MRI Texture Analysis Predicts p53 Status in Head and Neck Squamous Cell Carcinoma

Abstract

BACKGROUND AND PURPOSE:Head and neck cancer is common, and understanding the prognosis is an important part of patient management. In addition to the Tumor, Node, Metastasis staging system, tumor biomarkers are becoming more useful in understanding prognosis and directing treatment. We assessed whether MR imaging texture analysis would correctly classify oropharyngeal squamous cell carcinoma according to p53 status.

Characterization of Adrenal Lesions on Unenhanced MRI Using Texture Analysis: A Machine‐Learning Approach

“…They found that entropy features can differentiate between histological and immunohistochemical subtypes of breast cancer, suggesting that texture analysis of breast cancer potentially provides additional information for decision‐making . A machine‐learning software employing MR texture features has been also used in the head and neck field by Dang et al, who found that MRI texture analysis correctly predicted p53 status in oropharyngeal squamous cell carcinoma with ∼80% of diagnostic accuracy . Regarding adrenal imaging, previous authors have evaluated the role of histogram analysis to characterize adrenal lesions on CT images, while only in one study was this technique applied to MR images, particularly to differentiate adrenal adenomas from pheochromocytomas on ADC maps, showing that histogram‐derived parameters extracted from ADC maps could be useful for this purpose; to the best of our knowledge, this is the first report describing texture analysis with a machine‐learning approach for differential diagnosis of adrenal lesions using T 2 ‐w, IP and OP MR images.…”

“…12 A machine-learning software employing MR texture features has been also used in the head and neck field by Dang et al, who found that MRI texture analysis correctly predicted p53 status in oropharyngeal squamous cell carcinoma with 80% of diagnostic accuracy. 13 Regarding adrenal imaging, previous authors have evaluated the role of histogram analysis to characterize adrenal lesions on CT images, 6 while only in one study was this technique applied to MR images, particularly to differentiate adrenal adenomas from pheochromocytomas on ADC maps, showing that histogram-derived parameters extracted from ADC maps could be useful for this purpose 9 ; to the best of our knowledge, this is the first report describing texture analysis with a machine-learning approach for differential diagnosis of adrenal lesions using T 2 -w, IP and OP MR images. We decided to perform the analysis only on unenhanced MR images, as we intended to propose a faster and noninvasive diagnostic MRI method able to characterize adrenal lesions, in the light of the potential safety issues related to the use of gadolinium-based contrast agents.…”

“…Machine learning is a technique for recognizing patterns that can be applied to medical images by identifying the best combination of image texture features in order to create a predictive model for the diagnosis of interest and it has been applied to MR images in different fields …”

“…9 Machine learning is a technique for recognizing patterns that can be applied to medical images by identifying the best combination of image texture features in order to create a predictive model for the diagnosis of interest 10 and it has been applied to MR images in different fields. [11][12][13] The aim of this retrospective study was to assess the diagnostic effectiveness of texture analysis-derived parameters (morphologic, first-order, GLCM, and RLNM) using a machine-learning approach to characterize LRA, LPA, and NAL on unenhanced T 1 -weighted in-phase (IP) and out-ofphase (OP) as well as T 2 -weighted MR images.…”

An Exploratory Study to Detect Ménière’s Disease in Conventional MRI Scans Using Radiomics

“…Finally, these quantitative image features can be used for statistical analysis. Several recent studies have shown that radiomics can be used to obtain information about, for example, tumor phenotypes and prognosis (11, 12), tumor biomarkers (16), and distant metastasis (17). Studies have also shown structural differences in patients with amyotrophic lateral sclerosis (13) and Alzheimer’s disease (18) when compared to healthy subjects.…”