.png){kind=icon}
返回
Joint task semi-supervised semantic segmentation for TRUS image
.png){kind=icon}
PRE
AI
DOI：10.1016/j.bspc.2023.105654.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Transrectal ultrasound (TRUS) is an important tool for prostate observation, playing a crucial role in medical processes such as multimodal image registration and surgical planning. However, TRUS images are often plagued by blurry boundary information and artifacts, making manual annotation a time-consuming and labor-intensive task, which results in insufficient pixel-labeled data for training neural networks. Therefore, this paper introduces a semi-supervised neural network based on joint tasks for TRUS image segmentation, which combines confidence information from target localization and semantic segmentation to generate pseudo-labels for collectively training unlabeled samples. Additionally, this method supports the generation of pseudo-labels using only location information for weakly supervised training of neural networks. Compared to other state-of-the-art models, our results show that this approach outperforms in segmentation performance with a smaller dataset, achieving an mean Dice similarity coefficient and mean Jaccard similarity coefficient of 92.8 % and 88.4 %, respectively. Furthermore, the experiments reveal that reducing the coupling of two decoders' parameters between the segmentation and detection tasks improves segmentation accuracy as dataset size decreases.
Keyword:
Semi -supervised learning
Weakly supervised learning
Prostate segmentation
Transrectal ultrasound process
期刊
IF:
4.9
论文数:
1.0W
被引数:
2.4W
机构
引用论文
分享收藏Joint Multiclass Object Detection and Semantic Segmentation for Autonomous Driving面向自主驾驶的联合多类目标检测与语义分割.png)
IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAI分享收藏
查看更多内容