Magnetic Resonance Imaging-Based Differential Diagnosis of Parotid Gland Tumors Using Deep Learning

Esat Kaba; Kubilay Muhammed Sünnetci; Ahmet Alkan; Fatma Beyazal Celiker

doi:10.58600/eurjther2612

Authors

Esat Kaba Department of Radiology, Recep Tayyip Erdogan University, Rize,Türkiye https://orcid.org/0000-0001-7464-988X
Kubilay Muhammed Sünnetci Department of Electrical and Electronics Engineering, Osmaniye Korkut Ata University, Osmaniye,Türkiye 3 Department of Electrical and Electronics Engineering, Kahramanmaraş Sütçü İmam University, Kahramanmaraş,Türkiye https://orcid.org/0000-0002-3500-5640
Ahmet Alkan Department of Electrical and Electronics Engineering, Kahramanmaraş Sütçü İmam University, Kahramanmaraş,Türkiye https://orcid.org/0000-0003-0857-0764
Fatma Beyazal Celiker Department of Radiology, Recep Tayyip Erdogan University, Rize,Türkiye https://orcid.org/0000-0002-5420-9825

DOI:

https://doi.org/10.58600/eurjther2612

Keywords:

classification, deep learning, magnetic resonance imaging, Parotid Gland Tumors

Abstract

Objectives: It is aimed at magnetic resonance imaging (MRI)-based differential diagnosis of parotid gland tumors (PGTs) using deep learning.

Methods: This study included 117 PGTs obtained from 113 patients. T2-w, T1-w, contrast-enhanced T1-w, Diffusion Weighted Imaging-b0, Diffusion Weighted Imaging-b2000 (DWI-2000), and apparent diffusion coefficient sequences of these patients were used in the study. We implemented four different classification models, and we categorized the images as benign-malignant, pleomorphic adenoma (PA)-Warthin, Warthin-malignant, and all classes (mucoepidermoid carcinoma-other benign-other malignant-PA-Warthin). We constructed classification for each sequence separately using the ResNet18 architecture, with the dataset split into 80% for training and 20% for validation.

Results: The most successful model in this study, achieving an accuracy of 95.37% and an F1-score of 94.74% in classifying malignant-Warthin images in T1-w sequences, also demonstrated the highest accuracy among all models evaluated. For the classification of benign-malignant and the differentiation across All classes, the highest accuracies were achieved with the T2 sequence at 93.75% and 86.67%, respectively. In the differentiation of PA-Warthin, T1-weighted and DWI-b0 sequences demonstrated the highest performance, both with an accuracy of 90.36%.

Conclusion: The deep networks proposed in the study supported MRI-based differential diagnosis of PGTs with high accuracy, and the user-friendly software classified images with high accuracy in about 10 seconds.

Metrics

Metrics Loading ...

References

Coudert H, Mirafzal S, Dissard A, Boyer L, Montoriol PF (2021) Multiparametric magnetic resonance imaging of parotid tumors: A systematic review. Diagn Interv Imaging. 102(3):121-130. https://doi.org/10.1016/j.diii.2020.08.002

de Oliveira FA, Duarte EC, Taveira CT, Máximo AA, de Aquino EC, Alencar RdeC, Vencio EF (2009) Salivary gland tumor: a review of 599 cases in a Brazilian population. Head Neck Pathol. 3(4):271-275. https://doi.org/10.1007/s12105-009-0139-9

Guzzo M, Locati LD, Prott FJ, Gatta G, McGurk M, Licitra L (2010) Major and minor salivary gland tumors. Crit Rev Oncol Hematol. 74(2):134-148. https://doi.org/10.1016/j.critrevonc.2009.10.004

Piludu F, Marzi S, Ravanelli M, Pellini R, Covello R, Terrenato I, Farina D, Campora R, Ferrazzoli V, Vidiri A (2021) MRI-Based Radiomics to Differentiate between Benign and Malignant Parotid Tumors With External Validation. Front Oncol. 11:656918. https://doi.org/10.3389/fonc.2021.656918

Cantisani V, David E, Sidhu PS, Sacconi B, Greco A, Pandolfi F, Tombolini M, Lo Mele L, Calliada F, Brunese L, Catalano C, De Vincentiis M, Di Leo N, Ascenti G, D'Ambrosio F (2016) Parotid Gland Lesions: Multiparametric Ultrasound and MRI Features. Ultraschall Med. 37(5):454-471. https://doi.org/10.1055/s-0042-109171

Kim SY, Borner U, Lee JH, Wagner F, Tshering Vogel DW (2022) Magnetic resonance imaging of parotid gland tumors: a pictorial essay. BMC Med Imaging. 22(1):191. https://doi.org/10.1186/s12880-022-00924-0

Thoeny HC (2007) Imaging of salivary gland tumours. Cancer Imaging. 7(1):52-62. https://doi.org/10.1102/1470-7330.2007.0008

