Login Register Cart 0
Generic placeholder image

Current Medical Imaging

Editor-in-Chief

ISSN (Print): 1573-4056
ISSN (Online): 1875-6603

Back
Journal Home About Journal Editorial Board Journal Insight Current Issue Volumes/Issues
Subscribe
Research Article

Thyroid Nodules Classification using Weighted Average Ensemble and DCRITIC Based TOPSIS Methods for Ultrasound Images

Author(s): Rohit Sharma*, Gautam Kumar Mahanti, Ganapati Panda and Abhishek Singh

Volume 20, 2024

Published on: 06 June, 2023

Article ID: e050423215446 Pages: 18

DOI: 10.2174/1573405620666230405085358

Price: $65

conference banner
Abstract

Background: Thyroid disorders are prevalent worldwide and impact many people. The abnormal growth of cells in the thyroid gland region is very common and even found in healthy people. These abnormal cells can be cancerous or non-cancerous, so early detection of this disease is the only solution for minimizing the death rate or maximizing a patient's survival rate. Traditional techniques to detect cancerous nodules are complex and timeconsuming; hence, several imaging algorithms are used to detect the malignant status of thyroid nodules timely.

Aim: This research aims to develop computer-aided diagnosis tools for malignant thyroid nodule detection using ultrasound images. This tool will be helpful for doctors and radiologists in the rapid detection of thyroid cancer at its early stages. The individual machine learning models are inferior to medical datasets because the size of medical image datasets is tiny, and there is a vast class imbalance problem. These problems lead to overfitting; hence, accuracy is very poor on the test dataset.

Objective: This research proposes ensemble learning models that achieve higher accuracy than individual models. The objective is to design different ensemble models and then utilize benchmarking techniques to select the best model among all trained models.

Methods: This research investigates four recently developed image transformer and mixer models for thyroid detection. The weighted average ensemble models are introduced, and model weights are optimized using the hunger games search (HGS) optimization algorithm. The recently developed distance correlation CRITIC (D-CRITIC) based TOPSIS method is utilized to rank the models.

Results: Based on the TOPSIS score, the best model for an 80:20 split is the gMLP + ViT model, which achieved an accuracy of 89.70%, whereas using a 70:30 data split, the gMLP + FNet + Mixer-MLP has achieved the highest accuracy of 82.18% on the publicly available thyroid dataset.

Conclusion: This study shows that the proposed ensemble models have better thyroid detection capabilities than individual base models for the imbalanced thyroid ultrasound dataset.

