Rehman Zaka Ur, Zia M Sultan, Bojja Giridhar Reddy, Yaqub Muhammad, Jinchao Feng, Arshid Kaleem
Department of Computer science and IT, The University of Lahore, Gujrat Campus, Gujrat, Pakistan.
College of Business and Information Systems, Dakota State University, Madison, USA.
Med Hypotheses. 2020 Aug;141:109705. doi: 10.1016/j.mehy.2020.109705. Epub 2020 Apr 7.
In this paper, a machine learning approach was used for brain tumour localization on FLAIR scans of magnetic resonance images (MRI). The multi-modal brain images dataset (BraTs 2012) was used, that is a skull stripped and co-registered. In order to remove the noise, bilateral filtering is applied and then texton-map images are created by using the Gabor filter bank. From the texton-map, the image is segmented out into superpixel and then the low-level features are extracted: the first order intensity statistical features and also calculates the histogram level of texton-map at each superpixel level. There is a significant contribution here that the low features are not too much significant for the localization of brain tumour from MR images, but we have to make them meaningful by integrating features with the texton-map images at the region level approach. Then these features which are provided later to classifier for the prediction of three classes: background, tumour and non-tumour region, and used the labels for computation of two different areas (i.e. complete tumour and non-tumour). A Leave-one-out (LOOCV) cross validation technique is applied and achieves the dice overlap score of 88% for the whole tumour area localization, which is similar to the declared score in MICCAI BraTS challenge. This brain tumour localization approach using the textonmap image based on superpixel features illustrates the equivalent performance with other contemporary techniques. Recently, medical hypothesis generation by using autonomous computer based systems in disease diagnosis have given the great contribution in medical diagnosis.
在本文中，一种机器学习方法被用于在磁共振成像（MRI）的液体衰减反转恢复（FLAIR）扫描上进行脑肿瘤定位。使用了多模态脑图像数据集（BraTs 2012），该数据集已去除颅骨并进行了配准。为了去除噪声，应用了双边滤波，然后使用Gabor滤波器组创建纹理映射图像。从纹理映射中，将图像分割为超像素，然后提取低级特征：一阶强度统计特征，并在每个超像素级别计算纹理映射的直方图级别。这里有一个重要贡献，即这些低级特征对于从MR图像中定位脑肿瘤的意义不大，但我们必须通过在区域级别方法中将特征与纹理映射图像集成来使其有意义。然后将这些特征提供给分类器，用于预测三个类别：背景、肿瘤和非肿瘤区域，并使用这些标签来计算两个不同区域（即完整肿瘤和非肿瘤）。应用了留一法（LOOCV）交叉验证技术，在整个肿瘤区域定位中实现了88%的骰子重叠分数，这与MICCAI BraTS挑战赛中公布的分数相似。这种基于超像素特征的纹理映射图像的脑肿瘤定位方法展示了与其他当代技术相当的性能。最近，在疾病诊断中使用基于自主计算机的系统生成医学假设在医学诊断中做出了巨大贡献。
