AD-Net: Attention-based dilated convolutional residual network with guided decoder for robust skin lesion segmentation

TL;DR

AD-Net tackles challenging skin lesion segmentation by integrating four dilated residual encoder blocks, an Attention-based Spatial Feature Enhancement Block (ASFEB) for refined skip connections, and a guided decoder with multi-level supervision. The method achieves state-of-the-art performance across ISIC 2016/2017/2018 and PH2 while using fewer trainable parameters, with statistical validation via Wilcoxon tests. By combining multi-scale contextual encoding, attentive skip fusion, and per-block loss guidance, AD-Net delivers precise boundary delineation and robust generalization without data augmentation. This yields practical benefits for clinical CAD tools, offering high accuracy and efficiency in diverse imaging conditions.

Abstract

In computer-aided diagnosis tools employed for skin cancer treatment and early diagnosis, skin lesion segmentation is important. However, achieving precise segmentation is challenging due to inherent variations in appearance, contrast, texture, and blurry lesion boundaries. This research presents a robust approach utilizing a dilated convolutional residual network, which incorporates an attention-based spatial feature enhancement block (ASFEB) and employs a guided decoder strategy. In each dilated convolutional residual block, dilated convolution is employed to broaden the receptive field with varying dilation rates. To improve the spatial feature information of the encoder, we employed an attention-based spatial feature enhancement block in the skip connections. The ASFEB in our proposed method combines feature maps obtained from average and maximum-pooling operations. These combined features are then weighted using the active outcome of global average pooling and convolution operations. Additionally, we have incorporated a guided decoder strategy, where each decoder block is optimized using an individual loss function to enhance the feature learning process in the proposed AD-Net. The proposed AD-Net presents a significant benefit by necessitating fewer model parameters compared to its peer methods. This reduction in parameters directly impacts the number of labeled data required for training, facilitating faster convergence during the training process. The effectiveness of the proposed AD-Net was evaluated using four public benchmark datasets. We conducted a Wilcoxon signed-rank test to verify the efficiency of the AD-Net. The outcomes suggest that our method surpasses other cutting-edge methods in performance, even without the implementation of data augmentation strategies.

Figures (13)

• Figure 1: Dermoscopic skin lesion images present several challenges
• Figure 2: Parameters vs Jaccard Index details
• Figure 3: Performance of proposed method, Transformer model cao2023swin and attention model oktay2018attention with respect to parameters
• Figure 4: Overall components of the proposed AD-Net
• Figure 5: Attention-based Spatial Feature Enhancement Block.