Objective: This study aimed to develop and validate a deep learning (DL) algorithm for the quantitative measurement of thoracolumbar (TL) fracture features, and to evaluate its efficacy across varying levels of clinical expertise. Methods: Using the pretrained Mask Region-Based Convolutional Neural Networks model, originally developed for vertebral body segmentation and fracture detection, we fine-tuned the model and added a new module for measuring fracture metrics—compression rate (CR), Cobb angle (CA), Gardner angle (GA), and sagittal index (SI)—from lumbar spine lateral radiographs. These metrics were derived from six-point labeling by 3 radiologists, forming the ground truth (GT). Training utilized 1,000 nonfractured and 318 fractured radiographs, while validations employed 213 internal and 200 external fractured radiographs. The accuracy of the DL algorithm in quantifying fracture features was evaluated against GT using the intraclass correlation coefficient. Additionally, 4 readers with varying expertise levels, including trainees and an attending spine surgeon, performed measurements with and without DL assistance, and their results were compared to GT and the DL model. Results: The DL algorithm demonstrated good to excellent agreement with GT for CR, CA, GA, and SI in both internal (0.860, 0.944, 0.932, and 0.779, respectively) and external (0.836, 0.940, 0.916, and 0.815, respectively) validations. DL-assisted measurements significantly improved most measurement values, particularly for trainees. Conclusion The DL algorithm was validated as an accurate tool for quantifying TL fracture features using radiographs. DL-assisted measurement is expected to expedite the diagnostic process and enhance reliability, particularly benefiting less experienced clinicians.

Objective: This study aimed to develop and validate a deep learning (DL) algorithm for the quantitative measurement of thoracolumbar (TL) fracture features, and to evaluate its efficacy across varying levels of clinical expertise. Methods: Using the pretrained Mask Region-Based Convolutional Neural Networks model, originally developed for vertebral body segmentation and fracture detection, we fine-tuned the model and added a new module for measuring fracture metrics—compression rate (CR), Cobb angle (CA), Gardner angle (GA), and sagittal index (SI)—from lumbar spine lateral radiographs. These metrics were derived from six-point labeling by 3 radiologists, forming the ground truth (GT). Training utilized 1,000 nonfractured and 318 fractured radiographs, while validations employed 213 internal and 200 external fractured radiographs. The accuracy of the DL algorithm in quantifying fracture features was evaluated against GT using the intraclass correlation coefficient. Additionally, 4 readers with varying expertise levels, including trainees and an attending spine surgeon, performed measurements with and without DL assistance, and their results were compared to GT and the DL model. Results: The DL algorithm demonstrated good to excellent agreement with GT for CR, CA, GA, and SI in both internal (0.860, 0.944, 0.932, and 0.779, respectively) and external (0.836, 0.940, 0.916, and 0.815, respectively) validations. DL-assisted measurements significantly improved most measurement values, particularly for trainees. Conclusion The DL algorithm was validated as an accurate tool for quantifying TL fracture features using radiographs. DL-assisted measurement is expected to expedite the diagnostic process and enhance reliability, particularly benefiting less experienced clinicians.

Objective: This study aimed to develop and validate a deep learning (DL) algorithm for the quantitative measurement of thoracolumbar (TL) fracture features, and to evaluate its efficacy across varying levels of clinical expertise. Methods: Using the pretrained Mask Region-Based Convolutional Neural Networks model, originally developed for vertebral body segmentation and fracture detection, we fine-tuned the model and added a new module for measuring fracture metrics—compression rate (CR), Cobb angle (CA), Gardner angle (GA), and sagittal index (SI)—from lumbar spine lateral radiographs. These metrics were derived from six-point labeling by 3 radiologists, forming the ground truth (GT). Training utilized 1,000 nonfractured and 318 fractured radiographs, while validations employed 213 internal and 200 external fractured radiographs. The accuracy of the DL algorithm in quantifying fracture features was evaluated against GT using the intraclass correlation coefficient. Additionally, 4 readers with varying expertise levels, including trainees and an attending spine surgeon, performed measurements with and without DL assistance, and their results were compared to GT and the DL model. Results: The DL algorithm demonstrated good to excellent agreement with GT for CR, CA, GA, and SI in both internal (0.860, 0.944, 0.932, and 0.779, respectively) and external (0.836, 0.940, 0.916, and 0.815, respectively) validations. DL-assisted measurements significantly improved most measurement values, particularly for trainees. Conclusion The DL algorithm was validated as an accurate tool for quantifying TL fracture features using radiographs. DL-assisted measurement is expected to expedite the diagnostic process and enhance reliability, particularly benefiting less experienced clinicians.

