Department of Radiology, Massachusetts General Hospital and Harvard Medical School, 75 Blossom Court, Suite 248, Boston, MA 02114; Mass General Brigham Data Science Office (DSO), 100 Cambridge St, Boston, MA, US 02114.
Department of Radiology, Massachusetts General Hospital and Harvard Medical School, 75 Blossom Court, Suite 248, Boston, MA 02114.
Acad Radiol. 2023 Dec;30(12):2921-2930. doi: 10.1016/j.acra.2023.03.006. Epub 2023 Apr 3.
Suboptimal chest radiographs (CXR) can limit interpretation of critical findings. Radiologist-trained AI models were evaluated for differentiating suboptimal(sCXR) and optimal(oCXR) chest radiographs.
Our IRB-approved study included 3278 CXRs from adult patients (mean age 55 ± 20 years) identified from a retrospective search of CXR in radiology reports from 5 sites. A chest radiologist reviewed all CXRs for the cause of suboptimality. The de-identified CXRs were uploaded into an AI server application for training and testing 5 AI models. The training set consisted of 2202 CXRs (n = 807 oCXR; n = 1395 sCXR) while 1076 CXRs (n = 729 sCXR; n = 347 oCXR) were used for testing. Data were analyzed with the Area under the curve (AUC) for the model's ability to classify oCXR and sCXR correctly.
For the two-class classification into sCXR or oCXR from all sites, for CXR with missing anatomy, AI had sensitivity, specificity, accuracy, and AUC of 78%, 95%, 91%, 0.87(95% CI 0.82-0.92), respectively. AI identified obscured thoracic anatomy with 91% sensitivity, 97% specificity, 95% accuracy, and 0.94 AUC (95% CI 0.90-0.97). Inadequate exposure with 90% sensitivity, 93% specificity, 92% accuracy, and AUC of 0.91 (95% CI 0.88-0.95). The presence of low lung volume was identified with 96% sensitivity, 92% specificity, 93% accuracy, and 0.94 AUC (95% CI 0.92-0.96). The sensitivity, specificity, accuracy, and AUC of AI in identifying patient rotation were 92%, 96%, 95%, and 0.94 (95% CI 0.91-0.98), respectively.
The radiologist-trained AI models can accurately classify optimal and suboptimal CXRs. Such AI models at the front end of radiographic equipment can enable radiographers to repeat sCXRs when necessary.
不完美的胸部 X 光片（CXR）可能会限制对关键发现的解读。经过放射科医生培训的人工智能模型已被用于区分不完美（sCXR）和完美（oCXR）的胸部 X 光片。
我们的机构审查委员会批准的研究包括从五个地点的放射科报告中回顾性搜索 CXR 中确定的 3278 例成人患者的 CXR（平均年龄 55 ± 20 岁）。一名胸部放射科医生对所有 CXR 进行了不完美原因的评估。将去识别的 CXR 上传到人工智能服务器应用程序中，用于训练和测试 5 个人工智能模型。训练集包括 2202 例 CXR（n = 807 oCXR；n = 1395 sCXR），而 1076 例 CXR（n = 729 sCXR；n = 347 oCXR）用于测试。使用曲线下面积（AUC）分析数据，以评估模型正确分类 oCXR 和 sCXR 的能力。
对于来自所有站点的 sCXR 或 oCXR 的双分类，对于缺少解剖结构的 CXR，AI 的敏感性、特异性、准确性和 AUC 分别为 78%、95%、91%和 0.87（95%CI 0.82-0.92）。AI 识别出胸部解剖结构模糊的敏感度为 91%，特异性为 97%，准确性为 95%，AUC 为 0.94（95%CI 0.90-0.97）。曝光不足的敏感度为 90%，特异性为 93%，准确性为 92%，AUC 为 0.91（95%CI 0.88-0.95）。低肺容量的存在以 96%的敏感度、92%的特异性、93%的准确性和 0.94 的 AUC（95%CI 0.92-0.96）来识别。AI 识别患者旋转的敏感性、特异性、准确性和 AUC 分别为 92%、96%、95%和 0.94（95%CI 0.91-0.98）。
经过放射科医生培训的人工智能模型可以准确地对完美和不完美的 CXR 进行分类。这种在放射设备前端的人工智能模型可以使放射技师在必要时重复拍摄不完美的 CXR。
