Purpose: This study explored the feasibility of utilizing a deep learning artificial intelligence (AI) model to detect ileocolic intussusception on grayscale ultrasound images. Methods: This retrospective observational study incorporated ultrasound images of children who underwent emergency ultrasonography for suspected ileocolic intussusception. After excluding video clips, Doppler images, and annotated images, 40,765 images from two tertiary hospitals were included (positive-to-negative ratio: hospital A, 2,775:35,373; hospital B, 140:2,477). Images from hospital A were split into a training set, a tuning set, and an internal test set (ITS) at a ratio of 7:1.5:1.5. Images from hospital B comprised an external test set (ETS). For each image indicating intussusception, two radiologists provided a bounding box as the ground-truth label. If intussusception was suspected in the input image, the model generated a bounding box with a confidence score (0-1) at the estimated lesion location. Average precision (AP) was used to evaluate overall model performance. The performance of practical thresholds for the modelgenerated confidence score, as determined from the ITS, was verified using the ETS. Results: The AP values for the ITS and ETS were 0.952 and 0.936, respectively. Two confidence thresholds, CTopt and CTprecision, were set at 0.557 and 0.790, respectively. For the ETS, the perimage precision and recall were 95.7% and 80.0% with CTopt, and 98.4% and 44.3% with CTprecision. For per-patient diagnosis, the sensitivity and specificity were 100.0% and 97.1% with CTopt, and 100.0% and 99.0% with CTprecision. The average number of false positives per patient was 0.04 with CTopt and 0.01 for CTprecision. Conclusion The feasibility of using an AI model to diagnose ileocolic intussusception on ultrasonography was demonstrated. However, further study involving bias-free data is warranted for robust clinical validation.

Purpose: This study explored the feasibility of utilizing a deep learning artificial intelligence (AI) model to detect ileocolic intussusception on grayscale ultrasound images. Methods: This retrospective observational study incorporated ultrasound images of children who underwent emergency ultrasonography for suspected ileocolic intussusception. After excluding video clips, Doppler images, and annotated images, 40,765 images from two tertiary hospitals were included (positive-to-negative ratio: hospital A, 2,775:35,373; hospital B, 140:2,477). Images from hospital A were split into a training set, a tuning set, and an internal test set (ITS) at a ratio of 7:1.5:1.5. Images from hospital B comprised an external test set (ETS). For each image indicating intussusception, two radiologists provided a bounding box as the ground-truth label. If intussusception was suspected in the input image, the model generated a bounding box with a confidence score (0-1) at the estimated lesion location. Average precision (AP) was used to evaluate overall model performance. The performance of practical thresholds for the modelgenerated confidence score, as determined from the ITS, was verified using the ETS. Results: The AP values for the ITS and ETS were 0.952 and 0.936, respectively. Two confidence thresholds, CTopt and CTprecision, were set at 0.557 and 0.790, respectively. For the ETS, the perimage precision and recall were 95.7% and 80.0% with CTopt, and 98.4% and 44.3% with CTprecision. For per-patient diagnosis, the sensitivity and specificity were 100.0% and 97.1% with CTopt, and 100.0% and 99.0% with CTprecision. The average number of false positives per patient was 0.04 with CTopt and 0.01 for CTprecision. Conclusion The feasibility of using an AI model to diagnose ileocolic intussusception on ultrasonography was demonstrated. However, further study involving bias-free data is warranted for robust clinical validation.

Purpose: This study explored the feasibility of utilizing a deep learning artificial intelligence (AI) model to detect ileocolic intussusception on grayscale ultrasound images. Methods: This retrospective observational study incorporated ultrasound images of children who underwent emergency ultrasonography for suspected ileocolic intussusception. After excluding video clips, Doppler images, and annotated images, 40,765 images from two tertiary hospitals were included (positive-to-negative ratio: hospital A, 2,775:35,373; hospital B, 140:2,477). Images from hospital A were split into a training set, a tuning set, and an internal test set (ITS) at a ratio of 7:1.5:1.5. Images from hospital B comprised an external test set (ETS). For each image indicating intussusception, two radiologists provided a bounding box as the ground-truth label. If intussusception was suspected in the input image, the model generated a bounding box with a confidence score (0-1) at the estimated lesion location. Average precision (AP) was used to evaluate overall model performance. The performance of practical thresholds for the modelgenerated confidence score, as determined from the ITS, was verified using the ETS. Results: The AP values for the ITS and ETS were 0.952 and 0.936, respectively. Two confidence thresholds, CTopt and CTprecision, were set at 0.557 and 0.790, respectively. For the ETS, the perimage precision and recall were 95.7% and 80.0% with CTopt, and 98.4% and 44.3% with CTprecision. For per-patient diagnosis, the sensitivity and specificity were 100.0% and 97.1% with CTopt, and 100.0% and 99.0% with CTprecision. The average number of false positives per patient was 0.04 with CTopt and 0.01 for CTprecision. Conclusion The feasibility of using an AI model to diagnose ileocolic intussusception on ultrasonography was demonstrated. However, further study involving bias-free data is warranted for robust clinical validation.

