Title | ||
---|---|---|
Automated diagnosis of bone metastasis based on multi-view bone scans using attention-augmented deep neural networks. |
Abstract | ||
---|---|---|
•An automated bone metastasis diagnosis model based on multi-view images is proposed. This model contains three parts that aim to extract, aggregate, and classify high-level features in a data-driven manner.•A total of 15,474 whole-body bone scan examinations are used to train and evaluate the proposed method.•An attention-augmented feature aggregation operator parameterized by a deep neural network is proposed to bind the features from the anterior and posterior views of an examination.•Experimental results demonstrate that the proposed method achieved results comparable to three nuclear medicine physicians. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1016/j.media.2020.101784 | Medical Image Analysis |
Keywords | DocType | Volume |
Bone metastasis,Deep neural networks,Multi-view,Whole body bone scan | Journal | 65 |
ISSN | Citations | PageRank |
1361-8415 | 2 | 0.37 |
References | Authors | |
0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yong Pi | 1 | 16 | 3.06 |
Zhen Zhao | 2 | 2 | 0.37 |
Yongzhao Xiang | 3 | 2 | 1.05 |
Yuhao Li | 4 | 2 | 0.37 |
Huawei Cai | 5 | 2 | 1.05 |
Zhang Yi | 6 | 356 | 37.14 |