Department of Radiology, Huzhou Central Hospital, Affiliated Central Hospital of Huzhou University, Huzhou, 313000, Zhejiang Province, China.
Institute of Clinical Research, Biomind Technology, Beijing, 100050, China.
BMC Med Imaging. 2022 Mar 14;22(1):45. doi: 10.1186/s12880-022-00772-y.
Hematoma expansion is an independent predictor of patient outcome and mortality. The early diagnosis of hematoma expansion is crucial for selecting clinical treatment options. This study aims to explore the value of a deep learning algorithm for the prediction of hematoma expansion from non-contrast computed tomography (NCCT) scan through external validation.
102 NCCT images of hypertensive intracerebral hemorrhage (HICH) patients diagnosed in our hospital were retrospectively reviewed. The initial computed tomography (CT) scan images were evaluated by a commercial Artificial Intelligence (AI) software using deep learning algorithm and radiologists respectively to predict hematoma expansion and the corresponding sensitivity, specificity and accuracy of the two groups were calculated and compared. Comparisons were also conducted among gold standard hematoma expansion diagnosis time, AI software diagnosis time and doctors' reading time.
Among 102 HICH patients, the sensitivity, specificity, and accuracy of hematoma expansion prediction in the AI group were higher than those in the doctor group(80.0% vs 66.7%, 73.6% vs 58.3%, 75.5% vs 60.8%), with statistically significant difference (p < 0.05). The AI diagnosis time (2.8 ± 0.3 s) and the doctors' diagnosis time (11.7 ± 0.3 s) were both significantly shorter than the gold standard diagnosis time (14.5 ± 8.8 h) (p < 0.05), AI diagnosis time was significantly shorter than that of doctors (p < 0.05).
Deep learning algorithm could effectively predict hematoma expansion at an early stage from the initial CT scan images of HICH patients after onset with high sensitivity and specificity and greatly shortened diagnosis time, which provides a new, accurate, easy-to-use and fast method for the early prediction of hematoma expansion.
血肿扩大是患者预后和死亡率的独立预测因子。血肿扩大的早期诊断对于选择临床治疗方案至关重要。本研究旨在通过外部验证探讨深度学习算法从非增强 CT（NCCT）扫描预测血肿扩大的价值。
回顾性分析我院诊断的 102 例高血压性脑出血（HICH）患者的 102 例 NCCT 图像。初始 CT 扫描图像分别由商业人工智能（AI）软件和放射科医生使用深度学习算法进行评估，以预测血肿扩大，计算并比较两组的敏感性、特异性和准确性。还比较了金标准血肿扩大诊断时间、AI 软件诊断时间和医生阅读时间。
在 102 例 HICH 患者中，AI 组预测血肿扩大的敏感性、特异性和准确性均高于医生组（80.0%比 66.7%、73.6%比 58.3%、75.5%比 60.8%），差异有统计学意义（p<0.05）。AI 诊断时间（2.8±0.3 s）和医生诊断时间（11.7±0.3 s）均明显短于金标准诊断时间（14.5±8.8 h）（p<0.05），AI 诊断时间明显短于医生（p<0.05）。
深度学习算法可以从 HICH 患者发病后的初始 CT 扫描图像中有效预测血肿早期扩大，具有较高的敏感性和特异性，并大大缩短了诊断时间，为血肿早期预测提供了一种新的、准确、易用、快速的方法。
