The incidence of skin cancer around the world is increasing year by year. However, early diagnosis and treatment can greatly improve the survival rate of patients. Skin lesion boundary segmentation is essential to accurately locate lesion areas in dermatoscopic images. It is true that accurate segmentation of skin lesions is still challenging dues to problems such as blurred borders, which requires an accurate and automatic skin lesion segmentation method. In this paper, we propose an end-to-end framework which can perform skin lesion segmentation automatically and efficiently, called the CSARM-CNN (Channel & Spatial Attention Residual Module) model. Each CSARM block of the model combines channel attention and spatial attention to form a new attention module to enhance segmentation results. The multi-scale input images are obtained by the spatial pyramid pooling. Finally, a weighted cross-entropy loss function is used at each side of the output layer to sum the total loss of the model. We evaluated in two published standard datasets, ISIC 2017 and PH2, and achieved competitive results in terms of specificity and accuracy, with 99.03% and 99.45% specificity, 94.96% and 95.23% accuracy, respectively.

The automatic segmentation of skin lesions is considered to be a key step in the diagnosis and treatment of skin lesions, which is essential to improve the survival rate of patients. However, due to the low contrast, the texture and boundary are difficult to distinguish, which makes the accurate segmentation of skin lesions challenging. To cope with these challenges, this paper proposes an attention-guided network with densely connected convolution for skin lesion segmentation, called CSAG and DCCNet. In the last step of the encoding path, the model uses densely connected convolution to replace the ordinary convolutional layer. A novel attention-oriented filter module called Channel Spatial Fast Attention-guided Filter (CSFAG for short) was designed and embedded in the skip connection of the CSAG and DCCNet. On the ISIC-2017 data set, a large number of ablation experiments have verified the superiority and robustness of the CSFAG module and Densely Connected Convolution. The segmentation performance of CSAG and DCCNet is compared with other latest algorithms, and very competitive results have been achieved in all indicators. The robustness and cross-data set performance of our method was tested on another publicly available data set PH2, further verifying the effectiveness of the model.

Segmentation of retinal vessels is a critical step for the diagnosis of some fundus diseases. Methods: To further enhance the performance of vessel segmentation, we propose a method based on a gated skip-connection network with adaptive upsampling (GSAU-Net). In GSAU-Net, a novel skip-connection with gating is first utilized in the extension path, which facilitates the flow of information from the encoder to the decoder. Specifically, we used the gated skip-connection between the encoder and decoder to gate the lower-level information from the encoder. In the decoding phase, we used an adaptive upsampling to replace the bilinear interpolation, which recovers feature maps from the decoder to obtain the pixelwise prediction. Finally, we validated our method on the DRIVE, CHASE, and STARE datasets. Results: The experimental results showed that our proposed method outperformed some existing methods, such as DeepVessel, AG-Net, and IterNet, in terms of accuracy, F-measure, and AUC${}_R{}_O{}_C$. The proposed method achieved a vessel segmentation F-measure of 83.13%, 81.40%, and 84.84% on the DRIVE, CHASE, and STARE datasets, respectively.