Soft-Attention Improves Skin Cancer Classification Performance
This work addresses the problem of improving diagnostic accuracy in skin cancer detection for clinical applications, representing an incremental advancement.
The paper tackled skin cancer classification by integrating Soft-Attention mechanisms into deep neural networks, resulting in a 4.7% performance improvement over baseline with 93.7% precision on the HAM10000 dataset and a 3.8% sensitivity gain with 91.6% on the ISIC-2017 dataset.
In clinical applications, neural networks must focus on and highlight the most important parts of an input image. Soft-Attention mechanism enables a neural network toachieve this goal. This paper investigates the effectiveness of Soft-Attention in deep neural architectures. The central aim of Soft-Attention is to boost the value of important features and suppress the noise-inducing features. We compare the performance of VGG, ResNet, InceptionResNetv2 and DenseNet architectures with and without the Soft-Attention mechanism, while classifying skin lesions. The original network when coupled with Soft-Attention outperforms the baseline[16] by 4.7% while achieving a precision of 93.7% on HAM10000 dataset [25]. Additionally, Soft-Attention coupling improves the sensitivity score by 3.8% compared to baseline[31] and achieves 91.6% on ISIC-2017 dataset [2]. The code is publicly available at github.