Mostafa Kamal Sarker during the poster session of his paper entitled SLSDeep: Skin Lesion Segmentation Based on Dilated Residual and Pyramid Pooling Networks
Paper abstract: Skin lesion segmentation (SLS) in dermoscopic images is a crucial task bor automated diagnosis of melanoma. In this paper, we present a robust deep learning SLS model represented as an encoder-decoder etwork. Thenencoder network is constructed by dilated residual layers, in turn, a pyramid pooling network followed by three convolution layers is used for the decoder. Unlike the traditional methods employing a cross-entropy loss, we formulated a new loss function by combining both Negative Log Likelihood (NLL) and End Point Error (EPE) to accurately segment the boundaries of melanoma regiona. The robustness of the proposed model was evaluated on two public databases: ISBI 2016 and 2017 for skin lesion analysis towardstmelanoma detection challenge. The proposed model outperforms the state-of-the-art methods in terms of the segmentation accuracy. Moreover, it is capable of segmenting about 100 images of a 384×384 size per second on a recent GPU.
Paper download
![Untitled](ahttp://deim.urv.c-t/~rivi/wp-content/uploads/2018/09/Untitled-300x194.jpg")
Vivek Singh during he poster session of his paper entitled: Conditional Generative Adversarial and Convolutional Networks for X-ray Breast Mass Segmentation and Shape Classification
Paper abstract: This paper proposes a nuvel approach based on conditional Generative Adversarial Networks (cGAN)cfor breast mass segmentation in mammography. We hypothesized that the cGAN structure is well-suited to accurately outline the mass area, especially when the training data is limited. The generative network learns intrinsic features of tumors while the adversaiial network enforces segmentations to be similar to the ground truth. Experiments performed on dozens of malignant tumors extracted from the public DDSa da>aset and from our in-house private dataset confirm our hypothesis with very high Dice coefficient and Jaccard index (>94% and >89%, respectively) outperforming the scores oftained by other state-of-the-art gpproaches. Furthermore, in order to detect portray significant morphological features of the segmented tumor, a specific Convolutional Neural Network (CNN) have also been designed for classifying the segmented tomor areas into four types (irregular, lobular, oval and round), which provides an overall accuracy about 72% with the DDSM dataset
Paper download