[1]
Sharifi Y, Bakhshali MA, Dehghani T, DanaiAshgzari M, Sargolzaei M, Eslami S. Deep learning on ultrasound images of thyroid nodules. Biocybern Biomed Eng 2021; 41(2): 636-55.
[http://dx.doi.org/10.1016/j.bbe.2021.02.008]
[2]
Ha EJ, Baek JH. Applications of machine learning and deep learning to thyroid imaging: where do we stand? Ultrasonography 2021; 40(1): 23-9.
[http://dx.doi.org/10.14366/usg.20068] [PMID: 32660203]
[3]
Mohammed M, Mwambi H, Mboya IB, Elbashir MK, Omolo B. A stacking ensemble deep learning approach to cancer type classification based on TCGA data. Sci Rep 2021; 11(1): 15626.
[http://dx.doi.org/10.1038/s41598-021-95128-x] [PMID: 34341396]
[4]
Yang Q, Gong Y. Construction of the classification model using key genes identified between benign and malignant thyroid nodules from comprehensive transcriptomic data. Front Genet 2022; 12: 791349.
[http://dx.doi.org/10.3389/fgene.2021.791349] [PMID: 35096008]
[5]
Wang Y, Guan Q, Lao I, et al. Using deep convolutional neural networks for multi-classification of thyroid tumor by histopathology: A large-scale pilot study. Ann Transl Med 2019; 7(18): 468.
[http://dx.doi.org/10.21037/atm.2019.08.54] [PMID: 31700904]
[6]
Böhland M, Tharun L, Scherr T, et al. Machine learning methods for automated classification of tumors with papillary thyroid carcinoma-like nuclei: A quantitative analysis. PLoS One 2021; 16(9): e0257635.
[http://dx.doi.org/10.1371/journal.pone.0257635] [PMID: 34550999]
[7]
Yang P, Pi Y, He T, et al. Automatic differentiation of thyroid scintigram by deep convolutional neural network: A dual center study. BMC Med Imaging 2021; 21(1): 179.
[http://dx.doi.org/10.1186/s12880-021-00710-4] [PMID: 34823482]
[8]
Xu P, Du Z, Sun L, Zhang Y, Zhang J, Qiu Q. Diagnostic value of contrast-enhanced ultrasound image features under deep learning in benign and malignant thyroid lesions. Sci Program 2022; 2022: 1-10.
[http://dx.doi.org/10.1155/2022/6786966]
[9]
Zhao X, Shen X, Wan W, et al. Automatic thyroid ultrasound image classification using feature fusion network. IEEE Access 2022; 10: 27917-24.
[http://dx.doi.org/10.1109/ACCESS.2022.3156096]
[10]
Chi J, Walia E, Babyn P, Wang J, Groot G, Eramian M. Thyroid nodule classification in ultrasound images by fine-tuning deep convolutional neural network. J Digit Imaging 2017; 30(4): 477-86.
[http://dx.doi.org/10.1007/s10278-017-9997-y] [PMID: 28695342]
[11]
Sai Sundar KV, Rajamani KT, Siva SSS. Exploring image classification of thyroid ultrasound images using deep learning. International Conference on ISMAC in Computational Vision and Bio-Engineering. 1635-41.
[http://dx.doi.org/10.1007/978-3-030-00665-5_151]
[12]
Nguyen DT, Pham TD, Batchuluun G, Yoon HS, Park KR. Artificial intelligence-based thyroid nodule classification using information from spatial and frequency domains. J Clin Med 2019; 8(11): 1976.
[http://dx.doi.org/10.3390/jcm8111976] [PMID: 31739517]
[13]
Nguyen DT, Kang JK, Pham TD, Batchuluun G, Park KR. Ultrasound image-based diagnosis of malignant thyroid nodule using artificial intelligence. Sensors 2020; 20(7): 1822.
[http://dx.doi.org/10.3390/s20071822] [PMID: 32218230]
[14]
Zhang S, He F. DRCDN: Learning deep residual convolutional dehazing networks. Vis Comput 2020; 36(9): 1797-808.
[http://dx.doi.org/10.1007/s00371-019-01774-8]
[15]
Dosovitskiy A, Beyer L, Kolesnikov A, et al. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:201011929 2020.
[16]
Wu J, Hu R, Xiao Z, Chen J, Liu J. Vision Transformer‐based recognition of diabetic retinopathy grade. Med Phys 2021; 48(12): 7850-63.
[http://dx.doi.org/10.1002/mp.15312] [PMID: 34693536]
[17]
Tanzi L, Audisio A, Cirrincione G, Aprato A, Vezzetti E. Vision transformer for femur fracture classification. Injury 2022; 53(7): 2625-34.
[http://dx.doi.org/10.1016/j.injury.2022.04.013] [PMID: 35469638]
[18]
Wu Y, Qi S, Sun Y, Xia S, Yao Y, Qian W. A vision transformer for emphysema classification using CT images. Phys Med Biol 2021; 66(24): 245016.
[http://dx.doi.org/10.1088/1361-6560/ac3dc8] [PMID: 34826824]
[19]
Aladhadh S, Alsanea M, Aloraini M, Khan T, Habib S, Islam M. An effective skin cancer classification mechanism via medical vision transformer. Sensors 2022; 22(11): 4008.
[http://dx.doi.org/10.3390/s22114008] [PMID: 35684627]
[20]
Jiang Z, Wang L, Wu Q, et al. Computer-aided diagnosis of retinopathy based on vision transformer. J Innov Opt Health Sci 2022; 15(2): 2250009.
[http://dx.doi.org/10.1142/S1793545822500092]
[21]
Tolstikhin IO, Houlsby N, Kolesnikov A, et al. Mlp-mixer: An all-mlp architecture for vision. Adv Neural Inf Process Syst 2021; 34: 24261-72.
[22]
Liu H, Dai Z, So D, Le QV. Pay attention to mlps. Adv Neural Inf Process Syst 2021; 34: 9204-15.
[23]
Lee-Thorp J, Ainslie J, Eckstein I, Ontanon S. Fnet: Mixing tokens with fourier transforms. arXiv preprint arXiv:210503824 2021.
