Stein Joshua A, Asman Andrew J, Landman Bennett A
Electrical Engineering, Vanderbilt University, Nashville, TN, USA 37235.
Proc SPIE Int Soc Opt Eng. 2011 Mar 3;7966. doi: 10.1117/12.878412.
Labeling structures on medical images is crucial in determining clinically relevant correlations with morphometric and volumetric features. For the exploration of new structures and new imaging modalities, validated automated methods do not yet exist, and so researchers must rely on manually drawn landmarks. Voxel-by-voxel labeling can be extremely resource intensive, so large-scale studies are problematic. Recently, statistical approaches and software have been proposed to enable Internet-based collaborative labeling of medical images. While numerous labeling software tools have been created, the use of these packages as high-throughput labeling systems has yet to become entirely viable given training requirements. Herein, we explore two modifications to a typical mouse-based labeling system: (1) a platform independent overlay for recognition of mouse gestures and (2) an inexpensive touch-screen tracking device for non-mouse input. Through this study we characterize rater reliability in point, line, curve, and region placement. For the mouse input, we find a placement accuracy of 2.48±5.29 pixels (point), 0.630±1.81 pixels (curve), 1.234±6.99 pixels (line), and 0.058±0.027 (1 - Jaccard Index for region). The gesture software increased labeling speed by 27% overall and accuracy by approximately 30-50% on point and line tracing tasks, but the touch screen module lead to slower and more error prone labeling on all tasks, likely due to relatively poor sensitivity. In summary, the mouse gesture integration layer runs as a seamless operating system overlay and could potentially benefit any labeling software; yet, the inexpensive touch screen system requires improved usability optimization and calibration before it can provide an efficient labeling system.
在医学图像上标记结构对于确定与形态测量和体积特征的临床相关关联至关重要。对于新结构和新成像模式的探索，尚未存在经过验证的自动化方法，因此研究人员必须依赖手动绘制的地标。逐体素标记可能极其耗费资源，因此大规模研究存在问题。最近，有人提出了统计方法和软件，以实现基于互联网的医学图像协作标记。虽然已经创建了许多标记软件工具，但鉴于培训要求，将这些软件包用作高通量标记系统尚未完全可行。在此，我们探索了对典型的基于鼠标的标记系统的两种改进：（1）用于识别鼠标手势的平台独立覆盖层，以及（2）用于非鼠标输入的廉价触摸屏跟踪设备。通过这项研究，我们表征了在点、线、曲线和区域放置方面评分者的可靠性。对于鼠标输入，我们发现放置精度为2.48±5.29像素（点）、0.630±1.81像素（曲线）、1.234±6.99像素（线）和0.058±0.027（区域的1 - 杰卡德指数）。手势软件总体上使标记速度提高了27%，在点和线追踪任务上的准确性提高了约30 - 50%，但触摸屏模块在所有任务上导致标记速度变慢且更容易出错，这可能是由于灵敏度相对较差。总之，鼠标手势集成层作为无缝操作系统覆盖层运行，可能会使任何标记软件受益；然而，廉价的触摸屏系统在能够提供高效标记系统之前，需要改进可用性优化和校准。
