Radiomics and artificial intelligence applications in pediatric brain tumors.

BACKGROUND: The study of central nervous system (CNS) tumors is particularly relevant in the pediatric population because of their relatively high frequency in this demographic and the significant impact on disease- and treatment-related morbidity and mortality. While both morphological and non-morphological magnetic resonance imaging techniques can give important information concerning tumor characterization, grading, and patient prognosis, increasing evidence in recent years has highlighted the need for personalized treatment and the development of quantitative imaging parameters that can predict the nature of the lesion and its possible evolution. For this purpose, radiomics and the use of artificial intelligence software, aimed at obtaining valuable data from images beyond mere visual observation, are gaining increasing importance. This brief review illustrates the current state of the art of this new imaging approach and its contributions to understanding CNS tumors in children. DATA SOURCES: We searched the PubMed, Scopus, and Web of Science databases using the following key search terms: ("radiomics" AND/OR "artificial intelligence") AND ("pediatric AND brain tumors"). Basic and clinical research literature related to the above key research terms, i.e., studies assessing the key factors, challenges, or problems of using radiomics and artificial intelligence in pediatric brain tumors management, was collected. RESULTS: A total of 63 articles were included. The included ones were published between 2008 and 2024. Central nervous tumors are crucial in pediatrics due to their high frequency and impact on disease and treatment. MRI serves as the cornerstone of neuroimaging, providing cellular, vascular, and functional information in addition to morphological features for brain malignancies. Radiomics can provide a quantitative approach to medical imaging analysis, aimed at increasing the information obtainable from the pixels/voxel grey-level values and their interrelationships. The "radiomic workflow" involves a series of iterative steps for reproducible and consistent extraction of imaging data. These steps include image acquisition for tumor segmentation, feature extraction, and feature selection. Finally, the selected features, via training predictive model (CNN), are used to test the final model. CONCLUSIONS: In the field of personalized medicine, the application of radiomics and artificial intelligence (AI) algorithms brings up new and significant possibilities. Neuroimaging yields enormous amounts of data that are significantly more than what can be gained from visual studies that radiologists can undertake on their own. Thus, new partnerships with other specialized experts, such as big data analysts and AI specialists, are desperately needed. We believe that radiomics and AI algorithms have the potential to move beyond their restricted use in research to clinical applications in the diagnosis, treatment, and follow-up of pediatric patients with brain tumors, despite the limitations set out.

MRI-ARSACS: An Imaging Index for Autosomal Recessive Spastic Ataxia of Charlevoix-Saguenay (ARSACS) Identification Based on the Multicenter PROSPAX Study.

BACKGROUND: Autosomal recessive spastic ataxia of Charlevoix-Saguenay (ARSACS) and hereditary spastic paraplegia type 7 (SPG7) represent the most common genotypes of spastic ataxia (SPAX). To date, their magnetic resonance imaging (MRI) features have only been described qualitatively, and a pure neuroradiological differential diagnosis between these two conditions is difficult to achieve. OBJECTIVES: To test the performance of MRI measures to discriminate between ARSACS and SPG7 (as an index of common SPAX disease). METHODS: In this prospective multicenter study, 3D-T1-weighted images of 59 ARSACS (35.4 ± 10.3 years, M/F = 33/26) and 78 SPG7 (54.8 ± 10.3 years, M/F = 51/27) patients of the PROSPAX Consortium were analyzed, together with 30 controls (45.9 ± 16.9 years, M/F = 15/15). Different linear and surface measures were evaluated. A receiver operating characteristic analysis was performed, calculating area under the curve (AUC) and corresponding diagnostic accuracy parameters. RESULTS: The pons area proved to be the only metric increased exclusively in ARSACS patients (P = 0.02). Other different measures were reduced in ARSACS and SPG7 compared with controls (all with P ≤ 0.005). A cut-off value equal to 1.67 of the pons-to-superior vermis area ratio proved to have the highest AUC (0.98, diagnostic accuracy 93%, sensitivity 97%) in discriminating between ARSACS and SPG7. CONCLUSIONS: Evaluation of the pons-to-superior vermis area ratio can discriminate ARSACS from other SPAX patients, as exemplified here by SPG7. Hence, we hereby propose this ratio as the Magnetic Resonance Index for the Assessment and Recognition of patients harboring SACS mutations (MRI-ARSACS), a novel diagnostic tool able to identify ARSACS patients and useful for discriminating ARSACS from other SPAX patients undergoing MRI. © 2024 International Parkinson and Movement Disorder Society.

