论文标题
使用数字图像分析的KI-67乳腺癌指数测量
Ki-67 Index Measurement in Breast Cancer Using Digital Image Analysis
论文作者
论文摘要
KI-67是一种核蛋白，可以在细胞增殖过程中产生。在几种癌症中，Ki67指数是一个有价值的预后变量。在乳腺癌中，甚至常规检查了许多患者的指数。目前，病理学家使用免疫组织化学方法将KI-67阳性恶性细胞的百分比视为KI-67指数。较高的分数通常意味着更具侵略性的肿瘤行为。在临床实践中，KI-67指数的测量取决于视觉识别方法和手动计数。然而，视觉和手动评估方法是时间耗费，由于评估标准不同或评估中的肿瘤面积有限，因此可重复性差。在这里，我们使用数字图像处理技术，包括图像二进制和图像形态操作来创建数字图像分析方法来解释KI-67索引。然后，将10个乳腺癌标本用作高精度的验证（相关效率r = 0.95127）。借助数字图像分析，病理学家可以更有效地解释Ki67指数，而良好的可重复性。
Ki-67 is a nuclear protein that can be produced during cell proliferation. The Ki67 index is a valuable prognostic variable in several kinds of cancer. In breast cancer, the index is even routinely checked in many patients. Currently, pathologists use the immunohistochemistry method to calculate the percentage of Ki-67 positive malignant cells as Ki-67 index. The higher score usually means more aggressive tumor behavior. In clinical practice, the measurement of Ki-67 index relies on visual identifying method and manual counting. However, visual and manual assessment method is timeconsuming and leads to poor reproducibility because of different scoring standards or limited tumor area under assessment. Here, we use digital image processing technics including image binarization and image morphological operations to create a digital image analysis method to interpretate Ki-67 index. Then, 10 breast cancer specimens are used as validation with high accuracy (correlation efficiency r = 0.95127). With the assistance of digital image analysis, pathologists can interpretate the Ki67 index more efficiently, precisely with excellent reproducibility.
