1.Deep Learning Technology for Classification of Thyroid Nodules Using Multi-View Ultrasound Images: Potential Benefits and Challenges in Clinical Application
Jinyoung KIM ; Min-Hee KIM ; Dong-Jun LIM ; Hankyeol LEE ; Jae Jun LEE ; Hyuk-Sang KWON ; Mee Kyoung KIM ; Ki-Ho SONG ; Tae-Jung KIM ; So Lyung JUNG ; Yong Oh LEE ; Ki-Hyun BAEK
Endocrinology and Metabolism 2025;40(2):216-224
Background:
This study aimed to evaluate the applicability of deep learning technology to thyroid ultrasound images for classification of thyroid nodules.
Methods:
This retrospective analysis included ultrasound images of patients with thyroid nodules investigated by fine-needle aspiration at the thyroid clinic of a single center from April 2010 to September 2012. Thyroid nodules with cytopathologic results of Bethesda category V (suspicious for malignancy) or VI (malignant) were defined as thyroid cancer. Multiple deep learning algorithms based on convolutional neural networks (CNNs) —ResNet, DenseNet, and EfficientNet—were utilized, and Siamese neural networks facilitated multi-view analysis of paired transverse and longitudinal ultrasound images.
Results:
Among 1,048 analyzed thyroid nodules from 943 patients, 306 (29%) were identified as thyroid cancer. In a subgroup analysis of transverse and longitudinal images, longitudinal images showed superior prediction ability. Multi-view modeling, based on paired transverse and longitudinal images, significantly improved the model performance; with an accuracy of 0.82 (95% confidence intervals [CI], 0.80 to 0.86) with ResNet50, 0.83 (95% CI, 0.83 to 0.88) with DenseNet201, and 0.81 (95% CI, 0.79 to 0.84) with EfficientNetv2_ s. Training with high-resolution images obtained using the latest equipment tended to improve model performance in association with increased sensitivity.
Conclusion
CNN algorithms applied to ultrasound images demonstrated substantial accuracy in thyroid nodule classification, indicating their potential as valuable tools for diagnosing thyroid cancer. However, in real-world clinical settings, it is important to aware that model performance may vary depending on the quality of images acquired by different physicians and imaging devices.
2.Correlation between White Globe Appearance and Clinicopathologic Characteristics in Early Gastric Cancer
Dae Jin JUNG ; Gwang Ha KIM ; Kyungbin KIM ; Hye Kyung JEON ; Dong Chan JOO ; Moon Won LEE ; Bong Eun LEE
Gut and Liver 2025;19(1):50-58
Background/Aims:
Magnifying endoscopy with narrow-band imaging (ME-NBI) enables the visualization of detailed microsurface (MS) and microvascular (MV) structures in the gastrointestinal tract. White globe appearance (WGA) is a small whitish lesion with a globular shape identified during ME-NBI for early gastric cancer (EGC). This study aimed to investigate the associations between WGA, clinicopathological characteristics, and other ME-NBI findings in patients with EGC.
Methods:
The presence or absence of WGA in 122 patients (126 lesions) with an endoscopic diagnosis of EGC who underwent ME-NBI before endoscopic or surgical resection was prospectively collected and retrospectively analyzed. During ME-NBI, the MS and MV patterns and the presence of WGA and white opaque substances (WOS) were investigated. EGC cases were categorized as differentiated or undifferentiated type, and mucosal, submucosal, or advanced.
Results:
Of 126 lesions, WGA was observed in 25 (19.8%). WGA was associated with tumor size (≤2 cm [17/63, 27.0%] vs >2 cm [8/63, 12.7%]; p=0.044), histologic type differentiated type [22/89, 24.7%] vs undifferentiated type [3/37. 8.1%]; p=0.033), and tumor location (upper third [1/11, 9.1%] vs middle third [18/58, 31.0%] and lower third [6/57, 10.5%]; p=0.017). Although WGA was observed more frequently in lesions with an oval/tubular MS pattern, a fine-network MV pattern, and the absence of WOS, the difference was not statistically significant (MS pattern, p=0.358; MV pattern, p=0.212; WOS, p=0.121, respectively).
Conclusions
WGA was associated with small tumor size, differentiated-type histology, and middle-third tumor location, and was more frequently observed in lesions with an oval/tubular MS and fine-network MV patterns and the absence of WOS.