Fingertip amputation is a common traumatic injury which can be treated with revascularization therapy or composite grafting. This article reports two case studies showing the successful management of fingertip amputation using hyperbaric oxygen therapy (HBOT) and prostaglandin E1 (PGE1) treatment after composite grafting, where revascularization was not possible. HBOT was used to promote angiogenesis, improve oxygen transfer, and accelerate wound healing. At the same time, PGE1 was administered to control inflammation, stimulate cell proliferation, and promote tissue repair. These case reports offer effective approaches to treating fingertip amputation. The treatment strategy used in this study can be expected to improve patient outcomes and quality of life.

Purpose: This study explored the feasibility of utilizing a deep learning artificial intelligence (AI) model to detect ileocolic intussusception on grayscale ultrasound images. Methods: This retrospective observational study incorporated ultrasound images of children who underwent emergency ultrasonography for suspected ileocolic intussusception. After excluding video clips, Doppler images, and annotated images, 40,765 images from two tertiary hospitals were included (positive-to-negative ratio: hospital A, 2,775:35,373; hospital B, 140:2,477). Images from hospital A were split into a training set, a tuning set, and an internal test set (ITS) at a ratio of 7:1.5:1.5. Images from hospital B comprised an external test set (ETS). For each image indicating intussusception, two radiologists provided a bounding box as the ground-truth label. If intussusception was suspected in the input image, the model generated a bounding box with a confidence score (0-1) at the estimated lesion location. Average precision (AP) was used to evaluate overall model performance. The performance of practical thresholds for the modelgenerated confidence score, as determined from the ITS, was verified using the ETS. Results: The AP values for the ITS and ETS were 0.952 and 0.936, respectively. Two confidence thresholds, CTopt and CTprecision, were set at 0.557 and 0.790, respectively. For the ETS, the perimage precision and recall were 95.7% and 80.0% with CTopt, and 98.4% and 44.3% with CTprecision. For per-patient diagnosis, the sensitivity and specificity were 100.0% and 97.1% with CTopt, and 100.0% and 99.0% with CTprecision. The average number of false positives per patient was 0.04 with CTopt and 0.01 for CTprecision. Conclusion The feasibility of using an AI model to diagnose ileocolic intussusception on ultrasonography was demonstrated. However, further study involving bias-free data is warranted for robust clinical validation.

Purpose: This study explored the feasibility of utilizing a deep learning artificial intelligence (AI) model to detect ileocolic intussusception on grayscale ultrasound images. Methods: This retrospective observational study incorporated ultrasound images of children who underwent emergency ultrasonography for suspected ileocolic intussusception. After excluding video clips, Doppler images, and annotated images, 40,765 images from two tertiary hospitals were included (positive-to-negative ratio: hospital A, 2,775:35,373; hospital B, 140:2,477). Images from hospital A were split into a training set, a tuning set, and an internal test set (ITS) at a ratio of 7:1.5:1.5. Images from hospital B comprised an external test set (ETS). For each image indicating intussusception, two radiologists provided a bounding box as the ground-truth label. If intussusception was suspected in the input image, the model generated a bounding box with a confidence score (0-1) at the estimated lesion location. Average precision (AP) was used to evaluate overall model performance. The performance of practical thresholds for the modelgenerated confidence score, as determined from the ITS, was verified using the ETS. Results: The AP values for the ITS and ETS were 0.952 and 0.936, respectively. Two confidence thresholds, CTopt and CTprecision, were set at 0.557 and 0.790, respectively. For the ETS, the perimage precision and recall were 95.7% and 80.0% with CTopt, and 98.4% and 44.3% with CTprecision. For per-patient diagnosis, the sensitivity and specificity were 100.0% and 97.1% with CTopt, and 100.0% and 99.0% with CTprecision. The average number of false positives per patient was 0.04 with CTopt and 0.01 for CTprecision. Conclusion The feasibility of using an AI model to diagnose ileocolic intussusception on ultrasonography was demonstrated. However, further study involving bias-free data is warranted for robust clinical validation.

