相关实验视频

Updated: Jun 25, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

通过训练性能和任务功能,提高群众对医学图像注释的智慧

Eeshan Hasan^1,2, Erik Duhaime³, Jennifer S Trueblood^4,5

¹Department of Psychological and Brain Sciences, Indiana University, 1101 E. 10th St., Bloomington, IN, 47405-7007, USA. eehasan@iu.edu.

Cognitive research: principles and implications

|May 19, 2024

概括

高质量的标记医疗数据集对于人工智能 (AI) 是必不可少的. 群众智慧算法有效标记医疗图像,优于人工智能开发的专家性能.

科学领域:

医疗人工智能医疗人工智能
机器学习机器学习
皮肤病学皮肤病学

背景情况:

高质量的标记医疗数据集是开发医疗人工智能的重要瓶.
众包平台可以为数据标签任务招募各种各样的个人.

研究的目的:

为了评估群众的各种智慧,医疗图像标签的算法.
确定利用医疗AI中的群众智能的最佳方法.

主要方法:

通过应用程序招募个人,将2018年国际皮肤损伤挑战中的皮肤病变分为7类.
测试了群众算法的多重智慧,从简单的平均值到复杂的贝叶斯模型.
采用交换机分析来评估基于个体特征和任务环境的算法性能.

主要成果:

性能最好的算法选择了表现最好的人,根据训练准确度加权决策,并考虑了任务环境.
这些复杂的基于人群的标签方法明显超过了专家的表现.
个人经验和表现的变化是影响算法有效性的关键因素.

结论:

人群算法的智慧,特别是那些包含性能权重和错误分析的算法,可以有效地生成高质量的标记医疗数据.
这些发现对加速开发强大的医疗人工智能系统具有重大意义.
优化基于群众的标签策略对于克服医疗AI数据限制至关重要.

更多相关视频

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

相关概念视频

Positron Emission Tomography

Positron Emission Tomography

Positron emission tomography (PET) is a medical imaging technique involving radiopharmaceuticals — substances that emit short-lived radiation. Although the first PET scanner was introduced in 1961, it took 15 more years before radiopharmaceuticals were combined with the technique and revolutionized its potential.
One of the main requirements of a PET scan is a positron-emitting radioisotope, which is produced in a cyclotron and then attached to a substance used by the part of the body being...