Li Dantong, Hu Lianting, Peng Xiaoting, Xiao Ning, Zhao Hong, Liu Guangjian, Liu Hongsheng, Li Kuanrong, Ai Bin, Xia Huimin, Lu Long, Gao Yunfei, Wu Jian, Liang Huiying
Medical Big Data Center, Guangdong Provincial People's Hospital/Guangdong Academy of Medical Sciences, Guangzhou, Guangdong Province 510080, China.
Guangdong Cardiovascular Institute, Guangzhou, Guangdong Province 510080, China.
iScience. 2022 Feb 21;25(3):103961. doi: 10.1016/j.isci.2022.103961. eCollection 2022 Mar 18.
Artificial Intelligence (AI) has achieved state-of-the-art performance in medical imaging. However, most algorithms focused exclusively on improving the accuracy of classification while neglecting the major challenges in a real-world application. The opacity of algorithms prevents users from knowing when the algorithms might fail. And the natural gap between training datasets and the in-reality data may lead to unexpected AI system malfunction. Knowing the underlying uncertainty is essential for improving system reliability. Therefore, we developed a COVID-19 AI system, utilizing a Bayesian neural network to calculate uncertainties in classification and reliability intervals of datasets. Validated with four multi-region datasets simulating different scenarios, our approach was proved to be effective to suggest the system failing possibility and give the decision power to human experts in time. Leveraging on the complementary strengths of AI and health professionals, our present method has the potential to improve the practicability of AI systems in clinical application.
人工智能（AI）在医学成像领域已取得了最先进的性能。然而，大多数算法仅专注于提高分类的准确性，却忽略了实际应用中的主要挑战。算法的不透明性使用户无法知晓算法何时可能会失效。而且训练数据集与现实数据之间的天然差距可能会导致人工智能系统意外出现故障。了解潜在的不确定性对于提高系统可靠性至关重要。因此，我们开发了一个新冠病毒人工智能系统，利用贝叶斯神经网络来计算分类中的不确定性以及数据集的可靠性区间。通过四个模拟不同场景的多区域数据集进行验证，我们的方法被证明能有效地提示系统失效的可能性，并及时将决策权交给人类专家。利用人工智能与卫生专业人员的互补优势，我们目前的方法有潜力提高人工智能系统在临床应用中的实用性。
