对可靠的皮肤病变分类符合预测的实证验证
Jamil Fayyad1, Shadi Alijani1, Homayoun Najjaran1
1University of Victoria, 800 Finnerty Road, Victoria, V8P 5C2, BC, Canada; Cognia AI, 2031 Store street, Victoria, V8T 5L9, BC, Canada.
Computer methods and programs in biomedicine
|May 31, 2024
概括
符合性预测增强了医疗成像深度学习模型中的不确定性量化. 这种无分发的方法提供了强大而一致的性能,非常适合安全关键的应用.
科学领域:
- 人工智能的人工智能
- 医疗成像医学成像
- 机器学习 机器学习
背景情况:
- 不确定性量化对于可靠的AI系统至关重要,特别是在高风险的应用中.
- 现有的方法通常需要特定的假设或网络修改.
- 合规预测是一种新兴的无分布技术,用于量化不确定性.
研究的目的:
- 对医学成像中的其他不确定性量化方法进行一致预测的评估.
- 了解各种技术的优点和局限性.
- 评估各种医学成像数据集的性能.
主要方法:
- 开发并比较了符合性预测,蒙特卡洛脱落和证据深度学习.
- 在三个公共医学成像数据集上评估方法.
- 专注于染色皮肤病变和血液细胞类型检测的任务.
主要成果:
- 与其他方法相比,符合性预测显著改善了不确定性量化.
- 该研究提供了关于处理分布外样本的见解.
- 代码是公开可用的可复制性.
结论:
- 符合预测证明了强大而一致的性能.
- 它是安全关键的人工智能应用中决策的首选方法.
- 该技术在医学成像中提供可靠的不确定性估计.
更多相关视频
06:08Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging
Published on: May 5, 2011
16.8K
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
相关概念视频
01:30Skin Cancer
4.1K
Skin cancer is a type of cancer that occurs when there is an abnormal growth of skin cells, usually triggered by damage to the DNA within the skin cells. It is primarily caused by exposure to ultraviolet (UV) radiation from the sun or artificial sources like tanning beds. Skin cancer is the most common type of cancer worldwide, and its incidence continues to rise.
Basal Cell Carcinoma (BCC): BCC is the most common type of skin cancer, accounting for about 80% of cases. It typically develops in...
Basal Cell Carcinoma (BCC): BCC is the most common type of skin cancer, accounting for about 80% of cases. It typically develops in...
4.1K
01:15Receiver Operating Characteristic Plot
137
A ROC (Receiver Operating Characteristic) plot is a graphical tool used to assess the performance of a binary classification model by illustrating the trade-off between sensitivity (true positive rate) and specificity (false positive rate). By plotting sensitivity against 1 - specificity across various threshold settings, the ROC curve shows how well the model distinguishes between classes, with a curve closer to the top-left corner indicating a more accurate model. The area under the ROC curve...
137