Automatic segmentation of skin lesions in dermoscopy images is a challenging task due to the large size and shape variations of the lesions, the existence of various artifacts, the low contrast between the lesion and the surrounding skin. In this paper, we propose a novel Attention Based DenseUnet network (referred as Att-DenseUnet) with adversarial training for skin lesion segmentation. Att-DenseUnet is a Generative Adversarial Network which contains two major components: Segmentor and Discriminator. In the Segmentor module, we propose an architecture which is similar to DenseNet in the down-sampling path to ensure maximum multi-scale skin lesions information transfer between layers in the network at dense scale range, meanwhile, we design an attention module to automatically focus on the skin lesion features and suppress the irrelevant artifacts features in the output feature maps of the DenseBlocks. In the Discriminator module, we employ adversarial feature matching loss to train the Segmentor stably, force the Segmentor to extract multi-scale discriminative features, and guide the attention module focusing on the multi-scale skin lesions. A novel loss function of the Segmentor is proposed which combines the jaccard distance loss with the adversarial feature matching loss introduced by the Discriminator. We trained the proposed Att-DenseUnet on ISBI2017 dataset. The test results show that our approach gains the state-ofthe-art performance, especially for JAC (0.8045) and SEN (0.8734) scores which are significantly improved by 2.2% and 1.9%, respectively, also our network is robust to different datasets, and gains the lowest time cost which make our network suitable for clinical application.

No abstract

No abstract

Nasopharyngeal Carcinoma segmentation in magnetic resonance imagery (MRI) is vital to radiotherapy. Exact dose delivery hinges on an accurate delineation of the gross tumor volume (GTV). However, the large-scale variation in tumor volume is intractable, and the performance of current models is mostly unsatisfactory with indistinguishable and blurred boundaries of segmentation results of tiny tumor volume. To address the problem, we propose a densely connected deep convolutional network consisting of an encoder network and a corresponding decoder network, which extracts high-level semantic features from different levels and uses low-level spatial features concurrently to obtain fine-grained segmented masks. Skip-connection architecture is involved and modified to propagate spatial information to the decoder network. Preliminary experiments are conducted on 30 patients. Experimental results show our model outperforms all baseline models, with improvements of 4.17%. An ablation study is performed, and the effectiveness of the novel loss function is validated.