3.Survey of the Actual Practices Used for Endoscopic Removal of Colon Polyps in Korea: A Comparison with the Current Guidelines
Jeongseok KIM ; Tae-Geun GWEON ; Min Seob KWAK ; Su Young KIM ; Seong Jung KIM ; Hyun Gun KIM ; Sung Noh HONG ; Eun Sun KIM ; Chang Mo MOON ; Dae Seong MYUNG ; Dong-Hoon BAEK ; Shin Ju OH ; Hyun Jung LEE ; Ji Young LEE ; Yunho JUNG ; Jaeyoung CHUN ; Dong-Hoon YANG ; Eun Ran KIM ; Intestinal Tumor Research Group of the Korean Association for the Study of Intestinal Diseases
Gut and Liver 2025;19(1):77-86
Background/Aims:
We investigated the clinical practice patterns of Korean endoscopists for the endoscopic resection of colorectal polyps.
Methods:
From September to November 2021, an online survey was conducted regarding the preferred resection methods for colorectal polyps, and responses were compared with the international guidelines.
Results:
Among 246 respondents, those with <4 years, 4–9 years, and ≥10 years of experiencein colonoscopy practices accounted for 25.6%, 34.1%, and 40.2% of endoscopists, respectively. The most preferred resection methods for non-pedunculated lesions were cold forceps polypectomy for ≤3 mm lesions (81.7%), cold snare polypectomy for 4–5 mm (61.0%) and 6–9 mm (43.5%) lesions, hot endoscopic mucosal resection (EMR) for 10–19 mm lesions (72.0%), precut EMR for 20–25 mm lesions (22.0%), and endoscopic submucosal dissection (ESD) for ≥26 mm lesions (29.3%). Hot EMR was favored for pedunculated lesions with a head size <20 mm and stalk size <10 mm (75.6%) and for those with a head size ≥20 mm or stalk size ≥10 mm (58.5%). For suspected superficial and deep submucosal lesions measuring 10–19 mm and ≥20 mm, ESD (26.0% and 38.6%) and surgery (36.6% and 46.3%) were preferred, respectively. The adherence rate to the guidelines ranged from 11.2% to 96.9%, depending on the size, shape, and histology of the lesions.
Conclusions
Adherence to the guidelines for endoscopic resection techniques varied depend-ing on the characteristics of colorectal polyps. Thus, an individualized approach is required to increase adherence to the guidelines.
4.Incidence, Risk Factors, and Outcomes of Chronic AntibioticRefractory Pouchitis in Korean Patients with Ulcerative Colitis
Ji Eun BAEK ; Jung-Bin PARK ; June Hwa BAE ; Min Hyun KIM ; Seung Wook HONG ; Sung Wook HWANG ; Jong Lyul LEE ; Yong Sik YOON ; Dong-Hoon YANG ; Byong Duk YE ; Jeong-Sik BYEON ; Seung-Jae MYUNG ; Chang Sik YU ; Suk-Kyun YANG ; Sang Hyoung PARK
Gut and Liver 2025;19(3):388-397
Background/Aims:
The study investigated the incidence, risk factors, and clinical outcomes of chronic antibiotic-refractory pouchitis (CARP) in Korean patients with ulcerative colitis (UC).
Methods:
This single-center retrospective study included patients with UC who underwent total proctocolectomy with ileal pouch-anal anastomosis at the Asan Medical Center in Korea between January 1987 and December 2022. The primary outcomes were endoscopic remission and pouch failure. The Cox’s proportional hazard model was used to identify the risk factors for CARP.
Results:
The clinical data of 232 patients were analyzed. The most common cause of surgery was steroid refractoriness (50.9%), followed by dysplasia/colorectal cancer (26.7%). Among 74 patients (31.9%) with chronic pouchitis (CP), 31 (13.4%) had CARP, and 43 (18.5%) had chronic antibiotic-dependent pouchitis (CADP). The most frequent endoscopic phenotype was focal inflammation of the pouch (CP, 47.3%; CARP, 35.5%; CADP, 55.8%). Patients with CARP were less likely to use concomitant probiotics than patients with CADP (29.0% vs 72.1%, p<0.01). The endoscopic remission rate of CP, CARP, and CADP was 14.9%, 9.7%, and 18.6%, respectively.The pouch failure rate associated with CP, CARP, and CADP was 13.5%, 16.1%, and 11.6%, respectively. Current smoking status (adjusted hazard ratio [aHR], 2.96; 95% confidence interval [CI], 1.27 to 6.90; p=0.01) and previous use of biologics/small molecules (aHR, 2.40; 95% CI, 1.05 to 5.53; p=0.04) were significantly associated with CARP development.
