Deep learning-assisted diagnosis of benign and malignant parotid tumors based on contrast-enhanced CT: a multicenter study

Article Pathology

Clinicopathologic Characteristics and Prognostic Factors of Primary and Recurrent Pleomorphic Adenoma A Single Institution Retrospective Study of 705 Cases

Bayan Alzumaili et al.

Summary: This study investigates the prognostic features of primary and recurrent pleomorphic adenoma (PA) and finds that age, mitosis, and resection quality are key factors in predicting recurrence.

AMERICAN JOURNAL OF SURGICAL PATHOLOGY (2022)

Add to Collection

Article Radiology, Nuclear Medicine & Medical Imaging

Deep Learning-Based Image Conversion Improves the Reproducibility of Computed Tomography Radiomics Features A Phantom Study

Seul Bi Lee et al.

Summary: This study demonstrated that a deep learning-based image conversion algorithm can improve the reproducibility of radiomics features in computed tomography (CT) images, regardless of variations in CT protocols, reconstruction kernels, and CT scanners.

INVESTIGATIVE RADIOLOGY (2022)

Add to Collection

Review Otorhinolaryngology

Deep Lobe Parotid Tumors: A Systematic Review and Meta-analysis

Margaret H. Aasen et al.

Summary: Our systematic review and meta-analysis revealed that deep lobe parotid tumors had a 26.6% malignancy rate, which was significantly higher than superficial lobe tumors. Surgical excision of deep lobe tumors was associated with increased rates of temporary facial nerve paresis compared to superficial lobe tumors. Limited data were available regarding the utility of fine-needle aspiration.

OTOLARYNGOLOGY-HEAD AND NECK SURGERY (2022)

Add to Collection

Article Otorhinolaryngology

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

Emrah Gunduz et al.

Summary: This study successfully classified parotid tumors automatically with high accuracy using DL models and majority voting approach on MRI images of 123 patients.

EUROPEAN ARCHIVES OF OTO-RHINO-LARYNGOLOGY (2022)

Add to Collection

Article Oncology

Multiphasic CT-Based Radiomics Analysis for the Differentiation of Benign and Malignant Parotid Tumors

Qiang Yu et al.

Summary: This study investigates the value of machine learning models based on clinical-radiological features and multiphasic CT radiomics features in differentiating benign parotid tumors (BPTs) and malignant parotid tumors (MPTs). The results suggest that machine learning models based on clinical-radiological features and radiomics features have the potential to provide a valuable tool for discriminating these two types of tumors.

FRONTIERS IN ONCOLOGY (2022)

Add to Collection

Article Medicine, General & Internal

Deep learning radiomics of dual-modality ultrasound images for hierarchical diagnosis of unexplained cervical lymphadenopathy

Yangyang Zhu et al.

Summary: The study developed a DL radiomics model based on ultrasound images to assist radiologists in diagnosing unexplained CLA, achieving accurate classification of specific etiologies. The DL model significantly improved the accuracy, sensitivity, and specificity of radiologists with different levels of experience, reducing false-negative and false-positive rates.

BMC MEDICINE (2022)

Add to Collection

Article Radiology, Nuclear Medicine & Medical Imaging

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

Zhiying He et al.

Summary: This study demonstrates the effectiveness of machine learning models based on morphological MRI radiomics in the classification of parotid tumors. XGBoost and SVM outperform DT and radiologists in terms of accuracy.

EUROPEAN RADIOLOGY (2022)

Add to Collection

Article Radiology, Nuclear Medicine & Medical Imaging

CT-based radiomics analysis of different machine learning models for differentiating benign and malignant parotid tumors

Yunlin Zheng et al.

Summary: The combined model incorporating radiomics and clinical features demonstrated an excellent ability to distinguish between benign and malignant parotid tumors, providing a noninvasive and efficient method for clinical decision making.

EUROPEAN RADIOLOGY (2022)

Add to Collection

Review Otorhinolaryngology

Controversies in the Workup and Surgical Management of Parotid Neoplasms

Michael G. Moore et al.

Summary: This article reviews the evidence-based approach to evaluation and surgical management of parotid neoplasms, emphasizing the importance of evaluation, extent of surgery, and oncologic management of the primary lesion and surrounding areas.

OTOLARYNGOLOGY-HEAD AND NECK SURGERY (2021)

Add to Collection

Article Biophysics

Classification of parotid gland tumors by using multimodal MRI and deep learning

Yi-Ju Chang et al.

