Dense Pooling layers in Fully Convolutional Network for Skin Lesion Segmentation

TL;DR

This paper introduces a novel fully convolutional network with dense pooling layers that significantly improves the accuracy of skin lesion segmentation, aiding in better skin cancer detection.

Contribution

The paper proposes a new network architecture with dense pooling layers that outperforms existing methods in skin lesion segmentation accuracy.

Findings

Achieved higher segmentation accuracy than state-of-the-art methods.

Demonstrated effectiveness of dense pooling layers in medical image segmentation.

Improved border detection in skin lesion images.

Abstract

One of the essential tasks in medical image analysis is segmentation and accurate detection of borders. Lesion segmentation in skin images is an essential step in the computerized detection of skin cancer. However, many of the state-of-the-art segmentation methods have deficiencies in their border detection phase. In this paper, a new class of fully convolutional network is proposed, with new dense pooling layers for segmentation of lesion regions in skin images. This network leads to highly accurate segmentation of lesions on skin lesion datasets which outperforms state-of-the-art algorithms in the skin lesion segmentation.