Conclusions
UC patients who were current smokers and previously used biologics/small molecules had a higher risk of developing CARP. Concomitant use of probiotics was less likely to be associated with CARP development.
5.Eligibility for Lecanemab Treatment in the Republic of Korea:Real-World Data From Memory Clinics
Sung Hoon KANG ; Jee Hyang JEONG ; Jung-Min PYUN ; Geon Ha KIM ; Young Ho PARK ; YongSoo SHIM ; Seong-Ho KOH ; Chi-Hun KIM ; Young Chul YOUN ; Dong Won YANG ; Hyuk-je LEE ; Han LEE ; Dain KIM ; Kyunghwa SUN ; So Young MOON ; Kee Hyung PARK ; Seong Hye CHOI
Journal of Clinical Neurology 2025;21(3):182-189
Background:
and Purpose We aimed to determine the proportion of Korean patients with early Alzheimer’s disease (AD) who are eligible to receive lecanemab based on the United States Appropriate Use Recommendations (US AUR), and also identify the barriers to this treatment.
Methods:
We retrospectively enrolled 6,132 patients with amnestic mild cognitive impairment or mild amnestic dementia at 13 hospitals from June 2023 to May 2024. Among them, 2,058 patients underwent amyloid positron emission tomography (PET) and 1,199 (58.3%) of these patients were amyloid-positive on PET. We excluded 732 patients who did not undergo brain magnetic resonance imaging between June 2023 and May 2024. Finally, 467 patients were included in the present study.
Results:
When applying the criteria of the US AUR, approximately 50% of patients with early AD were eligible to receive lecanemab treatment. Among the 467 included patients, 36.8% did not meet the inclusion criterion of a Mini-Mental State Examination (MMSE) score of ≥22.
Conclusions
Eligibility for lecanemab treatment was not restricted to Korean patients with early AD except for those with an MMSE score of ≥22. The MMSE criteria should therefore be reconsidered in areas with a higher proportion of older people, who tend to have lower levels of education.
6.Erratum: Korean Gastric Cancer Association-Led Nationwide Survey on Surgically Treated Gastric Cancers in 2023
Dong Jin KIM ; Jeong Ho SONG ; Ji-Hyeon PARK ; Sojung KIM ; Sin Hye PARK ; Cheol Min SHIN ; Yoonjin KWAK ; Kyunghye BANG ; Chung-sik GONG ; Sung Eun OH ; Yoo Min KIM ; Young Suk PARK ; Jeesun KIM ; Ji Eun JUNG ; Mi Ran JUNG ; Bang Wool EOM ; Ki Bum PARK ; Jae Hun CHUNG ; Sang-Il LEE ; Young-Gil SON ; Dae Hoon KIM ; Sang Hyuk SEO ; Sejin LEE ; Won Jun SEO ; Dong Jin PARK ; Yoonhong KIM ; Jin-Jo KIM ; Ki Bum PARK ; In CHO ; Hye Seong AHN ; Sung Jin OH ; Ju-Hee LEE ; Hayemin LEE ; Seong Chan GONG ; Changin CHOI ; Ji-Ho PARK ; Eun Young KIM ; Chang Min LEE ; Jong Hyuk YUN ; Seung Jong OH ; Eunju LEE ; Seong-A JEONG ; Jung-Min BAE ; Jae-Seok MIN ; Hyun-dong CHAE ; Sung Gon KIM ; Daegeun PARK ; Dong Baek KANG ; Hogoon KIM ; Seung Soo LEE ; Sung Il CHOI ; Seong Ho HWANG ; Su-Mi KIM ; Moon Soo LEE ; Sang Hyun KIM ; Sang-Ho JEONG ; Yusung YANG ; Yonghae BAIK ; Sang Soo EOM ; Inho JEONG ; Yoon Ju JUNG ; Jong-Min PARK ; Jin Won LEE ; Jungjai PARK ; Ki Han KIM ; Kyung-Goo LEE ; Jeongyeon LEE ; Seongil OH ; Ji Hun PARK ; Jong Won KIM ;
Journal of Gastric Cancer 2025;25(2):400-402
7.Stratifying Risk of Lymph Node Metastasis After Non-Curative Endoscopic Submucosal Dissection of Early Gastric Cancer: Comparison of the eCura System and Elderly Criteria
Tae-woo KIM ; Hyo-Joon YANG ; Giho LEE ; Soo-Kyung PARK ; Yoon Suk JUNG ; Jung Ho PARK ; Dong Il PARK ; Chong Il SOHN
Journal of Gastric Cancer 2025;25(2):370-381
Purpose:
The novel curability criteria for elderly (EL) patients have been proposed to stratify their risk of lymph node metastasis (LNM), following non-curative endoscopic submucosal dissection (ESD) for early gastric cancer (EGC). Hence, this study aimed to evaluate the effectiveness of the EL criteria and compare them with those of the well-known eCura system.