The Current Diagnostic Performance of MRI-Based Radiomics for Glioma Grading: A Meta-Analysis.

BACKGROUND: Multiple radiomics models have been proposed for grading glioma using different algorithms, features, and sequences of magnetic resonance imaging. The research seeks to assess the present overall performance of radiomics for grading glioma. METHODS: A systematic literature review of the databases Ovid MEDLINE PubMed, and Ovid EMBASE for publications published on radiomics for glioma grading between 2012 and 2023 was performed. The systematic review was carried out following the criteria of Preferred Reporting Items for Systematic Reviews and Meta-Analysis. RESULTS: In the meta-analysis, a total of 7654 patients from 40 articles, were assessed. R-package mada was used for modeling the joint estimates of specificity (SPE) and sensitivity (SEN). Pooled event rates across studies were performed with a random-effects meta-analysis. The heterogeneity of SPE and SEN were based on the χ2 test. Overall values for SPE and SEN in the differentiation between high-grade gliomas (HGGs) and low-grade gliomas (LGGs) were 84% and 91%, respectively. With regards to the discrimination between World Health Organization (WHO) grade 4 and WHO grade 3, the overall SPE was 81% and the SEN was 89%. The modern non-linear classifiers showed a better trend, whereas textural features tend to be the best-performing (29%) and the most used. CONCLUSIONS: Our findings confirm that present radiomics' diagnostic performance for glioma grading is superior in terms of SEN and SPE for the HGGs vs. LGGs discrimination task when compared to the WHO grade 4 vs. 3 task.

New perspectives in the differential diagnosis of jaw lesions: Machine learning and inflammatory biomarkers.

This study aimed to assess the diagnostic performance of a machine learning approach that utilized radiomic features extracted from Cone Beam Computer Tomography (CBCT) images and inflammatory biomarkers for distinguishing between Dentigerous Cysts (DCs), Odontogenic Keratocysts (OKCs), and Unicystic Ameloblastomas (UAs). This retrospective study involves 103 patients who underwent jaw lesion surgery in the Maxillofacial Surgery Unit of Federico II University Of Naples between January 2018 and January 2023. Nonparametric Wilcoxon-Mann-Whitney and Kruskal Wallis tests were used for continuous variables. Linear and non-logistic regression models (LRM and NLRM) were employed, along with machine learning techniques such as decision tree (DT), k-nearest neighbor (KNN), and support vector machine (SVM), to predict the outcomes. When individual inflammatory biomarkers were considered alone, their ability to differentiate between OKCs, UAs, and DCs was below 50 % accuracy. However, a linear regression model combining four inflammatory biomarkers achieved an accuracy of 95 % and an AUC of 0.96. The accuracy of single radiomics predictors was lower than that of inflammatory biomarkers, with an AUC of 0.83. The Fine Tree model, utilizing NLR, SII, and one radiomic feature, achieved an accuracy of 94.3 % (AUC = 0.95) on the training and testing sets, and a validation set accuracy of 100 %. The Fine Tree model demonstrated the capability to discriminate between OKCs, UAs, and DCs. However, the LRM utilizing four inflammatory biomarkers proved to be the most effective algorithm for distinguishing between OKCs, UAs, and DCs.

METhodological RadiomICs Score (METRICS): a quality scoring tool for radiomics research endorsed by EuSoMII.

