Search Our Scientific Publications & Authors

Publications
find publications by category +
Translate page:

Deep learning model developed by multiparametric MRI in differential diagnosis of parotid gland tumors.

Authors:
Emrah Gunduz Omer Faruk Alçin Ahmet Kizilay Ismail Okan Yildirim

Eur Arch Otorhinolaryngol 2022 May 21. Epub 2022 May 21.

Department of Radiology, Inonu University Faculty of Medicine, Malatya, Turkey.

Purpose: To create a new artificial intelligence approach based on deep learning (DL) from multiparametric MRI in the differential diagnosis of common parotid tumors.

Methods: Parotid tumors were classified using the InceptionResNetV2 DL model and majority voting approach with MRI images of 123 patients. The study was conducted in three stages. At stage I, the classification of the control, pleomorphic adenoma, Warthin tumor and malignant tumor (MT) groups was examined, and two approaches in which MRI sequences were given in combined and non-combined forms were established. At stage II, the classification of the benign tumor, MT and control groups was made. At stage III, patients with a tumor in the parotid gland and those with a healthy parotid gland were classified.

Results: A stage I, the accuracy value for classification in the non-combined and combined approaches was 86.43% and 92.86%, respectively. This value at stage II and stage III was found respectively as 92.14% and 99.29%.

Conclusions: The approach presented in this study classifies parotid tumors automatically and with high accuracy using DL models.

Download full-text PDF

 Source
http://dx.doi.org/10.1007/s00405-022-07455-yDOI Listing
May 2022

Publication Analysis

Top Keywords

parotid gland
12
differential diagnosis
8
stage classification
8
deep learning
8
stage iii
8
multiparametric mri
8
mri differential
8
parotid tumors
8
stage
6
parotid
6
accuracy models
4
combined non-combined
4
non-combined forms
4
forms established
4
mri sequences
4
established stage
4
classification benign
4
benign tumor
4
tumor control
4
sequences combined
4

Keyword Occurance

Similar Publications

Primary amelanotic malignant melanoma of parotid and submandibular salivary gland: A rare case report.

Authors:
Mehebuba Sultana Rudra Prasad Chatterjee Sanchita Kundu Sk Abdul Mahmud

J Oral Maxillofac Pathol 2022 Apr-Jun;26(2):263-267. Epub 2022 Jun 28.

Department of Oral and Maxillofacial Pathology, GuruNanak Institute Of Dental Science And Research, Kolkata, West Bengal, India.

Primary amelanotic malignant melanomas (AMMs) of the parotid and submandibular salivary glands are extremely rare with only a few reported cases due to its low incidence and misdiagnosis. Malignant melanoma (MM) has a high predilection for the head-and-neck region and majority of the cases in the parotid gland reported as association with metastasis in and around the gland from a cutaneous primary tumor. Immunohistochemistry is solely needed for confirmation of diagnosis and MMs give positive reactivity for melan-A, HMB-45, and S-100. Read More

View Article and Full-Text PDF
June 2022
Similar Publications

Multimodal magnetic resonance imaging for the diagnosis of parotid gland malignancies: systematic review and meta-analysis.

Authors:
Zhi-Qun Li Jin-Niao Gao Shan Xu Yusen Shi Xudong Liu Xiuzhu Li Jianghua Wan

Transl Cancer Res 2022 Jul;11(7):2275-2282

Department of Radiology, The First Affiliated Hospital of Hainan Medical University, Haikou, China.

Background: To systematically evaluate the qualitative diagnostic value of multimodal magnetic resonance imaging (MRI) for parotid gland tumors. However, there is still a lot of controversy in this area, and the results of different studies are not consistent. Therefore, it is necessary to use meta method to analyze the significance of multimodal MRI in the diagnosis of parotid gland tumors. Read More

View Article and Full-Text PDF
July 2022
Similar Publications

Delayed Management of Parotid Sialocele: Role for Two-week Intraoral Drainage.

Authors:
Amin Rahpeyma Saeedeh Khajehahmadi

Curr Med Sci 2022 Aug 13;42(4):902-904. Epub 2022 Aug 13.

Dental Research Center, Mashhad University of Medical Sciences, Mashhad, Iran.

Iatrogenic injury or trauma to the salivary gland duct is one of the most common causes of parotid sialoceles, which are usually superficial, soft, and filled with saliva. The enrolled 7 patients with parotid sialocele were divided into two groups: trauma group (4 cases) and iatrogenic group (3 cases). No evidence of recurrence or cranial nerve injuries were observed. Read More

View Article and Full-Text PDF
August 2022
Similar Publications

Applying Tumescent solution for preserving the facial nerve in parotidectomy.

Authors:
Nguyen Quang Duc Nguyen Phuong Tien Nguyen Thanh Tu Vu Ngoc Lam

Asian J Surg 2022 Aug 10. Epub 2022 Aug 10.

Center for Craniofacial and Plastic Surgery, 108 Military Central Hospital, 1 Tran Hung Dao Street, Hanoi, Viet Nam.

Background: Facial nerve palsy is one of the most common complications in parotid gland surgery. This report evaluates the effectiveness of applying Tumescent solution for preserving the facial nerve in parotidectomy.

Material And Methods: Prospective and descriptive clinical study on 34 patients undergoing parotidectomy with facial nerve preservation. Read More

View Article and Full-Text PDF
August 2022
Similar Publications

Distinguishing Parotid Polymorphic Adenoma and Warthin Tumor Based on the CT Radiomics Nomogram: A Multicenter Study.

Authors:
Baomin Feng Zhou Wang Jingjing Cui Jiacun Li Han Xu Dexin Yu Qingshi Zeng Jianjun Xiu

Acad Radiol 2022 Aug 8. Epub 2022 Aug 8.

Department of Radiology, Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, Shandong, China. Electronic address:

Rationale And Objectives: To develop, validate, and test a comprehensive radiomics prediction model to distinguish parotid polymorphic adenomas (PAs) and warthin tumors (WTs) using clinical data and enhanced computed tomography (CT) from a multicenter cohort.

Materials And Methods: A total of 267 patients with PAs (n =172) or WTs (n = 95) from two hospitals were randomly divided into training (n =188) and validation (n =79) datasets. Radiomics features were extracted from the enhanced CT (arterial phase) followed by dimensionality reduction. Read More

View Article and Full-Text PDF
August 2022
Similar Publications
}