Global and Local Information Based Deep Network for Skin Lesion Segmentation

by   Jin Qi, et al.

With a large influx of dermoscopy images and a growing shortage of dermatologists, automatic dermoscopic image analysis plays an essential role in skin cancer diagnosis. In this paper, a new deep fully convolutional neural network (FCNN) is proposed to automatically segment melanoma out of skin images by end-to-end learning with only pixels and labels as inputs. Our proposed FCNN is capable of using both local and global information to segment melanoma by adopting skipping layers. The public benchmark database consisting of 150 validation images, 600 test images and 2000 training images in the melanoma detection challenge 2017 at International Symposium Biomedical Imaging 2017 is used to test the performance of our algorithm. All large size images (for example, 4000× 6000 pixels) are reduced to much smaller images with 384× 384 pixels (more than 10 times smaller). We got and submitted preliminary results to the challenge without any pre or post processing. The performance of our proposed method could be further improved by data augmentation and by avoiding image size reduction.


page 1

page 4


Automatic segmentation of skin lesions using deep learning

This paper summarizes the method used in our submission to Task 1 of the...

The Effects of Image Pre- and Post-Processing, Wavelet Decomposition, and Local Binary Patterns on U-Nets for Skin Lesion Segmentation

Skin cancer is a widespread, global, and potentially deadly disease, whi...

An End-to-End Approach for Seam Carving Detection using Deep Neural Networks

Seam carving is a computational method capable of resizing images for bo...

Data-Driven Color Augmentation Techniques for Deep Skin Image Analysis

Dermoscopic skin images are often obtained with different imaging device...

Improving Automatic Skin Lesion Segmentation using Adversarial Learning based Data Augmentation

Segmentation of skin lesions is considered as an important step in compu...

Learning morphological operators for skin detection

In this work we propose a novel post processing approach for skin detect...

Please sign up or login with your details

Forgot password? Click here to reset