A Novel Deep-Learning-Based CADx Architecture for Classification of Thyroid Nodules Using Ultrasound Images

Sree SV, Ph D, Molinari F, Ph D, Gupta S, Ph D, Bardales RH, Witkowska A, Aimbe F (2014) A review on ultrasound-based thyroid cancer tissue characterization and automated classification. Technol Cancer Res Treat 13(4):289–301. https://doi.org/10.7785/tcrt.2012.500381 Galbraith JD, Swann N, Cox B, Letendre N, Recabaren J (2018) The bethesda classification for thyroid fine needle aspiration: a predictor or an alarmist? Am Surg 84(1):161–164. https://doi.org/10.1177/000313481808400140 Anand V, Koundal D (2020) Computer-assisted diagnosis of thyroid cancer using medical ımages: a survey. In: Singh P, Kar A, Singh Y, Kolekar M, Tanwar S (eds) Proceedings of ICRIC 2019. Lecture notes in electrical engineering, vol 597. Springer, Cham. https://doi.org/10.1007/978-3-030-29407-6_39 Tessler FN et al (2017) ACR Thyroid Imaging, Reporting and Data System (TI-RADS): White Paper of the ACR TI-RADS Committee. J Am Coll Radiol 14(5):587–595. https://doi.org/10.1148/37.6.755 Koundal D, Gupta S, Singh S (2012) Applications of neutrosophic and intuitionistic fuzzy set on image processing, İn: National Conference on GreenTechnologies: Smart and Efficient Management (GTSEM-2012). SLIET, Longowal, pp 1–4 Mugasa H, Dua S, Koh JEW, Hagiwara Y, Shu O, Madla C, Kongmebhol P, Hoong K, Acharya UR (2020) An adaptive feature extraction model for classification of thyroid lesions in ultrasound images. Pattern Recogn Lett 131:463–473. https://doi.org/10.1016/j.patrec.2020.02.009 Arirangan S, Kottursamy K (2021) Multi-scaled feature fusion enabled convolutional neural network for predicting fibrous dysplasia bone disorder. Expert Syst. https://doi.org/10.1111/exsy.12882 Saranya A, Kottursamy K, AlZubi AA, Bashir AK (2022) Analyzing fibrous tissue pattern in fibrous dysplasia bone images using deep R-CNN networks for segmentation. Soft Comput 26(16):7519–7533. https://doi.org/10.1007/s00500-021-06519-1 Sollini M, Cozzi L, Chiti A, Kirienko M (2018) Texture analysis and machine learning to characterize suspected thyroid nodules and differentiated thyroid cancer: where do we stand? Eur J Radiol 99(November 2017):1–8. https://doi.org/10.1016/j.ejrad.2017.12.004 Xu L, Gao J, Wang Q, Yin J, Yu P, Bai B, Pei R, Chen D, Yang G, Wang S, Wan M (2020) Computer-aided diagnosis systems in diagnosing malignant thyroid nodules on ultrasonography: a systematic review and meta-analysis. Eur Thyroid J 9(4):186–193. https://doi.org/10.1159/000504390 Chu C, Zheng J, Zhou Y (2021) Computer Methods and Programs in Biomedicine Ultrasonic thyroid nodule detection method based on U-Net network. Comput Methods Programs Biomed 199:105906. https://doi.org/10.1016/j.cmpb.2020.105906 Li H, Weng J, Shi Y, Gu W, Mao Y, Wang Y, Liu W (2018) An improved deep learning approach for detection of thyroid papillary cancer in ultrasound images. Sci Rep. https://doi.org/10.1038/s41598-018-25005-7 Buda M, Tessler FN (2019) Management of thyroid nodules seen on US ımages : deep learning may match performance of radiologists. Radiology. https://doi.org/10.1148/radiol.2019181343 Li X, Zhang S, Zhang Q, Wei X, Pan Y, Zhao J, Xin X, Qin C, Wang X, Li J, Yang F (2019) Articles Diagnosis of thyroid cancer using deep convolutional neural network models applied to sonographic images: a retrospective, multicohort, diagnostic study. Lancet Oncol 20(2):193–201. https://doi.org/10.1016/S1470-2045(18)30762-9 Ma J, Wu F (2017) Cascade convolutional neural networks for automatic detection of thyroid