Park Inseo, Moon Gwiseong, Hong Ji Young, Heo Jeongwon, Ko Hongseok, Lee Doohee, Kim Yoon, Kim Woo Jin, Choi Hyun-Soo, Moon Kyoung Min
Department of Research and Development, ZIOVISION Co. Ltd., Chuncheon, 24341, Kangwon, Republic of Korea.
Division of Pulmonary and Critical Care Medicine, Department of Medicine, Chuncheon Sacred Heart Hospital, Hallym University Medical Center, Chuncheon, 24253, Republic of Korea.
Sci Rep. 2025 Apr 25;15(1):14556. doi: 10.1038/s41598-025-98562-3.
Accurate placement of nasogastric tubes (NGTs) is crucial for ensuring patient safety and effective treatment. Traditional methods relying on manual inspection are susceptible to human error, highlighting the need for innovative solutions. This study introduces a deep-learning model that enhances the detection and analysis of NGT positioning in chest radiographs. By integrating advanced segmentation and classification techniques, the model leverages the nnU-Net framework for segmenting critical regions and the ResNet50 architecture, pre-trained with MedCLIP, for classifying NGT placement. Trained on 1799 chest radiographs, the model demonstrates remarkable performance, achieving a Dice Similarity Coefficient of 65.35% for segmentation and an Area Under the Curve of 99.72% for classification. These results underscore its ability to accurately distinguish between correct and incorrect placements, outperforming traditional approaches. This method not only enhances diagnostic precision but also has the potential to streamline clinical workflows and improve patient care. A functional prototype of the model is accessible at https://ngtube.ziovision.ai .
鼻胃管（NGT）的准确放置对于确保患者安全和有效治疗至关重要。依赖人工检查的传统方法容易出现人为错误，这凸显了创新解决方案的必要性。本研究引入了一种深度学习模型，该模型可增强胸部X光片中鼻胃管位置的检测和分析。通过整合先进的分割和分类技术，该模型利用nnU-Net框架分割关键区域，并利用经MedCLIP预训练的ResNet50架构对鼻胃管放置进行分类。该模型在1799张胸部X光片上进行训练，表现出卓越的性能，分割的骰子相似系数达到65.35%，分类的曲线下面积达到99.72%。这些结果凸显了其准确区分正确和错误放置的能力，优于传统方法。该方法不仅提高了诊断精度，还具有简化临床工作流程和改善患者护理的潜力。该模型的功能原型可在https://ngtube.ziovision.ai上获取。
