Dermoscopic Image Segmentation via Multistage Fully Convolutional Networks

By Lei Bi, Jinman Kim, Euijoon Ahn, Ashnil Kumar, Michael J. Fulham, D. Feng. IEEE Transactions on Biomedical Engineering, 2017

301 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

CA-Net: Comprehensive Attention Convolutional Neural Networks for Explainable Medical Image Segmentation (2020, background): “The main challenge for this task is that the skin lesion areas have various scales, shapes and colors, which requires automatic segmentation methods to be robust against shape and scale variations of the lesion [34].”
A Mutual Bootstrapping Model for Automated Skin Lesion Segmentation and Classification (2019, methodology): “0%, which was achieved by the mFCNPI [7], to 86.”
Channel prior convolutional attention for medical image segmentation (2023, unknown): “DSC ↑ IoU ↑ SSLS (Ahn et al., 2015) 78.3 68.1 MSCA (Bi et al., 2016) 81.5 72.3 FCN (Long et al., 2015) 89.4 82.1 Bi et al. (Bi et al., 2017) 90.6 83.9 UNET-2022 (Guo et al., 2022a) 91.0 84.2 nnUNet (Isensee et al., 2021) 91.6 85.1 BAT (Wang et al., 2021a) 92.1 85.8 CPCANet(ours) 93.7 88.8 points…”
A fully integrated computer-aided diagnosis system for digital X-ray mammograms via deep learning detection, segmentation, and classification (2018, methodology): “specificity, producing ROC curves with AUC, is also used to evaluate the segmentation method [70].”