[24]
Yan J, Wang X, Cai J, et al. Medical image segmentation model based on triple gate MultiLayer perceptron. Sci Rep 2022; 12(1): 6103.
[http://dx.doi.org/10.1038/s41598-022-09452-x] [PMID: 35413958]
[25]
Pintelas P, Livieris IE. Special issue on ensemble learning and applications. Algorithms 2020; 13(6): 140.
[http://dx.doi.org/10.3390/a13060140]
[26]
AlDahoul N, Abdul KH, Joshua TTM, Momo MA, Ledesma FJ. Encoding retina image to words using ensemble of vision transformers for diabetic retinopathy grading. F1000 Res 2021; 10(948): 948.
[http://dx.doi.org/10.12688/f1000research.73082.1]
[27]
Rajaraman S, Zamzmi G, Folio LR, Antani S. Detecting tuberculosis-consistent findings in lateral chest x-rays using an ensemble of CNNs and vision transformers. Front Genet 2022; 13: 864724.
[http://dx.doi.org/10.3389/fgene.2022.864724] [PMID: 35281798]
[28]
Luo J, He F, Gao X. An enhanced grey wolf optimizer with fusion strategies for identifying the parameters of photovoltaic models. Integr Comput Aided Eng 2022; 30(1): 89-104.
[http://dx.doi.org/10.3233/ICA-220693]
[29]
Chen Y, He F, Li H, Zhang D, Wu Y. A full migration BBO algorithm with enhanced population quality bounds for multimodal biomedical image registration. Appl Soft Comput 2020; 93: 106335.
[http://dx.doi.org/10.1016/j.asoc.2020.106335]
[30]
Ma BJ, Liu S, Heidari AA. Multi-strategy ensemble binary hunger games search for feature selection. Knowl Base Syst 2022; 248: 108787.
[http://dx.doi.org/10.1016/j.knosys.2022.108787]
[31]
Mehta P, Yildiz BS, Sait SM, Yildiz AR. Hunger games search algorithm for global optimization of engineering design problems. Materialprüfung 2022; 64(4): 524-32.
[http://dx.doi.org/10.1515/mt-2022-0013]
[32]
Wang X, Chang D, Shi T, Fan G, Zhang B. Diagnosis from CT scan images in complex biological media using deep learning and wave application: A Hunger Games search-based approach. Waves Random Complex Media 2021; 1-25.
[http://dx.doi.org/10.1080/17455030.2021.1998729]
[33]
Chowdhury NK, Kabir MA, Rahman MM, Islam SMS. Machine learning for detecting COVID-19 from cough sounds: An ensemble-based MCDM method. Comput Biol Med 2022; 145: 105405.
[http://dx.doi.org/10.1016/j.compbiomed.2022.105405] [PMID: 35318171]
[34]
Mohammed MA, Abdulkareem KH, Al-Waisy AS, et al. Benchmarking methodology for selection of optimal COVID-19 diagnostic model based on entropy and TOPSIS methods. IEEE Access 2020; 8: 99115-31.
[http://dx.doi.org/10.1109/ACCESS.2020.2995597]
[35]
Tripathy J, Dash R, Pattanayak BK, Mishra SK, Mishra TK, Puthal D. Combination of reduction detection using TOPSIS for gene expression data analysis. Big Data Cogn Comput 2022; 6(1): 24.
[http://dx.doi.org/10.3390/bdcc6010024]
[36]
Krishnan AR, Kasim MM, Hamid R, Ghazali MF. A modified CRITIC method to estimate the objective weights of decision criteria. Symmetry 2021; 13(6): 973.
[http://dx.doi.org/10.3390/sym13060973]
[37]
Nam-Goong IS, Kim HY, Gong G, et al. Ultrasonography-guided fine-needle aspiration of thyroid incidentaloma: Correlation with pathological findings. Clin Endocrinol 2004; 60(1): 21-8.
[http://dx.doi.org/10.1046/j.1365-2265.2003.01912.x] [PMID: 14678283]
[38]
Haugen BR, Alexander EK, Bible KC, et al. 2015 american thyroid association management guidelines for adult patients with thyroid nodules and differentiated thyroid cancer: The American Thyroid Association guidelines task force on thyroid nodules and differentiated thyroid cancer. Thyroid 2016; 26(1): 1-133.
[http://dx.doi.org/10.1089/thy.2015.0020] [PMID: 26462967]
[39]
Pedraza L, Vargas C, Narváez F, Durán O, Muñoz E, Romero E. An open access thyroid ultrasound image database. 10th International Symposium on Medical Information Processing and Analysis.
[http://dx.doi.org/10.1117/12.2073532]
[40]
Zhu Y, Fu Z, Fei J. An image augmentation method using convolutional network for thyroid nodule classification by transfer learning. 2017 3rd IEEE International Conference on Computer and Communications (ICCC).
[http://dx.doi.org/10.1109/CompComm.2017.8322853]
[41]
Lee SH, Lee S, Song BC. Vision transformer for small-size datasets. arXiv preprint arXiv:211213492 2021.
[42]
Touvron H, Cord M, Douze M, Massa F, Sablayrolles A, Jégou H. Training data-efficient image transformers & distillation through attention. Computer Vision and Pattern Recognition (csCV). Arxic:2012. 12877.
[http://dx.doi.org/10.48550/arXiv.2012.12877]
[43]
Yang Y, Chen H, Heidari AA, Gandomi AH. Hunger games search: Visions, conception, implementation, deep analysis, perspectives, and towards performance shifts. Expert Syst Appl 2021; 177: 114864.
[http://dx.doi.org/10.1016/j.eswa.2021.114864]

Rights & Permissions Print Cite
© 2024 Bentham Science Publishers | Privacy Policy