Differentiation of Benign and Malignant Parotid Gland Tumors Based on the Fusion of Radiomics and Deep Learning Features on Ultrasound Images

Overview

Journal Front Oncol

Specialty Oncology

Date 2024 May 28

PMID 38803533

Authors

Yi Wang

Jiening Gao

Zhaolin Yin

Yue Wen

Meng Sun

Ruoling Han

Affiliations

Soon will be listed here.

Abstract

Objective: The pathological classification and imaging manifestation of parotid gland tumors are complex, while accurate preoperative identification plays a crucial role in clinical management and prognosis assessment. This study aims to construct and compare the performance of clinical models, traditional radiomics models, deep learning (DL) models, and deep learning radiomics (DLR) models based on ultrasound (US) images in differentiating between benign parotid gland tumors (BPGTs) and malignant parotid gland tumors (MPGTs).

Methods: Retrospective analysis was conducted on 526 patients with confirmed PGTs after surgery, who were randomly divided into a training set and a testing set in the ratio of 7:3. Traditional radiomics and three DL models (DenseNet121, VGG19, ResNet50) were employed to extract handcrafted radiomics (HCR) features and DL features followed by feature fusion. Seven machine learning classifiers including logistic regression (LR), support vector machine (SVM), RandomForest, ExtraTrees, XGBoost, LightGBM and multi-layer perceptron (MLP) were combined to construct predictive models. The most optimal model was integrated with clinical and US features to develop a nomogram. Receiver operating characteristic (ROC) curve was employed for assessing performance of various models while the clinical utility was assessed by decision curve analysis (DCA).

Results: The DLR model based on ExtraTrees demonstrated superior performance with AUC values of 0.943 (95% CI: 0.918-0.969) and 0.916 (95% CI: 0.861-0.971) for the training and testing set, respectively. The combined model DLR nomogram (DLRN) further enhanced the performance, resulting in AUC values of 0.960 (95% CI: 0.940- 0.979) and 0.934 (95% CI: 0.876-0.991) for the training and testing sets, respectively. DCA analysis indicated that DLRN provided greater clinical benefits compared to other models.

Conclusion: DLRN based on US images shows exceptional performance in distinguishing BPGTs and MPGTs, providing more reliable information for personalized diagnosis and treatment plans in clinical practice.

Citing Articles

Deep learning radiomics model based on contrast-enhanced MRI for distinguishing between tuberculous spondylitis and pyogenic spondylitis.

Yang X, Tian N, Zhang Y, Gao C, Hao D, Li J Eur Spine J. 2025; .

PMID: 39920318 DOI: 10.1007/s00586-025-08696-1.

Development of metastasis and survival prediction model of luminal and non-luminal breast cancer with weakly supervised learning based on pathomics.

Liu H, Ying L, Song X, Xiang X, Wei S PeerJ. 2025; 13:e18780.

PMID: 39866573 PMC: 11759606. DOI: 10.7717/peerj.18780.

References

Colella G, Cannavale R, Flamminio F, Foschini M . Fine-needle aspiration cytology of salivary gland lesions: a systematic review. J Oral Maxillofac Surg. 2010; 68(9):2146-53. DOI: 10.1016/j.joms.2009.09.064. View

Park Y, Kang M, Kim D, Koh Y, Kim S, Lim J . Surgical extent and role of adjuvant radiotherapy of surgically resectable, low-grade parotid cancer. Oral Oncol. 2020; 107:104780. DOI: 10.1016/j.oraloncology.2020.104780. View

Martiello Mastelini S, Nakano F, Vens C, de Carvalho A . Online Extra Trees Regressor. IEEE Trans Neural Netw Learn Syst. 2022; 34(10):6755-6767. DOI: 10.1109/TNNLS.2022.3212859. View

Quer M, Vander Poorten V, Takes R, Silver C, Boedeker C, de Bree R . Surgical options in benign parotid tumors: a proposal for classification. Eur Arch Otorhinolaryngol. 2017; 274(11):3825-3836. DOI: 10.1007/s00405-017-4650-4. View

Whitney H, Li H, Ji Y, Liu P, Giger M . Comparison of Breast MRI Tumor Classification Using Human-Engineered Radiomics, Transfer Learning From Deep Convolutional Neural Networks, and Fusion Methods. Proc IEEE Inst Electr Electron Eng. 2021; 108(1):163-177. PMC: 8152568. DOI: 10.1109/jproc.2019.2950187. View

Li Q, Jiang T, Zhang C, Zhang Y, Huang Z, Zhou H . A nomogram based on clinical information, conventional ultrasound and radiomics improves prediction of malignant parotid gland lesions. Cancer Lett. 2021; 527:107-114. DOI: 10.1016/j.canlet.2021.12.015. View

