Chen Yueh-Sheng, Luo Sheng-Dean, Lee Chi-Hsun, Lin Jian-Feng, Lin Te-Yen, Ko Sheung-Fat, Yu Chiun-Chieh, Chiang Pi-Ling, Wang Cheng-Kang, Chiu I-Min, Huang Yii-Ting, Tai Yi-Fan, Chiang Po-Teng, Lin Wei-Che
Department of Diagnostic Radiology, Kaohsiung Chang Gung Memorial Hospital, Chang Gung University College of Medicine, 123 Ta-Pei Road, Niao-Sung, Kaohsiung, 83305, Taiwan.
Department of Otolaryngology, Kaohsiung Chang Gung Memorial Hospital, Kaohsiung, Taiwan.
Insights Imaging. 2023 Mar 16;14(1):43. doi: 10.1186/s13244-023-01385-x.
We aimed to develop a deep learning artificial intelligence (AI) algorithm to detect impacted animal bones on lateral neck radiographs and to assess its effectiveness for improving the interpretation of lateral neck radiographs.
Lateral neck radiographs were retrospectively collected for patients with animal bone impaction between January 2010 and March 2020. Radiographs were then separated into training, validation, and testing sets. A total of 1733 lateral neck radiographs were used to develop the deep learning algorithm. The testing set was assessed for the stand-alone deep learning AI algorithm and for human readers (radiologists, radiology residents, emergency physicians, ENT physicians) with and without the aid of the AI algorithm. Another radiograph cohort, collected from April 1, 2020, to June 30, 2020, was analyzed to simulate clinical application by comparing the deep learning AI algorithm with radiologists' reports.
In the testing set, the sensitivity, specificity, and accuracy of the AI model were 96%, 90%, and 93% respectively. Among the human readers, all physicians of different subspecialties achieved a higher accuracy with AI-assisted reading than without. In the simulation set, among the 20 cases positive for animal bones, the AI model accurately identified 3 more cases than the radiologists' reports.
Our deep learning AI model demonstrated a higher sensitivity for detection of animal bone impaction on lateral neck radiographs without an increased false positive rate. The application of this model in a clinical setting may effectively reduce time to diagnosis, accelerate workflow, and decrease the use of CT.
我们旨在开发一种深度学习人工智能（AI）算法，以检测颈部侧位X线片上的嵌顿动物骨头，并评估其在改善颈部侧位X线片解读方面的有效性。
回顾性收集2010年1月至2020年3月间有动物骨头嵌顿的患者的颈部侧位X线片。然后将X线片分为训练集、验证集和测试集。共使用1733张颈部侧位X线片来开发深度学习算法。对测试集评估了独立的深度学习AI算法以及有和没有AI算法辅助的人类读者（放射科医生、放射科住院医师、急诊科医生、耳鼻喉科医生）。通过将深度学习AI算法与放射科医生的报告进行比较，分析了另一组于2020年4月1日至2020年6月30日收集的X线片，以模拟临床应用。
在测试集中，AI模型的敏感性、特异性和准确性分别为96%、90%和93%。在人类读者中，所有不同亚专业的医生在AI辅助阅读时的准确性都高于无辅助阅读时。在模拟集中，在20例动物骨头阳性病例中，AI模型比放射科医生的报告准确多识别出3例。
我们的深度学习AI模型在检测颈部侧位X线片上的动物骨头嵌顿时显示出更高的敏感性，且假阳性率未增加。该模型在临床环境中的应用可能有效减少诊断时间、加速工作流程并减少CT的使用。
