比较人工智能算法在检测数字化胸部X光片中肺结核放射学征象及其智能手机拍摄的X光片照片中的输出：回顾性研究。
Comparing the Output of an Artificial Intelligence Algorithm in Detecting Radiological Signs of Pulmonary Tuberculosis in Digital Chest X-Rays and Their Smartphone-Captured Photos of X-Ray Films: Retrospective Study.
作者信息
Ridhi Smriti, Robert Dennis, Soren Pitamber, Kumar Manish, Pawar Saniya, Reddy Bhargava
机构信息
Department of International Health, Johns Hopkins Bloomberg School of Public Health, Baltimore, MD, United States.
Qure.ai, Bangalore, India.
出版信息
JMIR Form Res. 2024 Aug 21;8:e55641. doi: 10.2196/55641.
BACKGROUND
Artificial intelligence (AI) based computer-aided detection devices are recommended for screening and triaging of pulmonary tuberculosis (TB) using digital chest x-ray (CXR) images (soft copies). Most AI algorithms are trained using input data from digital CXR Digital Imaging and Communications in Medicine (DICOM) files. There can be scenarios when only digital CXR films (hard copies) are available for interpretation. A smartphone-captured photo of the digital CXR film may be used for AI to process in such a scenario. There is a gap in the literature investigating if there is a significant difference in the performance of AI algorithms when digital CXR DICOM files are used as input for AI to process as opposed to photos of the digital CXR films being used as input.
OBJECTIVE
The primary objective was to compare the agreement of AI in detecting radiological signs of TB when using DICOM files (denoted as CXR) as input versus when using smartphone-captured photos of digital CXR films (denoted as CXR) with human readers.
METHODS
Pairs of CXR and CXR images were obtained retrospectively from patients screened for TB. AI results were obtained using both the CXR and CXR files. The majority consensus on the presence or absence of TB in CXR pairs was obtained from a panel of 3 independent radiologists. The positive and negative percent agreement of AI in detecting radiological signs of TB in CXR and CXR were estimated by comparing with the majority consensus. The distribution of AI probability scores was also compared.
RESULTS
A total of 1278 CXR pairs were analyzed. The positive percent agreement of AI was found to be 92.22% (95% CI 89.94-94.12) and 90.75% (95% CI 88.32-92.82), respectively, for CXR and CXR images (P=.09). The negative percent agreement of AI was 82.08% (95% CI 78.76-85.07) and 79.23% (95% CI 75.75-82.42), respectively, for CXR and CXR images (P=.06). The median of the AI probability score was 0.72 (IQR 0.11-0.97) in CXR and 0.72 (IQR 0.14-0.96) in CXR images (P=.75).
CONCLUSIONS
We did not observe any statistically significant differences in the output of AI in digital CXRs and photos of digital CXR films.
背景
基于人工智能（AI）的计算机辅助检测设备被推荐用于使用数字化胸部X线（CXR）图像（电子副本）对肺结核（TB）进行筛查和分流。大多数AI算法是使用来自数字化CXR医学数字成像和通信（DICOM）文件的输入数据进行训练的。在某些情况下，可能只有数字化CXR胶片（硬拷贝）可供解读。在这种情况下，数字化CXR胶片的智能手机拍摄照片可用于AI处理。在文献中，对于将数字化CXR DICOM文件用作AI处理的输入与将数字化CXR胶片的照片用作输入时，AI算法的性能是否存在显著差异，存在研究空白。
目的
主要目的是比较AI在将DICOM文件（表示为CXR）用作输入与将数字化CXR胶片的智能手机拍摄照片（表示为CXR）用作输入时，在检测TB放射学征象方面与人类阅片者的一致性。
方法
回顾性获取筛选TB患者的CXR和CXR图像对。使用CXR和CXR文件均获得AI结果。由3名独立放射科医生组成的小组对CXR图像对中是否存在TB达成多数共识。通过与多数共识进行比较，估计AI在检测CXR和CXR中TB放射学征象方面的阳性和阴性百分比一致性。还比较了AI概率评分的分布。
结果
共分析了1278对CXR图像。对于CXR和CXR图像，AI的阳性百分比一致性分别为92.22%（95%CI 89.94 - 94.12）和90.75%（95%CI 88.32 - 92.82）（P = 0.09）。对于CXR和CXR图像，AI的阴性百分比一致性分别为82.08%（95%CI 78.76 - 85.07）和79.23%（95%CI 75.75 - 82.42）（P = 0.06）。CXR中AI概率评分的中位数为0.72（IQR 0.11 - 0.97），CXR图像中为0.72（IQR 0.14 - 0.96）（P = 0.75）。
结论
我们未观察到数字化CXR和数字化CXR胶片照片中AI输出的任何统计学显著差异。
Zotero 插件