Purpose: To identify US findings suggestive of malignancy in thyroid nodules with follicular lesions of undetermined significance (FLUS) or follicular neoplasm (FN) on fine-needle aspiration cytology (FNAC) and evaluate the diagnostic performance. Materials and Methods: Seventy FLUS (n = 57) or FN (n = 13) nodules on FNAC that underwent surgical excision between February 2018 and November 2020 were selected. US findings were retrospectively reviewed. Orientation, margin, echogenicity, calcification, additional findings of the rim, echogenicity, heterogeneity of the solid portion, and the ratio of anterior posterior diameter to lateral diameter (criteria) were assessed. The diagnostic performances of US findings, criteria, and the Korean Society of Thyroid Radiology Thyroid Imaging Reporting and Data System (K-TIRADS) were evaluated using logistic regression analysis. Results: Microcalcification, homogeneous solid echotexture, and thickened rims were suggestive of malignancy. Our criteria showed a highest area under the ROC curve (AUC) value of 0.771, sensitivity of 97.14%, accuracy of 77.14%, positive predictive value of 93.33%, negative predictive value of 95.24%, and specificity of 97.14%. The criteria showed a significantly higher AUC value than K-TIRADS. Conclusion US findings of homogenous solid portions, thick rims, and microcalcifications suggested malignancy in nodules with FLUS or FN on FNAC. These additional US findings could improve the diagnostic performance of K-TIRADS.

The introduction of anti-amyloid therapies for Alzheimer’s disease (AD), such as lecanemab (Lequembi®), which was recently approved in Korea, necessitates careful monitoring for amyloid-related imaging abnormalities (ARIA) using brain MRI. To optimize ARIA monitoring in Korean clinical settings, the Korean Society of Neuroradiology (KSNR) and the Age and Neurodegeneration Imaging (ANDI) Study Group proposed MRI protocol recommendations on essential MR sequences, MRI acquisition parameters, timing and condition of MRI examinations, and essential details to provide a scientific basis for maximizing the safety and efficacy of AD treatment. A customized, standardized MRI protocol focusing on Korea’s healthcare environment can improve ARIA management and ensure patient safety through early detection of potential anti-amyloid therapy side effects, thereby enhancing treatment quality.

Sclerosing angiomatoid nodular transformation (SANT) of the spleen is extremely rare in pediatric patients. Here, we report the case of an 8-year-old boy with iron-deficiency anemia and a solitary splenic mass detected using US, CT, and MRI. The patient underwent partial splenectomy, and the final diagnosis was SANT. Herein, we discuss the radiological features of splenic SANT through a review of reported cases and the differential diagnosis of other primary splenic tumors.

Multiple cranial neuropathies are complex neurological disorders that present significant treatment challenges due to their intricate and multifaceted underlying causes. Persistent trigeminal artery variant (PTAV) is an unusual anastomosis that connects the internal carotid artery to the cerebellar artery, bypassing the basilar artery. The incidence of PTAVs is approximately 0.18% and neurovascular compression is rarely reported. Patients with schwannomatosis typically have multiple schwannomas without vestibular nerve involvement, which may develop in the spinal nerve roots and, less commonly, in the cranial nerves. We report the case of a 53-year-old female with trigeminal neuralgia associated with PTAV and schwannomatosis in the abducens and lower cranial nerves as dual etiologies for multiple cranial neuropathies.

Mesenchymal tumors of the breast, which originate from the mammary stroma, are rare accounting for only approximately 0.5%–1% of all breast tumors. Pathologically, they can exist on a spectrum, ranging from benign to malignant. Such tumors may present with nonspecific findings on breast imaging, including mammography, ultrasound, and MRI, which can lead to diagnostic challenges. In the 2019 revised 5th edition of the World Health Organization classification, breast mesenchymal tumors are categorized into six groups. The current pictorial essay aimed to explore the clinical, pathological, and imaging characteristics of representative lesions in each category according to this six-group classification, with the ultimate goal of enhancing awareness for early diagnosis.

