Effective Feature Selection on Transfer Deep Learning Algorithm for Thyroid Nodules Ultrasound Detection

Ghufran Basim Alghanimi; Hadeel Aljobouri; Khaleel Akeash Alshimmari; Rasha Massoud

doi:10.29194/NJES.27040396

Authors

Ghufran Basim Alghanimi Biomedical Engineering Department, College of Engineering, Al-Nahrain University, Baghdad, Iraq
Hadeel Aljobouri Biomedical Engineering Department, College of Engineering, Al-Nahrain University, Baghdad, Iraq
Khaleel Akeash Alshimmari Ministry of Health, Baghdad Medical City, Baghdad, Iraq
Rasha Massoud Biomedical Engineering Department, Faculty of Mechanical and Electrical Engineering, Damascus University., Damascus, Syria

DOI:

https://doi.org/10.29194/NJES.27040396

Keywords:

Feature Selection, Principal Component Analysis, Transfer Learning ResNet50, Thyroid Nodules, Ultrasound

Abstract

Thyroid nodules (TNs) are discrete abnormalities located within the thyroid gland that are radiologically different from the surrounding thyroid tissue. Ultrasound is an accurate and efficient way to diagnose thyroid nodules. Recently, several methods of AI were proposed to improve the detection of thyroid nodules ultrasound images with good performances. However, in some cases related to the type or size of the dataset using machine or transfer deep learning methods alone is unable to achieve high accuracy and high specificity. Consequently, the addition of feature selection)FS) to the deep learning method enhances the results by reducing the high features and the time needed for training the dataset. This study proposes two deep-learning models for classifying thyroid nodule US images into two categories: benign and malignant. ResNet50 was the first model used to extract deep features from US images. The second model integrates ResNet50 and principal component analysis (PCA) for feature selection, intending to reduce dataset dimensionality while maintaining the greatest data variance possible before classification. The proposed model was created using a freely available dataset. The dataset consists of 800 images, 400 benign and 400 malignant. The suggested system was accessed based on accuracy, precision, recall, and F1 score. The classification accuracy for ResNet50 was 85%, while ReNet50-PCA was 89.16%. The combination of deep learning and FS techniques in this research produces an interesting diagnostic framework that can potentially increase efficiency and accuracy in thyroid cancer detection, especially in local healthcare centers.

Downloads

Download data is not yet available.

References

N. Q. Tran, B. H. Le, C. K. Hoang, H. T. Nguyen, and T. T. Thai, “Prevalence of Thyroid Nodules and Associated Clinical Characteristics: Findings from a Large Sample of People Undergoing Health Checkups at a University Hospital in Vietnam,” Risk Management and Healthcare Policy, vol. 16, pp. 899–907, 2023. DOI: https://doi.org/10.2147/RMHP.S410964

H. Yu et al., “Intelligent diagnosis algorithm for thyroid nodules based on deep learning and statistical features,” Biomedical Signal Processing and Control, vol. 78, p. 103924, Sep. 2022, doi: 10.1016/J.BSPC.2022.103924. DOI: https://doi.org/10.1016/j.bspc.2022.103924

X. Wu, B. L. Li, C. J. Zheng, and X. D. He, “Predictive factors for central lymph node metastases in papillary thyroid microcarcinoma,” World Journal of Clinical Cases, vol. 8, no. 8, pp. 1350–1360, Apr. 2020, doi: 10.12998/WJCC.V8.I8.1350. DOI: https://doi.org/10.12998/wjcc.v8.i8.1350

L. Enewold et al., “Rising thyroid cancer incidence in the United States by demographic and tumor characteristics, 1980-2005,” Cancer Epidemiology Biomarkers and Prevention, vol. 18, no. 3, pp. 784–791, Mar. 2009, doi: 10.1158/1055-9965.EPI-08-0960/347793/P/RISING-THYROID-CANCER-INCIDENCE-IN-THE-UNITED. DOI: https://doi.org/10.1158/1055-9965.EPI-08-0960

