Boundary-Aware Transformers for Skin Lesion Segmentation

  title={Boundary-Aware Transformers for Skin Lesion Segmentation},
  author={Jiacheng Wang and Lan Wei and Liansheng Wang and Qichao Zhou and Lei Zhu and Jing Qin},
  • Jiacheng Wang, Lan Wei, +3 authors Jing Qin
  • Published 8 October 2021
  • Computer Science, Engineering
  • ArXiv
Skin lesion segmentation from dermoscopy images is of great importance for improving the quantitative analysis of skin cancer. However, the automatic segmentation of melanoma is a very challenging task owing to the large variation of melanoma and ambiguous boundaries of lesion areas. While convolutional neutral networks (CNNs) have achieved remarkable progress in this task, most of existing solutions are still incapable of effectively capturing global dependencies to counteract the inductive… 

Figures and Tables from this paper


Automatic Skin Lesion Segmentation Using Deep Fully Convolutional Networks With Jaccard Distance
A fully automatic method for skin lesion segmentation by leveraging 19-layer deep convolutional neural networks that is trained end-to-end and does not rely on prior knowledge of the data to ensure effective and efficient learning with limited training data is presented.
Dermoscopic Image Segmentation via Multistage Fully Convolutional Networks
This work proposes to leverage fully convolutional networks (FCNs) to automatically segment the skin lesions and introduces a new parallel integration method to combine the complementary information derived from individual segmentation stages to achieve a final segmentation result that has accurate localization and well-defined lesion boundaries, even for the most challenging skin lesions.
Automated saliency-based lesion segmentation in dermoscopic images
  • Euijoon Ahn, Lei Bi, +4 authors D. Feng
  • Medicine, Computer Science
    2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
  • 2015
A new automated saliency-based skin lesion segmentation (SSLS) that is designed to exploit the inherent properties of dermoscopic images, which have a focal central region and subtle contrast discrimination with the surrounding regions is proposed.
TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation
It is argued that Transformers can serve as strong encoders for medical image segmentation tasks, with the combination of U-Net to enhance finer details by recovering localized spatial information.
Automated Melanoma Recognition in Dermoscopy Images via Very Deep Residual Networks
This study corroborates that very deep CNNs with effective training mechanisms can be employed to solve complicated medical image analysis tasks, even with limited training data.
Automated skin lesion segmentation via image-wise supervised learning and multi-scale superpixel based cellular automata
This work proposes using ISL to derive a probabilistic map for automated seeds selection, which removes the reliance on user-defined seeds as in conventional methods and produces higher capacity to segment skin lesions with various sizes and contrast than single-scale pixel-based CA model.
CE-Net: Context Encoder Network for 2D Medical Image Segmentation
Comprehensive results show that the proposed CE-Net method outperforms the original U- net method and other state-of-the-art methods for optic disc segmentation, vessel detection, lung segmentation , cell contour segmentation and retinal optical coherence tomography layer segmentation.
UNet++: A Nested U-Net Architecture for Medical Image Segmentation
This paper presents UNet++, a new, more powerful architecture for medical image segmentation where the encoder and decoder sub-networks are connected through a series of nested, dense skip pathways, and argues that the optimizer would deal with an easier learning task when the feature maps from the decoder and encoder networks are semantically similar.
Rethinking Atrous Convolution for Semantic Image Segmentation
The proposed `DeepLabv3' system significantly improves over the previous DeepLab versions without DenseCRF post-processing and attains comparable performance with other state-of-art models on the PASCAL VOC 2012 semantic image segmentation benchmark.
Structure Boundary Preserving Segmentation for Medical Image With Ambiguous Boundary
A novel image segmentation method to tackle two critical problems of medical image, which are ambiguity of structure boundary in the medical image domain and uncertainty of the segmented region without specialized domain knowledge is proposed.