PURPOSE: To propose a new quality scoring tool, METhodological RadiomICs Score (METRICS), to assess and improve research quality of radiomics studies. METHODS: We conducted an online modified Delphi study with a group of international experts. It was performed in three consecutive stages: Stage#1, item preparation; Stage#2, panel discussion among EuSoMII Auditing Group members to identify the items to be voted; and Stage#3, four rounds of the modified Delphi exercise by panelists to determine the items eligible for the METRICS and their weights. The consensus threshold was 75%. Based on the median ranks derived from expert panel opinion and their rank-sum based conversion to importance scores, the category and item weights were calculated. RESULT: In total, 59 panelists from 19 countries participated in selection and ranking of the items and categories. Final METRICS tool included 30 items within 9 categories. According to their weights, the categories were in descending order of importance: study design, imaging data, image processing and feature extraction, metrics and comparison, testing, feature processing, preparation for modeling, segmentation, and open science. A web application and a repository were developed to streamline the calculation of the METRICS score and to collect feedback from the radiomics community. CONCLUSION: In this work, we developed a scoring tool for assessing the methodological quality of the radiomics research, with a large international panel and a modified Delphi protocol. With its conditional format to cover methodological variations, it provides a well-constructed framework for the key methodological concepts to assess the quality of radiomic research papers. CRITICAL RELEVANCE STATEMENT: A quality assessment tool, METhodological RadiomICs Score (METRICS), is made available by a large group of international domain experts, with transparent methodology, aiming at evaluating and improving research quality in radiomics and machine learning. KEY POINTS: • A methodological scoring tool, METRICS, was developed for assessing the quality of radiomics research, with a large international expert panel and a modified Delphi protocol. • The proposed scoring tool presents expert opinion-based importance weights of categories and items with a transparent methodology for the first time. • METRICS accounts for varying use cases, from handcrafted radiomics to entirely deep learning-based pipelines. • A web application has been developed to help with the calculation of the METRICS score ( https://metricsscore.github.io/metrics/METRICS.html ) and a repository created to collect feedback from the radiomics community ( https://github.com/metricsscore/metrics ).

Prediction of diabetes insipidus occurrence after endoscopic endonasal removal of sellar lesions using MRI-based radiomics and machine learning.

BACKGROUND: Pituitary adenomas and craniopharyngiomas are the most common lesions of the sellar region. These tumors are responsible for invasion or compression of crucial neurovascular structures. The involvement of the pituitary stalk warrants high rates of both pre- and post- operative diabetes insipidus. The aim of our study was to assess the accuracy of machine learning analysis from preoperative MRI of pituitary adenomas and craniopharyngiomas for the prediction of DI occurrence. METHODS: All patients underwent MRI exams either on a 1.5- or 3-T MR scanner from two Institutions, including coronal T2-weighted (T2-w) and contrast-enhanced T1-weighted (CE T1-w) Turbo Spin Echo sequences. Feature selection was carried out as a multi-step process, with a threshold of 0.75 to identify robust features. Further feature selection steps included filtering based on feature variance (threshold >0.01) and pairwise correlation (threshold <0.80). A Bayesian Network model was trained with 10-fold cross validation employing SMOTE to balance classes exclusively within the training folds. RESULTS: Thirty patients were included in this study. In total 2394 features were extracted and 1791 (75%) resulted stable after ICC analysis. The number of variant features was 1351 and of non-colinear features was 125. Finally, 10 features were selected by oneR ranking. The Bayesian Network model showed an accuracy of 63% with a precision of 77% for DI prediction (0.68 area under the precision-recall curve). CONCLUSIONS: We assessed the accuracy of machine learning analysis of texture-derived parameters from preoperative MRI of pituitary adenomas and craniopharyngiomas for the prediction of DI occurrence.

Reproducibility of radiomics quality score: an intra- and inter-rater reliability study.