nodules in ultrasound images. Med Phys. https://doi.org/10.1002/mp.12134 Abdolali F, Kapur J, Jaremko JL, Noga M, Hareendranathan AR, Punithakumar K (2020) Automated thyroid nodule detection from ultrasound imaging using deep convolutional neural networks. Comput Biol Med 122(March):103871. https://doi.org/10.1016/j.compbiomed.2020.103871 Koundal D, Sharma S, Guo Y (2020) Intuitionistic based segmentation of thyroid nodules in ultrasound images. Comput Biol Med 121:103776. https://doi.org/10.1016/j.compbiomed.2020.103776 Koundal D, Gupta S, Singh S (2016) Automated delineation of thyroid nodules in ultrasound images usingspatial neutrosophic clustering and level set. Appl Soft Comput 40(2016):86–97. https://doi.org/10.1016/j.asoc.2015.11.035 Li Z, Zhou S, Chang C, Wang Y, Guo Y (2023) A weakly supervised deep active contour model for nodule segmentation in thyroid ultrasound images. Pattern Recogn Lett 165:128–137. https://doi.org/10.1016/j.patrec.2022.12.015 Li G, Chen R, Zhang J, Liu K, Geng C, Lyu L (2023) Fusing enhanced Transformer and large kernel CNN for malignant thyroid nodule segmentation. Biomed Signal Process Control 83:104636. https://doi.org/10.1016/j.bspc.2023.104636 Koundal D, Gupta S, Singh S (2018) Computer aided thyroid nodule detection system using medical ultrasound images. Biomed Signal Process Control 40:117–130. https://doi.org/10.1016/j.bspc.2017.08.025 Sharifi Y, Amin M, Dehghani T (2021) Deep learning on ultrasound images of thyroid nodules. Biobybernetics Biomed Eng 41:636–655. https://doi.org/10.1016/j.bbe.2021.02.008 Acharya UR, Faust O, Sree SV, Molinari F, Suri JS (2011) ThyroScreen system: high resolution ultrasound thyroid image characterization into benign and malignant classes using novel combination of texture and discrete wavelet transform. Comput Methods Programs Biomed 107(2):233–241. https://doi.org/10.1016/j.cmpb.2011.10.001 Pedraza L, Vargas C, Romero E (2015) An open access thyroid ultrasound-image database. https://doi.org/10.1117/12.2073532 Pérez-garcía F, Sparks R, Ourselin S (2021) TorchIO: a Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning. Comput Methods Programs Biomed 208:106236. https://doi.org/10.1016/j.cmpb.2021.106236 Shi G, Wang J, Qiang Y, Yang X, Zhao J, Hao R, Yang W, Du Q, Kazihise NG (2020) Computer Methods and Programs in Biomedicine Knowle dge-guide d synthetic medical image adversarial augmentation for ultrasonography thyroid nodule classification. Comput Methods Programs Biomed 196:105611. https://doi.org/10.1016/j.cmpb.2020.105611 Zhang J, Cheng X, Su B, Wang X, Wang L (2020) The increased risk of thyroid cancer-specific mortality with tumor size in stage IVB patients. Front Oncol 10(November):1–11. https://doi.org/10.3389/fonc.2020.560203 Wang H, Maldonado D, Silwal S (2011) A nonparametric-test-based structural similarity measure for digital images. Comput Stat Data Anal 55(11):2925–2936. https://doi.org/10.1016/j.csda.2011.04.021 Wang J, Chen P, Zheng N, Chen B, Principe JC, Wang F (2021) Neurocomputing Associations between MSE and SSIM as cost functions in linear decomposition with application to bit allocation for sparse coding. Neurocomputing 422:139–149. https://doi.org/10.1016/j.neucom.2020.10.018 Wang Z, Wang C, Wei J, Liu J (2021) Knowledge-based systems multi-class feature selection by exploring reliable class correlation. Knowl Based Syst 230:107377. https://doi.org/10.1016/j.knosys.2021.107377 Horé A (2010) Image quality metrics: PSNR vs. SSIM Image quality metrics: PSNR vs. SSIM. August. https://doi.org/10.1109/ICPR.2010.579 Lo