Multi-class discrimination of lymphadenopathy by using dual-modal ultrasound radiomics with elastography and B-mode ultrasound_Journal of Biomedical Engineering

Authors：

SHI Jie ^1,2 , JIANG Jianwei ³ , CHANG Wanying ³ ,  CHEN Man ³ ,  ZHANG Qi ^1,2

1. The SMART (Smart Medicine and AI-based Radiology Technology) Lab, Institute of Biomedical Engineering, School of Communication and Information Engineering, Shanghai University, Shanghai 200444, P.R.China;
2. Shanghai Institute for Advanced Communication and Data Science, Shanghai University, Shanghai 200444, P.R.China;
3. Department of Medical Ultrasound, Tong Ren Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200336, P.R.China;

Corresponding author：

CHEN Man, Email: maggiech1221@126.com; ZHANG Qi, Email: zhangq@t.shu.edu.cn

Keywords：

lymph node; radiomics; dual-modal; multi-class classification; feature selection

DOI：

10.7507/1001-5515.201807015

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

The purpose of our study is to evaluate the diagnostic performance of radiomics in multi-class discrimination of lymphadenopathy based on elastography and B-mode dual-modal ultrasound images. We retrospectively analyzed a total of 251 lymph nodes (89 benign lymph nodes, 70 lymphoma and 92 metastatic lymph nodes) from 248 patients, which were examined by both elastography and B-mode sonography. Firstly, radiomic features were extracted from multimodal ultrasound images, including shape features, intensity statistics features and gray-level co-occurrence matrix texture features. Secondly, three feature selection methods based on information theory were used on the radiomic features to select different subsets of radiomic features, consisting of conditional infomax feature extraction, conditional mutual information maximization, and double input symmetric relevance. Thirdly, the support vector machine classifier was performed for diagnosis of lymphadenopathy on each radiomic subsets. Finally, we fused the results from different modalities and different radiomic feature subsets with Adaboost to improve the performance of lymph node classification. The results showed that the accuracy and overall F1 score with five-fold cross-validation were 76.09%±1.41% and 75.88%±4.32%, respectively. Moreover, when considering on benign lymph nodes, lymphoma or metastatic lymph nodes respectively, the area under the receiver operating characteristic curve of multi-class classification were 0.77, 0.93 and 0.84, respectively. This study indicates that radiomic features derived from multimodal ultrasound images are benefit for diagnosis of lymphadenopathy. It is expected to be useful in clinical differentiation of lymph node diseases.

Citation： SHI Jie, JIANG Jianwei, CHANG Wanying, CHEN Man, ZHANG Qi. Multi-class discrimination of lymphadenopathy by using dual-modal ultrasound radiomics with elastography and B-mode ultrasound. Journal of Biomedical Engineering, 2019, 36(6): 957-963. doi: 10.7507/1001-5515.201807015 Copy

1.	张麒, 戴伟, 韩红, 等. 淋巴结超声造影图像序列的特征提取. 自动化仪表, 2015, 36(10): 40-43.
2.	Li Qin, Wang Ling, Wu Haojie, et al. Controlled study of traditional ultrasound and ultrasound elastography on the diagnosis of breast masses. Ultrasound Q, 2015, 31(4): 250-254.
3.	Dietrich C F, Saftoiu A, Jenssen C. Real time elastography endoscopic ultrasound (RTE-EUS), a comprehensive review. Eur J Radiol, 2014, 83(3): 405-414.
4.	Aoyagi S, Izumi K, Hata H, et al. Usefulness of real-time tissue elastography for detecting lymph-node metastases in squamous cell carcinoma. Clin Exp Dermatol, 2009, 34(8): e744-e747.
5.	Zhang Qi, Li Chaolun, Han Hong, Et al. Computer-aided quantification of contrast agent spatial distribution within atherosclerotic plaque in contrast-enhanced ultrasound image sequences. Biomed Signal Process Control, 2014, 13: 50-61.
6.	Aerts H J W L, Velazquez E R, Leijenaar R T H, et al. Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat Commun, 2014, 5: 4006.
7.	Cameron A, Khalvati F, Haider M A, et al. MAPS: A quantitative radiomics approach for prostate cancer detection. IEEE Trans Biomed Eng, 2016, 63(6): 1145-1156.
8.	Zhang Qi, Xiao Yang, Suo Jingfeng, et al. Sonoelastomics for breast tumor classification: a radiomics approach with clustering-based feature selection on sonoelastography. Ultrasound Med Biol, 2017, 43(5): 1058-1069.
9.	索静峰, 张麒, 常婉英, 等. 依托弹性与 B 型双模态超声影像组学的腋窝淋巴结转移评价. 中国医疗器械杂志, 2017, 41(5): 313-316, 326.
10.	Lambin P, Rios-Velazquez E, Leijenaar R, et al. Radiomics: extracting more information from medical images using advanced feature analysis. Eur J Cancer, 2012, 48(4): 441-446.
11.	Lin Dahua, Tang Xiaoou. Conditional Infomax Learning: An integrated framework for feature extraction and fusion // Leonardis A, Bischof H, Pinz A. Computer Vision–ECCV 2006. Springer Berlin Heidelberg, 2006: 68-82.
12.	Fleuret F. Fast binary feature selection with conditional mutual information. J Mach Learn Res, 2004, 5(3): 1531-1555.
13.	Meyer P E, Bontempi G. On the use of variable complementarity for feature selection in cancer classification// Workshops on Applications of Evolutionary Computation. Springer Berlin Heidelberg, 2006: 91-102.
14.	Vapnik V N. An overview of statistical learning theory. IEEE Trans Neural Netw, 1999, 10(5): 988-999.
15.	Schapire R E, Freund Y. A short introduction to boosting. J Jpn Soc Artif Intell, 1999, 14(5): 771-780.
16.	Vergara J R, Estévez P A. A review of feature selection methods based on mutual information. Neural Comput Appl, 2014, 24(1): 175-186.
17.	Duan K B, Keerthi S S. Which Is the best multiclass SVM method? An empirical study// Oza NC, Polikar R, Kittler J, et al. Multiple Classifier Systems—6th International Workshop, MCS 2005. Springer Berlin Heidelberg, 2005: 278-285.
18.	Picard R R, Cook R D. Cross-validation of regression models. Publications of the American Statistical Association, 1984, 79(387): 575-583.
19.	Moon W K, Lee Y W, Huang Y S, et al. Computer-aided prediction of axillary lymph node status in breast cancer using tumor surrounding tissue features in ultrasound images. Comput Methods Programs Biomed, 2017, 146: 143-150.
20.	纪岩磊, 韩真, 马恒敏, 等. 超声弹性成像对乳腺癌腋窝淋巴结诊断价值的探讨. 中华肿瘤防治杂志, 2016, 23(16): 1081-1084.
21.	Bhatia K S, Cho C C, Yuen Y H, et al. Real-time qualitative ultrasound elastography of cervical lymph nodes in routine clinical practice: interobserver agreement and correlation with malignancy. Ultrasound Med Biol, 2010, 36(12): 1990-1997.

