Deep Learning-Based MRI Volumetry for Living Kidney Donor Assessment: A New Tool for Predicting Post-Donation Renal Function.
Аннотация
BACKGROUND
Living kidney donation is a crucial option for addressing the global organ shortage and providing kidney transplantation for patients suffering from end-stage kidney disease. Ensuring donor safety necessitates a comprehensive preoperative assessment of kidney anatomy and function. This study evaluates the relationship between kidney volumes derived from deep learning-based MRI volumetry, intraoperative kidney volume measurements, split renal function measured by renal scintigraphy, and post-donation eGFR. Deep learning-based MRI volumetry is hypothesized to be a reliable method with good correlation.
METHODS
This retrospective study analyzed 178 living kidney donors. Deep learning MRI volumetry-based kidney volumes were compared with intraoperative volumes of the explanted donor kidneys obtained using the water displacement method. Additionally, MRI-based volume ratios were compared with scintigraphy-based split renal function ratios to determine their ability to predict the kidney with poorer renal function and post-donation eGFR.
RESULTS
Deep learning-based MRI volumetry strongly correlated with intraoperatively measured kidney volumes (Pearson's correlation; r = 0.7671; p < 0.0001), confirming its precision in volume estimation. Although MRI-based kidney volume ratios demonstrated only a moderate correlation with scintigraphy-based split renal function ratios (r = 0.4798), MRI volumetry correlated with 1-year post-donation eGFR. It tended to be better than renal scintigraphy (r = 0.6829 versus r = 0.6191).
CONCLUSION
Deep learning-based MRI volumetry is a reliable, non-invasive tool for estimating kidney volumes in living donors, offering a radiation-free alternative for preoperative assessment. While it differs from renal scintigraphy in evaluating split renal function ratios, its correlation with post-donation eGFR tends to be better, supporting its potential role in living kidney donor assessment.
Предметные рубрики MeSH
Подготовка и перевод публикации
Обработка статьи · этапы, ошибки и управление
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Тип публикации указан по данным источника. Уровень доказательности автоматически не присваивается.