2024 Consensus Statement on Coronary Stenosis and Plaque Evaluation in CT Angiography From the Asian Society of Cardiovascular Imaging-Practical Tutorial (ASCI-PT).

The Asian Society of Cardiovascular Imaging-Practical Tutorial (ASCI-PT) is an instructional initiative of the ASCI School designed to enhance educational standards. In 2021, the ASCI-PT was convened with the goal of formulating a consensus statement on the assessment of coronary stenosis and coronary plaque using coronary CT angiography (CCTA). Nineteen experts from four countries conducted thorough reviews of current guidelines and deliberated on eight key issues to refine the process and improve the clarity of reporting CCTA findings. The experts engaged in both online and on-site sessions to establish a unified agreement. This document presents a summary of the ASCI-PT 2021 deliberations and offers a comprehensive consensus statement on the evaluation of coronary stenosis and coronary plaque in CCTA.

Strategies to Modulate the Copper Oxidation State Toward Selective C2+ Production in the Electrochemical CO2 Reduction Reaction.

The electrochemical reduction of CO2 to form value-added chemicals receives considerable attention in recent years. Copper (Cu) is recognized as the only element capable of electro-reducing CO2 into hydrocarbons with two or more carbon atoms (C2+), but the low product selectivity of the Cu-based catalyst remains a major technological challenge to overcome. Therefore, identification of the structural features of Cu-based catalysts is of great importance for the highly selective production of C2+ products (ethylene, ethanol, n-propanol, etc.), and the oxidation state of Cu species in the catalysts is found critical to the catalyst performance. This review introduces recent efforts to fine-tune the oxidation state of Cu to increase carbon capture and produce specific C2+ compounds, with the intention of greatly expediting the advance in the catalyst designs. It also points to the remaining challenges and fruitful research directions for the development of Cu-based catalysts that can shape the practical CO2 reduction technology.

Stable 1T-MoS2 by Facile Phase Transition Synthesis for Efficient Electrocatalytic Oxygen Evolution Reaction.

The 1T phase of MoS2 exhibits much higher electrocatalytic activity and better stability than the 2H phase. However, the harsh conditions of 1T phase synthesis remain a significant challenge for various extensions and applications of MoS2 . In this work, a simple hydrothermal-based synthesis method for the phase transition of MoS2 is being developed. For this, the NH2 -MIL-125(Ti) (Ti MOF) is successfully utilized to induce the phase transition of MoS2 from 2H to 1T, achieving a high conversion ratio of ≈78.3%. The optimum phase-induced MoS2 /Ti MOF heterostructure demonstrates enhanced oxygen evolution reaction (OER) performance, showing an overpotential of 290 mV at a current density of 10 mA cm-2 . The density functional theory (DFT) calculations are demonstrating the benefits of this phase transition, determining the electronic properties and OER performance of MoS2 .

An Amiable Design of Cobalt Single Atoms as the Active Sites for Oxygen Evolution Reaction in Desalinated Seawater.

Green fuel from water splitting is hardcore for future generations, and the limited source of fresh water (<1%) is a bottleneck. Seawater cannot be used directly as a feedstock in current electrolyzer techniques. Until now single atom catalysts were reported by many synthetic strategies using notorious chemicals and harsh conditions. A cobalt single-atom (CoSA) intruding cobalt oxide ultrasmall nanoparticle (Co3 O4 USNP)-intercalated porous carbon (PC) (CoSA-Co3 O4 @PC) electrocatalyst was synthesized from the waste orange peel as a single feedstock (solvent/template). The extended X-ray absorption fine structure spectroscopy (EXAFS) and theoretical fitting reveal a clear picture of the coordination environment of the CoSA sites (CoSA-Co3 O4 and CoSA-N4 in PC). To impede the direct seawater corrosion and chlorine evolution the seawater has been desalinated (Dseawater) with minimal cost and the obtained PC is used as an adsorbent in this process. CoSA-Co3 O4 @PC shows high oxygen evolution reaction (OER) activity in transitional metal impurity-free (TMIF) 1 M KOH and alkaline Dseawater. CoSA-Co3 O4 @PC exhibits mass activity that is 15 times higher than the commercial RuO2 . Theoretical interpretations suggest that the optimized CoSA sites in Co3 O4 USNPs reduce the energy barrier for alkaline water dissociation and simultaneously trigger an excellent OER followed by an adsorbate evolution mechanism (AEM).