CM, Chang YC, Yang YW, Huang CS, Chang RF (2015) Quantitative breast mass classification based on the integration of B-mode features and strain features in elastography. Comput Biol Med 64:91–100. https://doi.org/10.1016/j.compbiomed.2015.06.013 Moon WK, Lo C, Chang JM (2013) Quantitative ultrasound analysis for classification of BI-RADS category 3 breast masses. J Digit Imaging 26:1091–1098. https://doi.org/10.1007/s10278-013-9593-8 Ji S, Xu W, Yang M, Yu K (2013) 3D convolutional neural networks for human action recognition. IEEE Trans Pattern Anal Mach Intell 35(1):221–231. https://doi.org/10.1109/TPAMI.2012.59 Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. 3rd ınternational conference on learning representations, ICLR 2015—conference track proceedings, pp 1–14. https://arxiv.org/abs/1409.1556. Zhu J, Wang X, Kou L, Zheng L, Zhang H (2021) Applied surface science application of combined transfer learning and convolutional neural networks to optimize plasma spraying. Appl Surf Sci 563(October 2020):150098. https://doi.org/10.1016/j.apsusc.2021.150098 Ashraf R, Habib MA, Akram M, Latif MA, Sheraz M, Malik A, Awais M, Dar SH, Mahmood T, Yasir M, Abbas Z (2020) Deep convolution neural network for big data medical image classification. IEEE Access 8:105659–105670. https://doi.org/10.1109/ACCESS.2020.2998808 Brodzicki A, Jaworek-korjakowska J, Kleczek P (2020) Pre-trained deep convolutional neural network for clostridioides difficile bacteria cytotoxicity classification based on fluorescence ımages. Sensors. https://doi.org/10.3390/s20236713 Anil G, Hegde A, Chong FHV (2011) Thyroid nodules: risk stratification for malignancy with ultrasound and guided biopsy. Cancer Imaging 11:209–223. https://doi.org/10.1102/1470-7330.2011.0030 Pereira R, Zanchetta M, Cesar D (2012) Expert systems with applications texture extraction: an evaluation of ridgelet, wavelet and co-occurrence based methods applied to mammograms. Expert Syst Appl 39(12):11036–11047. https://doi.org/10.1016/j.eswa.2012.03.020 Kim E, Park CS, Oh KK, Kim DI, Lee JT, Yoo HS (2002) New sonographic criteria for recommending fine-needle aspiration biopsy of nonpalpable solid nodules of the thyroid. AJR Am J Roentgenol 178:687–691. https://doi.org/10.2214/ajr.178.3.1780687 Iwanowski M, Skoneczny S (2014) Image features extraction using mathematical morphology. https://doi.org/10.1117/12.279581 Haralick RM, Dinstein I, Shanmugam K (1973) Textural features for ımage classification. IEEE Trans Syst Man Cybern SMC-3(6):610–621. https://doi.org/10.1109/TSMC.1973.4309314 Mall PK, Singh PK, Yadav D (2019) GLCM based feature extraction and medical X-ray ımage classification using machine learning techniques Uzunhisarcıklı E, Goreke V (2018) A novel classifier model for mass classification using BI-RADS category in ultrasound images based on Type-2 fuzzy inference system. Sādhanā 43(9):138. https://doi.org/10.1007/s12046-018-0915-x Göreke V, Sarı V, Kockanat S (2021) A novel classifier architecture based on deep neural network for COVID-19 detection using laboratory findings. Appl Soft Comput J 106:107329. https://doi.org/10.1016/j.asoc.2021.107329 Deng Y, Liu Y, Zhou D (2015) An ımproved genetic algorithm with ınitial population strategy for symmetric TSP. Math Probl Eng 2015:1–6. https://doi.org/10.1155/2015/212794 Chen J, Zhang S, Gao Z, Yang L (2010) Feature-based initial population generation for the optimization of job shop problems. J Zhejiang Univ Sci C 11(10):767–777. https://doi.org/10.1631/jzus.C0910707 Sharma D, Deb K (2011) Domain-specific initial population