• Journal of Biomedical Engineering Research
• /
• v.43 no.4
• /
• pp.259-270
• /
• 2022

Artificial intelligence (AI) has been studied in various fields of medical imaging. Currently, top-notch deep learning (DL) techniques have led to high diagnostic accuracy and fast computation. However, they are rarely used in real clinical practices because of a lack of reliability concerning their results. Most DL models can achieve high performance by extracting features from large volumes of data. However, increasing model complexity and nonlinearity turn such models into black boxes that are seldom accessible, interpretable, and transparent. As a result, scientific interest in the field of explainable artificial intelligence (XAI) is gradually emerging. This study aims to review diverse XAI approaches currently exploited in medical imaging. We identify the concepts of the methods, introduce studies applying them to imaging modalities such as computational tomography (CT), magnetic resonance imaging (MRI), and endoscopy, and lastly discuss limitations and challenges faced by XAI for future studies.

• Journal of Digestive Cancer Research
• /
• v.10 no.2
• /
• pp.56-64
• /
• 2022

Narrow-band imaging (NBI) is the most widely used image-enhanced endoscopic technique. The superficial microanatomy of gastric mucosa can be visualized when used with a magnifying endoscopy with narrow-band imaging (ME-NBI). The diagnostic criteria for early gastric cancer (EGC), using the classification system for microvascular and microsurface pattern of ME-NBI, have been developed, and their usefulness has been proven in the differential diagnosis of small depressed cancer from focal gastritis and in lateral extent delineation of EGC. Some studies reported on the prediction of histologic differentiation and invasion depth of gastric cancer using ME-NBI; however, its application is limited in clinical practice, and further well-designed studies are necessary. Clinicians should understand the ME-NBI classification system and acquire appropriate diagnostic skills through various experiences and training to improve the quality of endoscopy for EGC diagnosis.

• Korean Journal of Biological Psychiatry
• /
• v.18 no.2
• /
• pp.55-60
• /
• 2011

Neuroimaging studies in schizophrenia have remarkably increased and provided some clues to understand its pathophysiology. Here, we reviewed the neuroimaging, studies including volume analysis, functional magnetic resonance imaging (MRI) and diffusion tensor imaging, and findings in both early stage schizophrenia and high-risk group. The reviewed studies suggested that the brain with schizophrenia showed both regional deficits and dysconnectivity of neural circuit in the first episode, even high-risk group as well as chronic schizophrenia. Multimodal neuroimaging or combined approach with genetic, electro-or magneto-encephalographic data could provide promising results to understand schizophrenia in the near future.

• Applied Science and Convergence Technology
• /
• v.24 no.6
• /
• pp.203-214
• /
• 2015

We have been developing a new label-free nanobio imaging platform using non-linear optics such as Coherent Anti-Stokes Raman Spectroscopy (CARS) and ion beam techniques based on sputtering and scattering such as Secondary Ion Mass Spectrometry (SIMS) and Medium Energy Ion Scattering Spectroscopy (MEIS), which have been widely used for atomic and molecular level analysis of semiconductors and nanomaterials. To apply techniques developed for semiconductors and nanomaterials for biomedical applications, the convergence of nano-analysis and biology were tried. Our activities on label-free nanobio imaging during the last decade are summarized in this review about non-linear optical 3D imaging, ellipsometric interface imaging, SIMS imaging, and TOF-MEIS nano analysis for cardiovascular tissues, collagen thin films, peptides on microarray, nanoparticles, and cell adhesion studies and finally the present snapshot of nanobio imaging and the future prospect are described.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2013.02a
• /
• pp.113-114
• /
• 2013

Time-of-flight secondary ion mass spectrometry (TOF-SIMS) imaging is a powerful technique for producing chemical images of small biomolecules (ex. metabolites, lipids, peptides) "as received" because of its high molecular specificity, high surface sensitivity, and submicron spatial resolution. In addition, matrix-assisted laser desorption and ionization time-of-flight (MALDI-TOF) imaging is an essential technique for producing chemical images of large biomolecules (ex. genes and proteins). For this talk, we will show that label-free mass imaging technique can be a platform technology for biomedical studies such as early detection/diagnostics, accurate histologic diagnosis, prediction of clinical outcome, stem cell therapy, biosensors, nanomedicine and drug screening [1-7].

• Nuclear Medicine and Molecular Imaging
• /
• v.41 no.2
• /
• pp.158-165
• /
• 2007

Technological advances in molecular imaging made it possible to image synaptic neurotransmitter concentration in living human brain. The dopaminergic system has been most intensively studied because of its importance in neurological as well as psychiatric disorders. This paper provides a brief overview of recent progress in imaging studies of dopamine release induced by pharmacologic and nonpharmacologic stimulations.

