摘要
乳腺癌的发病率在逐年增加,给全球女性的身体健康带来了极大的影响。而影像组学的高速发展,核磁共振检查已成为乳腺癌早期诊断必不可少的一部分。相关医学研究也表明,乳腺DWI影像作为DCE-MRI影像的辅助影像,能有效地提高乳腺癌病灶检出的准确度和可靠性。本文通过对乳腺MRI的两种不同模态的影像序列进行影像预处理、配准后,根据多模态影像的配准结果使用基于决策级的影像融合策略,提高乳腺癌良恶性分类的准确度。
With the incidence of breast cancer increases year by year,it has seriously endangered the health of women worldwide.With the rapid development of imaging omics,MRI has played an important role of the early diagnosis of breast cancer.Relevant medical research shows that breast DWI as auxiliary images of DCE-MRI can effectively improve the accuracy of breast lesion detection and ensure the reliability of breast cancer detection.In this paper,after preprocessing and registration of image sequences of two different modalities of breast MRI,a decision-level fusion strategy is used according to the obtained registration results from multi-modal image to improve the accuracy of breast cancer classification.
作者
顾莹莹
GU Yingying(School of Computer Science and Technology,Donghua University,Shanghai 201620,China)
出处
《智能计算机与应用》
2020年第12期62-63,68,共3页
Intelligent Computer and Applications