DSNet: Automatic Dermoscopic Skin Lesion Segmentation

07/09/2019
by   Md. Kamrul Hasan, et al.
3

Automatic segmentation of skin lesion is considered a crucial step in Computer Aided Diagnosis (CAD) for melanoma diagnosis. Despite its significance, skin lesion segmentation remains a challenging task due to their diverse color, texture, and indistinguishable boundaries and forms an open problem. Through this study, we present a new and automatic semantic segmentation network for robust skin lesion segmentation named Dermoscopic Skin Network (DSNet). In order to reduce the number of parameters to make the network lightweight, we used depth-wise separable convolution in lieu of standard convolution to project the learned discriminating features onto the pixel space at different stages of the encoder. Additionally, we implemented U-Net and Fully Convolutional Network (FCN8s) to compare against the proposed DSNet. We evaluate our proposed model on two publicly available datasets, namely ISIC-2017 and PH2. The obtained mean Intersection over Union (mIoU) is 77.5 outperformed the ISIC-2017 challenge winner by 1.0 proposed network also outperformed U-Net and FCN8s respectively by 3.6 6.8 lesion segmentation outperforms other methods and can provide better segmented masks on two different test datasets which can lead to better performance in melanoma detection. Our trained model along with the source code and predicted masks are made publicly available.

READ FULL TEXT

page 3

page 6

page 7

page 10

page 12

page 18

research
04/05/2019

Comparative Analysis of Automatic Skin Lesion Segmentation with Two Different Implementations

Lesion segmentation from the surrounding skin is the first task for deve...
research
12/28/2020

Lesion Net – Skin Lesion Segmentation Using Coordinate Convolution and Deep Residual Units

Skin lesions segmentation is an important step in the process of automat...
research
07/13/2018

Automatic segmentation of skin lesions using deep learning

This paper summarizes the method used in our submission to Task 1 of the...
research
07/21/2023

FEDD – Fair, Efficient, and Diverse Diffusion-based Lesion Segmentation and Malignancy Classification

Skin diseases affect millions of people worldwide, across all ethnicitie...
research
10/23/2019

Semantic Segmentation of Skin Lesions using a Small Data Set

Early detection of melanoma is difficult for the human eye but a crucial...
research
06/02/2022

XBound-Former: Toward Cross-scale Boundary Modeling in Transformers

Skin lesion segmentation from dermoscopy images is of great significance...
research
02/28/2017

II-FCN for skin lesion analysis towards melanoma detection

Dermoscopy image detection stays a tough task due to the weak distinguis...

Please sign up or login with your details

Forgot password? Click here to reset