Objective: This study aimed to develop and validate a deep learning (DL) algorithm for the quantitative measurement of thoracolumbar (TL) fracture features, and to evaluate its efficacy across varying levels of clinical expertise. Methods: Using the pretrained Mask Region-Based Convolutional Neural Networks model, originally developed for vertebral body segmentation and fracture detection, we fine-tuned the model and added a new module for measuring fracture metrics—compression rate (CR), Cobb angle (CA), Gardner angle (GA), and sagittal index (SI)—from lumbar spine lateral radiographs. These metrics were derived from six-point labeling by 3 radiologists, forming the ground truth (GT). Training utilized 1,000 nonfractured and 318 fractured radiographs, while validations employed 213 internal and 200 external fractured radiographs. The accuracy of the DL algorithm in quantifying fracture features was evaluated against GT using the intraclass correlation coefficient. Additionally, 4 readers with varying expertise levels, including trainees and an attending spine surgeon, performed measurements with and without DL assistance, and their results were compared to GT and the DL model. Results: The DL algorithm demonstrated good to excellent agreement with GT for CR, CA, GA, and SI in both internal (0.860, 0.944, 0.932, and 0.779, respectively) and external (0.836, 0.940, 0.916, and 0.815, respectively) validations. DL-assisted measurements significantly improved most measurement values, particularly for trainees. Conclusion The DL algorithm was validated as an accurate tool for quantifying TL fracture features using radiographs. DL-assisted measurement is expected to expedite the diagnostic process and enhance reliability, particularly benefiting less experienced clinicians.

Objective: This study aimed to develop and validate a deep learning (DL) algorithm for the quantitative measurement of thoracolumbar (TL) fracture features, and to evaluate its efficacy across varying levels of clinical expertise. Methods: Using the pretrained Mask Region-Based Convolutional Neural Networks model, originally developed for vertebral body segmentation and fracture detection, we fine-tuned the model and added a new module for measuring fracture metrics—compression rate (CR), Cobb angle (CA), Gardner angle (GA), and sagittal index (SI)—from lumbar spine lateral radiographs. These metrics were derived from six-point labeling by 3 radiologists, forming the ground truth (GT). Training utilized 1,000 nonfractured and 318 fractured radiographs, while validations employed 213 internal and 200 external fractured radiographs. The accuracy of the DL algorithm in quantifying fracture features was evaluated against GT using the intraclass correlation coefficient. Additionally, 4 readers with varying expertise levels, including trainees and an attending spine surgeon, performed measurements with and without DL assistance, and their results were compared to GT and the DL model. Results: The DL algorithm demonstrated good to excellent agreement with GT for CR, CA, GA, and SI in both internal (0.860, 0.944, 0.932, and 0.779, respectively) and external (0.836, 0.940, 0.916, and 0.815, respectively) validations. DL-assisted measurements significantly improved most measurement values, particularly for trainees. Conclusion The DL algorithm was validated as an accurate tool for quantifying TL fracture features using radiographs. DL-assisted measurement is expected to expedite the diagnostic process and enhance reliability, particularly benefiting less experienced clinicians.

Korean Renal Data System (KORDS) is a nationwide end-stage renal disease (ESRD) registry database operated by the Korean Society of Nephrology (KSN). Diabetes mellitus is currently the leading cause of ESRD in Korea; this article provides an update on the trends and characteristics of diabetic ESRD patients. The KORDS Committee of KSN collects data on dialysis centers and patients through an online registry program. Here, we analyzed the status and trends in characteristics of diabetic chronic kidney disease stage 5D (CKD 5D) patients using data from 2001 to 2021. In 2021, the dialysis adequacy of hemodialysis (HD) was lower in diabetic CKD 5D patients than in nondiabetic CKD 5D patients, while that of peritoneal dialysis (PD) was similar. Diabetic CKD 5D patients had a higher proportion of cardiac and vascular diseases and were more frequently admitted to hospitals than nondiabetic CKD 5D patients, and the leading cause of death was cardiac disease. From 2001 to 2020, diabetic CKD 5D patients had a higher mortality rate than nondiabetic CKD 5D patients, but in 2021 this trend was reversed. Diabetic PD patients had the highest mortality rate over 20 years. The mortality rate of diabetic HD patients was higher than that of nondiabetic HD patients until 2019 but became lower starting in 2020. There was a decreasing trend in mortality rate in diabetic CKD 5D patients, but cardiac and vascular diseases were still prevalent in diabetic CKD 5D patients with frequent admissions to hospitals. More specialized care is needed to improve the clinical outcomes of diabetic CKD 5D patients.

