A deep learning model based on fusion images of chest radiography and X-ray sponge images supports human visual characteristics of retained surgical items detection
A deep learning model based on fusion images of chest radiography and X-ray sponge images supports human visual characteristics of retained surgical items detection
复制标题
DOI：
10.1007/s11548-022-02816-8
复制
发表时间：
2022-12-30
影响因子：
3
通讯作者：
Ishigami, Kousei
中科院分区：
文献类型：
--
作者：
Kawakubo, Masateru;Waki, Hiroto;Ishigami, Kousei
目的虽然提出了一种新的深度学习软件，该软件使用通过融合正常术后X射线摄影和手术海绵的X射线图像获得的后处理图像，但尚未充分研究保留的手术项目可检测性与人类视觉评估的关联。在这项研究中，我们调查了深度学习和人类主观评价之间的关联性保留的手术项目detectability.方法从2987个训练图像和1298个验证图像构建深度学习模型，这些图像是通过对正常术后X射线图像和手术海绵之间的图像融合进行后处理获得的。然后，使用另外800个图像，即，400个有手术海绵和400个没有手术海绵。结果深度学习模型和观察者分别得出以下值：概率的截断值分别为0.37和0.45，曲线下面积分别为0.87和0.76;结论对于手术海绵的检测，深度学习模型具有更高的灵敏度，而人类观察者具有更高的特异性。这些特征表明，与人类互补的深度学习系统可以支持手术室的临床工作流程，以防止手术物品残留。目的虽然提出了一种新的深度学习软件，该软件使用通过融合正常术后放射线照相的X射线图像和手术海绵而获得的后处理图像，保留的手术物品可检测性与人类视觉评估的关联还没有被充分地检验。在这项研究中，我们调查了深度学习和人类主观评价之间保留手术项目可检测性的关联。方法利用2987幅训练图像和1298幅验证图像构建深度学习模型，其中训练图像和验证图像是通过对正常手术后X线片和手术海绵的图像融合后处理获得的。然后，使用另外800个图像，即，400个有手术海绵和400个没有手术海绵。使用受试者操作者特征分析模型和具有10年临床经验的一般观察者之间的残留海绵的检测特征。从深度学习模型和观察者分别得出以下值：概率的截止值为0.37和0.45;曲线下面积为0.87和0.76;灵敏度值为85%和61%;特异性值为73%和92%。结论对于手术海绵的检测，我们得出结论，深度学习模型具有更高的灵敏度，而人类观察者具有更高的特异性。这些特征表明，与人类互补的深度学习系统可以支持手术室的临床工作流程，以防止手术物品残留。
Purpose Although a novel deep learning software was proposed using post-processed images obtained by the fusion between X-ray images of normal post-operative radiography and surgical sponge, the association of the retained surgical item detectability with human visual evaluation has not been sufficiently examined. In this study, we investigated the association of retained surgical item detectability between deep learning and human subjective evaluation.Methods A deep learning model was constructed from 2987 training images and 1298 validation images, which were obtained from post-processing of the image fusion between X-ray images of normal post-operative radiography and surgical sponge. Then, another 800 images were used, i.e., 400 with and 400 without surgical sponge. The detection characteristics of retained sponges between the model and a general observer with 10-year clinical experience were analyzed using the receiver operator characteristics.Results The following values from the deep learning model and observer were, respectively, derived: Cutoff values of probability were 0.37 and 0.45; areas under the curves were 0.87 and 0.76; sensitivity values were 85% and 61%; and specificity values were 73% and 92%.Conclusion For the detection of surgical sponges, we concluded that the deep learning model has higher sensitivity, while the human observer has higher specificity. These characteristics indicate that the deep learning system that is complementary to humans could support the clinical workflow in operation rooms for prevention of retained surgical items.PurposeAlthough a novel deep learning software was proposed using post-processed images obtained by the fusion between X-ray images of normal post-operative radiography and surgical sponge, the association of the retained surgical item detectability with human visual evaluation has not been sufficiently examined. In this study, we investigated the association of retained surgical item detectability between deep learning and human subjective evaluation. MethodsA deep learning model was constructed from 2987 training images and 1298 validation images, which were obtained from post-processing of the image fusion between X-ray images of normal post-operative radiography and surgical sponge. Then, another 800 images were used, i.e., 400 with and 400 without surgical sponge. The detection characteristics of retained sponges between the model and a general observer with 10-year clinical experience were analyzed using the receiver operator characteristics. ResultsThe following values from the deep learning model and observer were, respectively, derived: Cutoff values of probability were 0.37 and 0.45; areas under the curves were 0.87 and 0.76; sensitivity values were 85% and 61%; and specificity values were 73% and 92%. ConclusionFor the detection of surgical sponges, we concluded that the deep learning model has higher sensitivity, while the human observer has higher specificity. These characteristics indicate that the deep learning system that is complementary to humans could support the clinical workflow in operation rooms for prevention of retained surgical items.