OBJECTIVES: To investigate the intra- and inter-rater reliability of the total radiomics quality score (RQS) and the reproducibility of individual RQS items' score in a large multireader study. METHODS: Nine raters with different backgrounds were randomly assigned to three groups based on their proficiency with RQS utilization: Groups 1 and 2 represented the inter-rater reliability groups with or without prior training in RQS, respectively; group 3 represented the intra-rater reliability group. Thirty-three original research papers on radiomics were evaluated by raters of groups 1 and 2. Of the 33 papers, 17 were evaluated twice with an interval of 1 month by raters of group 3. Intraclass coefficient (ICC) for continuous variables, and Fleiss' and Cohen's kappa (k) statistics for categorical variables were used. RESULTS: The inter-rater reliability was poor to moderate for total RQS (ICC 0.30-055, p < 0.001) and very low to good for item's reproducibility (k - 0.12 to 0.75) within groups 1 and 2 for both inexperienced and experienced raters. The intra-rater reliability for total RQS was moderate for the less experienced rater (ICC 0.522, p = 0.009), whereas experienced raters showed excellent intra-rater reliability (ICC 0.91-0.99, p < 0.001) between the first and second read. Intra-rater reliability on RQS items' score reproducibility was higher and most of the items had moderate to good intra-rater reliability (k - 0.40 to 1). CONCLUSIONS: Reproducibility of the total RQS and the score of individual RQS items is low. There is a need for a robust and reproducible assessment method to assess the quality of radiomics research. CLINICAL RELEVANCE STATEMENT: There is a need for reproducible scoring systems to improve quality of radiomics research and consecutively close the translational gap between research and clinical implementation. KEY POINTS: • Radiomics quality score has been widely used for the evaluation of radiomics studies. • Although the intra-rater reliability was moderate to excellent, intra- and inter-rater reliability of total score and point-by-point scores were low with radiomics quality score. • A robust, easy-to-use scoring system is needed for the evaluation of radiomics research.

The role of unidentified bright objects in the neurocognitive profile of neurofibromatosis type 1 children: a volumetric MRI analysis.

PURPOSE: Cognitive impairment is described in 80% of Neurofibromatosis type 1 (NF1) patients. Brain focal areas of T2w increased signal intensity on MRI, the so-called Unidentified Bright Objects (UBOs) have been hypothesized to be related to cognitive dysfunction, although conflicting results are available in literature. Here, we investigated the possible relation between UBOs' volume, cognitive impairment, and language disability in NF1 patients. MATERIAL AND METHODS: In this retrospective study, clinical and MRI data of 21 NF1 patients (M/F = 12/9; mean age 10.1 ± 4.5) were evaluated. Brain intellectual functioning and language abilities were assessed with specific scales, while the analyzed MRI sequences included axial 2D-T2-weighted and FLAIR sequences. These images were used independently for UBOs segmentation with a semiautomatic approach and obtained volumes were normalized for biparietal diameters to take into account for brain volume. Possible differences in terms of normalized UBOs volumes were probed between cognitively affected and preserved patients, as well as between subjects with or without language impairment. RESULTS: Patients cognitively affected were not different in terms of UBOs volume compared to those preserved (p = 0.35 and p = 0.30, for T2-weighted and FLAIR images, respectively). Similarly, no differences were found between patients with and without language impairment (p = 0.47 and p = 0.40, for the two sequences). CONCLUSIONS: The relation between UBOs and cognition in children with NF1 has been already investigated in literature, although leading to conflicting results. Our study expands the current knowledge, showing a lack of correlation between UBOs volume and both cognitive impairment and language disability in NF1 patients.

Impact of Sarcopenia on Survival of Patients With Malignant Salivary Glands Tumors.

OBJECTIVE: Malignant salivary glands tumors (MSGTs) are a quite rare and heterogeneous group of tumors. Management of these lesions remains controversial and challenging. Thus, finding new prognostic factors that can help to guide the decision-making process, appears to be paramount. The aim of this study was to evaluate the prognostic performance of preoperative sarcopenia to stratify MSGTs patients at high risk of disease progression. STUDY DESIGN: Retrospective study. SETTING: A single-institution analysis (Maxillo-facial Surgery Unit, University of Naples Federico II). METHODS: The study consists of a retrospective analysis of 74 patients surgically treated for MSGTs. For all patients, the skeletal muscle index (SMI) was calculated and sarcopenia was defined as SMI < 41 in females and <43 in males. The correlation between sarcopenia and tumor variables was analyzed. The prognostic performance of sarcopenia was evaluated through survival Kaplan-Meier curves. RESULTS: Sarcopenia resulted statistically related to age (P < .001), tumor size (P < .001), lymph node metastases (P < .001), and American Joint Committee on Cancer tumor, node, metastasis stage (P < .001). Kaplan-Meier survival curves show that 47.3% of sarcopenic patients died before their final follow-up. CONCLUSION: Data obtained from our study seem to confirm the correlation between sarcopenia and other high-risk features. The early detection of sarcopenia in patients with negative prognostic factors could be used to implement the support therapeutic strategies aimed at restore the clinical conditions of the patients. Sarcopenia may be routinely investigated before surgery to suggest the implementation of precautionary therapeutic strategies to improve the standard treatment response, reducing possible complications.

