Department of Computer Science, COMSATS University Islamabad, Wah Campus 47040, Pakistan.
Department of Mathematics, COMSATS University Islamabad, Wah Campus 47040, Pakistan.
Int J Med Inform. 2019 Jun;126:26-34. doi: 10.1016/j.ijmedinf.2019.02.001. Epub 2019 Feb 28.
Massive work by distinguished researchers in the domain of breast segmentation has been proposed. However, no significant solution reduces the limitations of the false positive rate of cancerous cells in the breast body for probing the abnormalities of particular features. This problem is challenging in its nature and essential to be solved. It is needed to reach the optimal measurements of the breast parenchyma, the breast patchy regions of the mammogram, or the breast registration for searching of precise oddities.
In this work, we propose a novel approach for observing the abnormal breast cells identification with high sensitivity. A cancer tumor often produces a specific protein in the blood that serves as a marker for the cancer cells. These cells break off from the cancer and move into the blood stream. However, presence of pectoral muscle in breast mammogram highly affects the detection process of breast tumor. A novel aspect of the proposed method is that the curve stitching technique is developed for removing of pectoral muscle. Following this, an adaptive hysteresis thresholding is used for segmentation. This hybrid technique is used for segmenting a breast region of digital mammogram with suppression of pectoral muscle.
The proposed method attains a highest sensitivity rate of 96.6% for the MIAS dataset and 96.4% for the DDSM dataset as compared to existing methods.
The main idea behind this is to improve the threshold based segmentation techniques to create an adaptive threshold and apposite templates, in order to conserve tumor salient features about suspicious regions to classify benign and malignant mass in mammogram. First, a spline based curve fitting is applied on edges of the breast parenchyma and fill the region with a very low intensity value and map on original image to preserve the original intensity of breast region free of pectoral muscle. The results of the experiments show that the proposed segmentation technique is efficient when tested on MIAS and DDSM dataset.
在乳腺分割领域，杰出研究人员已经提出了大量工作。然而，没有显著的解决方案可以降低乳腺体中癌细胞假阳性率的局限性，以探测特定特征的异常。这个问题具有挑战性，需要解决。需要达到乳腺实质、乳腺斑点区域或乳腺注册的最佳测量，以搜索精确的异常。
在这项工作中，我们提出了一种用于观察具有高灵敏度的异常乳腺细胞识别的新方法。癌症肿瘤通常会在血液中产生一种特定的蛋白质，作为癌细胞的标志物。这些细胞从癌症中分离出来并进入血流。然而，乳腺 X 光片中的胸肌会极大地影响乳腺肿瘤的检测过程。所提出方法的一个新颖方面是开发了曲线拼接技术来去除胸肌。之后，使用自适应滞后阈值处理来进行分割。该混合技术用于分割数字乳腺 X 光片中的乳腺区域，并抑制胸肌。
与现有方法相比，所提出的方法在 MIAS 数据集上达到了最高 96.6%的灵敏度率，在 DDSM 数据集上达到了最高 96.4%的灵敏度率。
背后的主要思想是改进基于阈值的分割技术，创建自适应阈值和适当的模板，以保留关于可疑区域的肿瘤显著特征，以便在乳腺 X 光片中对良性和恶性肿块进行分类。首先，在乳腺实质的边缘上应用基于样条的曲线拟合，并使用非常低的强度值填充区域，并将其映射到原始图像上，以保留无胸肌的乳腺区域的原始强度。实验结果表明，所提出的分割技术在 MIAS 和 DDSM 数据集上测试时是有效的。
