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

TL;DR

This paper introduces a novel skin lesion segmentation model called Lesion Net that combines coordinate convolution, deep residual units, and a dual-loss function to improve accuracy and robustness across multiple datasets.

Contribution

The paper proposes a new segmentation approach integrating coordinate convolution and residual units with a combined loss function, enhancing generalization and training efficiency.

Findings

Outperforms existing methods on multiple datasets

Improves segmentation accuracy and convergence speed

Demonstrates robustness across diverse skin lesion datasets

Abstract

Skin lesions segmentation is an important step in the process of automated diagnosis of the skin melanoma. However, the accuracy of segmenting melanomas skin lesions is quite a challenging task due to less data for training, irregular shapes, unclear boundaries, and different skin colors. Our proposed approach helps in improving the accuracy of skin lesion segmentation. Firstly, we have introduced the coordinate convolutional layer before passing the input image into the encoder. This layer helps the network to decide on the features related to translation invariance which further improves the generalization capacity of the model. Secondly, we have leveraged the properties of deep residual units along with the convolutional layers. At last, instead of using only cross-entropy or Dice-loss, we have combined the two-loss functions to optimize the training metrics which helps in converging the loss more quickly and smoothly. After training and validating the proposed model on ISIC 2018 (60% as train set + 20% as validation set), we tested the robustness of our trained model on various other datasets like ISIC 2018 (20% as test-set) ISIC 2017, 2016 and PH2 dataset. The results show that the proposed model either outperform or at par with the existing skin lesion segmentation methods.