Background: Wound healing is a complex process influenced by a variety of environmental factors. Dressing materials play a critical role in creating barriers against contaminants, maintaining optimal moisture levels, and absorbing wound exudate. Therefore, selecting materials tailored to wound characteristics is crucial for enhancing outcomes. Hyaluronic acid (HA) is a natural biocompatible polymer that supports healing by regulating inflammation and promoting tissue repair. This study compared HA- and hydrocolloid-based hydrogels in a rat model to optimize wound care strategies. Methods: Full-thickness dermal wounds (diameter, 8 mm) were created on the dorsal skin of 12 Sprague-Dawley rats under sevoflurane anesthesia. The wounds were treated with HA/silver sulfadiazine gel (group A), hydrocolloid gel (group B), or left untreated (control), all covered with a transparent dressing. Biopsy specimens on days 3, 7, and 21 were used to assess histological parameters: inflammatory cell infiltration, fibroblast infiltration, collagen deposition, neovascularization, and epithelial thickness, using a semi-quantitative scoring system. Histological analyses were conducted blindly, and statistical analyses were performed using the Kruskal-Wallis test (p< 0.05). Results: On day 3, group A showed significantly higher inflammatory cell infiltration and collagen deposition than other groups, indicating extracellular matrix formation. By day 7, angiogenesis was highest in group A, followed by group B and controls. By day 21, all wounds had completely healed. Epithelial layer thickness, reflecting inflammation and fibroblast maturity, was significantly higher in group A. Conclusion This study compared HA-based hydrogel and hydrocolloid-based dressings through histological analyses to elucidate wound healing mechanics. HA-based hydrogel dressings significantly enhanced wound recovery. However, generalizing these outcomes requires future studies to expand the range of effective wound treatment materials. These findings underscore the potential of HA-based dressings to enhance clinical outcomes in wound management, suggesting avenues for improving therapeutic strategies.

Background: Adrenocortical carcinomas (ACCs) are rare tumors with aggressive but varied prognosis. Stage, Grade, Resection status, Age, Symptoms (S-GRAS) score, based on clinical and pathological factors, was found to best stratify the prognosis of European ACC patients. This study assessed the prognostic performance of modified S-GRAS (mS-GRAS) scores including modified grade (mG) by integrating mitotic counts into the Ki67 index (original grade), in Korean ACC patients. Methods: Patients who underwent surgery for ACC between January 1996 and December 2022 at three medical centers in Korea were retrospectively analyzed. mS-GRAS scores were calculated based on tumor stage, mG (Ki67 index or mitotic counts), resection status, age, and symptoms. Patients were divided into four groups (0–1, 2–3, 4–5, and 6–9 points) based on total mS-GRAS score. The associations of each variable and mS-GRAS score with recurrence and survival were evaluated using Cox regression analysis, Harrell’s concordance index (C-index), and the Kaplan–Meier method. Results: Data on mS-GRAS components were available for 114 of the 153 patients who underwent surgery for ACC. These 114 patients had recurrence and death rates of 61.4% and 48.2%, respectively. mS-GRAS score was a significantly better predictor of recurrence (C-index=0.829) and death (C-index=0.747) than each component (P<0.05), except for resection status. mS-GRAS scores correlated with shorter progression-free survival (P=8.34E-24) and overall survival (P=2.72E-13). Conclusion mS-GRAS scores showed better prognostic performance than tumor stage and grade in Asian patients who underwent surgery for ACC.