With an increasing aging population, the mean age of patients with end-stage kidney disease (ESKD) is globally increasing. However, the current clinical status of elderly patients undergoing hemodialysis (HD) is rarely reported in Korea. The current study analyzed the clinical features and trends of older patients undergoing HD from the Korean Renal Data System (KORDS) database. The patients were divided into three groups according to age: <65 years (the young group), n = 50,591 (35.9%); 65–74 years (the younger-old group), n = 37,525 (26.6%); and ≥75 years (the older-old group), n = 52,856 (37.5%). The proportion of older-old group undergoing HD significantly increased in incidence and decreased in prevalence from 2013 to 2022. The median levels of hemoglobin, serum creatinine, albumin, calcium, phosphorus, and intact parathyroid hormone significantly decreased in the older-old group. The proportions of arteriovenous fistula creation and left forearm placement showed decreased trends with age. Although the utilization of low surface area dialyzers increased with age, the dialysis adequacy, including urea reduction ratio and Kt/V was within acceptable range in the older-old group on HD. Over the past 20 years, the mortality rate in the older-old group has increased, with cardiovascular diseases decreasing and infectious diseases increasing. The incidence of elderly patients undergoing HD has increased over time, but the high mortality of the older-old group needs to be solved. Therefore, it is imperative to develop holistic strategies based on age and individual needs for patients with ESKD.

Objective: The purpose of this study was to evaluate the esthetic preference for various Korean silhouette profiles. Methods: The Korean average male and female profiles were modified by changing the lower facial height and anteroposterior lip position to produce nine types of profiles. In order to test intrarater reliability, the average profile was copied once more to be included for evaluation. A questionnaire containing 10 profiles for each sex, each of which had to be rated for preference on a numerical rating scale from 0 to 10, was administered to 30 adult orthodontic patients, 30 dental students, 30 orthodontists, and 30 dentists excluding orthodontists. The data were statistically analyzed using the intraclass correlation coefficient (ICC), independent t-test, and one-way ANOVA. Results: The ICC of overall intrarater reliability was 0.629. For several profiles, significantly higher scores were given to male profiles than to female profiles (p < 0.05). However, no significant differences were found in the scores for all profiles among the four rater groups.Among the short profiles, a significantly higher score was given to the retruded profile, and among the vertically average and long profiles, a significantly higher score was given to the horizontally average profile (p < 0.001). Among all the profiles, significantly lower scores were given to the protruded profile (p < 0.001). Conclusions This study revealed good overall intrarater reliability, with several types of male profiles being esthetically preferred over female profiles. Moreover, while retruded and horizontally average profiles were generally preferred, protruded profiles were not.

OBJECTIVE: To compare the image quality of low-tube-voltage and low-iodine-concentration-contrast-medium (LVLC) computed tomography urography (CTU) with iterative reconstruction (IR) with that of conventional CTU. MATERIALS AND METHODS: This prospective, multi-institutional, randomized controlled trial was performed at 16 hospitals using CT scanners from various vendors. Patients were randomly assigned to the following groups: 1) the LVLC-CTU (80 kVp and 240 mgI/mL) with IR group and 2) the conventional CTU (120 kVp and 350 mgI/mL) with filtered-back projection group. The overall diagnostic acceptability, sharpness, and noise were assessed. Additionally, the mean attenuation, signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and figure of merit (FOM) in the urinary tract were evaluated. RESULTS: The study included 299 patients (LVLC-CTU group: 150 patients; conventional CTU group: 149 patients). The LVLC-CTU group had a significantly lower effective radiation dose (5.73 ± 4.04 vs. 8.43 ± 4.38 mSv) compared to the conventional CTU group. LVLC-CTU showed at least standard diagnostic acceptability (score ≥ 3), but it was non-inferior when compared to conventional CTU. The mean attenuation value, mean SNR, CNR, and FOM in all pre-defined segments of the urinary tract were significantly higher in the LVLC-CTU group than in the conventional CTU group. CONCLUSION: The diagnostic acceptability and quantitative image quality of LVLC-CTU with IR are not inferior to those of conventional CTU. Additionally, LVLC-CTU with IR is beneficial because both radiation exposure and total iodine load are reduced.
Commerce ; Contrast Media* ; Humans ; Iodine ; Noise ; Prospective Studies ; Radiation Exposure ; Signal-To-Noise Ratio ; Urinary Tract ; Urography*

A Hyalinizing Trabecular Tumor (HTT) is a very rare tumor. We report one case that was confirmed to be HTT after an operation. A 44-year-old female visited our hospital with about a 1.3-cm-sized mass on the left thyroid. Fine Needle Aspiration Biopsy (FNAB) indicated papillary thyroid cancer. After a left hemithyroidectomy, a frozen section biopsy reported the possibility of HTT. Therefore, we did not proceed with the surgery. According to the final report, she was diagnosed with HTT. Five lymph nodes were dissected and were found to be benign. Thyroid transcription factor-1 and neuron specific enolase were positive, and in addition calcitonin was negative. Ki-67 was recorded to be less than 5%. She was discharged without any complication. HTT is benign in most cases, but the possibility of malignancy should be considered. Because it is hard to differentiate between it and PTC or MTC, an accurate diagnosis through histologic examination of specimens and surgical resection is necessary.
Adult ; Biopsy ; Biopsy, Fine-Needle ; Calcitonin ; Diagnosis ; Female ; Frozen Sections ; Humans ; Hyalin* ; Lymph Nodes ; Phosphopyruvate Hydratase ; Thyroid Gland* ; Thyroid Neoplasms