Deterministic Synthesis of Pd Nanocrystals Enclosed by High-Index Facets and Their Enhanced Activity toward Formic Acid Oxidation.

Noble-metal nanocrystals enclosed by high-index facets are of growing interest due to their enhanced catalytic performance in a variety of reactions. Herein, we report the deterministic synthesis of Pd nanocrystals encased by high-index facets by controlling the rate of deposition (Vdeposition) relative to that of surface diffusion (Vdiffusion). For octahedral seeds with truncated corners, a reduction rate (and thus deposition rate) faster than that of surface diffusion (i.e., Vdeposition/Vdiffusion > 1) led to the formation of concave trisoctahedra (TOH) with high-index facets. When the reduction was slowed down, in contrast, surface diffusion dominated the growth pathway. In the case of Vdeposition/Vdiffusion ≈ 1, truncated octahedra with enlarged sizes were produced. When the reduction rate was between these two extremes, we obtained concave tetrahexahedra (THH) without or with truncation. Similar growth patterns were also observed for the cuboctahedral seeds. When the Pd octahedra, concave TOH, and concave THH were tested for electrocatalyzing the formic acid oxidation (FAO) reaction, those with high-index facets were advantageous over the conventional Pd octahedra enclosed by {111} facets. This work not only contributes to the understanding of surface diffusion and its role in nanocrystal growth but also offers a general protocol for the synthesis of nanocrystals enclosed by high-index facets.

Electrochemically Activatable Liquid Organic Hydrogen Carriers and Their Applications.

Hydrogen has been chosen as an environmentally benign energy source to replace fossil-fuel-based energy systems. Since hydrogen is difficult to store and transport in its gaseous phase, thermochemical liquid organic hydrogen carriers (LOHCs) have been developed as one of the alternative technologies. However, the high temperature and pressure requirements of thermochemical LOHC systems result in huge energy waste and impracticality. This Perspective proposes electrochemical (EC)-LOHCs capable of more efficient, safer, and lower temperature and pressure hydrogen storage/utilization. To enable this technology, several EC-LOHC candidates such as isopropanol, phenolic compounds, and organic acids are described, and the latest research trends and design concepts of related homo/hetero-based electrocatalysts are discussed. In addition, we propose efficient fuel-cell-based systems that implement electrochemical (de)hydrogenation of EC-LOHCs and present prospects for relevant technologies.

Incidence and Clinicopathological Features of Differentiated High-Grade Thyroid Carcinomas: An Institutional Experience.

Differentiated high-grade thyroid carcinoma (DHGTC) is a new entity in the 2022 WHO classification. We aimed to investigate the incidence and clinicopathological features of differentiated HG thyroid carcinoma (DHGTC) and compare the clinicopathological parameters of DHGTC, DTC without HG features, and poorly differentiated thyroid carcinoma (PDTC). A total of 1069 DTCs including papillary thyroid carcinomas (PTCs) and follicular thyroid carcinomas (FTCs) were included in this study. Consecutive 22 PDTCs were also included for comparative purposes. There were a total of 14 (1.3%) cases of DHGTCs, with 13 HGPTCs (1.2% of PTCs) and one HGFTC (6.7% of FTCs). Compared to DTCs without HG features, DHGTCs were associated with larger tumor size, presence of blood vessel invasion, gross extrathyroidal extension, distant metastasis at the time of diagnosis, higher American Joint Committee on Cancer stage, high American Thyroid Association risk, and TERT promoter mutations. DHGTC and PDTC showed a significantly shorter recurrence-free survival (RFS) than DTC without HG features. Multivariate Cox regression analysis revealed that blood vessel invasion, lateral node metastasis, TERT promoter mutations, and HG features were independent prognostic factors (all p < 0.05). When tumor necrosis and increased mitotic count were evaluated separately, tumor necrosis, but not increased mitotic counts, was found to be an independent prognostic factor (p = 0.006). This study confirmed that DHGTC is significantly associated with aggressive clinicopathological features and poor clinical outcomes, similar to PDTC. Although the incidence is low, careful microscopic examination of HG features in DTC is required.

Surface distortion of FeRu nanoparticles improves the hydrogen evolution reaction performance in alkaline media.

