CKD-TransBTS: Clinical Knowledge-Driven Hybrid Transformer With Modality-Correlated Cross-Attention for Brain Tumor Segmentation

Lin, Jianwei; Lin, Jiatai; Lu, Cheng; Chen, Hao; Lin, Huan; Zhao, Bingchao; Shi, Zhenwei; Qiu, Bingjiang; Pan, Xipeng; Xu, Zeyan; Huang, Biao; Liang, Changhong; Han, Guoqiang; Liu, Zaiyi; Han, Chu

doi:10.1109/tmi.2023.3250474

articleIEEE Transactions on Medical ImagingFeb 28, 2023BRONZE OA

CKD-TransBTS: Clinical Knowledge-Driven Hybrid Transformer With Modality-Correlated Cross-Attention for Brain Tumor Segmentation

JLJianwei Lin JLJiatai Lin CLCheng Lu HCHao Chen HLHuan Lin

South China University of Technology · Guangdong Academy of Medical Sciences · +3 more institutions

PubMed

Indexed incrossrefpubmed

Abstract

Brain tumor segmentation (BTS) in magnetic resonance image (MRI) is crucial for brain tumor diagnosis, cancer management and research purposes. With the great success of the ten-year BraTS challenges as well as the advances of CNN and Transformer algorithms, a lot of outstanding BTS models have been proposed to tackle the difficulties of BTS in different technical aspects. However, existing studies hardly consider how to fuse the multi-modality images in a reasonable manner. In this paper, we leverage the clinical knowledge of how radiologists diagnose brain tumors from multiple MRI modalities and propose a clinical knowledge-driven brain tumor segmentation model, called CKD-TransBTS. Instead of directly…

Citation impact

193

total citations

FWCI: 22.56
Percentile: 100%
References: 76

Citations per year

Authors

15

Topics & keywords

Topics

Keywords

Segmentation
Transformer
Artificial intelligence
Image segmentation
Modality (human–computer interaction)
Computer science
Computer vision
Medicine

No related works found for this paper.