Automatic Classification for Pathological Prostate Images Based on Fractal Analysis
Automatic Classification for Pathological Prostate Images Based on Fractal Analysis
复制标题
DOI：
10.1109/tmi.2009.2012704
复制
发表时间：
2009-07-01
影响因子：
10.6
通讯作者：
Lee, Cheng-Hsiung
中科院分区：
文献类型：
--
作者：
Huang, Po-Whei;Lee, Cheng-Hsiung
前列腺癌病理影像的准确分级对预后和治疗方案具有重要意义。由于人为分级费时且主观，本文提出了一种计算机辅助系统，根据目前最常用的前列腺组织组织学分级方法Gleason分级系统对病理图像进行自动分级。提出了两种基于分形维数的特征提取方法来分析感兴趣区域的强度变化和纹理复杂度。每个图像可以分别使用贝叶斯、k-NN和支持向量机（SVM）分类器分类到适当的等级。使用留一和k倍交叉验证程序来估计正确分类率（CCR）。实验结果表明，对于205张病理前列腺图像，贝叶斯分类器、k-NN分类器和SVM分类器的CCR分别可以达到91.2%、93.7%和93.7%。如果我们基于分形的特征集通过顺序浮动前向选择方法进行优化，使用上述三种分类器，CCR分别可以提升到94.6%，94.2%和94.6%。实验结果还表明，我们的特征集比多小波、Gabor滤波器和灰度共现矩阵方法提取的特征集更好，因为它具有更小的尺寸，并且仍然保持了最强大的前列腺图像判别能力。
Accurate grading for prostatic carcinoma in pathological images is important to prognosis and treatment planning. Since human grading is always time-consuming and subjective, this paper presents a computer-aided system to automatically grade pathological images according to Gleason grading system which is the most widespread method for histological grading of prostate tissues. We proposed two feature extraction methods based on fractal dimension to analyze variations of intensity and texture complexity in regions of interest. Each image can be classified into an appropriate grade by using Bayesian, k-NN, and support vector machine (SVM) classifiers, respectively. Leave-one-out and k-fold cross-validation procedures were used to estimate the correct classification rates (CCR). Experimental results show that 91.2%, 93.7%, and 93.7% CCR can be achieved by Bayesian, k-NN, and SVM classifiers, respectively, for a set of 205 pathological prostate images. If our fractal-based feature set is optimized by the sequential floating forward selection method, the CCR can be promoted up to 94.6%, 94.2%, and 94.6%, respectively, using each of the above three classifiers. Experimental results also show that our feature set is better than the feature sets extracted from multiwavelets, Gabor filters, and gray-level co-occurrence matrix methods because it has a much smaller size and still keeps the most powerful discriminating capability in grading prostate images.