model were "Breast Ultrasound Images" (BUSI) and a set of optic images of poultry breast tissue samples acquired at our lab. The generated pseudo anatomical images provide improved visual discrimination of the lesions with clearer border definition and pronounced contrast. Furthermore, the algorithm manages to overcome the acoustic shadows artifacts commonly appearing in ultrasonic images. In order to evaluate the preservation of the anatomical features, the lesions in the ultrasonic images and the generated pseudo anatomical images were both automatically segmented and compared. This comparison yielded median dice score of 0.78 for the benign tumors and 0.43 for the malignancies. Median lesion center error of 2.38% and 8.42% for the benign and malignancies respectively and median area error index of 0.77% and 5.06% for the benign and malignancies respectively. In conclusion, these generated pseudo anatomical images, which are presented in a more intuitive way, preserve tissue anatomy and can potentially simplify the diagnosis and improve the clinical outcome.
翻译:超声波是医学成像中第二多使用的模式。 它具有成本效益、 无危害、 便携式且在众多临床程序中例行实施。 尽管如此, 图像质量的特点是颗粒外观、 低 SNR 和 闪烁噪音。 用于恶性肿瘤的特有, 边际模糊和分辨。 因此, 非常需要改进超声波图像质量。 我们假设, 可以通过将它转换成更现实的解剖显示, 使用神经网络。 为了实现这一目标, 最好的做法是使用一组配对图像。 然而, 而在我们的情况中, 这实际上是不可能的。 因此, 使用 CyellGAN 来分别学习每个域的属性和跨域周期的一致性。 用于培训模型的两套数据集是“ 最小超声波图像” (BUSI) 和在实验室中获取的一组家禽乳组织样本的光图像。 生成的假解剖图像通过更清晰度和清晰度的边界定义, 提供了更好的视觉分析。 此外, 算法可以克服在超声压的正影中、 良性图像的中间结构分析中, 和正值分析结果中, 。 在超声学图像中, 将结果中, 将结果中, 和正值分析中, 将产生一个序列分析结果中, 。