可靠的多模式医疗图像对图像翻译独立于像素对齐的数据
1Jiangsu Key Laboratory for Biomaterials and Devices, School of Biological Science and Medical Engineering, Southeast University, Nanjing, China.
Medical physics
|August 17, 2024
概括
这项研究引入了一种新的医学图像对图像翻译模型 (MITIA),即使使用错位训练数据,也可靠地工作. MITIA克服了现有方法的局限性,为多模式医学成像任务提供了更好的性能和稳定性.
科学领域:
- 医疗成像医学成像
- 人工智能的人工智能
- 计算机视觉 计算机视觉
背景情况:
- 当前的多模体医学图像对图像翻译方法面临着一个困境:监督方法需要像素对齐的数据,这是很难获得的,而无监督方法缺乏保证的可靠性.
- 现有的方法在没有精确对齐的多模式医疗图像数据集的情况下,难以产生可靠的翻译结果.
研究的目的:
- 开发一种新的医学图像对图像翻译模型,独立于像素对齐数据 (MITIA).
- 为了使可靠的多模式医疗图像翻译,即使训练数据是不对齐.
主要方法:
- MITIA模型采用先前提取网络与注册和错位检测模块,以利用错位数据中的信息.
- 它使用提取的先前信息来创建一个无监督循环一致的生成对抗网络 (GAN) 的规范化术语.
- 该模型在不同的数据集上进行了训练,具有不同程度的错位,并根据最先进的方法进行了评估.
主要成果:
- 与现有方法相比,MITIA在不对齐和对齐的数据集上表现出卓越的性能和稳定性.
- 该模型的有效性在不同类型和严重程度的错位错误中是一致的.
- 定量指标 (PSNR,SSIM) 和定性评估证实了MITIA的先进能力.
结论:
- 在不需要对齐的训练数据的情况下,MITIA方法在多模式医疗图像翻译中取得了出色的结果.
- 鉴于在获取像素对齐的医疗图像数据方面面临的挑战,MITIA已准备好在这个领域获得重大实际应用.
相关概念视频
02:07Improving Translational Accuracy
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
02:07Improving Translational Accuracy
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...