• Korean Journal of Radiology
• /
• v.22 no.5
• /
• pp.840-860
• /
• 2021

Imaging plays a key role in the diagnosis and characterization of thyroid diseases, and the information provided by imaging studies is essential for management planning. A referral guideline for imaging studies may help physicians make reasonable decisions and minimize the number of unnecessary examinations. The Korean Society of Thyroid Radiology (KSThR) developed imaging guidelines for thyroid nodules and differentiated thyroid cancer using an adaptation process through a collaboration between the National Evidence-based Healthcare Collaborating Agency and the working group of KSThR, which is composed of radiologists specializing in thyroid imaging. When evidence is either insufficient or equivocal, expert opinion may supplement the available evidence for recommending imaging. Therefore, we suggest rating the appropriateness of imaging for specific clinical situations in this guideline.

• Journal of Biomedical Engineering Research
• /
• v.45 no.1
• /
• pp.26-36
• /
• 2024

Functional brain imaging techniques have been used to diagnose psychiatric disorders such as dementia, depression, and autism. Recently, these techniques have also been actively used to study hearing loss. The present study reviewed the application of the functional brain imaging techniques in auditory research, especially those focusing on hearing loss, over the past decade. EEG, fMRI, fNIRS, MEG, and PET have been utilized in auditory research, and the number of research studies using these techniques has been increasing. In particular, fMRI and EEG were the most frequently used technique in auditory research. EEG studies mostly used event-related designs to analyze the direct relationship between stimulus and the related response, and in fMRI studies, resting-state functional connectivity and block designs were utilized to analyze alterations in brain functionality in hearing-related areas. In terms of age, while studies involving children mainly focused on congenital and pre- and post-lingual hearing loss to analyze developmental characteristics with and without hearing loss, those involving adults focused on age-related hearing loss to investigate changes in the characteristics of the brain based on the presence of hearing loss and the use of a hearing device. Overall, ranging from EEG to PET, various functional brain imaging techniques have been used in auditory research, but it is difficult to perform a comprehensive analysis due to the lack of consistency in experimental designs, analysis methods, and participant characteristics. Thus, it is necessary to develop standardized research protocols to obtain high-quality clinical and research evidence.

• Journal of Biosystems Engineering
• /
• v.42 no.3
• /
• pp.199-216
• /
• 2017

Purpose: This study reviewed the major nondestructive measurement techniques used to assess internal properties of agricultural materials that significantly influence the quality, safety, and value of the products in markets. Methods: Imaging technologies are powerful nondestructive analytical tools that possess specific advantages in revealing the internal properties of products. Results: This review was exploring the application of various imaging techniques, specifically, hyperspectral imaging (HSI), magnetic resonance imaging (MRI), soft X-ray, X-ray computed tomography (XRI-CT), thermal imaging (TI), and ultrasound imaging (UI), to investigate the internal properties of agricultural commodities. Conclusions: The basic instruments used in these techniques are discussed in the initial part of the review. In the context of an investigation of the internal properties of agricultural products, including crops, fruits, vegetables, poultry, meat, fish, and seeds, various extant studies are examined to understand the potential of these imaging technologies. Future trends for these imaging techniques are also presented.

• Korean Journal of Radiology
• /
• v.21 no.12
• /
• pp.1345-1354
• /
• 2020

Objective: To evaluate radiomics analysis in studies on mild cognitive impairment (MCI) and Alzheimer's disease (AD) using a radiomics quality score (RQS) system to establish a roadmap for further improvement in clinical use. Materials and Methods: PubMed MEDLINE and EMBASE were searched using the terms 'cognitive impairment' or 'Alzheimer' or 'dementia' and 'radiomic' or 'texture' or 'radiogenomic' for articles published until March 2020. From 258 articles, 26 relevant original research articles were selected. Two neuroradiologists assessed the quality of the methodology according to the RQS. Adherence rates for the following six key domains were evaluated: image protocol and reproducibility, feature reduction and validation, biologic/clinical utility, performance index, high level of evidence, and open science. Results: The hippocampus was the most frequently analyzed (46.2%) anatomical structure. Of the 26 studies, 16 (61.5%) used an open source database (14 from Alzheimer's Disease Neuroimaging Initiative and 2 from Open Access Series of Imaging Studies). The mean RQS was 3.6 out of 36 (9.9%), and the basic adherence rate was 27.6%. Only one study (3.8%) performed external validation. The adherence rate was relatively high for reporting the imaging protocol (96.2%), multiple segmentation (76.9%), discrimination statistics (69.2%), and open science and data (65.4%) but low for conducting test-retest analysis (7.7%) and biologic correlation (3.8%). None of the studies stated potential clinical utility, conducted a phantom study, performed cut-off analysis or calibration statistics, was a prospective study, or conducted cost-effectiveness analysis, resulting in a low level of evidence. Conclusion: The quality of radiomics reporting in MCI and AD studies is suboptimal. Validation is necessary using external dataset, and improvements need to be made to feature reproducibility, feature selection, clinical utility, model performance index, and pursuits of a higher level of evidence.