Schmidt R, Hall B, Wilson A, Layfield L . A systematic review and meta-analysis of the diagnostic accuracy of fine-needle aspiration cytology for parotid gland lesions. Am J Clin Pathol. 2011; 136(1):45-59. DOI: 10.1309/AJCPOIE0CZNAT6SQ. View

Zheng Y, Xu W, Hao D, Liu X, Gao C, Tang G . A CT-based radiomics nomogram for differentiation of lympho-associated benign and malignant lesions of the parotid gland. Eur Radiol. 2020; 31(5):2886-2895. DOI: 10.1007/s00330-020-07421-4. View

Vanguri R, Luo J, Aukerman A, Egger J, Fong C, Horvat N . Multimodal integration of radiology, pathology and genomics for prediction of response to PD-(L)1 blockade in patients with non-small cell lung cancer. Nat Cancer. 2022; 3(10):1151-1164. PMC: 9586871. DOI: 10.1038/s43018-022-00416-8. View

10.

He Q, Feng J, Lv F, Jiang Q, Xiao M . Deep learning and radiomic feature-based blending ensemble classifier for malignancy risk prediction in cystic renal lesions. Insights Imaging. 2023; 14(1):6. PMC: 9834471. DOI: 10.1186/s13244-022-01349-7. View

11.

Zhang L, Wang R, Gao J, Tang Y, Xu X, Kan Y . A novel MRI-based deep learning networks combined with attention mechanism for predicting CDKN2A/B homozygous deletion status in IDH-mutant astrocytoma. Eur Radiol. 2023; 34(1):391-399. DOI: 10.1007/s00330-023-09944-y. View

12.

Qi J, Gao A, Ma X, Song Y, Zhao G, Bai J . Differentiation of Benign From Malignant Parotid Gland Tumors Using Conventional MRI Based on Radiomics Nomogram. Front Oncol. 2022; 12:937050. PMC: 9309371. DOI: 10.3389/fonc.2022.937050. View

13.

Zuo H . The Clinical Characteristics and CT Findings of Parotid and Submandibular Gland Tumours. J Oncol. 2021; 2021:8874100. PMC: 8272666. DOI: 10.1155/2021/8874100. View

14.

Gao M, Hao Y, Huang M, Ma D, Chen Y, Luo H . Salivary gland tumours in a northern Chinese population: a 50-year retrospective study of 7190 cases. Int J Oral Maxillofac Surg. 2016; 46(3):343-349. DOI: 10.1016/j.ijom.2016.09.021. View

15.

Jiang M, Li C, Luo X, Chuan Z, Chen R, Tang S . Radiomics model based on shear-wave elastography in the assessment of axillary lymph node status in early-stage breast cancer. Eur Radiol. 2021; 32(4):2313-2325. DOI: 10.1007/s00330-021-08330-w. View

16.

Sheikh K, Lee S, Cheng Z, Lakshminarayanan P, Peng L, Han P . Predicting acute radiation induced xerostomia in head and neck Cancer using MR and CT Radiomics of parotid and submandibular glands. Radiat Oncol. 2019; 14(1):131. PMC: 6664784. DOI: 10.1186/s13014-019-1339-4. View

17.

Yu Q, Ning Y, Wang A, Li S, Gu J, Li Q . Deep learning-assisted diagnosis of benign and malignant parotid tumors based on contrast-enhanced CT: a multicenter study. Eur Radiol. 2023; 33(9):6054-6065. DOI: 10.1007/s00330-023-09568-2. View

18.

Itani M, Assaker R, Moshiri M, Dubinsky T, Dighe M . Inter-observer Variability in the American College of Radiology Thyroid Imaging Reporting and Data System: In-Depth Analysis and Areas for Improvement. Ultrasound Med Biol. 2018; 45(2):461-470. DOI: 10.1016/j.ultrasmedbio.2018.09.026. View

19.

Lu Y, Liu H, Liu Q, Wang S, Zhu Z, Qiu J . CT-based radiomics with various classifiers for histological differentiation of parotid gland tumors. Front Oncol. 2023; 13:1118351. PMC: 10036756. DOI: 10.3389/fonc.2023.1118351. View

20.

van Herpen C, Vander Poorten V, Skalova A, Terhaard C, Maroldi R, van Engen A . Salivary gland cancer: ESMO-European Reference Network on Rare Adult Solid Cancers (EURACAN) Clinical Practice Guideline for diagnosis, treatment and follow-up. ESMO Open. 2022; 7(6):100602. PMC: 9808465. DOI: 10.1016/j.esmoop.2022.100602. View