Rational design of electrocatalysts, including an increased catalytic surface area, a unique surface structure, and improved conductivity, for facilitating the hydrogen evolution reaction (HER) is emerging as an important issue. In this work, we consider the engineering of catalyst surfaces as an effective and feasible way to accelerate the HER kinetics. By etching the surface Fe of FeRu alloy nanoparticles (NPs) using hydrofluoric acid (HF), a distorted catalytic surface of FeRu NPs was formed. The distorted surface of the HF-treated FeRu NPs was successfully analyzed by X-ray absorption spectroscopy, high-resolution photoemission spectroscopy, and electrochemical absorption/desorption experiments. The electrocatalytic HER activity of the HF-treated FeRu NPs demonstrated that surface distortion enhances the water dissociation reaction and the electron transfer rate. As a result, the surface-distorted FeRu NPs improved HER performances in alkaline media compared to the pristine FeRu alloy NP/C, commercial Ru/C, and the state-of-the-art Pt/C catalysts.

BRAFV600E and TERT promoter C228T mutations on ThyroSeq v3 analysis of delayed skin metastasis from papillary thyroid cancer: a case report and literature review.

BACKGROUND: Skin metastasis from papillary thyroid cancer (PTC) is a rare entity that can occur up to decades after treatment of the primary tumor. Here, we present a patient who developed skin metastasis 10 years after treatment of her primary tumor and describe the molecular findings of the metastatic lesion. CASE PRESENTATION: A 44-year-old female with a history of PTC who underwent a total thyroidectomy and radioactive iodine (RAI) treatment 10 years ago presented with a 1.3-cm skin lesion along the prior thyroidectomy scar. A biopsy revealed metastatic PTC, and the patient underwent surgical excision of the lesion. ThyroSeq molecular testing showed the copresence of BRAFV600E mutation and TERT promoter C228T mutation. The patient subsequently received one round of adjuvant RAI therapy. CONCLUSIONS: A high index of suspicion is warranted in patients with a history of PTC who develop a skin lesion, even several years after remission of the primary disease. In patients with high-risk mutations, such as BRAFV600E and TERT promoter C228T mutations, long-term surveillance of disease recurrence is particularly important.

Explainable gait recognition with prototyping encoder-decoder.

Human gait is a unique behavioral characteristic that can be used to recognize individuals. Collecting gait information widely by the means of wearable devices and recognizing people by the data has become a topic of research. While most prior studies collected gait information using inertial measurement units, we gather the data from 40 people using insoles, including pressure sensors, and precisely identify the gait phases from the long time series using the pressure data. In terms of recognizing people, there have been a few recent studies on neural network-based approaches for solving the open set gait recognition problem using wearable devices. Typically, these approaches determine decision boundaries in the latent space with a limited number of samples. Motivated by the fact that such methods are sensitive to the values of hyper-parameters, as our first contribution, we propose a new network model that is less sensitive to changes in the values using a new prototyping encoder-decoder network architecture. As our second contribution, to overcome the inherent limitations due to the lack of transparency and interpretability of neural networks, we propose a new module that enables us to analyze which part of the input is relevant to the overall recognition performance using explainable tools such as sensitivity analysis (SA) and layer-wise relevance propagation (LRP).

Achieving complete electrooxidation of ethanol by single atomic Rh decoration of Pt nanocubes.

SignificanceDirect ethanol fuel cells are attracting growing attention as portable power sources due to their advantages such as higher mass-energy density than hydrogen and less toxicity than methanol. However, it is challenging to achieve the complete electrooxidation to generate 12 electrons per ethanol, resulting in a low fuel utilization efficiency. This manuscript reports the complete ethanol electrooxidation by engineering efficient catalysts via single-atom modification. The combined electrochemical measurements, in situ characterization, and density functional theory calculations unravel synergistic effects of single Rh atoms and Pt nanocubes and identify reaction pathways leading to the selective C-C bond cleavage to oxidize ethanol to CO2. This study provides a unique single-atom approach to tune the activity and selectivity toward complicated electrocatalytic reactions.

Better survival of patients with hepatitis B virus-related hepatocellular carcinoma in South Korea: Changes in 16-years cohorts.