Large language models in radiology: fundamentals, applications, ethical considerations, risks, and future directions.

With the advent of large language models (LLMs), the artificial intelligence revolution in medicine and radiology is now more tangible than ever. Every day, an increasingly large number of articles are published that utilize LLMs in radiology. To adopt and safely implement this new technology in the field, radiologists should be familiar with its key concepts, understand at least the technical basics, and be aware of the potential risks and ethical considerations that come with it. In this review article, the authors provide an overview of the LLMs that might be relevant to the radiology community and include a brief discussion of their short history, technical basics, ChatGPT, prompt engineering, potential applications in medicine and radiology, advantages, disadvantages and risks, ethical and regulatory considerations, and future directions.

Temporal bone CT-based anatomical parameters associated with the development of cholesteatoma.

BACKGROUND: Cholesteatoma is caused by disorders of the middle ear ventilation that trigger a progressive series of events responsible for its formation. The aim of this study was to identify possible radiological CT-derived parameters predisposing to ventilation disorders and cholesteatoma. METHODS: In this retrospective study, patients diagnosed with cholesteatomatous chronic otitis media who underwent temporal bone CT and open tympanoplasty surgery have been included, as well as control patients with clinical examination negative for organic otological pathology who underwent temporal bone CT for other reasons. For each patient, the following parameters have been extracted from CT volumes: degree of mastoid pneumatization, prominence of the cog, patency of the Eustachian tube, antrum width, aditus width, anterior and posterior epitympanic widths, and epitympanic height. RESULTS: Sixty patients have been included, thirty of whom belonged to the group of patients with cholesteatoma and the remaining part to the group of patients without organic otological pathology. The prevalence of a low degree of mastoid pneumatization was significantly higher among patients with cholesteatoma, as well as for the prevalence of cog prominence (p < 0.001). All the continuous variables were found to have statistical significance (p < 0.05) in the comparison between groups except for the width of the antrum. CONCLUSION: Mastoid pneumatization degree, prominence of the cog and epitympanic measures based on temporal bone CT could be good radiological correlates of the ventilatory capabilities of the epitympanum which, if compromised, can facilitate the development of cholesteatoma.

Segmentation methods applied to MRI-derived radiomic analysis for the prediction of placenta accreta spectrum in patients with placenta previa.

PURPOSE: To retrospectively evaluate the performance of different manual segmentation methods of placenta MR images for predicting Placenta Accreta Spectrum (PAS) disorders in patients with placenta previa (PP) using a Machine Learning (ML) Radiomics analysis. METHODS: 64 patients (n=41 with PAS and n= 23 without PAS) with PP who underwent MRI examination for suspicion of PAS were retrospectively selected. All MRI examinations were acquired on a 1.5 T using T2-weighted (T2w) sequences on axial, sagittal and coronal planes. Ten different manual segmentation methods were performed on sagittal placental T2-weighted images obtaining five sets of 2D regions of interest (ROIs) and five sets of 3D volumes of interest (VOIs) from each patient. In detail, ROIs and VOIs were positioned on the following areas: placental tissue, retroplacental myometrium, cervix, placenta with underneath myometrium, placenta with underneath myometrium and cervix. For feature stability testing, the same process was repeated on 30 randomly selected placental MRI examinations by two additional radiologists, working independently and blinded to the original segmentation. Radiomic features were extracted from all available ROIs and VOIs. 100 iterations of 5-fold cross-validation with nested feature selection, based on recursive feature elimination, were subsequently run on each ROI/VOI to identify the best-performing method to classify instances correctly. RESULTS: Among the segmentation methods, the best performance in predicting PAS was obtained by the VOIs covering the retroplacental myometrium (Mean validation score: 0.761, standard deviation: 0.116). CONCLUSION: Our preliminary results show that the VOI including the retroplacental myometrium using T2w images seems to be the best method when segmenting images for the development of ML radiomics predictive models to identify PAS in patients with PP.

