Andalusian Research Institute in Data Science and Computational Intelligence (DaSCI). University of Córdoba, Córdoba, Spain; Maimónides Biomedical Research Institute of Córdoba (IMIBIC). University of Córdoba, Córdoba, Spain.
Andalusian Research Institute in Data Science and Computational Intelligence (DaSCI). University of Córdoba, Córdoba, Spain; Maimónides Biomedical Research Institute of Córdoba (IMIBIC). University of Córdoba, Córdoba, Spain.
Artif Intell Med. 2023 Jul;141:102556. doi: 10.1016/j.artmed.2023.102556. Epub 2023 Apr 28.
Early melanoma diagnosis is the most important factor in the treatment of skin cancer and can effectively reduce mortality rates. Recently, Generative Adversarial Networks have been used to augment data, prevent overfitting and improve the diagnostic capacity of models. However, its application remains a challenging task due to the high levels of inter and intra-class variance seen in skin images, limited amounts of data, and model instability. We present a more robust Progressive Growing of Adversarial Networks based on residual learning, which is highly recommended to ease the training of deep networks. The stability of the training process was increased by receiving additional inputs from preceding blocks. The architecture is able to produce plausible photorealistic synthetic 512 × 512 skin images, even with small dermoscopic and non-dermoscopic skin image datasets as problem domains. In this manner, we tackle the lack of data and the imbalance problems. Additionally, the proposed approach leverages a skin lesion boundary segmentation algorithm and transfer learning to enhance the diagnosis of melanoma. Inception score and Matthews Correlation Coefficient were used to measure the performance of the models. The architecture was evaluated qualitatively and quantitatively through the use of an extensive experimental study on sixteen datasets, illustrating its effectiveness in the diagnosis of melanoma. Finally, four state-of-the-art data augmentation techniques applied in five convolutional neural network models were significantly outperformed. The results indicated that a bigger number of trainable parameters will not necessarily obtain a better performance in melanoma diagnosis.
早期黑色素瘤诊断是治疗皮肤癌的最重要因素，可有效降低死亡率。最近，生成对抗网络已被用于扩充数据、防止过拟合和提高模型的诊断能力。然而，由于皮肤图像存在较高的类内和类间差异、数据量有限以及模型不稳定，其应用仍然是一个具有挑战性的任务。我们提出了一种基于残差学习的更稳健的渐进式对抗网络，强烈建议使用该方法来简化深度网络的训练。通过接收来自前面块的额外输入，增加了训练过程的稳定性。该架构能够生成逼真的 512×512 皮肤图像，即使在小的皮肤镜和非皮肤镜皮肤图像数据集作为问题领域的情况下也是如此。通过这种方式，我们解决了数据不足和不平衡的问题。此外，该方法利用皮肤病变边界分割算法和迁移学习来增强黑色素瘤的诊断。采用 inception 分数和马修斯相关系数来衡量模型的性能。通过在十六个数据集上进行广泛的实验研究，对架构进行了定性和定量评估，证明了其在黑色素瘤诊断中的有效性。最后，在五个卷积神经网络模型中应用了四种最先进的数据增强技术，明显优于其他技术。结果表明，更多的可训练参数不一定能在黑色素瘤诊断中获得更好的性能。