AIMS: The incidence and mortality of hepatocellular carcinoma (HCC) have decreased over time in South Korea, where hepatitis B virus (HBV) in endemic. This study investigated the changes in the characteristics and clinical outcomes of HCC patients in Korea. METHODS: Patients initially diagnosed with HCC and treated at the National Cancer Center, Korea between 2000 and 2015 (n = 4,291) were followed up until February 2017. Differences in patient characteristics and outcomes were compared between chronological cohorts: cohort A (2000-2004, n = 1,157) vs. B (2005-2009, n = 1,678) vs. C (2010-2015, n = 1,456). RESULTS: The median age of the patient cohort was 57 years (range, 13-98 years), and male predominance was noted (81.6%). HBV infection was the most common etiology (74.8%). The proportion of patients diagnosed with good liver function and small tumors (<2 cm) increased significantly over time: 74.6%, 79.9%, and 87.4% for Child-Pugh class A (p<0.001) and 8.0%, 8.5%, and 12.0% for modified UICC stage I (p<0.001) in cohorts A, B, and C, respectively. Median overall survival improved significantly over time: 14.4 months (95% confidence interval [CI], 12.0-16.8 months), 22.9 months (95% CI, 20.3-25.5 months), and 53.6 months (95% CI, 45.7-61.5 months) in cohorts A, B, and C, respectively. HBV-related patients showed significantly improved survival (12.7 vs. 20.4 vs. 64.5 months, p<0.001) associated with the use of antiviral treatments (adjusted hazard ratio, 0.72; 95% CI, 0.64-0.80). CONCLUSIONS: The survival of patients with HCC, especially HBV-related HCC, has improved significantly over time in Korea.

Clinicopathological indicators for TERT promoter mutation in papillary thyroid carcinoma.

OBJECTIVE: Mutations in the telomerase reverse transcriptase (TERT) promoter have been reported as a convincing prognostic factor in papillary thyroid carcinomas (PTCs). We aimed to investigate the frequency of TERT promoter mutations in patients with thyroid cancer and identify the clinicopathological factors associated with them in PTCs. DESIGN: A total of 1086 consecutive cases of thyroid cancer composed of mostly PTCs were included in this study. TERT promoter and BRAF mutations were detected by pyrosequencing and their associations with clinicopathological features of tumour were analyzed. RESULTS: TERT promoter mutations were observed in 1.9% of PTCs, 6.7% of follicular thyroid carcinomas, 8.3% of Hurthle cell carcinomas and 25.0% of poorly differentiated thyroid carcinomas and in a single case of anaplastic thyroid carcinoma. In PTCs, aggressive clinicopathological features, higher stage and BRAF V600E mutation were all found to be associated with TERT promoter mutations. Distant metastasis and disease recurrence were more frequent in TERT promoter-mutated PTCs. In multivariate analysis, age ≥55 years, tall cell variant, mitoses ≥3/10 high-power fields, tumour necrosis, and gross extrathyroidal extension (ETE) were identified as independent factors associated with TERT promoter mutations in PTCs. CONCLUSIONS: This study revealed a relatively low frequency of TERT promoter mutations in Korean patients with PTC. Certain clinicopathological features including old age, tall cell variant, increased mitoses, tumour necrosis and gross ETE were found to be indicative of TERT promoter mutations in PTCs, suggesting that mutational analysis in a particular group of PTCs can be effective in regions with low mutation rates.

Semi-Quantitative Scoring of Late Gadolinium Enhancement of the Left Ventricle in Patients with Ischemic Cardiomyopathy: Improving Interobserver Reliability and Agreement Using Consensus Guidance from the Asian Society of Cardiovascular Imaging-Practical Tutorial (ASCI-PT) 2020.

OBJECTIVE: This study aimed to evaluate the effect of implementing the consensus statement from the Asian Society of Cardiovascular Imaging-Practical Tutorial 2020 (ASCI-PT 2020) on the reliability of cardiac MR with late gadolinium enhancement (CMR-LGE) myocardial viability scoring between observers in the context of ischemic cardiomyopathy. MATERIALS AND METHODS: A total of 17 cardiovascular imaging experts from five different countries evaluated CMR obtained in 26 patients (male:female, 23:3; median age [interquartile range], 55.5 years [50-61.8]) with ischemic cardiomyopathy. For LGE scoring, based on the 17 segments, the extent of LGE in each segment was graded using a five-point scoring system ranging from 0 to 4 before and after exposure according to the consensus statement. All scoring was performed via web-based review. Scores for slices, vascular territories, and total scores were obtained as the sum of the relevant segmental scores. Interobserver reliability for segment scores was assessed using Fleiss' kappa, while the intraclass correlation coefficient (ICC) was used for slice score, vascular territory score, and total score. Inter-observer agreement was assessed using the limits of agreement from the mean (LoA). RESULTS: Interobserver reliability (Fleiss' kappa) in each segment ranged 0.242-0.662 before the consensus and increased to 0.301-0.774 after the consensus. The interobserver reliability (ICC) for each slice, each vascular territory, and total score increased after the consensus (slice, 0.728-0.805 and 0.849-0.884; vascular territory, 0.756-0.902 and 0.852-0.941; total score, 0.847 and 0.913, before and after implementing the consensus statement, respectively. Interobserver agreement in scoring also improved with the implementation of the consensus for all slices, vascular territories, and total score. The LoA for the total score narrowed from ± 10.36 points to ± 7.12 points. CONCLUSION: The interobserver reliability and agreement for CMR-LGE scoring for ischemic cardiomyopathy improved when following guidance from the ASCI-PT 2020 consensus statement.