A "masked" pleomorphic xanthoastrocytoma.

The latest WHO Classification of tumours of the Central Nervous System (CNS) emphasizes the necessity of an integrated diagnostic approach during the workup of a CNS neoplasm. In addition to the mutational status, assessment of methylation profile of a tumour emerged as a helpful (often necessary) tool to make a correct and unequivocal diagnosis. Here we present a case of a Pleomorphic Xanthoastrocytoma with clinical, radiological and histopathological findings remarkably overlapping with a recently described paediatric-type glioma namly Polymorphic Low-grade Neuroepithelial Tumour of the Young (PLNTY). The differential diagnosis here discussed represents a methodological paradigm in the modern neuropathology. In fact, the presentation of this case is a demonstration that in day-to-day practice, clinical, radiological, and histopathological data can all be misleading, and the correct diagnosis can only be reached by integration with molecular analysis. In the modern neuro-oncology, it is by far mandatory for all the specialists dealing with cerebral tumours to "contaminate" their own cultural heritage with other ones, to optimally manage a patient with CNS tumour.

The "chameleon" sellar lesions: a case report of unexpected sellar lesions.

Introduction: The sellar region and its boundaries represent a challenging area, harboring a variety of tissues of different linings. Therefore, a variety of diseases can arise or involve in this area (i.e., neoplastic or not). A total of three challenging cases of "chameleon" sellar lesions treated via EEA were described, and the lesions mimicked radiological features of common sellar masses such as craniopharyngiomas and/or pituitary adenomas, and we also report a literature review of similar cases. Methods: A retrospective analysis of three primary cases was conducted at the Università degli Studi di Napoli Federico II, Naples, Italy. Clinical information, radiological examinations, and pathology reports were illustrated. Results: A total of three cases of so-called "chameleon" sellar lesions comprising two men and one woman were reported. Based on the intraoperative finding and pathological examination, we noticed that case 1 had suprasellar glioblastoma, case 2 had a primary neuroendocrine tumor, and case 3 had cavernous malformation. Conclusion: Neurosurgeons should consider "unexpected" lesions of the sellar/suprasellar region in the preoperative differential diagnosis. A multidisciplinary approach with the collaboration of neurosurgeons, neuroradiologists, and pathologists plays a fundamental role. The recognition of unusual sellar lesions can help surgeons with better preoperative planning; so an endoscopic endonasal approach may represent a valid surgical technique to obtain decompression of the optic apparatus and vascular structures and finally a pathological diagnosis.

CheckList for EvaluAtion of Radiomics research (CLEAR): a step-by-step reporting guideline for authors and reviewers endorsed by ESR and EuSoMII.

Even though radiomics can hold great potential for supporting clinical decision-making, its current use is mostly limited to academic research, without applications in routine clinical practice. The workflow of radiomics is complex due to several methodological steps and nuances, which often leads to inadequate reporting and evaluation, and poor reproducibility. Available reporting guidelines and checklists for artificial intelligence and predictive modeling include relevant good practices, but they are not tailored to radiomic research. There is a clear need for a complete radiomics checklist for study planning, manuscript writing, and evaluation during the review process to facilitate the repeatability and reproducibility of studies. We here present a documentation standard for radiomic research that can guide authors and reviewers. Our motivation is to improve the quality and reliability and, in turn, the reproducibility of radiomic research. We name the checklist CLEAR (CheckList for EvaluAtion of Radiomics research), to convey the idea of being more transparent. With its 58 items, the CLEAR checklist should be considered a standardization tool providing the minimum requirements for presenting clinical radiomics research. In addition to a dynamic online version of the checklist, a public repository has also been set up to allow the radiomics community to comment on the checklist items and adapt the checklist for future versions. Prepared and revised by an international group of experts using a modified Delphi method, we hope the CLEAR checklist will serve well as a single and complete scientific documentation tool for authors and reviewers to improve the radiomics literature.

