返回
MOTDNet: Multi organ task decoupling network for cell segmentation
DOI:10.1016/j.media.2026.104045.png)
摘要
En 中文
一种新型多器官异构任务解耦细胞分割网络(MOTDNet)。• 针对不同任务设计了多任务特定卷积和译码器。• MOTDNet优于现有方法,在PanNuke数据集上实现了mPQ、bPQ和F-1分数分别为0.4999、0.6804,具有3200万参数和18 GFLOPs的计算量,展示了当前最佳性能。• MOTDNet在MoNuSeg、NYU-V2和Cityscapes数据集上表现出优异的泛化能力。
Keyword:
cell segmentation
multi-organ
task decoupling
deep learning
image analysis
期刊
IF:
11.8
论文数:
3.9K
被引数:
2.4W
机构
引用论文
Data-efficient and weakly supervised computational pathology on whole-slide images全载玻片图像上的数据高效和弱监督计算病理学
Hover-Net: Simultaneous segmentation and classification of nuclei in multi-tissue histology imagesHover-Net: 多组织组织学图像中细胞核的同时分割和分类
MEDICAL IMAGE ANALYSIS
IF11.8
TSFD-Net: Tissue specific feature distillation network for nuclei segmentation and classification
NEURAL NETWORKS
IF6.3
Novel digital signatures of tissue phenotypes for predicting distant metastasis in colorectal cancer用于预测结直肠癌远处转移的组织表型的新型数字签名
SCIENTIFIC REPORTS
IF3.9
Detection and Segmentation of Cell Nuclei in Virtual Microscopy Images: A Minimum-Model Approach
SCIENTIFIC REPORTS
IF3.9