Comparison of the Incidence of Postoperative Hypothyroidism in Patients Undergoing Conventional Thyroid Lobectomy and Pyramid- and Isthmus-Preserving Lobectomy.

Hypothyroidism is a recognized sequela of conventional thyroid lobectomy. However, there have been no studies on the incidence of hypothyroidism following the preservation of the isthmus and pyramid during lobectomy. Therefore, in the present study, we compared the incidence of hypothyroidism following conventional lobectomy and lobectomy during which the isthmus and pyramidal lobe were preserved. Data for a total of 65 patients collected between September 2018 and April 2019 were reviewed retrospectively. Circulating thyroid-stimulating hormone (TSH) concentration was measured before and after surgery in a group who underwent conventional thyroid lobectomy (n = 29) and in a group in which the isthmus and pyramid were preserved (n = 36). We found no significant difference in TSH concentration between the two groups before surgery, or 3 months or 1 year after surgery. Thus, there might be no difference in the incidence of postoperative hypothyroidism between patients who undergo conventional thyroid lobectomy and those in which the isthmus and pyramid are preserved.

Crystal Phase Transition Creates a Highly Active and Stable RuCX Nanosurface for Hydrogen Evolution Reaction in Alkaline Media.

Although metastable crystal structures have received much attention owing to their utilization in various fields, their phase-transition to a thermodynamic structure has attracted comparably little interest. In the case of nanoscale crystals, such an exothermic phase-transition releases high energy within a confined surface area and reconstructs surface atomic arrangement in a short time. Thus, this high-energy nanosurface may create novel crystal structures when some elements are supplied. In this work, the creation of a ruthenium carbide (RuCX , X < 1) phase on the surface of the Ru nanocrystal is discovered during phase-transition from cubic-close-packed to hexagonal-close-packed structure. When the electrocatalytic hydrogen evolution reaction (HER) is tested in alkaline media, the RuCX exhibits a much lower overpotential and good stability relative to the counterpart Ru-based catalysts and the state-of-the-art Pt/C catalyst. Density functional theory calculations predict that the local heterogeneity of the outermost RuCX surface promotes the bifunctional HER mechanism by providing catalytic sites for both H adsorption and facile water dissociation.

Reliability of Machine and Human Examiners for Detection of Laryngeal Penetration or Aspiration in Videofluoroscopic Swallowing Studies.

Computer-assisted analysis is expected to improve the reliability of videofluoroscopic swallowing studies (VFSSs), but its usefulness is limited. Previously, we proposed a deep learning model that can detect laryngeal penetration or aspiration fully automatically in VFSS video images, but the evidence for its reliability was insufficient. This study aims to compare the intra- and inter-rater reliability of the computer model and human raters. The test dataset consisted of 173 video files from which the existence of laryngeal penetration or aspiration was judged by the computer and three physicians in two sessions separated by a one-month interval. Intra- and inter-rater reliability were calculated using Cohen's kappa coefficient, the positive reliability ratio (PRR) and the negative reliability ratio (NRR). Intrarater reliability was almost perfect for the computer and two experienced physicians. Interrater reliability was moderate to substantial between the model and each human rater and between the human raters. The average PRR and NRR between the model and the human raters were similar to those between the human raters. The results demonstrate that the deep learning model can detect laryngeal penetration or aspiration from VFSS video as reliably as human examiners.

Pharmacological prevention of delayed hypersensitivity reactions caused by iodinated contrast media.