Support Tools in the Differential Diagnosis of Salivary Gland Tumors through Inflammatory Biomarkers and Radiomics Metrics: A Preliminary Study.

BACKGROUND: The purpose of this study was to investigate how the systemic inflammation response index (SIRI), systemic immune-inflammation index (SII), neutrophil/lymphocyte ratio (NLR) and platelet/lymphocyte ratio (PLR), and radiomic metrics (quantitative descriptors of image content) extracted from MRI sequences by machine learning increase the efficacy of proper presurgical differentiation between benign and malignant salivary gland tumors. METHODS: A retrospective study of 117 patients with salivary gland tumors was conducted between January 2015 and November 2022. Univariate analyses with nonparametric tests and multivariate analyses with machine learning approaches were used. RESULTS: Inflammatory biomarkers showed statistically significant differences (p < 0.05) in the Kruskal-Wallis test based on median values in discriminating Warthin tumors from pleomorphic adenoma and malignancies. The accuracy of NLR, PLR, SII, and SIRI was 0.88, 0.74, 0.76, and 0.83, respectively. Analysis of radiomic metrics to discriminate Warthin tumors from pleomorphic adenoma and malignancies showed statistically significant differences (p < 0.05) in nine radiomic features. The best multivariate analysis result was obtained from an SVM model with 86% accuracy, 68% sensitivity, and 91% specificity for six features. CONCLUSIONS: Inflammatory biomarkers and radiomic features can comparably support a pre-surgical differential diagnosis.

Radiomics Applications in Head and Neck Tumor Imaging: A Narrative Review.

Recent advances in machine learning and artificial intelligence technology have ensured automated evaluation of medical images. As a result, quantifiable diagnostic and prognostic biomarkers have been created. We discuss radiomics applications for the head and neck region in this paper. Molecular characterization, categorization, prognosis and therapy recommendation are given special consideration. In a narrative manner, we outline the fundamental technological principles, the overall idea and usual workflow of radiomic analysis and what seem to be the present and potential challenges in normal clinical practice. Clinical oncology intends for all of this to ensure informed decision support for personalized and useful cancer treatment. Head and neck cancers present a unique set of diagnostic and therapeutic challenges. These challenges are brought on by the complicated anatomy and heterogeneity of the area under investigation. Radiomics has the potential to address these barriers. Future research must be interdisciplinary and focus on the study of certain oncologic functions and outcomes, with external validation and multi-institutional cooperation in order to achieve this.

MRI and steroid-responsive encephalopathy associated with autoimmune thyroiditis: first report of conus medullaris involvement and literature review of the known neuroimaging profiles.

BACKGROUND: Steroid-responsive encephalopathy associated with autoimmune thyroiditis (SREAT) is a rare but potentially reversible autoimmune encephalopathy. The most frequent neuroimaging correlates are normal brain MRI or non-specific white matter hyperintensities. METHODS: We present the first description of conus medullaris involvement, also providing an extensive review of MRI patterns described so far. RESULTS: Our results show that in less than 30% of cases, it is possible to find focal SREAT neuroanatomical correlates. Among these, T2w/FLAIR temporal hyperintensities are the most frequent, followed by basal ganglia/thalamic and brainstem involvement, respectively. CONCLUSIONS: Unfortunately, spinal cord investigation is an uncommon practice in the diagnostic approach of encephalopathies, thus neglecting potential pathological lesions of the medulla spinalis. In our opinion, the extension of the MRI study to the cervical, thoracic, and lumbosacral regions may allow finding new, and hopefully specific, anatomical correlates.