Publications by authors named "Se Jin Cho"
Objective: Ultrasound-guided thermal ablation, including radiofrequency ablation (RFA) and microwave ablation (MWA), has become one of the main options for treating benign thyroid nodules (BTNs). To assess the efficacy of thermal ablation of BTNs, we performed a systematic review and meta-analysis of relevant studies.
Materials And Methods: A comprehensive search of MEDLINE, EMBASE, and COCHRANE databases was performed up to September 25, 2023, to identify studies directly comparing RFA and MWA for pathologically proven BTNs and reporting clinical outcomes and complications.
We developed artificial intelligence models to predict the brain metastasis (BM) treatment response after stereotactic radiosurgery (SRS) using longitudinal magnetic resonance imaging (MRI) data and evaluated prediction accuracy changes according to the number of sequential MRI scans. We included four sequential MRI scans for 194 patients with BM and 369 target lesions for the Developmental dataset. The data were randomly split (8:2 ratio) for training and testing.
View Article and Find Full Text PDFBackground And Purpose: Intracranial steno-occlusive lesions are responsible for acute ischemic stroke. However, the clinical benefits of artificial intelligence (AI)-based methods for detecting pathologic lesions in intracranial arteries have not been evaluated. We aimed to validate the clinical utility of an AI model for detecting steno-occlusive lesions in the intracranial arteries.
View Article and Find Full Text PDFIntroduction: Glymphatic dysfunction can contribute to α-synucleinopathies. We examined glymphatic function in idiopathic Parkinson's disease (PD) utilizing Diffusion Tensor Image Analysis aLong the Perivascular Space (DTI-ALPS).
Methods: This study enrolled consecutive patients diagnosed with de novo PD between June 2017 and March 2019 who underwent brain DTI with concurrent I-2β-carbomethoxy-3β-(4-iodophenyl)-N-(3-fluoropropyl)-nortropane (I-FP-CIT) SPECT, and age- and sex-matched controls.
Article Synopsis
- Researchers combined advanced brain imaging techniques—susceptibility-weighted imaging (SWI) and SPECT—to evaluate Parkinsonism by analyzing nigrosome-1 and dopamine transporter activity.
- A deep-learning model was developed to predict striatal I-FP-CIT uptake from nigrosome MRI, using data from 367 participants, with a focus on the relationship between nigral hyperintensity and dopamine levels.
- The results demonstrated a strong correlation between predicted and actual dopamine uptake measurements, validating the model as a reliable tool for assessing Parkinsonism.
Background Brain glymphatic dysfunction may contribute to the development of α-synucleinopathies. Yet, noninvasive imaging and quantification remain lacking. Purpose To examine glymphatic function of the brain in isolated rapid eye movement sleep behavior disorder (RBD) and its relevance to phenoconversion with use of diffusion-tensor imaging (DTI) analysis along the perivascular space (ALPS).
View Article and Find Full Text PDFObjective: We aimed to investigate current expectations and clinical adoption of artificial intelligence (AI) software among neuroradiologists in Korea.
Materials And Methods: In April 2022, a 30-item online survey was conducted by neuroradiologists from the Korean Society of Neuroradiology (KSNR) to assess current user experiences, perceptions, attitudes, and future expectations regarding AI for neuro-applications. Respondents with experience in AI software were further investigated in terms of the number and type of software used, period of use, clinical usefulness, and future scope.
To train an automatic brain tumor segmentation model, a large amount of data is required. In this paper, we proposed a strategy to overcome the limited amount of clinically collected magnetic resonance image (MRI) data regarding meningiomas by pre-training a model using a larger public dataset of MRIs of gliomas and augmenting our meningioma training set with normal brain MRIs. Pre-operative MRIs of 91 meningioma patients (171 MRIs) and 10 non-meningioma patients (normal brains) were collected between 2016 and 2019.
View Article and Find Full Text PDFArticle Synopsis
- The study explores the challenges in timely diagnosis of Alzheimer's disease (AD) due to limited specialist access, highlighting the potential of a deep learning algorithm, VUNO Med-DeepBrain AD (DBAD), as a decision support tool.
