A Case Study of DenseNet, ResNet and Vision Transformers for Thyroid Nodule Analysis in Medical Imaging


Authors : Karima Bahmane; Hamid Aksasse; Brahim Alkhalil Chaouki

Volume/Issue : Volume 10 - 2025, Issue 3 - March

Google Scholar : https://tinyurl.com/muc8c6yw

Scribd : https://tinyurl.com/yk8k4m7t

DOI : https://doi.org/10.38124/ijisrt/25mar1818

PlumX Metrics

Semantic Scholar

ResearchGate

IJISRT Repository

Google Scholar

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Note : Google Scholar may take 15 to 20 days to display the article.

Abstract : In order to classify thyroid nodules using ultrasound imaging [1], this study assesses the effectiveness of three deep learning models: Vision Transformer (ViT), DenseNet, and ResNet. Seven thousand thyroid ultrasound pictures from Morocco's Hassan II Hospital (2005–2022) were utilized as the dataset. Accuracy, F1-score, sensitivity, and specificity were important parameters. DenseNet did somewhat better with 89.3% accuracy and F1-score than ResNet, which had 87.7% accuracy and an 87.8% F1-score. ViT outperformed both, achieving 91.5% accuracy and a 91.4% F1-score, demonstrating superior global context capture. ResNet excels in gradient flow optimization, DenseNet in feature propagation for smaller datasets, and ViT in versatility but requires larger datasets. The study highlights trade-offs between transformer-based and CNN-based architectures, emphasizing the importance of dataset characteristics and task requirements for optimal diagnostic outcomes in medical imaging.

Keywords : Thyroid Nodules, Deep Learning, Convolutional Neural Networks, Densenet, Resnet, Vision Transformer (ViT), Medical Imaging, Ultrasound Analysis, Classification, Artificial Intelligence In Healthcare.

References :