strategy for compliant mechanisms using customized genetic algorithm. Struct Multidisc Optim 43:541–554. https://doi.org/10.1007/s00158-010-0575-x Mumtaz W, Qayyum A (2019) A deep learning framework for automatic diagnosis of unipolar depression. Int J Med Informatics 132(September):103983. https://doi.org/10.1016/j.ijmedinf.2019.103983 Alakus TB, Turkoglu I (2020) Comparison of deep learning approaches to predict COVID-19 infection. Chaos Solitons Fractals 140:110120. https://doi.org/10.1016/j.chaos.2020.110120 Pierce R (2009) Evaluating information: validity, reliability, accuracy and triangulation. Retrieved March 21, 2017. https://www.sagepub.com/sites/default/files/upm-binaries/17810_5052_Pierce_Ch07.pdf. https://doi.org/10.4135/9780857024589.D12 Ding J, Cheng H, Ning C, Huang J, Zhang Y (2011) Quantitative measurement for thyroid cancer characterization based on elastography. J Ultrasound Med 30(9):1259–1266. https://doi.org/10.7863/jum.2011.30.9.1259 Acharya UR, Sree SV, Krishnan MM, Molinari F, Garberoglio R, Suri JS (2012) Non-invasive automated 3D thyroid lesion classification in ultrasound: a class of ThyroScan™ systems. Ultrasonics 52(4):508–520. https://doi.org/10.1016/j.ultras.2011.11.003 Acharya UR, Sree SV, Swapna G, Gupta S, Molinari F, Garberoglio R, Witkowska A, Suri JS (2013) Effect of complex wavelet transform filter on thyroid tumor classification in three-dimensional ultrasound. Proc Inst Mech Eng [H] 227(3):284–292. https://doi.org/10.1177/0954411912472422 Raghavendra U, Acharya UR, Gudigar A, Tan JH, Fujita H, Hagiwara Y, Molinari F, Kongmebhol P, Ng KH (2017) Fusion of spatial gray level dependency and fractal texture features for the characterization of thyroid lesions. Ultrasonics 77:110–120. https://doi.org/10.1016/j.ultras.2017.02.003 Chi J, Walia E, Babyn P, Wang J, Groot G, Eramian M (2017) Thyroid nodule classification in ultrasound images by fine-tuning deep convolutional neural network. J Digit Imaging 30:477–486. https://doi.org/10.1007/s10278-017-9997-y Seo JK, Kim YJ, Kim KG, Shin I, Shin JH, Kwak JY (2017) Differentiation of the follicular neoplasm on the gray-scale US by image selection subsampling along with the marginal outline using convolutional neural network. BioMed Res Int 2017:3098293. https://doi.org/10.1155/2017/3098293 Song W, Li S, Liu J, Qin H, Zhang B, Zhang S, Hao A (2019) Multitask cascade convolution neural networks for automatic thyroid nodule detection and recognition. IEEE J Biomed Health Inform 23(3):1215–1224. https://doi.org/10.1109/JBHI.2018.2852718 Ying X, Yu Z, Yu R, Li X, Yu M, Zhao M, Liu K (2018) Thyroid nodule segmentation in ultrasound images based on cascaded convolutional neural network. In: Cheng L, Leung A, Ozawa S (eds) Neural information processing. ICONIP 2018. Lecture notes in computer science, vol 11306. Springer, Cham, pp 373–384 Kang Q, Lao Q, Li Y, Jiang Z, Qiu Y, Zhang S, Li K (2022) Thyroid nodule segmentation and classification in ultrasound images through intra- and inter-task consistent learning. Med Image Anal 79:102443. https://doi.org/10.1016/j.media.2022.102443 Zhu Y, Fu Z, Fei J (2017) An image augmentation method using convolutional network for thyroid nodule classification by transfer learning. In: 2017 3rd IEEE international conference on computer and communications (ICCC). https://doi.org/10.1109/CompComm.2017.8322853 Nguyen DT, Kang JK, Pham TD, Batchuluun G, Park KR (2020) Ultrasound image-based diagnosis of malignant thyroid nodule using artificial intelligence. Sensors 20(7):1822. https://doi.org/10.3390/s20071822