- By evaluating 98 elderly participants, the study compares the diagnostic accuracy of DBAD with medical experts (ME) using MRI scans, finding DBAD performed slightly better in accuracy, sensitivity, and specificity.
- The findings suggest that DBAD could assist non-specialist physicians in diagnosing AD, potentially improving access to timely diagnosis and treatment for patients.
[MRI Findings in Parkinson's Disease: Radiologic Assessment of Nigrostriatal Degeneration].
Taehan Yongsang Uihakhoe Chi
May 2022
Article Synopsis
- Parkinson's disease (PD) is a movement disorder caused by the loss of dopamine-producing cells in a specific area of the brain called the substantia nigra.
- Recent advances in MRI technology have revealed various imaging features that can help identify the disease and differentiate it from similar disorders.
- The review discusses MRI techniques like nigrosome and neuromelanin imaging, highlighting how these methods illustrate the degeneration of the nigrostriatal pathway associated with Parkinson's disease.
Background: The glymphatic system has been described as one that facilitates the exchange between the cerebrospinal fluid (CSF) and interstitial fluid, and many recent studies have demonstrated glymphatic flow based on magnetic resonance imaging (MRI). We aim to systematically review the studies demonstrating a normal glymphatic flow in a human population using MRI and to propose a detailed glymphatic imaging protocol.
Methods: We searched the MEDLINE and EMBASE databases to identify studies with human participants involving MRI-based demonstrations of the normal glymphatic flow.
Background: The T2-fluid-attenuated inversion recovery (FLAIR) mismatch sign, has been considered a highly specific imaging biomarker of IDH-mutant, 1p/19q noncodeleted low-grade glioma. This systematic review and meta-analysis aimed to evaluate the diagnostic performance of T2-FLAIR mismatch sign for prediction of a patient with IDH-mutant, 1p/19q noncodeleted low-grade glioma, and identify the causes responsible for the heterogeneity across the included studies.
Methods: A systematic literature search in the Ovid-MEDLINE and EMBASE databases was performed for studies reporting the relevant topic before November 17, 2020.
Granulomatosis with polyangiitis (GPA) can involve the skull base or the Eustachian tubes. GPA is diagnosed on the basis of clinical manifestations and serological tests, although it is challenging to discriminate GPA from infectious processes driving skull base osteomyelitis (SBO) and malignant processes such as nasopharyngeal carcinoma (NPC). Moreover, current serological tests have a low sensitivity and cannot distinguish GPA from these other conditions.
View Article and Find Full Text PDFArticle Synopsis
- A retrospective study aimed to create a computer-aided detection (CAD) system that uses deep learning to automate the detection of brain metastases (BMs) and evaluate treatment responses, addressing the need for more efficient assessments in this challenging area.
- The study analyzed 214 MRI exams from 147 patients, separating the data into training, testing, and external validation sets to rigorously assess the CAD's performance against radiologists.
- Results indicated that the CAD system demonstrated varying sensitivity levels (75.1% to 94.7%) and moderate to substantial agreement with the established RANO-BM criteria, showing promise in effectively identifying BMs larger than 5 mm.
Article Synopsis
- The study compares the effectiveness and safety of thermal ablation and surgery for treating low-risk papillary thyroid microcarcinomas (PTMCs), as prior systematic evaluations were lacking.
- A review of four studies was conducted, involving a total of 659 patients, and results showed no local recurrence or distant metastasis in either treatment group.
- Although both methods are effective, thermal ablation had a significantly lower complication rate (3.3%) compared to surgery (7.8%), suggesting it could be a preferable option for patients who cannot or choose not to undergo surgery.
Background: Classification of true progression from nonprogression (eg, radiation-necrosis) after stereotactic radiotherapy/radiosurgery of brain metastasis is known to be a challenging diagnostic task on conventional magnetic resonance imaging (MRI). The scope and status of research using artificial intelligence (AI) on classifying true progression are yet unknown.
