当前位置: X-MOL 学术Magn. Reson. Imaging › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
A knowledge-driven feature learning and integration method for breast cancer diagnosis on multi-sequence MRI.
Magnetic Resonance Imaging ( IF 2.5 ) Pub Date : 2020-03-12 , DOI: 10.1016/j.mri.2020.03.001
Hongwei Feng 1 , Jiaqi Cao 1 , Hongyu Wang 2 , Yilin Xie 1 , Di Yang 3 , Jun Feng 1 , Baoying Chen 4
Affiliation  

Background

The classification of benign versus malignant breast lesions on multi-sequence Magnetic Resonance Imaging (MRI) is a challenging task since breast lesions are heterogeneous and complex. Recently, deep learning methods have been used for breast lesion diagnosis with raw image input. However, without the guidance of domain knowledge, these data-driven methods cannot ensure that the features extracted from images are comprehensive for breast cancer diagnosis. Specifically, these features are difficult to relate to clinically relevant phenomena.

Purpose

Inspired by the cognition process of radiologists, we propose a Knowledge-driven Feature Learning and Integration (KFLI) framework, to discriminate between benign and malignant breast lesions using Multi-sequences MRI.

Methods

Starting from sequence division based on characteristics, we use domain knowledge to guide the feature learning process so that the feature vectors of sub-sequence are constrained to lie in characteristic-related semantic space. Then, different deep networks are designed to extract various sub-sequence features. Furthermore, a weighting module is employed for the integration of the features extracted from different sub-sequence images adaptively.

Results

The KFLI is a domain knowledge and deep network ensemble, which can extract sufficient and effective features from each sub-sequence for a comprehensive diagnosis of breast cancer. Experiments on 100 MRI studies have demonstrated that the KFLI achieves sensitivity, specificity, and accuracy of 84.6%, 85.7% and 85.0%, respectively, which outperforms other state-of-the-art algorithms.



中文翻译:

一种基于知识的特征学习和集成方法,用于多序列MRI的乳腺癌诊断。

背景

由于乳腺病变是异质且复杂的,因此在多序列磁共振成像(MRI)上对乳腺良恶性病变的分类是一项艰巨的任务。最近,深度学习方法已用于通过原始图像输入进行乳腺病变诊断。但是,如果没有领域知识的指导,这些数据驱动的方法就无法确保从图像中提取的特征对于乳腺癌的诊断是全面的。具体而言,这些特征很难与临床相关现象相关。

目的

受到放射科医生认知过程的启发,我们提出了一种知识驱动的特征学习和整合(KFLI)框架,以使用多序列MRI来区分乳腺良性和恶性病变。

方法

从基于特征的序列划分开始,我们使用领域知识来指导特征学习过程,从而将子序列的特征向量约束在特征相关的语义空间中。然后,设计不同的深度网络以提取各种子序列特征。此外,采用加权模块来自适应地整合从不同子序列图像提取的特征。

结果

KFLI是一个领域知识和深度网络集成,可以从每个子序列中提取足够有效的特征,以对乳腺癌进行综合诊断。在100项MRI研究中进行的实验表明,KFLI的灵敏度,特异性和准确性分别达到84.6%,85.7%和85.0%,优于其他最新算法。

更新日期:2020-03-12
down
wechat
bug