Quantel Medical, 11 rue du Bois Joli, 63808, Cournon-d'Auvergne, France.
EnCoV, IP, UMR 6602 CNRS / Université Clermont Auvergne, 28 place Henri Dunant, 63001, Clermont-Ferrand, France.
Int J Comput Assist Radiol Surg. 2017 Jun;12(6):911-920. doi: 10.1007/s11548-017-1555-z. Epub 2017 Mar 13.
The slit lamp is an essential instrument for eye care. It is used in navigated laser treatment with retina mosaicing to assist diagnosis. Specifics of the imaging setup introduce bothersome illumination artifacts. They not only degrade the quality of the mosaic but may also affect the diagnosis. Existing solutions in SLIM manage to deal with strong glares which corrupt the retinal content entirely while leaving aside the correction of semitransparent specular highlights and lens flare. This introduces ghosting and information loss.
We propose an effective technique to detect and correct light reflections of different degrees in SLIM. We rely on the specular-free image concept to obtain glare-free image and use it coupled with a contextually driven probability map to segment the visible part of the retina in every frame before image mosaicing. We then perform the image blending on a subset of all spatially aligned frames. We detect the lens flare and label each pixel as 'flare' or 'non flare' using a probability map. We then invoke an adequate blending method. We also introduce a new quantitative measure for global photometric quality.
We tested on a set of video sequences obtained from slit lamp examination sessions of 11 different patients presenting healthy and unhealthy retinas. The segmentation of glare and visible retina was evaluated and compared to state-of-the-art methods. The correction of lens flare and semitransparent highlight with content-aware blending was applied and its performance was evaluated qualitatively and quantitatively.
The experiments demonstrated that integrating the proposed method to the mosaicing framework significantly improves the global photometric quality of the mosaics and outperforms existing works in SLIM.
裂隙灯是眼科护理的重要仪器。它用于视网膜镶嵌导航激光治疗以协助诊断。成像设置的具体细节会引入令人烦恼的照明伪影。这些伪影不仅会降低镶嵌图像的质量，还可能影响诊断。SLIM 中的现有解决方案设法处理完全破坏视网膜内容的强烈眩光，而忽略了对半透明镜面反射高光和镜头耀斑的校正。这会导致重影和信息丢失。
我们提出了一种在 SLIM 中检测和校正不同程度光反射的有效技术。我们依赖于无镜面反射图像的概念来获得无眩光的图像，并在图像镶嵌之前，使用它结合上下文驱动的概率图来分割每一帧中可见的视网膜部分。然后，我们在所有空间对齐帧的子集中执行图像混合。我们使用概率图检测镜头耀斑，并将每个像素标记为“耀斑”或“非耀斑”。然后调用适当的混合方法。我们还引入了一种新的全局光度质量定量度量。
我们在一组从 11 位不同患者的裂隙灯检查会话中获得的视频序列上进行了测试，这些患者的视网膜健康或不健康。评估并比较了耀斑和可见视网膜的分割与最新技术方法。应用了基于内容感知混合的镜头耀斑和半透明高光校正，并对其性能进行了定性和定量评估。
实验表明，将所提出的方法集成到镶嵌框架中，可以显著提高镶嵌图像的全局光度质量，并在 SLIM 中优于现有作品。
