Department of Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, 33431, FL, USA.
Department of Electrical Engineering and Computer Engineering, Technische Universität Dresden, Dresden, 01069, Saxony, Germany.
J Digit Imaging. 2023 Jun;36(3):1137-1147. doi: 10.1007/s10278-023-00776-2. Epub 2023 Jan 23.
Skin cancer is one of the primary causes of death globally, and experts diagnose it by visual inspection, which can be inaccurate. The need for developing a computer-aided method to aid dermatologists in diagnosing skin cancer is highlighted by the fact that early identification can lower the number of deaths caused by skin malignancies. Among computer-aided techniques, deep learning is the most popular for identifying cancer from skin lesion images. Due to their power-efficient behavior, spiking neural networks are attractive deep neural networks for hardware implementation. We employed deep spiking neural networks using the surrogate gradient descent method to classify 3670 melanoma and 3323 non-melanoma images from the ISIC 2019 dataset. We achieved an accuracy of 89.57% and an F1 score of 90.07% using the proposed spiking VGG-13 model, which is higher than the VGG-13 and AlexNet using less trainable parameters.
皮肤癌是全球主要死因之一，专家通过目视检查进行诊断，但这种方法可能不够准确。由于早期诊断可以降低皮肤恶性肿瘤导致的死亡人数，因此需要开发一种计算机辅助方法来帮助皮肤科医生诊断皮肤癌。在计算机辅助技术中，深度学习是识别皮肤病变图像中癌症的最流行方法。由于 Spike 神经网络具有节能的特点，因此它们是用于硬件实现的有吸引力的深度神经网络。我们使用替代梯度下降方法的深度 Spike 神经网络对来自 ISIC 2019 数据集的 3670 张黑色素瘤和 3323 张非黑色素瘤图像进行分类。我们使用所提出的 Spike VGG-13 模型实现了 89.57%的准确率和 90.07%的 F1 分数，该模型使用的可训练参数少于 VGG-13 和 AlexNet。
