深度学习系统用于预测囊性病变中的恶性瘤风险:一个多中心研究
Quan-Hao He1, Jia-Jun Feng2, Ling-Cheng Wu1
1Department of Urology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, People's Republic of China.
Insights into imaging
|May 19, 2024
概括
一个人工智能 (AI) 系统准确地预测了囊性病变 (CRLs) 中的恶性瘤风险. 这种非侵入性工具可以改善诊断,减少不必要的治疗和对普遍存在的偶然CRL进行后续检查.
科学领域:
- 医学成像分析 医学成像分析
- 医疗保健中的人工智能
- 脏病理学 脏病理学
背景情况:
- 囊性病变 (CRLs) 越来越多地被检测到,需要准确的恶性瘤风险分层.
- 区分良性与恶性CRL对于适当的患者管理至关重要.
- 当前的诊断方法可能具有侵入性或缺乏绝对准确性.
研究的目的:
- 开发和验证一个交互式,非侵入性人工智能 (AI) 系统,用于预测CRL中的恶性瘤风险.
- 为了提高CRL的诊断准确性和临床决策.
- 减少与偶然的CRL相关的过度处理和过度随访.
主要方法:
- 一项回顾性多中心研究,涉及715名具有CRL的患者.
- 使用基于地理的方法开发CRL的3D细分模型.
- 实现一个空间编码器时间解码器 (SETD) 分类模型,结合3D-ResNet50和封闭循环单元 (GRU) 进行多相CT分析.
- 使用AUC,准确性,子相似性,IOU,敏感性和特异性等指标进行性能评估.
主要成果:
- 人工智能系统在验证和测试数据集方面都取得了出色的表现.
- 验证数据集:AUC=0.973,准确度=0.916,子=0.847,账单=0.743,灵敏度=0.840,特异性=1.000.这些数据集中的AUC值为0.973,准确度=0.916,子=0.847,账单=0.743,敏感度=0.840,特异性=1.000.
- 测试数据集:AUC=0.998,准确度=0.988,子=0.861,IOU=0.762,敏感度=0.876,特异性=1.000. 测试数据集:AUC=0.998,准确度=0.988,子=0.861,IOU=0.762,敏感度=0.876,特异性=1.000. 测试数据集:AUC=0.998,准确度=0.988,子=0.861,IOU=0.762,敏感度=0.876,特异性=1.000.
结论:
- 人工智能系统表现出强大的区分良性和恶性CRL的能力.
- 开发的系统显示了改善CRL管理中的临床决策的巨大潜力.
- 这种非侵入性AI工具为CRL准确诊断提供了一个有前途的解决方案,在普遍偶然发现的时代.
更多相关视频
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
8.2K
07:15Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
6.8K
相关概念视频
02:43Mouse Models of Cancer Study
Mice have long served as models for studying human biology and pathology because of their phylogenetic and physiological similarity with humans. They are also easy to maintain and breed in the laboratory, and hence, many inbred strains are now available for research. Studies on mice have contributed immeasurably to our understanding of cancer biology.
The development of transgenic, knockout, and knock-in mice has led to an exponential increase in their use as model organisms in research,...
The development of transgenic, knockout, and knock-in mice has led to an exponential increase in their use as model organisms in research,...
02:43Mouse Models of Cancer Study
Mice have long served as models for studying human biology and pathology because of their phylogenetic and physiological similarity with humans. They are also easy to maintain and breed in the laboratory, and hence, many inbred strains are now available for research. Studies on mice have contributed immeasurably to our understanding of cancer biology.
The development of transgenic, knockout, and knock-in mice has led to an exponential increase in their use as model organisms in research,...
The development of transgenic, knockout, and knock-in mice has led to an exponential increase in their use as model organisms in research,...