Methods: We performed a systematic literature search of MEDLINE and EMBASE databases to identify studies that investigated the performance of AI-assisted MRI in classifying true progression after stereotactic radiotherapy/radiosurgery of brain metastasis, published before November 11, 2020.
Parkinson disease is characterized by dopaminergic cell loss in the substantia nigra of the midbrain. There are various imaging markers for Parkinson disease. Recent advances in MRI have enabled elucidation of the underlying pathophysiologic changes in the nigral structure.
View Article and Find Full Text PDFObjective: To evaluate the diagnostic performance of iron-sensitive sequences targeting the substantia nigra for distinguishing patients with Parkinson's disease from control participants and to identify factors causing heterogeneity.
Methods: A systematic literature search in the Ovid-MEDLINE and EMBASE databases was performed for studies reporting the relevant topic before March 6, 2020. The pooled sensitivity and specificity values with their 95% confidence intervals were calculated using bivariate random-effects modeling.
This systematic review and meta-analysis aimed to evaluate the pooled proportion of image findings of acute to subacute craniocervical arterial dissection (AD) direct signs on magnetic resonance vessel wall imaging (MR-VWI) and to identify factors responsible for the heterogeneity across the included studies. A systematic literature search in the Ovid-MEDLINE and EMBASE databases was performed for studies published on the relevant topic before April 14, 2020. Pooled sensitivity and specificity values and their 95% confidence intervals (CIs) were calculated using bivariate random-effects modeling.
View Article and Find Full Text PDFArticle Synopsis
- The study aimed to assess the effectiveness of the open mouth maneuver and Metal Artifact Reduction for orthopedic implants (O-MAR) in improving CT scans of the oral cavity and oropharynx.
- A total of 59 subjects underwent both conventional and open mouth CT scans, with images evaluated for noise levels and visual quality across various regions.
- Results showed that the open mouth technique generally improved image quality in some areas, but in others, it increased noise and decreased visual scores, indicating that the techniques impact image quality differently depending on the specific anatomical site.
Objectives: Confidence in long-term treatment results of thermal ablation for papillary thyroid microcarcinoma (PTMC) is required in comparison with active surveillance. The objective of this meta-analysis is to report 5-year follow-up results of thermal ablation for PTMC.
Methods: Ovid MEDLINE and EMBASE databases were searched through May 30, 2020, for studies reporting outcomes in patients with PTMC treated with thermal ablation and followed up for at least 5 years.
Objectives: More clear classification of chronic invasive fungal infection of paranasal sinuses in the clinical presentation, radiologic findings, and pathology is needed. To describe the imaging findings of patients with chronic invasive fungal sinusitis (CIFS) and chronic granulomatous invasive fungal sinusitis (CGIFS).
Methods: Eleven patients with CIFS or CGIFS between January 2014 and July 2019 were included in this retrospective study.
Article Synopsis
- The study aimed to improve the diagnosis of frontal, ethmoid, and maxillary sinusitis using a deep learning algorithm that analyzes Waters' and Caldwell view radiographs, which are often difficult to interpret.
- The algorithm was trained on a dataset of over 1,400 cases, achieving notable diagnostic accuracy with area under the curve (AUC) values of 0.71 to 0.88 for different types of sinusitis, outperforming radiologists for certain conditions.
- The findings suggest that this deep learning model can serve as an effective first-line tool for assessing sinusitis, demonstrating better performance compared to traditional single-view methods.
Altered glymphatic system in idiopathic normal pressure hydrocephalus.
Parkinsonism Relat Disord
January 2021
Objective: To assess the glymphatic activity in patients with idiopathic normal pressure hydrocephalus (NPH) using the "Diffusion Tensor Image-Analysis aLong the Perivascular Space (DTI-ALPS)" method, and determine the feasibility of non-invasive MRI for the evaluation of the glymphatic function.
Methods: Between April 2017 and March 2019, 16 patients diagnosed with NPH and 16 age- and sex-matched controls were included. On 3T DTI-MRI, the diffusivities along x-, y-, and z-axes were measured, and the ALPS-index - a ratio that accentuated water diffusion along the perivascular space - was calculated by two independent readers.