Materials and Methods:
A retrospective analysis was performed on 143 patients who did not meet the curative ESD criteria at a tertiary hospital in Korea between 2011 and 2022. Of these, 102 underwent additional surgery, while 41 were followed up without further treatment. The LNM rates based on the EL and eCura systems were stratified and compared.
Results:
In the surgery group, 29.4% (30/102) patients were classified as EL-low (EL-L) and 70.2% (72/102) as EL-high (EL-H). The LNM rates (95% confidence interval) were 0.0% (0.0–11.6) and 9.7% (4.0–19.0) for EL-L and EL-H, respectively (P=0.102). EL-L was closely aligned with the eCura low-risk category, with a similar patient proportion (32.4%) and an LNM rate of 0.0% (0.0–10.6). The eCura system classified 94.1% (48/51) of the EL-L patients as lowrisk, with an 86% concordance rate (123/143). Discordant cases included patients with positive vertical margins, but without other risk factors, who were classified as EL-H without LNM.
Conclusions
Patients with EL-L showed no LNM, and the EL criteria demonstrated high concordance with the eCura system. The EL criteria may be as effective as the eCura system in identifying low-risk patients after non-curative ESD for EGC.
8.Korean Gastric Cancer AssociationLed Nationwide Survey on Surgically Treated Gastric Cancers in 2023
Dong Jin KIM ; Jeong Ho SONG ; Ji-Hyeon PARK ; Sojung KIM ; Sin Hye PARK ; Cheol Min SHIN ; Yoonjin KWAK ; Kyunghye BANG ; Chung-sik GONG ; Sung Eun OH ; Yoo Min KIM ; Young Suk PARK ; Jeesun KIM ; Ji Eun JUNG ; Mi Ran JUNG ; Bang Wool EOM ; Ki Bum PARK ; Jae Hun CHUNG ; Sang-Il LEE ; Young-Gil SON ; Dae Hoon KIM ; Sang Hyuk SEO ; Sejin LEE ; Won Jun SEO ; Dong Jin PARK ; Yoonhong KIM ; Jin-Jo KIM ; Ki Bum PARK ; In CHO ; Hye Seong AHN ; Sung Jin OH ; Ju-Hee LEE ; Hayemin LEE ; Seong Chan GONG ; Changin CHOI ; Ji-Ho PARK ; Eun Young KIM ; Chang Min LEE ; Jong Hyuk YUN ; Seung Jong OH ; Eunju LEE ; Seong-A JEONG ; Jung-Min BAE ; Jae-Seok MIN ; Hyun-dong CHAE ; Sung Gon KIM ; Daegeun PARK ; Dong Baek KANG ; Hogoon KIM ; Seung Soo LEE ; Sung Il CHOI ; Seong Ho HWANG ; Su-Mi KIM ; Moon Soo LEE ; Sang Hyun KIM ; Sang-Ho JEONG ; Yusung YANG ; Yonghae BAIK ; Sang Soo EOM ; Inho JEONG ; Yoon Ju JUNG ; Jong-Min PARK ; Jin Won LEE ; Jungjai PARK ; Ki Han KIM ; Kyung-Goo LEE ; Jeongyeon LEE ; Seongil OH ; Ji Hun PARK ; Jong Won KIM ; The Information Committee of the Korean Gastric Cancer Association
Journal of Gastric Cancer 2025;25(1):115-132
Purpose:
Since 1995, the Korean Gastric Cancer Association (KGCA) has been periodically conducting nationwide surveys on patients with surgically treated gastric cancer. This study details the results of the survey conducted in 2023.