Purpose: To develop and evaluate a deep learning technique to automatically segment bone structures in zero echo time (ZTE) for skull magnetic resonance imaging (MRI) in children. Materials and Methods: From January to December 2021, 38 bone ZTE MRIs from infants and children (age range, 1–31 months) were collected for model development.Mask images were generated by manually segmenting the craniofacial bone using a commercial segmentation program. Among them, 35 ZTE series were used to train the three-dimensional (3D)-nnUnet deep learning model and the remaining three series were used for model validation. A temporally different dataset of 19 ZTE bone MRIs obtained in May 2022 from infants and children (age range, 3–168 months) was used to determine the model’s performance. Dice similarity coefficient was calculated for each test case.From 3D volume rendering images, segmentation accuracy, overall image quality, and visibility of cranial sutures were subjectively evaluated on a 5-point scale and compared with ground truth data from manual segmentation. Reasons for segmentation failure were analyzed using axially segmented ZTE images. Results: For the test set, the mean Dice similarity coefficient was 0.985 ± 0.019. The segmentation accuracy was lower than the ground truth without showing a statistically significant difference between the two (3.39 ± 1.11 vs. 3.73 ± 0.77, p = 0.055). The overall image quality and suture visibility showed no significant difference (3.34 ± 0.75 vs.3.42 ± 0.69, p = 0.317; 3.55 ± 0.97 vs. 3.60 ± 0.95, p = 0.157). Common reasons for low segmentation accuracy were well-pneumatized sinuses, metal artifacts, skin at the vertex level, and bones too thin. Conclusion The deep learning-based automatic segmentation technique of bone ZTE MRIs showed comparable segmentation performance to manual segmentation. Using the deep learning-based segmentation results, acceptable 3D-volume rendering images of craniofacial bones were generated.

Background: The coronavirus disease 2019 (COVID-19) pandemic has caused the death of thousands of patients worldwide. Although age is known to be a risk factor for morbidity and mortality in COVID-19 patients, critical illness or death is occurring even in the younger age group as the epidemic spreads. In early 2022, omicron became the dominant variant of the COVID-19 virus in South Korea, and the epidemic proceeded on a large scale. Accordingly, this study aimed to determine whether young adults (aged ≤ 50 years) with critical COVID-19 infection during the omicron period had different characteristics from older patients and to determine the risk factors for mortality in this specific age group. Methods: We evaluated 213 critical adult patients (high flow nasal cannula or higher respiratory support) hospitalized for polymerase chain reaction-confirmed COVID-19 in nine hospitals in South Korea between February 1, 2022 and April 30, 2022. Demographic characteristics, including body mass index (BMI) and vaccination status; underlying diseases; clinical features and laboratory findings; clinical course; treatment received; and outcomes were collected from electronic medical records (EMRs) and analyzed according to age and mortality. Results: Overall, 71 critically ill patients aged ≤ 50 years were enrolled, and 142 critically ill patients aged over 50 years were selected through 1:2 matching based on the date of diagnosis. The most frequent underlying diseases among those aged ≤ 50 years were diabetes and hypertension, and all 14 patients who died had either a BMI ≥ 25 kg/m 2 or an underlying disease. The total case fatality rate among severe patients (S-CFR) was 31.0%, and the S-CFR differed according to age and was higher than that during the delta period. The S-CFR was 19.7% for those aged ≤ 50 years, 36.6% for those aged > 50 years, and 38.1% for those aged ≥ 65 years. In multivariate analysis, age (odds ratio [OR], 1.084; 95% confidence interval [CI], 1.043–1.127), initial low-density lipoprotein > 600 IU/L (OR, 4.782; 95% CI, 1.584–14.434), initial C-reactive protein > 8 mg/dL (OR, 2.940; 95% CI, 1.042–8.293), highest aspartate aminotransferase > 200 IU/L (OR, 12.931; 95% CI, 1.691–98.908), and mechanical ventilation implementation (OR, 3.671; 95% CI, 1.294–10.420) were significant independent predictors of mortality in critical COVID-19 patients during the omicron wave. A similar pattern was shown when analyzing the data by age group, but most had no statistical significance owing to the small number of deaths in the young critical group. Although the vaccination completion rate of all the patients (31.0%) was higher than that in the delta wave period (13.6%), it was still lower than that of the general population. Further, only 15 (21.1%) critically ill patients aged ≤ 50 years were fully vaccinated. Overall, the severity of hospitalized critical patients was significantly higher than that in the delta period, indicating that it was difficult to find common risk factors in the two periods only with a simple comparison. Conclusion Overall, the S-CFR of critically ill COVID-19 patients in the omicron period was higher than that in the delta period, especially in those aged ≤ 50 years. All of the patients who died had an underlying disease or obesity. In the same population, the vaccination rate was very low compared to that in the delta wave, indicating that non-vaccination significantly affected the progression to critical illness. Notably, there was a lack of prescription for Paxlovid for these patients although they satisfied the prescription criteria. Early diagnosis and active initial treatment was necessary, along with the proven methods of vaccination and personal hygiene. Further studies are needed to determine how each variant affects critically ill patients.