Christe A, Waldherr C, Hallett R, Zbaeren P, Thoeny H (2011) MR imaging of parotid tumors: typical lesion characteristics in MR imaging improve discrimination between benign and malignant disease. AJNR Am J Neuroradiol. 32(7):1202-1207. https://doi.org/10.3174/ajnr.A2520

Liang YY, Xu F, Guo Y, Wang J (2018) Diagnostic accuracy of magnetic resonance imaging techniques for parotid tumors, a systematic review and meta-analysis. Clin Imaging. 52:36-43. https://doi.org/10.1016/j.clinimag.2018.05.026

Xu Z, Chen M, Zheng S, Chen S, Xiao J, Hu Z, Lu L, Yang Z, Lin D (2022) Differential diagnosis of parotid gland tumours: Application of SWI combined with DWI and DCE-MRI. Eur J Radiol. 146:110094. https://doi.org/10.1016/j.ejrad.2021.110094

Xia X, Feng B, Wang J, Hua Q, Yang Y, Sheng L, Mou Y, Hu W (2021) Deep learning for differentiating benign from malignant parotid lesions on MR images. Front Oncol. 11:632104. https://doi.org/10.3389/fonc.2021.632104

Gunduz E, Alçin OF, Kizilay A, Yildirim IO (2022) Deep learning model developed by multiparametric MRI in differential diagnosis of parotid gland tumors. Eur Arch Otorhinolaryngol. 279(11):5389-5399. https://doi.org/10.1007/s00405-022-07455-y

Chlap P, Min H, Vandenberg N, Dowling J, Holloway L, Haworth A (2021) A review of medical image data augmentation techniques for deep learning applications. J Med Imaging Radiat Oncol. 65(5):545-563. https://doi.org/10.1111/1754-9485.13261

“Resnet18 @ Www.Mathworks.Com.” [Online]. Available: https://www.mathworks.com/help/deeplearning/ref/resnet18.html

Xiang H, Zou Q, Nawaz MA, Huang X, Zhang F, Yu H (2023) Deep learning for image inpainting: A survey. Pattern Recognit. 134:109046. https://doi.org/10.1016/j.patcog.2022.109046

Guher AB, Tasdemir S, Yaniktepe B (2020) Effective estimation of hourly global solar radiation using machine learning algorithms. Int J Photoenergy. 2020:8843620. https://doi.org/10.1155/2020/8843620

Chang YJ, Huang TY, Liu YJ, Chung HW, Juan CJ (2021) Classification of parotid gland tumors by using multimodal MRI and deep learning. NMR Biomed. 34(1):e4408. https://doi.org/10.1002/nbm.4408

Liu X, Pan Y, Zhang X, Sha Y, Wang S, Li H, Liu J (2023) A deep learning model for classification of parotid neoplasms based on multimodal magnetic resonance image sequences. Laryngoscope. 133(2):327-335. https://doi.org/10.1002/lary.30154

Matsuo H, Nishio M, Kanda T, Kojita Y, Kono AK, Hori M, Teshima M, Otsuki N, Nibu KI, Murakami T (2020) Diagnostic accuracy of deep-learning with anomaly detection for a small amount of imbalanced data: discriminating malignant parotid tumors in MRI. Sci Rep. 10(1):19388. https://doi.org/10.1038/s41598-020-76389-4

Shen XM, Mao L, Yang ZY, Chai ZK, Sun TG, Xu Y, Sun ZJ (2023) Deep learning-assisted diagnosis of parotid gland tumors by using contrast-enhanced CT imaging. Oral Dis. 29(8):3325-3336. https://doi.org/10.1111/odi.14474

Zhang G, Zhu L, Huang R, Xu Y, Lu X, Chen Y, Li C, Lei Y, Luo X, Li Z, Yi S, He J, Zheng C (2023) A deep learning model for the differential diagnosis of benign and malignant salivary gland tumors based on ultrasound imaging and clinical data. Quant Imaging Med Surg. 13(5):2989-3000. https://doi.org/10.21037/qims-22-950

Sunnetci KM, Kaba E, Celiker FB, Alkan A (2024) MR Image Fusion-Based Parotid Gland Tumor Detection. J Imaging Inform Med. https://doi.org/10.1007/s10278-024-01137-3

Sunnetci KM, Kaba E, Beyazal Çeliker F, Alkan A (2023) Comparative parotid gland segmentation by using ResNet-18 and MobileNetV2-based DeepLab v3+ architectures from magnetic resonance images. Concurr Comput Pract Exp. 35(1):1-14. https://doi.org/10.1002/cpe.7405

Sunnetci KM, Kaba E, Celiker FB, Alkan A (2024) Deep Network-Based Comprehensive Parotid Gland Tumor Detection. Acad Radiol. 31(1):157-167. https://doi.org/10.1016/j.acra.2023.04.028