Materials and Methods:
The survey was conducted from March to December 2024 using a standardized case report form. Data were collected on 86 items, including patient demographics, tumor characteristics, surgical procedures, and surgical outcomes. The results of the 2023 survey were compared with those of previous surveys.
Results:
Data from 12,751 cases were collected from 66 institutions. The mean patient age was 64.6 years, and the proportion of patients aged ≥71 years increased from 9.1% in 1995 to 31.7% in 2023. The proportion of upper-third tumors slightly decreased to 16.8% compared to 20.9% in 2019. Early gastric cancer accounted for 63.1% of cases in 2023.Regarding operative procedures, a totally laparoscopic approach was most frequently applied (63.2%) in 2023, while robotic gastrectomy steadily increased to 9.5% from 2.1% in 2014.The most common anastomotic method was the Billroth II procedure (48.8%) after distal gastrectomy and double-tract reconstruction (51.9%) after proximal gastrectomy in 2023.However, the proportion of esophago-gastrostomy with anti-reflux procedures increased to 30.9%. The rates of post-operative mortality and overall complications were 1.0% and 15.3%, respectively.
Conclusions
The results of the 2023 nationwide survey demonstrate the current status of gastric cancer treatment in Korea. This information will provide a basis for future gastric cancer research.
9.Gynecologic oncology in 2024:breakthrough trials and evolving treatment strategies for cervical, uterine corpus, and ovarian cancers
Sung Jong LEE ; Ji Geun YOO ; Jin Hwi KIM ; Jeong-Yeol PARK ; Jung-Yun LEE ; Yoo-Young LEE ; Dong Hoon SUH
Journal of Gynecologic Oncology 2025;36(1):e72-
This review summarized the results of clinical trials in 2024 that were believed to have a significant impact on clinical practice in the field of gynecologic oncology. The SHAPE trial, INTERLACE and KEYNOTE-A18 trials, and BEATcc and COMPASSION-16 trials were included in early-stage, locally advanced, and recurrent/metastatic cervical cancer, respectively. For uterine corpus cancer, updated survival data of the four trials (NRG-GY018, RUBY, AtTEnd, DUO-E) for endometrial cancer and the first survival data of LMS-04 trial for leiomyosarcoma were described. For ovarian cancer, the final overall survival results of PRIMA study were followed by DUO-O, ATHENA-combo, and FIRST-ENGOT-OV44 trial in different disease conditions. Finally, the results of DESTINY-PanTumor02, a basket trial of trastuzumab deruxtecan, were briefly addressed.
10.Clinical practice guidelines for ovarian cancer: an update to the Korean Society of Gynecologic Oncology guidelines
Banghyun LEE ; Suk-Joon CHANG ; Byung Su KWON ; Joo-Hyuk SON ; Myong Cheol LIM ; Yun Hwan KIM ; Shin-Wha LEE ; Chel Hun CHOI ; Kyung Jin EOH ; Jung-Yun LEE ; Yoo-Young LEE ; Dong Hoon SUH ; Yong Beom KIM
Journal of Gynecologic Oncology 2025;36(1):e69-
We updated the Korean Society of Gynecologic Oncology (KSGO) practice guideline for the management of ovarian cancer as version 5.1. The ovarian cancer guideline team of the KSGO published announced the fifth version (version 5.0) of its clinical practice guidelines for the management of ovarian cancer in December 2023. In version 5.0, the selection of the key questions and the systematic reviews were based on the data available up to December 2022.Therefore, we updated the guidelines version 5.0 with newly accumulated clinical data and added 5 new key questions reflecting the latest insights in the field of ovarian cancer between 2023 and 2024. For each question, recommendation was provided together with corresponding level of evidence and grade of recommendation, all established through expert consensus.

Result Analysis
Print
Save
E-mail