Thyroid nodule classification in ultrasound images by fine-tuning deep convolutional neural network
Open accessAbstract
With many thyroid nodules being incidentally detected, it is important to identify as many malignant nodules as possible while excluding those that are highly likely to be benign from fine needle aspiration (FNA) biopsies or surgeries. This paper presents a computer-aided diagnosis (CAD) system for classifying thyroid nodules in ultrasound images. We use deep learning approach to extract features from thyroid ultrasound images. Ultrasound images are pre-processed to calibrate their scale and remove the artifacts. A pre-trained GoogLeNet model is then fine-tuned using the pre-processed image samples which leads to superior feature extraction. The extracted features of the thyroid ultrasound images are sent to a Cost-sensitive Random Forest classifier to classify the images into "malignant" and "benign" cases. The experimental results show the proposed fine-tuned GoogLeNet model achieves excellent classification performance, attaining 98.29% classification accuracy, 99.10% sensitivity and 93.90% specificity for the images in an open access database (Pedraza et al. 16), while 96.34% classification accuracy, 86% sensitivity and 99% specificity for the images in our local health region database.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
CNN is one of the most popular deep architectures and has gained great success in image classification, object detection, and target segmentation.
“CNN is known as one of the most popular deep architectures and has also gained great success in various tasks, such as image classification [48,49], object detection [29,30], and target segmentation [44,50].”
From Deep Learning in Medical Ultrasound Analysis: A Review (2019) · cites this paper as [48]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · see citing works
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562 · see citing works
Advances in Neural Information Processing Systems 25
Zhang, Y., Sutton, C. A., Storkey, A., & Zoubin Ghahramani, A. (2012) · Cited by 12,653 · see citing works
Caffe: Convolutional Architecture for Fast Feature Embedding
Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., & Darrell, T. (2014) · Proceedings of the 22nd ACM international conference on Multimedia · doi:10.1145/2647868.2654889 · Cited by 11,077 · see citing works
Kwak, J. Y., Han, K., Yoon, J. H., Moon, H. J., Son, E. J., Park, S., Jung, H. K., Choi, J. S., Kim, B. M., & Kim, E. (2011) · Radiology · doi:10.1148/radiol.11110206 · Cited by 1,101 · see citing works
Image Restoration by the Method of Convex Projections: Part 1ߞTheory
Youla, D. C., & Webb, H. (1982) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.1982.4307555 · Cited by 1,025 · see citing works
Breast cancer histopathological image classification using Convolutional Neural Networks
Spanhol, F. A., Oliveira, L. S., Petitjean, C., & Heutte, L. (2016) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2016.7727519 · Cited by 996 · see citing works
Roth, H. R., Lu, L., Seff, A., Cherry, K. M., Hoffman, J., Wang, S.-J., Liu, J., Turkbey, E., & Summers, R. (2014) · International Conference on Medical Image Computing and Computer-Assisted Intervention · doi:10.1007/978-3-319-10404-1_65 · Cited by 593 · see citing works
An open access thyroid ultrasound image database
Pedraza, L. R., Vargas, C., Narváez, F., et al. (2015) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2073532 · Cited by 275 · see citing works
Li, W., Cao, P., Zhao, D., & Wang, J. (2016) · Computational and Mathematical Methods in Medicine · doi:10.1155/2016/6215085 · Cited by 199 · see citing works
Self-citationFuzzy Local Binary Patterns for Ultrasound Texture Characterization
Iakovidis, D. K., Keramidas, E. G., & Maroulis, D. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-69812-8_74 · Cited by 170 · see citing works
On the Impact of Data Set Size in Transfer Learning Using Deep Neural Networks
Soekhoe, D., van der Putten, P., & Plaat, A. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46349-0_5 · Cited by 137 · see citing works
Chang, C., Chen, S.-J., & Tsai, M. (2010) · Pattern Recognition · doi:10.1016/j.patcog.2010.04.023 · Cited by 117 · see citing works
A Review on Ultrasound-Based Thyroid Cancer Tissue Characterization and Automated Classification
Acharya, U. R., Swapna, G., Sree, S. V., Molinari, F., Gupta, S., Bardales, R. H., Witkowska, A., & Suri, J. S. (2013) · Technology in Cancer Research & Treatment · doi:10.7785/tcrt.2012.500381 · Cited by 99 · see citing works
Robust Convolutional Neural Networks for Image Recognition
Hayder, M., Haider, A., & Naz, E. (2015) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2015.061115 · Cited by 89 · see citing works
Thyroid nodule classification using ultrasound elastography via linear discriminant analysis
Luo, S., Kim, E.-H., Dighe, M., et al. (2010) · Ultrasonics · doi:10.1016/j.ultras.2010.11.008 · Cited by 79 · see citing works
Fusion of fuzzy statistical distributions for classification of thyroid ultrasound patterns
Iakovidis, D. K., Keramidas, E. G., & Maroulis, D. (2010) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2010.04.004 · Cited by 64 · see citing works