Summary: Various MRI sequences can discriminate parotid gland tumors, with the deep learning model utilizing diffusion-weighted parameters showing better performance. The proposed model could classify Warthin and pleomorphic adenoma tumors accurately but not malignant tumors.

NMR IN BIOMEDICINE (2021)

Add to Collection

Review Radiology, Nuclear Medicine & Medical Imaging

Multiparametric magnetic resonance imaging of parotid tumors: A systematic review

H. Coudert et al.

Summary: This systematic review provides an overview of the contribution of multiparametric MRI in the diagnosis of parotid tumors, highlighting the use of DWI and DCE imaging, as well as the differences in morphological signs between benign and malignant tumors. The combination of different imaging modalities can significantly increase the diagnostic accuracy of MRI for focal parotid tumors.

DIAGNOSTIC AND INTERVENTIONAL IMAGING (2021)

Add to Collection

Article Radiology, Nuclear Medicine & Medical Imaging

MRI-Based radiomics nomogram for differentiation of benign and malignant lesions of the parotid gland

Ying-mei Zheng et al.

Summary: The MRI-based radiomics nomogram showed good performance in differentiating between benign and malignant parotid gland tumors, providing valuable information for clinical decision-making.

EUROPEAN RADIOLOGY (2021)

Add to Collection

Article Radiology, Nuclear Medicine & Medical Imaging

Utility of deep learning for the diagnosis of otosclerosis on temporal bone CT

Noriyuki Fujima et al.

Summary: The study found that deep learning analysis could be a useful supportive tool in diagnosing otosclerosis on temporal bone CT images. The diagnostic accuracies of VGGNet, GoogLeNet, and ResNet were comparable to that of a subspecialty trained radiologist, with GoogLeNet and ResNet showing non-inferiority compared to the radiologist.

EUROPEAN RADIOLOGY (2021)

Add to Collection

Letter Oncology

Deep learning for differential diagnosis of malignant hepatic tumors based on multi-phase contrast-enhanced CT and clinical data

Ruitian Gao et al.

Summary: The study developed an automatic diagnostic model, STIC, based on multimodal medical data to differentiate malignant hepatic tumors. By incorporating Deep CNN and gated RNN, the model achieved high accuracy and could assist doctors in achieving better diagnostic performance for liver cancer treatment.

JOURNAL OF HEMATOLOGY & ONCOLOGY (2021)

Add to Collection

Article Oncology

The Clinical Characteristics and CT Findings of Parotid and Submandibular Gland Tumours

Houdong Zuo

Summary: The study investigated the clinical characteristics and CT findings of parotid and submandibular gland tumors, revealing distinct imaging features between benign and malignant tumors on CT scans. Radiologists may utilize this information for accurate diagnosis in clinical practice.

JOURNAL OF ONCOLOGY (2021)

Add to Collection

Article Radiology, Nuclear Medicine & Medical Imaging

The Discriminative Power and Stability of Radiomics Features With Computed Tomography Variations Task-Based Analysis in an Anthropomorphic 3D-Printed CT Phantom

Oscar Jimenez-Del-Toro et al.

Summary: This study investigated the stability of radiomics features against CT parameter variations and their discriminative power in tissue classification. Results showed significant differences in radiomics features among CT parameter variations and successful differentiation among different liver tissue types. The differences between radiomics features of different liver tissue types are generally larger than those caused by CT parameter variations.

INVESTIGATIVE RADIOLOGY (2021)

Add to Collection

Article Computer Science, Information Systems

Research on the Classification of Benign and Malignant Parotid Tumors Based on Transfer Learning and a Convolutional Neural Network

Hongbin Zhang et al.

Summary: The classification of parotid tumors is crucial for surgical method selection and prognosis. The study proposes to use deep learning methods in computer-aided diagnosis, achieving an accuracy of 97.78% with an improved CNN model for parotid CT image classification.

IEEE ACCESS (2021)

Add to Collection

Article Radiology, Nuclear Medicine & Medical Imaging

Intravoxel Incoherent Motion Magnetic Resonance Imaging for Assessing Parotid Gland Tumors: Correlation and Comparison with Arterial Spin Labeling Imaging

Gao Ma et al.

Summary: The findings suggest that IVIM and ASL imaging can help differentiate parotid gland tumors, with significant differences in D, D*, f, and SIR values among different tumor types. Additionally, a positive correlation between SIR on ASL imaging and f was observed, indicating the potential of ASL imaging in discriminating between malignant tumors and Warthin's tumors.

KOREAN JOURNAL OF RADIOLOGY (2021)

Add to Collection

Article Computer Science, Artificial Intelligence