1. 张麒, 戴伟, 韩红, 等. 淋巴结超声造影图像序列的特征提取. 自动化仪表, 2015, 36(10): 40-43.
2. Li Qin, Wang Ling, Wu Haojie, et al. Controlled study of traditional ultrasound and ultrasound elastography on the diagnosis of breast masses. Ultrasound Q, 2015, 31(4): 250-254.
3. Dietrich C F, Saftoiu A, Jenssen C. Real time elastography endoscopic ultrasound (RTE-EUS), a comprehensive review. Eur J Radiol, 2014, 83(3): 405-414.
4. Aoyagi S, Izumi K, Hata H, et al. Usefulness of real-time tissue elastography for detecting lymph-node metastases in squamous cell carcinoma. Clin Exp Dermatol, 2009, 34(8): e744-e747.
5. Zhang Qi, Li Chaolun, Han Hong, Et al. Computer-aided quantification of contrast agent spatial distribution within atherosclerotic plaque in contrast-enhanced ultrasound image sequences. Biomed Signal Process Control, 2014, 13: 50-61.
6. Aerts H J W L, Velazquez E R, Leijenaar R T H, et al. Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat Commun, 2014, 5: 4006.
7. Cameron A, Khalvati F, Haider M A, et al. MAPS: A quantitative radiomics approach for prostate cancer detection. IEEE Trans Biomed Eng, 2016, 63(6): 1145-1156.
8. Zhang Qi, Xiao Yang, Suo Jingfeng, et al. Sonoelastomics for breast tumor classification: a radiomics approach with clustering-based feature selection on sonoelastography. Ultrasound Med Biol, 2017, 43(5): 1058-1069.
9. 索静峰, 张麒, 常婉英, 等. 依托弹性与 B 型双模态超声影像组学的腋窝淋巴结转移评价. 中国医疗器械杂志, 2017, 41(5): 313-316, 326.
10. Lambin P, Rios-Velazquez E, Leijenaar R, et al. Radiomics: extracting more information from medical images using advanced feature analysis. Eur J Cancer, 2012, 48(4): 441-446.
11. Lin Dahua, Tang Xiaoou. Conditional Infomax Learning: An integrated framework for feature extraction and fusion // Leonardis A, Bischof H, Pinz A. Computer Vision–ECCV 2006. Springer Berlin Heidelberg, 2006: 68-82.
12. Fleuret F. Fast binary feature selection with conditional mutual information. J Mach Learn Res, 2004, 5(3): 1531-1555.
13. Meyer P E, Bontempi G. On the use of variable complementarity for feature selection in cancer classification// Workshops on Applications of Evolutionary Computation. Springer Berlin Heidelberg, 2006: 91-102.
14. Vapnik V N. An overview of statistical learning theory. IEEE Trans Neural Netw, 1999, 10(5): 988-999.
15. Schapire R E, Freund Y. A short introduction to boosting. J Jpn Soc Artif Intell, 1999, 14(5): 771-780.
16. Vergara J R, Estévez P A. A review of feature selection methods based on mutual information. Neural Comput Appl, 2014, 24(1): 175-186.
17. Duan K B, Keerthi S S. Which Is the best multiclass SVM method? An empirical study// Oza NC, Polikar R, Kittler J, et al. Multiple Classifier Systems—6th International Workshop, MCS 2005. Springer Berlin Heidelberg, 2005: 278-285.
18. Picard R R, Cook R D. Cross-validation of regression models. Publications of the American Statistical Association, 1984, 79(387): 575-583.
19. Moon W K, Lee Y W, Huang Y S, et al. Computer-aided prediction of axillary lymph node status in breast cancer using tumor surrounding tissue features in ultrasound images. Comput Methods Programs Biomed, 2017, 146: 143-150.
20. 纪岩磊, 韩真, 马恒敏, 等. 超声弹性成像对乳腺癌腋窝淋巴结诊断价值的探讨. 中华肿瘤防治杂志, 2016, 23(16): 1081-1084.
21. Bhatia K S, Cho C C, Yuen Y H, et al. Real-time qualitative ultrasound elastography of cervical lymph nodes in routine clinical practice: interobserver agreement and correlation with malignancy. Ultrasound Med Biol, 2010, 36(12): 1990-1997.

Journal of Biomedical Engineering

Multi-class discrimination of lymphadenopathy by using dual-modal ultrasound radiomics with elastography and B-mode ultrasound

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content