  1. Karima Bahmane Hamid Aksasse and Brahim Alkhalil Chaouki Radiologists Versus Artificial Intelligence in Distinguishing Between Thyroid Nodules on Ultrasound Images April 2024Progress in Medical Sciences 8(2):1-5 DOI: 10.47363/PMS/2024(8)203
  2. T. Liu, S. Xie, J. Yu, L. Niu, W. Sun, Classification of thyroid nodules in ultrasound images using deep model based transfer learning and hybrid features, in: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP, 2017, pp. 919–923, http://dx.doi.org/10.1109/ICASSP.2017.7952290.
  3. B. Wildman-Tobriner, M. Buda, J.K. Hoang, W.D. Middleton, D. Thayer, R.G. Short, F.N. Tessler, M.A. Mazurowski, Using artificial intelligence to revise ACR TI-RADS risk stratification of thyroid nodules: Diagnostic accuracy and utility, Radiology 292 (1) (2019) 112–119, http://dx.doi.org/10.1148/radiol.2019182128.
  4. M. Buda, B. Wildman-Tobriner, J.K. Hoang, D. Thayer, F.N. Tessler, W.D. Middleton, M.A. Mazurowski, Management of thyroid nodules seen on US images: Deep learning may match performance of radiologists, Radiology 292 (3) (2019) 695–701, http://dx.doi.org/10.1148/radiol.2019181343.
  5. E. Horvath, S. Majlis, R. Rossi, C. Franco, J.P. Niedmann, A. Castro, M. Dominguez, An ultrasonogram reporting system for thyroid nodules stratifying cancer risk for clinical management, J. Clin. Endocrinol. Metab. 94 (5) (2009) 1748–1751, http://dx.doi.org/10.1210/jc.2008-1724.
  6. A. Persichetti, E. Di Stasio, R. Guglielmi, G. Bizzarri, S. Taccogna, I. Misischi, F. Graziano, L. Petrucci, A. Bianchini, E. Papini, Predictive value of malignancy of thyroid nodule ultrasound classification systems: A prospective study, J. Clin. Endocrinol. Metab. 103 (4) (2018) 1359–1368, http://dx.doi.org/10.1210/jc.2017-01708.
  7. D.T. Nguyen, T.D. Pham, G. Batchuluun, H.S. Yoon, K.R. Park, Artificial intelligence-based thyroid nodule classification using information from spatial and frequency domains, J. Clin. Med. 8 (11) (2019) http://dx.doi.org/10.3390/jcm8111976.
  8. J. Chi, E. Walia, P. Babyn, J. Wang, G. Groot, M. Eramian, Thyroid nodule classification in ultrasound images by fine-tuning deep convolutional neural network, J. Digit. Imaging 30 (4) (2017) 477–486, http://dx.doi.org/10.1007/s10278-017-9997-y.
  9. L. Wang, L. Zhang, M. Zhu, X. Qi, Z. Yi, Automatic diagnosis for thyroid nodules in ultrasound images by deep neural networks, Med. Image Anal. 61 (2020) 101665, http://dx.doi.org/10.1016/j.media.2020.101665.
  10. J. Ma, F. Wu, J. Zhu, D. Xu, D. Kong, A pre-trained convolutional neural network based method for thyroid nodule diagnosis, Ultrasonics 73 (2017) 221–230, http://dx.doi.org/10.1016/j.ultras.2016.09.011.
  11. O. Moussa, H. Khachnaoui, R. Guetari, N. Khlifa, Thyroid nodules classification and diagnosis in ultrasound images using fine-tuning deep convolutional neural network, Int. J. Imaging Syst. Technol. 30 (1) (2020) 185–195, http://dx.doi.org/10.1002/ima.22363.
  12. W. Song, S. Li, J. Liu, H. Qin, B. Zhang, S. Zhang, A. Hao, Multitask cascade convolution neural networks for automatic thyroid nodule detection and recognition, IEEE J. Biomed. Health Inf. 23 (3) (2019) 1215–1224, http://dx.doi.org/10.1109/JBHI.2018.2852718.
  13. T. Liu, Q. Guo, C. Lian, X. Ren, S. Liang, J. Yu, L. Niu, W. Sun, D. Shen, Automated detection and classification of thyroid nodules in ultrasound images using clinical-knowledge-guided convolutional neural networks, Med. Image Anal. 58 (2019) 101555, http://dx.doi.org/10.1016/j.media.2019.101555.
  14. G. Shi, J. Wang, Y. Qiang, X. Yang, J. Zhao, R. Hao, W. Yang, Q. Du, N.G.-F. Kazihise, Knowledge-guided synthetic medical image adversarial augmentation for ultrasonography thyroid nodule classification, Comput. Methods Programs Biomed. 196 (2020) 105611, http://dx.doi.org/10.1016/j.cmpb.2020.105611.
  15. P. Wan, F. Chen, C. Liu, W. Kong, D. Zhang, Hierarchical temporal attention network for thyroid nodule recognition using dynamic CEUS imaging, IEEE Trans. Med. Imaging 40 (6) (2021) 1646–1660, http://dx.doi.org/10.1109/TMI.2021.3063421.
  16. Y. Chen, D. Li, X. Zhang, J. Jin, Y. Shen, Computer aided diagnosis of thyroid nodules based on the devised small-datasets multi-view ensemble learning, Med. Image Anal. 67 (2021) 101819, http://dx.doi.org/10.1016/j.media.2020.101819.
  17. X. He, E.-L. Tan, H. Bi, X. Zhang, S. Zhao, B. Lei, Fully transformer network for skin lesion analysis, Med. Image Anal. 77 (2022) 102357, http://dx.doi.org/10.1016/j.media.2022.102357.
  18. O. Dalmaz, M. Yurt, T. Cukur, ResViT: Residual vision transformers for multi-modal medical image synthesis, 2021, arXiv.
  19. A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A.N. Gomez, L. Kaiser, I. Polosukhin, Attention is all you need, in: Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS ’17, Curran Associates Inc., Red Hook, NY, USA, 2017, pp. 6000–6010.

In order to classify thyroid nodules using ultrasound imaging [1], this study assesses the effectiveness of three deep learning models: Vision Transformer (ViT), DenseNet, and ResNet. Seven thousand thyroid ultrasound pictures from Morocco's Hassan II Hospital (2005–2022) were utilized as the dataset. Accuracy, F1-score, sensitivity, and specificity were important parameters. DenseNet did somewhat better with 89.3% accuracy and F1-score than ResNet, which had 87.7% accuracy and an 87.8% F1-score. ViT outperformed both, achieving 91.5% accuracy and a 91.4% F1-score, demonstrating superior global context capture. ResNet excels in gradient flow optimization, DenseNet in feature propagation for smaller datasets, and ViT in versatility but requires larger datasets. The study highlights trade-offs between transformer-based and CNN-based architectures, emphasizing the importance of dataset characteristics and task requirements for optimal diagnostic outcomes in medical imaging.

Keywords : Thyroid Nodules, Deep Learning, Convolutional Neural Networks, Densenet, Resnet, Vision Transformer (ViT), Medical Imaging, Ultrasound Analysis, Classification, Artificial Intelligence In Healthcare.

Video Explanation for Published paper

Never miss an update from Papermashup

Get notified about the latest tutorials and downloads.

Subscribe by Email

Get alerts directly into your inbox after each post and stay updated.
Subscribe
OR

Subscribe by RSS

Add our RSS to your feedreader to get regular updates from us.
Subscribe