Dermoscopic image retrieval technology can provide dermatologists with valuable information such as similar confirmed skin disease cases and their diagnosis reports to assist doctors in their diagnosis. In this study, we design a dermoscopic image retrieval algorithm using convolutional neural networks (CNNs) and hash coding. A hybrid dilated convolution spatial attention module is proposed, which can focus on key information and suppress irrelevant information based on the complex morphological characteristics of dermoscopic images. Furthermore, we also propose a cauchy rotation invariance loss function in view of the skin lesion target without the main direction. This function constrains CNNs to learn output differences in samples from different angles and to make CNNs obtain a certain rotation invariance. Extensive experiments are conducted on a dermoscopic image dataset to verify the effectiveness and versatility of the proposed module, algorithm, and loss function. Experiment results show that the rotation-invariance deep hashing network with proposed spatial attention module obtains better performance on the dermoscopic image retrieval.

皮肤镜图像检索技术可以为皮肤科医生提供有价值的信息，例如类似的确诊皮肤病病例及其诊断报告，以协助医生进行诊断。在这项研究中，我们设计了一种使用卷积神经网络 (CNN) 和哈希编码的皮肤镜图像检索算法。提出了一种混合扩张卷积空间注意模块，该模块可以基于皮肤镜图像的复杂形态特征，关注关键信息并抑制无关信息。此外，我们还针对没有主要方向的皮肤病变目标提出了柯西旋转不变性损失函数。该函数约束CNNs从不同角度学习样本的输出差异，并使CNNs获得一定的旋转不变性。在皮肤镜图像数据集上进行了广泛的实验，以验证所提出的模块、算法和损失函数的有效性和多功能性。实验结果表明，提出的空间注意模块的旋转不变深度哈希网络在皮肤镜图像检索中获得了更好的性能。