Nakappan Senthilnathan, Park Sun Young, Serachitopol Dan, Price Roderick, Cardeno Mark, Au Sylvia, Mackinnon Nick, MacAulay Calum, Follen Michele, Pikkula Brian M
Biomedical Engineering Center, The University of Texas M. D. Anderson Cancer Center, Houston, Texas 77030, USA.
Gynecol Oncol. 2007 Oct;107(1 Suppl 1):S215-22. doi: 10.1016/j.ygyno.2007.07.016. Epub 2007 Sep 7.
The diagnostic ability of algorithms developed for the Multispectral Digital Colposcope (MDC) is highly dependent on the quality of the image. The field of objective medical image quality analysis has great potential but has not been well exploited. Various researchers have reported different measures of image quality but with an existence of a reference image. The quality of an image can be attributed to several sources of errors, a few of which would be inclusion of presence of extraneous components, improper illumination, or an image out of focus. This can be due to motion artifact or the region of interest out of the focal plane.
With spectroscopic measurements, assessment of data quality has been used by our group in the past to avoid hardware errors at the time of acquisition. We are currently developing algorithms that will help identify hardware and acquisition errors to the clinician in under a few seconds.
Minimizing these errors not only provides quality images for a diagnostic algorithm, but reduces the necessity for complex and time intensive post-processing software for enhancing the images.
We propose a no reference image quality system specifically designed for MDC that can be modified to similar spectroscopic imaging applications.
为多光谱数字阴道镜（MDC）开发的算法的诊断能力高度依赖于图像质量。客观医学图像质量分析领域具有巨大潜力，但尚未得到充分利用。不同的研究人员报告了不同的图像质量测量方法，但都存在参考图像。图像质量可能归因于多种误差来源，其中一些可能是存在无关组件、光照不当或图像失焦。这可能是由于运动伪影或感兴趣区域不在焦平面上。
过去我们小组通过光谱测量来评估数据质量，以避免采集时的硬件错误。我们目前正在开发算法，这些算法将在几秒钟内帮助临床医生识别硬件和采集错误。
最小化这些误差不仅为诊断算法提供了高质量的图像，而且减少了用于增强图像的复杂且耗时的后处理软件的必要性。
我们提出了一种专门为MDC设计的无参考图像质量系统，该系统可以修改以用于类似的光谱成像应用。