BACKGROUND: Delayed hypersensitivity reactions (DHRs) to radiocontrast media (RCM) occur in approximately 0.5-23.0% of patients and are thought to be caused by T cell-mediated mechanisms. However, an optimal pharmacological preventive strategy is not yet established in patients with histories of delayed reactions to RCM. OBJECTIVE: We aimed to evaluate the efficacy of pharmacological prevention in patients with histories of delayed reactions to non-ionic low-osmolar RCM when re-exposed to RCM. METHODS: A retrospective review of electronic medical records of 117 patients with previous histories of DHRs to RCM who visited an allergy clinic for the prevention of reactions after the re-exposure to RCM was conducted. The effects of pharmacological prevention were compared according to the symptom scores of previous reactions based on their intensities and durations with electronic medical records (EMRs). RESULTS: Of the 117 patients who experienced DHRs after RCM injection, we confirmed the outcomes of RCM re-exposure in 101 patients. For pharmacological prevention, 92 patients (91.1%) received steroids before RCM injection and among them, 50 patients (49.5%) received additional steroids after RCM injection. With this pharmacological prevention, patients of symptoms improved or no recurrence, recurrence of similar previous symptoms, and recurrence of worse symptoms were 98 (97.0%), 2 (2.0%), and 1 (1.0%), respectively. The proportions of no recurrence after pharmacological prevention were lower in patients with severe reactions and higher symptom scores. CONCLUSION: Pharmacological prevention showed a beneficial effect in most patients with delayed hypersensitivity to RCM. Further investigations are needed to establish an effective protocol for the prevention of delayed reactions to RCM.

Hyoid Bone Tracking in a Videofluoroscopic Swallowing Study Using a Deep-Learning-Based Segmentation Network.

Kinematic analysis of the hyoid bone in a videofluorosopic swallowing study (VFSS) is important for assessing dysphagia. However, calibrating the hyoid bone movement is time-consuming, and its reliability shows wide variation. Computer-assisted analysis has been studied to improve the efficiency and accuracy of hyoid bone identification and tracking, but its performance is limited. In this study, we aimed to design a robust network that can track hyoid bone movement automatically without human intervention. Using 69,389 frames from 197 VFSS files as the data set, a deep learning model for detection and trajectory prediction was constructed and trained by the BiFPN-U-Net(T) network. The present model showed improved performance when compared with the previous models: an area under the curve (AUC) of 0.998 for pixelwise accuracy, an accuracy of object detection of 99.5%, and a Dice similarity of 90.9%. The bounding box detection performance for the hyoid bone and reference objects was superior to that of other models, with a mean average precision of 95.9%. The estimation of the distance of hyoid bone movement also showed higher accuracy. The deep learning model proposed in this study could be used to detect and track the hyoid bone more efficiently and accurately in VFSS analysis.

Method for Diagnosing the Bone Marrow Edema of Sacroiliac Joint in Patients with Axial Spondyloarthritis Using Magnetic Resonance Image Analysis Based on Deep Learning.

Axial spondyloarthritis (axSpA) is a chronic inflammatory disease of the sacroiliac joints. In this study, we develop a method for detecting bone marrow edema by magnetic resonance (MR) imaging of the sacroiliac joints and a deep-learning network. A total of 815 MR images of the sacroiliac joints were obtained from 60 patients diagnosed with axSpA and 19 healthy subjects. Gadolinium-enhanced fat-suppressed T1-weighted oblique coronal images were used for deep learning. Active sacroiliitis was defined as bone marrow edema, and the following processes were performed: setting the region of interest (ROI) and normalizing it to a size suitable for input to a deep-learning network, determining bone marrow edema using a convolutional-neural-network-based deep-learning network for individual MR images, and determining sacroiliac arthritis in subject examinations based on the classification results of individual MR images. About 70% of the patients and normal subjects were randomly selected for the training dataset, and the remaining 30% formed the test dataset. This process was repeated five times to calculate the average classification rate of the five-fold sets. The gradient-weighted class activation mapping method was used to validate the classification results. In the performance analysis of the ResNet18-based classification network for individual MR images, use of the ROI showed excellent detection performance of bone marrow edema with 93.55 ± 2.19% accuracy, 92.87 ± 1.27% recall, and 94.69 ± 3.03% precision. The overall performance was additionally improved using a median filter to reflect the context information. Finally, active sacroiliitis was diagnosed in individual subjects with 96.06 ± 2.83% accuracy, 100% recall, and 94.84 ± 3.73% precision. This is a pilot study to diagnose bone marrow edema by deep learning based on MR images, and the results suggest that MR analysis using deep learning can be a useful complementary means for clinicians to diagnose bone marrow edema.