PDF(Pubmed)
Abstract：
UNASSIGNED: Necrotizing enterocolitis (NEC) is a severe neonatal intestinal disease, often occurring in preterm infants following the administration of hyperosmolar formula. It is one of the leading causes of neonatal mortality in the NICU, and currently, there are no clear standards for surgical intervention, which typically depends on the joint discretion of surgeons and neonatologists. In recent years, deep learning has been extensively applied in areas such as image segmentation, fracture and pneumonia classification, drug development, and pathological diagnosis.
UNASSIGNED: Investigating deep learning applications using bedside x-rays to help optimizing surgical decision-making in neonatal NEC.
UNASSIGNED: Through a retrospective analysis of anteroposterior bedside chest and abdominal x-rays from 263 infants diagnosed with NEC between January 2015 and April 2023, including a surgery group (94 cases) and a non-surgery group (169 cases), the infants were divided into a training set and a validation set in a 7:3 ratio. Models were built based on Resnet18, Densenet121, and SimpleViT to predict whether NEC patients required surgical intervention. Finally, the model\'s performance was tested using an additional 40 cases, including both surgical and non-surgical NEC cases, as a test group. To enhance the interpretability of the models, the study employed 2D-Grad-CAM technology to describe the models\' focus on significant areas within the x-ray images.
UNASSIGNED: Resnet18 demonstrated outstanding performance in binary diagnostic capability, achieving an accuracy of 0.919 with its precise lesion imaging and interpretability particularly highlighted. Its precision, specificity, sensitivity, and F1 score were significantly high, proving its advantages in optimizing surgical decision-making for neonatal NEC.
UNASSIGNED: The Resnet18 deep learning model, constructed using bedside chest and abdominal imaging, effectively assists clinical physicians in determining whether infants with NEC require surgical intervention.
UNASSIGNED: Investigating deep learning applications using bedside x-rays to help optimizing surgical decision-making in neonatal NEC.
UNASSIGNED: Through a retrospective analysis of anteroposterior bedside chest and abdominal x-rays from 263 infants diagnosed with NEC between January 2015 and April 2023, including a surgery group (94 cases) and a non-surgery group (169 cases), the infants were divided into a training set and a validation set in a 7:3 ratio. Models were built based on Resnet18, Densenet121, and SimpleViT to predict whether NEC patients required surgical intervention. Finally, the model\'s performance was tested using an additional 40 cases, including both surgical and non-surgical NEC cases, as a test group. To enhance the interpretability of the models, the study employed 2D-Grad-CAM technology to describe the models\' focus on significant areas within the x-ray images.
UNASSIGNED: Resnet18 demonstrated outstanding performance in binary diagnostic capability, achieving an accuracy of 0.919 with its precise lesion imaging and interpretability particularly highlighted. Its precision, specificity, sensitivity, and F1 score were significantly high, proving its advantages in optimizing surgical decision-making for neonatal NEC.
UNASSIGNED: The Resnet18 deep learning model, constructed using bedside chest and abdominal imaging, effectively assists clinical physicians in determining whether infants with NEC require surgical intervention.
摘要：
■坏死性小肠结肠炎（NEC）是一种严重的新生儿肠道疾病，常发生在早产儿服用高渗配方后。它是NICU新生儿死亡的主要原因之一，目前,手术干预没有明确的标准，这通常取决于外科医生和新生儿科医师的共同判断。近年来,深度学习已经广泛应用于图像分割等领域，骨折和肺炎分类，药物开发,和病理诊断。
■使用床边X射线研究深度学习应用，以帮助优化新生儿NEC的手术决策。
■通过对2015年1月至2023年4月诊断为NEC的263例婴儿的前后床旁胸部和腹部X射线的回顾性分析，包括手术组（94例）和非手术组（169例），以7:3的比例将婴儿分为训练集和验证集.基于Resnet18，Densenet121和SimpleViT建立模型，以预测NEC患者是否需要手术干预。最后,使用额外的40个案例测试了模型的性能，包括手术和非手术的NEC病例，作为一个测试组。为了增强模型的可解释性，该研究采用2D-Grad-CAM技术来描述模型，重点放在X射线图像中的重要区域。
■Resnet18在二进制诊断能力方面表现突出，达到0.919的准确性，其精确的病变成像和可解释性特别强调。它的精度，特异性，灵敏度,F1得分明显较高，证明了其在优化新生儿NEC手术决策方面的优势。
■Resnet18深度学习模型，使用床边胸部和腹部成像构建，有效地帮助临床医生确定NEC婴儿是否需要手术干预。
■使用床边X射线研究深度学习应用，以帮助优化新生儿NEC的手术决策。
■通过对2015年1月至2023年4月诊断为NEC的263例婴儿的前后床旁胸部和腹部X射线的回顾性分析，包括手术组（94例）和非手术组（169例），以7:3的比例将婴儿分为训练集和验证集.基于Resnet18，Densenet121和SimpleViT建立模型，以预测NEC患者是否需要手术干预。最后,使用额外的40个案例测试了模型的性能，包括手术和非手术的NEC病例，作为一个测试组。为了增强模型的可解释性，该研究采用2D-Grad-CAM技术来描述模型，重点放在X射线图像中的重要区域。
■Resnet18在二进制诊断能力方面表现突出，达到0.919的准确性，其精确的病变成像和可解释性特别强调。它的精度，特异性，灵敏度,F1得分明显较高，证明了其在优化新生儿NEC手术决策方面的优势。
■Resnet18深度学习模型，使用床边胸部和腹部成像构建，有效地帮助临床医生确定NEC婴儿是否需要手术干预。