A. Mjali and B. Najeh Hasan Al Baroodi, “Some Facts About Cancers in Karbala province of Iraq, 2012-2020,” Asian Pacific Journal of Cancer Care, vol. 5, no. 2, pp. 67–69, 2020, doi: 10.31557/apjcc.2020.5.2.67-69. DOI: https://doi.org/10.31557/apjcc.2020.5.2.67-69

J. Xia et al., “Ultrasound-based differentiation of malignant and benign thyroid Nodules: An extreme learning machine approach,” Computer Methods and Programs in Biomedicine, vol. 147, pp. 37–49, 2017, doi: 10.1016/j.cmpb.2017.06.005. DOI: https://doi.org/10.1016/j.cmpb.2017.06.005

M. Blum, “Ultrasonography of the Thyroid,” Europe PMC, no. 6, pp. 1–44, 2015.

L. Wang, L. Zhang, M. Zhu, X. Qi, and Z. Yi, “Automatic diagnosis for thyroid nodules in ultrasound images by deep neural networks,” Medical Image Analysis, vol. 61, Apr. 2020, doi: 10.1016/j.media.2020.101665. DOI: https://doi.org/10.1016/j.media.2020.101665

J. Chen, H. You, and K. Li, “A review of thyroid gland segmentation and thyroid nodule segmentation methods for medical ultrasound images,” Computer Methods and Programs in Biomedicine, vol. 185, p. 105329, Mar. 2020, doi: 10.1016/J.CMPB.2020.105329. DOI: https://doi.org/10.1016/j.cmpb.2020.105329

A. F. Ahmed, “Efficient Approach for De-Speckling Medical Ultrasound Images Using Improved Adaptive Shock Filter,” Journal for Engineering Sciences (NJES), vol. 20, no. 5, pp. 1192–1197, 2017.

P. Hamet and J. Tremblay, “Artificial intelligence in medicine,” Metabolism, vol. 69, pp. S36–S40, Apr. 2017, doi: 10.1016/J.METABOL.2017.01.011. DOI: https://doi.org/10.1016/j.metabol.2017.01.011

G.-G. Wu et al., “Artificial intelligence in breast ultrasound,” World Journal of Radiology, vol. 11, no. 2, p. 19, Feb. 2019, doi: 10.4329/WJR.V11.I2.19. DOI: https://doi.org/10.4329/wjr.v11.i2.19

S. M. Alnedawe and H. K. Aljobouri, “A New Model Design for Combating COVID -19 Pandemic Based on SVM and CNN Approaches,” Baghdad Science Journal, vol. 20, no. 4, pp. 1402–1402, Aug. 2023, doi: 10.21123/BSJ.2023.7403. DOI: https://doi.org/10.21123/bsj.2023.7403

T. Abd, U.-M. Sadoon, and M. H. Ali, “Coronavirus 2019 (COVID-19) Detection Based on Deep Learning,” Al-Nahrain Journal for Engineering Sciences NJES, vol. 23, no. 4, pp. 408–415, 2020, doi: 10.29194/NJES.23040408. DOI: https://doi.org/10.29194/NJES.23040408

H. Alrubaie, H. K. Aljobouri, Z. J. AL-Jobawi, and I. Çankaya, “Convolutional Neural Network Deep Learning Model for Improved Ultrasound Breast Tumor Classification,” Al-Nahrain Journal for Engineering Sciences, vol. 26, no. 2, pp. 57–62, 2023, doi: 10.29194/njes.26020057. DOI: https://doi.org/10.29194/NJES.26020057

R. K. Sinha, R. Pandey, and R. Pattnaik, “Deep Learning For Computer Vision Tasks: A review,” 2017 International Conference on Intelligent Computing and Control (I2C2), 2018.