Breast cancer is the most common cancer in women worldwide, and its early detection is critical for improving survival outcomes. As a diagnostic and screening tool, mammography can be less effective owing to the masking effect of fibroglandular tissue, but breast US has good sensitivity even in dense breasts. However, breast US is highly operator dependent, highlighting the need for artificial intelligence (AI)-driven solutions. Unlike other modalities, US is performed using a handheld device that produces a continuous real-time video stream, yielding 12000–48000 frames per examination. This can be significantly challenging for AI development and requires real-time AI inference capabilities. In this review, we classified AI solutions as computer-aided diagnosis and computer-aided detection to facilitate a functional understanding and review commercial software supported by clinical evidence.In addition, to bridge healthcare gaps and enhance patient outcomes in geographically under resourced areas, we propose a novel framework by reviewing the existing AI-based triage workflows including mobile ultrasound.

Digital breast tomosynthesis (DBT) provides improved cancer detection and lower recall rates when compared with full-field digital mammography (DM) and has been widely adopted for breast cancer screening. However, adopting DBT presents new challenges such as an increased number of acquired images resulting in longer interpretation times. Artificial intelligence (AI) offers numerous opportunities to enhance the advantages of DBT and mitigate its shortcomings. Research in the DBT AI domain has grown significantly and AI algorithms play a key role in the screening and diagnostic phases of breast cancer detection and characterization. The application of AI may streamline the workflow and reduce the time required for radiologists to interpret images. In addition, AI can minimize radiation exposure and enhance lesion visibility in synthetic two-dimensional DM images. This review provides an overview of AI technology in DBT, its clinical applications, and future considerations.

Rosai-Dorfman disease (RDD) is an uncommon proliferative histiocytic disorder of unknown etiology typically presenting as massive lymphadenopathy, and in some cases, with extranodal involvement. However, serous membranes are rarely involved in extranodal RDDs, and reports regarding pericardial involvement are scarce. Herein, we report a case of extranodal RDD manifesting as diffuse pericardial thickening and effusion in a 79-year-old man with monoclonal gammopathy. The patient complained of dyspnea, hence chest CT and PET scans were performed. They showed irregular thickening of the pericardium with a marked increase in metabolic activity. Pericardial biopsy showed the characteristic S100-positive and CD68-positive histiocytes exhibiting emperipolesis. The disease progressively evolved to bilateral pleural thickening with effusion of the pericardium, and finally led to death even with corticosteroid treatment. Although exceedingly rare, this case demonstrates the importance of RDD in the differential diagnosis of effusion in serous cavities based on imaging findings.

Background: This study was performed to compare the thickness of the ganglion cell-inner plexiform layer (GCIPL) depending on the presence or absence of fixation preference in patients with intermittent exotropia (IXT) with refractive values close to emmetropia and with no amblyopia. Methods: The study recruited pediatric patients diagnosed with IXT with a spherical equivalent within ±1.25 diopter and no amblyopia. The patients were categorized into two groups: a monocular exotropia group with fixation preference and an alternating exotropia group without fixation preference. GCIPL thickness was measured using spectral domain optical coherence tomography, and the macula was divided into nine sectors according to the Early Treatment Diabetic Retinopathy Study (ETDRS). GCIPL thickness in each sector was compared between the monocular and alternating exotropia groups. Results: In the monocular exotropia group, GCIPL thickness was significantly thinner in the dominant eye than in the nondominant eye in the S1 sector (91.2±7.4 μm vs. 93.3±5.2 μm, p=0.019). However, in the alternating exotropia group, there were no significant differences between the eyes across all ETDRS sectors. When comparing the interocular differences in GCIPL thickness between the two groups, the monocular exotropia group (absolute value of the dominant eye minus the nondominant eye) exhibited significantly greater differences in several ETDRS sectors than the alternating exotropia group (absolute value of the right eye minus the left eye). Conclusion The significant interocular difference in GCIPL thickness in the monocular exotropia group suggests that fixation preference may influence the anatomical structure of the macula in patients with IXT.