We present a method for skin lesion segmentation for the ISIC 2017 Skin Lesion Segmentation Challenge. Our approach is based on a Fully Convolutional Neural Network architecture which is trained end to end, from scratch, on a small dataset. Our semantic segmentation architecture utilizes several recent innovations in deep learning particularly in the combined use of (i) atrous convolutions to i...

Melanoma is the most lethal malignant tumour, and its prevalence increasing. Early detection diagnosis of skin cancer can alert patients to manage precautions dramatically improve lives people. Recently, deep learning has grown increasingly popular in extraction categorization features for effective prediction. A model learns co-adapts representations from training data point where it fails per...

Edoardo Baldini,1,2 Andreas Mann,1 Benjamin P. P. Mallett,3 Christopher Arrell,2 Frank van Mourik,2 Thomas Wolf,4 Dragan Mihailovic,5 Jeffrey L. Tallon,6 Christian Bernhard,3 José Lorenzana,7 and Fabrizio Carbone1 1Laboratory for Ultrafast Microscopy and Electron Scattering, IPHYS, EPFL, CH-1015 Lausanne, Switzerland 2Laboratory of Ultrafast Spectroscopy, ISIC, EPFL, CH-1015 Lausanne, Switzerla...

We use a pretrained fully convolutional neural network to detect clinical dermoscopic features from dermoscopy skin lesion images. We reformulate the superpixel classification task as an image segmentation problem, and extend a neural network architecture originally designed for image classification to detect dermoscopic features. Specifically, we interpolate the feature maps from several layer...

1Laboratory of Ultrafast Spectroscopy, ISIC and LACUS, EPFL, CH-1015 Lausanne, Switzerland 2Laboratory for Ultrafast Microscopy and Electron Scattering, IPHYS and LACUS, EPFL, CH-1015 Lausanne, Switzerland 3Unit of Nonlinear Physics and Mathematical Modeling, Department of Engineering, Università Campus Bio-Medico di Roma, Via Álvaro del Portillo 21, I-00128, Rome, Italy 4Center for Life Nano S...

We have developed advanced numerical algorithms to model biological fluids in multiscale flow environments using the software framework developed under the SciDAC APDEC ISIC. The foundation of our computational effort is an approach for modeling DNAladen fluids as “bead-rod” polymers whose dynamics are fully coupled to an incompressible viscous solvent. The method is capable of modeling short r...

An automated method to detect and analyze the melanoma is presented to improve diagnosis which will leads to the exact treatment. Image processing techniques such as segmentation, feature descriptors and classification models are involved in this method. In the First phase the lesion region is segmented using CIELAB Color space Based Segmentation. Then feature descriptors such as shape, color a...

Edoardo Baldini,1,* Adriel Dominguez,2 Letizia Chiodo,3 Evgeniia Sheveleva,4 Meghdad Yazdi-Rizi,4 Christian Bernhard,4 Angel Rubio,2,5 and Majed Chergui1 1Laboratory of Ultrafast Spectroscopy, ISIC and Lausanne Centre for Ultrafast Science (LACUS), École Polytechnique Fédérale de Lausanne, CH-1015 Lausanne, Switzerland 2Max Planck Institute for the Structure and Dynamics of Matter, D-22761 Hamb...

In this study, a multi-task deep neural network is proposed for skin lesion analysis. The proposed multi-task learning model solves different tasks (e.g., lesion segmentation and two independent binary lesion classifications) at the same time by exploiting commonalities and differences across tasks. This results in improved learning efficiency and potential prediction accuracy for the task-spec...

The ability to visually understand and interpret learned features from complex predictive models is crucial for their acceptance in sensitive areas such as health care. To move closer to this goal of truly interpretable complex models, we present PatchNet, a network that restricts global context for image classification tasks in order to easily provide visual representations of learned texture ...