双学生对抗框架与歧视和一致性驱动的学习为半监督医疗图像细分半监督医疗图像细分.
IEEE journal of biomedical and health informatics
|August 11, 2025
概括
这项研究引入了一种新的双学生对抗框架,以改善半监督医疗图像细分. 该方法增强了伪标签的可靠性和训练稳定性,从而带来了优异的细分性能.
科学领域:
- 医疗成像医学成像
- 计算机视觉 计算机视觉
- 机器学习 机器学习
背景情况:
- 半监督医疗图像细分可以降低手动注释成本,但面临着不可靠的伪标签和确认偏差的挑战.
- 由于这些局限性,现有的方法往往表现出不稳定的优化和性能退化.
研究的目的:
- 为强大的半监督医疗图像细分提出一个新的双学生对抗框架.
- 通过提高伪标签质量和培训稳定性来解决现有方法的局限性.
主要方法:
- 引入了双学生对抗框架,其中包含了基于学习的对抗细分精细化 (ALSR) 模块,用于预测多样性和伪标签精细化.
- 在不确定性估计中使用剩余指数移动平均值 (R-EMA),用于稳定的教师模型和基于不确定性的过.
- 开发了一个对比表示稳定 (CRS) 模块,用于在自信区域上使用对比学习增强语音级语义对齐.
主要成果:
- 拟议的方法在对基准数据集的广泛实验中始终超过了最先进的方法.
- 与现有的半监督方法相比,证明了较好的细分精度和稳定性.
结论:
- 双学生对抗框架为半监督医疗图像细分提供了强大的解决方案.
- 集成的ALSR,R-EMA,UIM和CRS模块有效地提高了伪标签的可靠性,培训的稳定性和特征的可区分性.
相关概念视频
01:28Imaging Studies I: Kidney, Ureter, and Bladder Studies
871
Kidney, Ureter, and Bladder (KUB) StudiesKidney, Ureter, and Bladder (KUB) studies are standard diagnostic imaging procedures used to assess the anatomy of the urinary system. They are commonly utilized for patients experiencing abdominal pain or urinary symptoms. By using a simple X-ray of the abdomen, KUB studies can reveal structural and pathological abnormalities within the kidneys, ureters, and bladder. These studies are particularly valuable in diagnosing kidney stones, urinary...
871
01:24Imaging Studies II: Ultrasonography
909
IntroductionUltrasonography, or renal ultrasound, is a noninvasive medical imaging technique that uses high-frequency sound waves to visualize the kidneys, ureters, bladder, and surrounding tissues.Indications for Urinary System UltrasonographyUrinary system ultrasonography is indicated in various clinical scenarios, such as:Kidney Stones (Urolithiasis): To detect and monitor the size and presence of kidney or urinary tract stones.Hydronephrosis: To assess the dilation of the renal pelvis and...
909