Non-invasive automated 3D thyroid lesion classification in ultrasound: a class of ThyroScan™ systems - PubMed (original) (raw)
Non-invasive automated 3D thyroid lesion classification in ultrasound: a class of ThyroScan™ systems
U Rajendra Acharya et al. Ultrasonics. 2012 Apr.
Abstract
Ultrasound-based thyroid nodule characterization into benign and malignant types is limited by subjective interpretations. This paper presents a Computer Aided Diagnostic (CAD) technique that would present more objective and accurate classification and further would offer the physician a valuable second opinion. In this paradigm, we first extracted the features that quantify the local changes in the texture characteristics of the ultrasound off-line training images from both benign and malignant nodules. These features include: Fractal Dimension (FD), Local Binary Pattern (LBP), Fourier Spectrum Descriptor (FS), and Laws Texture Energy (LTE). The resulting feature vectors were used to build seven different classifiers: Support Vector Machine (SVM), Decision Tree (DT), Sugeno Fuzzy, Gaussian Mixture Model (GMM), K-Nearest Neighbor (KNN), Radial Basis Probabilistic Neural Network (RBPNN), and Naive Bayes Classifier (NBC). Subsequently, the feature vector-classifier combination that results in the maximum classification accuracy was used to predict the class of a new on-line test thyroid ultrasound image. Two data sets with 3D Contrast-Enhanced Ultrasound (CEUS) and 3D High Resolution Ultrasound (HRUS) images of 20 nodules (10 benign and 10 malignant) were used. Fine needle aspiration biopsy and histology results were used to confirm malignancy. Our results show that a combination of texture features coupled with SVM or Fuzzy classifiers resulted in 100% accuracy for the HRUS dataset, while GMM classifier resulted in 98.1% accuracy for the CEUS dataset. Finally, for each dataset, we have proposed a novel integrated index called Thyroid Malignancy Index (TMI) using the combination of FD, LBP, LTE texture features, to diagnose benign or malignant nodules. This index can help clinicians to make a more objective differentiation of benign/malignant thyroid lesions. We have compared and benchmarked the system with existing methods.
Copyright © 2011 Elsevier B.V. All rights reserved.
Similar articles
- Cost-effective and non-invasive automated benign and malignant thyroid lesion classification in 3D contrast-enhanced ultrasound using combination of wavelets and textures: a class of ThyroScan™ algorithms.
Acharya UR, Faust O, Sree SV, Molinari F, Garberoglio R, Suri JS. Acharya UR, et al. Technol Cancer Res Treat. 2011 Aug;10(4):371-80. doi: 10.7785/tcrt.2012.500214. Technol Cancer Res Treat. 2011. PMID: 21728394 - Automated benign & malignant thyroid lesion characterization and classification in 3D contrast-enhanced ultrasound.
Acharya UR, S VS, Molinari F, Garberoglio R, Witkowska A, Suri JS. Acharya UR, et al. Annu Int Conf IEEE Eng Med Biol Soc. 2012;2012:452-5. doi: 10.1109/EMBC.2012.6345965. Annu Int Conf IEEE Eng Med Biol Soc. 2012. PMID: 23365926 - ThyroScreen system: high resolution ultrasound thyroid image characterization into benign and malignant classes using novel combination of texture and discrete wavelet transform.
Acharya UR, Faust O, Sree SV, Molinari F, Suri JS. Acharya UR, et al. Comput Methods Programs Biomed. 2012 Aug;107(2):233-41. doi: 10.1016/j.cmpb.2011.10.001. Epub 2011 Nov 4. Comput Methods Programs Biomed. 2012. PMID: 22054816 - A review on ultrasound-based thyroid cancer tissue characterization and automated classification.
Acharya UR, Swapna G, Sree SV, Molinari F, Gupta S, Bardales RH, Witkowska A, Suri JS. Acharya UR, et al. Technol Cancer Res Treat. 2014 Aug;13(4):289-301. doi: 10.7785/tcrt.2012.500381. Epub 2013 Nov 4. Technol Cancer Res Treat. 2014. PMID: 24206204 Review. - Texture analysis and machine learning to characterize suspected thyroid nodules and differentiated thyroid cancer: Where do we stand?
Sollini M, Cozzi L, Chiti A, Kirienko M. Sollini M, et al. Eur J Radiol. 2018 Feb;99:1-8. doi: 10.1016/j.ejrad.2017.12.004. Epub 2017 Dec 7. Eur J Radiol. 2018. PMID: 29362138 Review.
Cited by
- Advancements in Hyperspectral Imaging and Computer-Aided Diagnostic Methods for the Enhanced Detection and Diagnosis of Head and Neck Cancer.
Wu IC, Chen YC, Karmakar R, Mukundan A, Gabriel G, Wang CC, Wang HC. Wu IC, et al. Biomedicines. 2024 Oct 11;12(10):2315. doi: 10.3390/biomedicines12102315. Biomedicines. 2024. PMID: 39457627 Free PMC article. Review. - A systematic review of machine learning based thyroid tumor characterisation using ultrasonographic images.
Yadav N, Dass R, Virmani J. Yadav N, et al. J Ultrasound. 2024 Jun;27(2):209-224. doi: 10.1007/s40477-023-00850-z. Epub 2024 Mar 27. J Ultrasound. 2024. PMID: 38536643 Review. - Artificial intelligence in thyroid ultrasound.
Cao CL, Li QL, Tong J, Shi LN, Li WX, Xu Y, Cheng J, Du TT, Li J, Cui XW. Cao CL, et al. Front Oncol. 2023 May 12;13:1060702. doi: 10.3389/fonc.2023.1060702. eCollection 2023. Front Oncol. 2023. PMID: 37251934 Free PMC article. Review. - Segmentation of thyroid glands and nodules in ultrasound images using the improved U-Net architecture.
Zheng T, Qin H, Cui Y, Wang R, Zhao W, Zhang S, Geng S, Zhao L. Zheng T, et al. BMC Med Imaging. 2023 Apr 14;23(1):56. doi: 10.1186/s12880-023-01011-8. BMC Med Imaging. 2023. PMID: 37060061 Free PMC article. - A Novel Deep-Learning-Based CADx Architecture for Classification of Thyroid Nodules Using Ultrasound Images.
Göreke V. Göreke V. Interdiscip Sci. 2023 Sep;15(3):360-373. doi: 10.1007/s12539-023-00560-4. Epub 2023 Mar 28. Interdiscip Sci. 2023. PMID: 36976511 Free PMC article.
MeSH terms
Substances
LinkOut - more resources
Full Text Sources
Other Literature Sources
Miscellaneous