Literature DB >> 35748897

Machine learning-based radiomics for histological classification of parotid tumors using morphological MRI: a comparative study.

Zhiying He1,2,3, Yitao Mao4, Shanhong Lu1,2,3, Lei Tan5, Juxiong Xiao4, Pingqing Tan6, Hailin Zhang6, Guo Li1,2,3, Helei Yan1,2,3, Jiaqi Tan1,2,3, Donghai Huang1,2,3, Yuanzheng Qiu1,2,3, Xin Zhang1,2,3,4, Xingwei Wang7,8,9, Yong Liu10,11,12,13.   

Abstract

OBJECTIVES: To evaluate the effectiveness of machine learning models based on morphological magnetic resonance imaging (MRI) radiomics in the classification of parotid tumors.
METHODS: In total, 298 patients with parotid tumors were randomly assigned to a training and test set at a ratio of 7:3. Radiomics features were extracted from the morphological MRI images and screened using the Select K Best and LASSO algorithm. Three-step machine learning models with XGBoost, SVM, and DT algorithms were developed to classify the parotid neoplasms into four subtypes. The ROC curve was used to measure the performance in each step. Diagnostic confusion matrices of these models were calculated for the test cohort and compared with those of the radiologists.
RESULTS: Six, twelve, and eight optimal features were selected in each step of the three-step process, respectively. XGBoost produced the highest area under the curve (AUC) for all three steps in the training cohort (0.857, 0.882, and 0.908, respectively), and for the first step in the test cohort (0.826), but produced slightly lower AUCs than SVM in the latter two steps in the test cohort (0.817 vs. 0.833, and 0.789 vs. 0.821, respectively). The total accuracies of XGBoost and SVM in the confusion matrices (70.8% and 59.6%) outperformed those of DT and the radiologist (46.1% and 49.2%).
CONCLUSION: This study demonstrated that machine learning models based on morphological MRI radiomics might be an assistive tool for parotid tumor classification, especially for preliminary screening in absence of more advanced scanning sequences, such as DWI. KEY POINTS: • Machine learning algorithms combined with morphological MRI radiomics could be useful in the preliminary classification of parotid tumors. • XGBoost algorithm performed better than SVM and DT in subtype differentiation of parotid tumors, while DT seemed to have a poor validation performance. • Using morphological MRI only, the XGBoost and SVM algorithms outperformed radiologists in the four-type classification task for parotid tumors, thus making these models a useful assistant diagnostic tool in clinical practice.
© 2022. The Author(s), under exclusive licence to European Society of Radiology.

Entities:  

Keywords:  Algorithms; Diagnosis; Machine learning; Magnetic resonance imaging; Parotid tumor

Year:  2022        PMID: 35748897     DOI: 10.1007/s00330-022-08943-9

Source DB:  PubMed          Journal:  Eur Radiol        ISSN: 0938-7994            Impact factor:   5.315


  46 in total

1.  Fine-needle aspiration cytology: a reliable tool in the diagnosis of salivary gland lesions.

Authors:  Kanwar Deep Singh Nanda; Anurag Mehta; Jasmine Nanda
Journal:  J Oral Pathol Med       Date:  2011-08-29       Impact factor: 4.253

Review 2.  Pictorial review: MR imaging of parotid tumours.

Authors:  R Soler; A Bargiela; I Requejo; E Rodríguez; J L Rey; F Sancristan
Journal:  Clin Radiol       Date:  1997-04       Impact factor: 2.350

3.  Salivary neoplasms: overview of a 35-year experience with 2,807 patients.

Authors:  R H Spiro
Journal:  Head Neck Surg       Date:  1986 Jan-Feb

Review 4.  Sensitivity, Specificity, and Posttest Probability of Parotid Fine-Needle Aspiration: A Systematic Review and Meta-analysis.

Authors:  C Carrie Liu; Ashok R Jethwa; Samir S Khariwala; Jonas Johnson; Jennifer J Shin
Journal:  Otolaryngol Head Neck Surg       Date:  2015-10-01       Impact factor: 3.497

Review 5.  Radiomics: extracting more information from medical images using advanced feature analysis.

Authors:  Philippe Lambin; Emmanuel Rios-Velazquez; Ralph Leijenaar; Sara Carvalho; Ruud G P M van Stiphout; Patrick Granton; Catharina M L Zegers; Robert Gillies; Ronald Boellard; André Dekker; Hugo J W L Aerts
Journal:  Eur J Cancer       Date:  2012-01-16       Impact factor: 9.162

6.  Preoperative diagnostic values of fine-needle cytology and MRI in parotid gland tumors.

Authors:  J Paris; F Facon; T Pascal; M A Chrestian; G Moulin; M Zanaret
Journal:  Eur Arch Otorhinolaryngol       Date:  2004-01-15       Impact factor: 2.503

Review 7.  Major and minor salivary gland tumours.

Authors:  Gemma Gatta; Marco Guzzo; Laura D Locati; Mark McGurk; Franz Josef Prott
Journal:  Crit Rev Oncol Hematol       Date:  2020-05-18       Impact factor: 6.312

Review 8.  Diagnosis and Management of Malignant Salivary Gland Tumors of the Parotid Gland.

Authors:  Aaron G Lewis; Tommy Tong; Ellie Maghami
Journal:  Otolaryngol Clin North Am       Date:  2016-04       Impact factor: 3.346

9.  Radiomics: Images Are More than Pictures, They Are Data.

Authors:  Robert J Gillies; Paul E Kinahan; Hedvig Hricak
Journal:  Radiology       Date:  2015-11-18       Impact factor: 11.105

Review 10.  Cross-sectional imaging and cytologic investigations in the preoperative diagnosis of parotid gland tumors - An updated literature review.

Authors:  Sebastian Stoia; Grigore Băciuț; Manuela Lenghel; Radu Badea; Csaba Csutak; Georgeta Mihaela Rusu; Mihaela Băciuț; Tiberiu Tamaș; Emil Boțan; Gabriel Armencea; Simion Bran; Cristian Dinu
Journal:  Bosn J Basic Med Sci       Date:  2021-02-01       Impact factor: 3.363

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.