Learning Rich Attention for Pediatric Bone Age Assessment

Liu, Chuanbin; Xie, Hongtao; Yan, Yunyan; Mao, Zhendong; Zhang, Yongdong

doi:10.1007/978-3-030-59710-8_23

Cited by 3 publications

(1 citation statement)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the development of deep learning research, a large number of semantic segmentation methods have been proposed for skin lesion segmentation. Recently, the methods mainly focus on network structure, 16,17 sampling mechanisms, 18,19 and data augmentation, 20 whereas some mainly use additional constraints. 21,22 U-Net 23 is a traditional network in the tasks of medical image segmentation.…”

Section: Skin Lesion Segmentationmentioning

confidence: 99%

Confidence-aware cross-supervised model for semi-supervised skin lesion segmentation

Shen

Sun

et al. 2023

J. Electron. Imag.

View full text Add to dashboard Cite

.A long-standing problem in melanoma segmentation is that the pixel-level skin lesion label must be manually labeled by experts. Semi-supervised learning is considered a promising way to solve this problem. However, the pseudo labels obtained in the training phase are not accurate and will introduce wrong guidance to the model’s training. The segmentation of the unlabeled data after filtering by the confidence map can be a reliable pseudo label in training processing. Thus, a confidence-aware cross-supervised network is proposed for skin lesion segmentation, using captured confidence to make the training process more reliable. Our method is composed of two parallel and independently initialized segmentation networks. The output of one segmentation branch filters the low-confidence area by the confidence map of the same network and is used as a pseudo label to supervise another branch. Furthermore, a consistency loss is designed to calculate cross-entropy between the pseudo label and prediction segmentation to make full use of the unlabeled data. We also propose a simple yet effective attention module to capture the feature from the target area. This approach effectively mines the semantic information of the input image. To validate the effectiveness of our method, we conduct experiments on the ISIC 2017 dataset and achieve state-of-the-art results.

show abstract