Wu, H., Deng, Z., Zhang, B., Liu, Q., & Chen, J. (2016) · American Journal of Roentgenology · doi:10.2214/ajr.15.15813 · Cited by 57 · see citing works
Lim, K. J., Choi, C. S., Yoon, D. Y., et al. (2008) · Academic Radiology · doi:10.1016/j.acra.2007.12.022 · Cited by 53 · see citing works
Chen, S.-J., Chang, C., Chang, K. W., et al. (2010) · Ultrasound in Medicine & Biology · doi:10.1016/j.ultrasmedbio.2010.08.019 · Cited by 45 · see citing works
Acharya, U. R., Sree, S. V., Swapna, G., et al. (2013) · Proceedings of the Institution of Mechanical Engineers Part H Journal of Engineering in Medicine · doi:10.1177/0954411912472422 · Cited by 43 · see citing works
Computational Characterization of Thyroid Tissue in the Radon Domain
Savelonas, M. A., Iakovidis, D. K., Dimitropoulos, N., et al. (2007) · Proceedings - IEEE Symposium on Computer-Based Medical Systems · doi:10.1109/cbms.2007.33 · Cited by 40 · see citing works
Lingam, R. K., Qarib, M. H., & Tolley, N. (2013) · Insights into Imaging · doi:10.1007/s13244-013-0256-6 · Cited by 30 · see citing works
A Contourlet Transform Feature Extraction Scheme for Ultrasound Thyroid Texture Classification
Katsigiannis, S., Keramidas, E. G., & Maroulis, D. (2010) · Cited by 30 · see citing works
COMPUTER-BASED NODULE MALIGNANCY RISK ASSESSMENT IN THYROID ULTRASOUND IMAGES
Legakis, I., Savelonas, M. A., Maroulis, D., et al. (2011) · International Journal of Computers and Applications · doi:10.2316/journal.202.2011.1.202-2955 · Cited by 26 · see citing works
Savelonas, M. A., Maroulis, D., Iakovidis, D. K., et al. (2008) · Panhellenic Conference on Informatics · doi:10.1109/pci.2008.44 · Cited by 16 · see citing works
Automatic removal of manually induced artefacts in ultrasound images of thyroid gland
Narayan, N. S., Marziliano, P., & Hobbs, C. (2013) · doi:10.1109/embc.2013.6610271 · Cited by 13 · see citing works
COMPUTER-AIDED DIAGNOSIS FOR THYROID GRAVES' DISEASE IN ULTRASOUND IMAGES
Chang, C., Liu, H.-Y., Tseng, C., et al. (2010) · Biomedical Engineering Applications Basis and Communications · doi:10.4015/s1016237210001815 · Cited by 11 · see citing works
Automated detection of grayscale bar and distance scale in ultrasound images
Ahmed, W., & Eramian, M. (2010) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.844579 · Cited by 4 · see citing works
Self-citation
Flagged first, then by citations
Research works printed but not linked: 1
- [1]Diana Gaitini, Rhodri M Evans, and Gordana Ivanac, Chapter 16: thyroid ultrasound. EFSUMB Course Book, 2011.
Cited by
Sorted by citations
Deep Learning in Medical Ultrasound Analysis: A Review
Liu, S., Wang, Y., Yang, X., Lei, B., Liu, L., Li, S. X., Ni, D., & Wang, T. (2019) · Engineering · doi:10.1016/j.eng.2018.11.020 · Cited by 798 · see citing works
A scoping review of transfer learning research on medical image analysis using ImageNet
Morid, M. A., Borjali, A., & Del Fiol, G. (2021) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2020.104115 · Cited by 508 · see citing works
Deep learning with convolutional neural network in radiology
Yasaka, K., Akai, H., Kunimatsu, A., Kiryu, S., & Abe, O. (2018) · Japanese Journal of Radiology · doi:10.1007/s11604-018-0726-3 · Cited by 368 · see citing works
Using deep-learning algorithms to classify fetal brain ultrasound images as normal or abnormal
Xie, H. N., Wang, N., He, M., Zhang, L. H., Cai, H. M., Xian, J. B., Lin, M. F., Zheng, J., & Yang, Y. Z. (2020) · Ultrasound in Obstetrics & Gynecology · doi:10.1002/uog.21967 · Cited by 176 · see citing works
Xi, P., Guan, H., Shu, C., Borgeat, L., & Goubran, R. (2020) · The Visual Computer · doi:10.1007/s00371-019-01775-7 · Cited by 47 · see citing works
Sun, H., Jiao, J., Ren, Y., Guo, Y., & Wang, Y. (2023) · Pregnancy Hypertension · doi:10.1016/j.preghy.2022.12.003 · Cited by 10 · see citing works
- Authors
- Chi, J., Walia, E., Babyn, P., Wang, J., Groot, G., & Eramian, M.
- Affiliations
- University of Saskatchewan (CA)
- Royal University Hospital (CA)
- Corresponding author
- Chi, Jianning
- Venue
- Journal of Digital Imaging
- Published
- 2017-07-10
- Volume
- 30
- Issue
- 4
- Pages
- 477-486
- ISSN
- 0897-1889 (ISSN-L)
- 1618-727X
- PMC
- PMC5537102
- OpenAlex
- W2735666957
- Cited by
- 396
- References
- 29
- Citations by year
- 2026: 24 · 2025: 30 · 2024: 35 · 2023: 58 · 2022: 62 · 2021: 58 · 2020: 69 · 2019: 42 · 2018: 16 · 2017: 2
- FWCI
- 21.04
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Locations
- Journal of Imaging Informatics in Medicine (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Funders
- Saskatchewan Health Research Foundation (3702)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Health Sciences › Medicine › Endocrinology, Diabetes and Metabolism › Thyroid Cancer Diagnosis and Treatment
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiomics and Machine Learning in Medical Imaging
- Keywords
- thyroid nodule classification, thyroid ultrasound, computer-aided diagnosis, GoogLeNet, fine-tuning, malignancy prediction, benign versus malignant nodules, feature extraction, image artifact removal, scale calibration
- MeSH terms
- Diagnosis, Computer-Assisted, Humans, Sensitivity and Specificity, Thyroid Gland, Ultrasonography, Neural Networks, Computer, Thyroid Nodule, Biopsy, Fine-Needle
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