G. Chartrand et al., “Deep Learning: A Primer for Radiologists,” Radiographics, vol. 37, no. 7, pp. 2113–2131, Nov. 2017. DOI: https://doi.org/10.1148/rg.2017170077

G. Ayana, J. Park, J. W. Jeong, and S. W. Choe, “A Novel Multistage Transfer Learning for Ultrasound Breast Cancer Image Classification,” Diagnostics, vol. 12, no. 1, p. 135, Jan. 2022, doi: 10.3390/DIAGNOSTICS12010135/S1. DOI: https://doi.org/10.3390/diagnostics12010135

J. Chi, E. Walia, P. Babyn, J. Wang, G. Groot, and M. Eramian, “Thyroid nodule classification in ultrasound images by fine-tuning deep convolutional neural network,” Journal of digital imaging, vol. 30, pp. 477–486, 2017. DOI: https://doi.org/10.1007/s10278-017-9997-y

M. Guo and Y. Du, “Classification of Thyroid Ultrasound Standard Plane Images using ResNet-18 Networks,” 2019 IEEE 13th International Conference on Anti-counterfeiting, Security, and Identification (ASID), pp. 324–328, 2019. DOI: https://doi.org/10.1109/ICASID.2019.8925267

N. Aboudi, H. Khachnaoui, O. Moussa, and N. Khlifa, “Bilinear Pooling for Thyroid Nodule Classification in Ultrasound Imaging,” Arabian Journal for Science and Engineering, vol. 48, no. 8, pp. 10563–10573, 2023, doi: 10.1007/s13369-023-07674-3. DOI: https://doi.org/10.1007/s13369-023-07674-3

G. Swathi, A. Altalbe, and R. P. Kumar, “QuCNet: Quantum-Inspired Convolutional Neural Networks for Optimized Thyroid Nodule Classification,” IEEE Access, vol. 12, pp. 27829–27842, 2024, doi: 10.1109/ACCESS.2024.3367806. DOI: https://doi.org/10.1109/ACCESS.2024.3367806

“Algerian Ultrasound Images Thyroid Dataset: AUITD.” Accessed: Dec. 25, 2023. [Online]. Available: https://www.kaggle.com/datasets/azouzmaroua/algeria-ultrasound-images-thyroid-dataset-auitd

M. J. Willemink et al., “Preparing medical imaging data for machine learning,” Radiology, vol. 295, no. 1, pp. 4–15, Feb. 2020, doi: 10.1148/Radiol.2020192224/Asset/Images/Large/Radiol.2020192224.Fig5b.Jpeg. DOI: https://doi.org/10.1148/radiol.2020192224

A. Sai Bharadwaj Reddy and D. Sujitha Juliet, “Transfer learning with RESNET-50 for malaria cell-image classification,” 2019 International Conference on Communication and Signal Processing (ICCSP), pp. 945–949, Apr. 2019, doi: 10.1109/ICCSP.2019.8697909. DOI: https://doi.org/10.1109/ICCSP.2019.8697909

O. Moussa, H. Khachnaoui, R. Guetari, and N. Khlifa, “Thyroid nodules classification and diagnosis in ultrasound images using fine-tuning deep convolutional neural network,” International Journal of Imaging Systems and Technology, vol. 30, no. 1, pp. 185–195, Mar. 2020, doi: 10.1002/IMA.22363. DOI: https://doi.org/10.1002/ima.22363

R. Zebari, A. Abdulazeez, D. Zeebaree, D. Zebari, and J. Saeed, “A Comprehensive Review of Dimensionality Reduction Techniques for Feature Selection and Feature Extraction,” Journal of Applied Science and Technology Trends, vol. 1, no. 1, pp. 56–70, 2020, doi: 10.38094/jastt1224. DOI: https://doi.org/10.38094/jastt1224

P. Jindal and D. Kumar, “A Review on Dimensionality Reduction Techniques,” International Journal of Computer Applications, vol. 173, no. 2, pp. 975–8887, 2017. DOI: https://doi.org/10.5120/ijca2017915260

T. Howley, M. G. Madden, M. L. O’Connell, and A. G. Ryder, “The effect of principal component analysis on machine learning accuracy with high-dimensional spectral data,” Knowledge-Based Systems, vol. 19, no. 5, pp. 363–370, 2006, doi: 10.1016/j.knosys.2005.11.014. DOI: https://doi.org/10.1016/j.knosys.2005.11.014