Solitary fibrous tumors (SFTs) of the central nervous system occurring in the brain parenchyma are rare. We report an elderly female who presented with intermittent headaches and a solitary mass was noted in the right cerebellum that was misdiagnosed preoperatively as a hemangioblastoma. The postoperative pathologic diagnosis was a SFT. When an isolated mass appears in the cerebellar hemisphere with slight hyperdensity on CT images, heterogenous signals on T1WI and T2WI images, and a nodule with a hypointense signal on a T2WI image, the possibility of a SFT should be considered.

Alzheimer’s disease (AD) is the most common neurodegenerative brain disorder that is characterized by the deposition of amyloid-β protein (Aβ) and neurofibrillary aggregates (tau). There is currently no cure for AD; however, early diagnosis and intervention may prevent progression to dementia. In addition to CSF and blood biomarkers, imaging techniques, such as PET, fMRI, volumetric MRI, and chemical exchange saturation transfer (CEST), have facilitated the early diagnosis of AD and provided essential information about the pathophysiology of AD. Indeed, CEST findings have helped clarify important aspects of the pathophysiology underlying AD. In this article we provide an in-depth review of different CEST applications, including endogenous CEST (APT, creatine-CEST, and glutamate-CEST) and exogenous CEST (angiopep2, glucose, and glymphatic system-related CEST), in further elucidating the pathophysiology of AD and discuss the potential of novel approaches.

Background and Purpose: With the increasing prevalence of cerebrovascular risk factors in young adults, accurate differentiation of multiple sclerosis (MS) from cerebral small vessel disease (SVD) remains challenging because of the significant overlap in the appearance of white matter lesions on conventional magnetic resonance (MR) images. The purpose of this study was to use quantitative susceptibility mapping (QSM) to differentiate patients with MS from patients with SVD. Materials and Methods: Thirty-two patients with relapsing-remitting MS and 40 patients with SVD were selected in this institution review board-approved retrospective study. All patient examinations included QSM and T2-weighted FLAIR (T2w). All T2w hyperintense lesions were analyzed on QSM for susceptibility relative to normal-appearing white matter and were evaluated for the presence of hyperintense rims and the central vein sign. Receiver operating characteristic (ROC) curve analysis was performed to assess the diagnostic accuracy of differentiating MS patients from SVD patients. Results: The mean susceptibility value of SVD lesions was significantly lower than MS lesions (2.31 ± 9.68 ppb vs. 27.77 ± 20.27 ppb, p < 0.001). Of MS patients and MS lesions, 68.8% and 22.2% had hyperintense rims on QSM, respectively. Of MS patients and MS lesions, 75% and 37.6% had a central vein sign on QSM, respectively. Lesion susceptibility values allowed accurate differentiation MS from SVD with an area under the ROC curve (AUC) = 0.848 for lesion differentiation, AUC = 0.999 for patient differentiation, and an optimal cut-off susceptibility value of 14.88 ppb. Conclusions: Magnetic susceptibility measured using QSM allows accurate differentiation of MS patients from SVD patients.

Background: Radiomics and deep learning have been widely investigated in the quantitative analysis of medical images. Deep learning radiomics (DLR), combining the strengths of both methods, is increasingly used in head and neck cancer (HNC). This systematic review was aimed at evaluating existing studies and assessing the potential application of DLR in HNC prognosis. Materials and methods: The PubMed, Embase, Scopus, Web of Science, and Cochrane databases were searched for articles published in the past 10 years with the keywords “radiomics,” “deep learning,” and “head and neck cancer” (and synonyms). Two independent reviewers searched, screened, and reviewed the English literature. The methodological quality of each article was evaluated with the Radiomics Quality Score (RQS). Data from the studies were extracted and collected in tables. A systematic review of radiomics prognostic prediction models for HNC incorporating deep learning techniques is presented. Result: A total of eight studies, published in 2012–2022, with a varying number of patients (59–707 cases), were included. Each study used deep learning; three studies performed automatic segmentation of regions of interest (ROI), and the Dice score range for automatic segmentation was 0.75–0.81. Four studies involved extraction of deep learning features, one study combined different modality features, and two studies performed predictive model building. The range of the area under the curve (AUC) was 0.84–0.96, the range of the concordance index (C-index) was 0.72–0.82, and the range of model accuracy (ACC) was 0.72–0.96. The median total RQS for these studies was 13 (10–15), corresponding to a percentage of 36.11% (27.78%–41.67). Low scores were due to a lack of prospective design, cost-effectiveness analysis, detection and discussion of biologically relevant factors, and external validation. Conclusion: DLR has potential to improve model performance in HNC prognosis.

Cancers are the main cause of death worldwide. Assessment of tumors by imaging is key to formulating treatment plans. More noninvasive markers of imaging are needed to evaluate primary tumors and treatment responses to achieve individualized diagnosis and treatment. However, conventional image assessment has limitations based on differences in individual radiologists’ interpretation and inability to read hidden high-dimensional features. Artificial intelligence (AI) can provide quantitative, rather than qualitative, assessments based on radiographic characteristics, and has been frequently and successfully applied in the medical image analysis field. In this review, we summarize research progress in the use of AI for evaluating the diagnosis and treatment response of patients with common tumors, including gliomas, lung cancer, liver cancer and colorectal cancer. We further discuss several issues that must be solved in the future to make better use of AI in tumor diagnosis and assessment of treatment response.

As professional sports leagues have begun to recognize the detrimental short- and long-term impact of concussions, understanding the severity of concussions has taken on increasing importance. The ability to understand the microstructural and functional brain pathology of sports-related concussions (SRCs) has improved due to advances in neuroimaging. Advanced magnetic resonance imaging (MRI) techniques can now clearly show brain damage caused by concussions; however, little is known with respect to the link between brain damage and the long-term effects. This overview summarizes the potential association between advanced imaging findings and prognosis of SRCs. We found that diffusion tensor imaging, quantitative susceptibility mapping, neurite orientation dispersion and density imaging, perfusion weighted imaging, near-infrared spectroscopy, positron emission tomography, and functional MRI are promising technologies for providing objective prognostic information in patients with SRCs. Additional research is warranted to investigate the early imaging diagnosis of long-term effects, such as chronic traumatic encephalopathy and post-concussion syndrome.