Semantic Segmentation of Skin Lesions using a Small Data Set

10/23/2019
by   Beril Sirmacek, et al.
21

Early detection of melanoma is difficult for the human eye but a crucial step towards reducing its death rate. Computerized detection of these melanoma and other skin lesions is necessary. The central research question in this paper is "How to segment skin lesion images using a neural network with low available data?". This question is divided into three sub questions regarding best performing network structure, training data and training method. First theory associated with these questions is discussed. Literature states that U-net CNN structures have excellent performances on the segmentation task, more training data increases network performance and utilizing transfer learning enables networks to generalize to new data better. To validate these findings in the literature two experiments are conducted. The first experiment trains a network on data sets of different size. The second experiment proposes twelve network structures and trains them on the same data set. The experimental results support the findings in the literature. The FCN16 and FCN32 networks perform best in the accuracy, intersection over union and mean BF1 Score metric. Concluding from these results the skin lesion segmentation network is a fully convolutional structure with a skip architecture and an encoder depth of either one or two. Weights of this network should be initialized using transfer learning from the pre trained VGG16 network. Training data should be cropped to reduce complexity and augmented during training to reduce the likelihood of overfitting.

READ FULL TEXT

page 9

page 12

page 17

page 18

page 20

page 22

page 23

research
11/28/2017

Multi-class Semantic Segmentation of Skin Lesions via Fully Convolutional Networks

Early detection of skin cancer, particularly melanoma, is crucial to ena...
research
01/11/2021

Analysis of skin lesion images with deep learning

Skin cancer is the most common cancer worldwide, with melanoma being the...
research
09/08/2016

Extraction of Skin Lesions from Non-Dermoscopic Images Using Deep Learning

Melanoma is amongst most aggressive types of cancer. However, it is high...
research
07/09/2019

DSNet: Automatic Dermoscopic Skin Lesion Segmentation

Automatic segmentation of skin lesion is considered a crucial step in Co...
research
09/23/2018

Leveraging Transfer Learning for Segmenting Lesions and their Attributes in Dermoscopy Images

Computer-aided diagnosis systems for classification of different type of...
research
07/24/2018

Skin Lesion Segmentation Using Atrous Convolution via DeepLab v3

As melanoma diagnoses increase across the US, automated efforts to ident...
research
04/08/2021

A transfer-learning approach for lesion detection in endoscopic images from the urinary tract

Ureteroscopy and cystoscopy are the gold standard methods to identify an...

Please sign up or login with your details

Forgot password? Click here to reset