Literature DB >> 27908158

Similarity measurement of lung masses for medical image retrieval using kernel based semisupervised distance metric.

Guohui Wei1, He Ma2, Wei Qian3, Min Qiu4.   

Abstract

PURPOSE: To develop a new algorithm to measure the similarity between the query lung mass and reference lung mass data set for content-based medical image retrieval (CBMIR).
METHODS: A lung mass data set including 746 mass regions of interest (ROIs) was assembled. Among them, 375 ROIs depicted malignant lesions and 371 depicted benign lesions. Each mass ROI is represented by a vector of 26 texture features. A kernel function was employed to map the original data in input space to a feature space. In this space, a semisupervised distance metric was learned, which used differential scatter discriminant criterion to represent the semantic relevance, and the regularization term to represent the visual similarity. The learned distance metric can measure the similarity of the query mass and reference mass data set. The clustering accuracy is used to configure the parameters. The retrieval accuracy and classification accuracy are used as the performance assessment index.
RESULTS: After configuring the parameters, a mean clustering accuracy of 0.87 can be achieved. For retrieval accuracy, our algorithm achieves better performance than other state-of-the-art retrieval algorithms when applying a leave-one-out validation method to the testing data set. For classification accuracy, the area under the ROC curve of our algorithm can be achieved as 0.941 ± 0.006. The running times of 346 query images with the proposed algorithm are 5.399 and 6.0 s, respectively.
CONCLUSIONS: The study results demonstrated the proposed algorithm outperforms the compared algorithms, when taking the semantic relevant and visual similarity into account in kernel space. The algorithm can be used in a CBMIR system for a query mass to retrieve similarity masses, which can help doctors make better decisions.

Mesh:

Year:  2016        PMID: 27908158     DOI: 10.1118/1.4966030

Source DB:  PubMed          Journal:  Med Phys        ISSN: 0094-2405            Impact factor:   4.071


  5 in total

1.  DeepLesion: automated mining of large-scale lesion annotations and universal lesion detection with deep learning.

Authors:  Ke Yan; Xiaosong Wang; Le Lu; Ronald M Summers
Journal:  J Med Imaging (Bellingham)       Date:  2018-07-20

2.  Content-based image retrieval for Lung Nodule Classification Using Texture Features and Learned Distance Metric.

Authors:  Guohui Wei; Hui Cao; He Ma; Shouliang Qi; Wei Qian; Zhiqing Ma
Journal:  J Med Syst       Date:  2017-11-29       Impact factor: 4.460

3.  Cold-hot nature identification based on GC similarity analysis of Chinese herbal medicine ingredients.

Authors:  Guohui Wei; Xianjun Fu; Xueying He; Peng Qiu; Lu Yue; Rong Rong; Zhenguo Wang
Journal:  RSC Adv       Date:  2021-07-27       Impact factor: 4.036

4.  Cold-hot nature identification of Chinese herbal medicines based on the similarity of HPLC fingerprints.

Authors:  Guohui Wei; Ronghao Jia; Zhiyong Kong; Chengjie Ji; Zhenguo Wang
Journal:  Front Chem       Date:  2022-09-20       Impact factor: 5.545

5.  A multi-feature image retrieval scheme for pulmonary nodule diagnosis.

Authors:  Guohui Wei; Min Qiu; Kuixing Zhang; Ming Li; Dejian Wei; Yanjun Li; Peiyu Liu; Hui Cao; Mengmeng Xing; Feng Yang
Journal:  Medicine (Baltimore)       Date:  2020-01       Impact factor: 1.817

  5 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.