Automated detection of prostatic adenocarcinoma from high-resolution ex vivo MRI
Automated detection of prostatic adenocarcinoma from high-resolution ex vivo MRI
复制标题
DOI：
10.1109/tmi.2005.859208
复制
发表时间：
2005-12-01
影响因子：
10.6
通讯作者：
Chute, D
中科院分区：
文献类型：
--
作者：
Madabhushi, A;Feldman, MD;Chute, D
前列腺癌是美国男性中最常见的癌症，仅次于皮肤癌。目前，唯一确定前列腺癌存在的方法是经直肠超声（TRUS）指导活检。由于超声图像质量差，TRUS的准确率仅为20%-25%。与超声相比，高分辨率磁共振成像（MRI）已被证明具有更高的前列腺癌检测准确性。因此，一些研究人员一直在探索高分辨率MRI在前列腺活检中的应用。然而，前列腺癌的视觉检测仍然很困难，因为它明显缺乏形状，而且一些恶性和良性结构具有重叠的强度和纹理特征。在本文中，我们提出了一种全自动计算机辅助检测（CAD）系统，用于从前列腺的4 Testa离体磁共振（MR）图像中检测前列腺腺癌。在对获取的磁共振图像进行背景非均匀性和非标准性校正后，从三维MRI场景中提取新的三维纹理特征。然后，贝叶斯分类器为每个图像体素独立分配每个特征的恶性“可能性”。以这种方式生成的“似然”图像然后使用最优加权特征组合方案进行组合。通过将CAD结果与人工确定的MRL上肿瘤的基础真值进行比较来进行定量评估。MR切片上的肿瘤标签由专家通过视觉上将MR切片与组织学切片上的相应区域注册来手动确定。我们对来自5个不同的前列腺3-D MR研究的总共33个二维（2-D） MR切片进行了CAD系统评估。来自两个不同腺体的五片切片用于训练。我们的特征组合方案优于单个纹理特征，也优于其他常用的特征组合方法，包括AdaBoost、集合平均和多数投票。此外，在一些情况下，我们的CAD系统在准确性方面比专家表现得更好，专家分割仅通过对MRI数据的视觉检查来确定。此外，系统内变异性（CAD精度随系统参数值变化的变化）显著低于相应的观察者内变异性和观察者间变异性。在不同的训练集上，CAD的性能非常相似。未来的工作将集中于扩展该方法，以指导高分辨率mri辅助的体内前列腺活检。
Prostatic adenocarcinoma is the most commonly occurring cancer among men in the United States, second only to skin cancer. Currently, the only definitive method to ascertain the presence of prostatic cancer is by trans-rectal ultrasound (TRUS) directed biopsy. Owing to the poor image quality of ultrasound, the accuracy of TRUS is only 20%-25%. High-resolution magnetic resonance imaging (MRI) has been shown to have a higher accuracy of prostate cancer detection compared to ultrasound. Consequently, several researchers have been exploring the use of high resolution MRI in performing prostate biopsies. Visual detection of prostate cancer, however, continues to be difficult owing to its apparent lack of shape, and the fact that several malignant and benign structures have overlapping intensity and texture characteristics. In this paper, we present a fully automated computer-aided detection (CAD) system for detecting prostatic adenocarcinoma from 4 Testa ex vivo magnetic resonance (MR) imagery of the prostate. After the acquired MR images have been corrected for background inhomogeneity and nonstandardness, novel three-dimensional (3-D) texture features are extracted from the 3-D MRI scene. A Bayesian classifier then assigns each image voxel a "likelihood" of malignancy for each feature independently. The "likelihood" images generated in this fashion are then combined using an optimally weighted feature combination scheme. Quantitative evaluation was performed by comparing the CAD results with the manually ascertained ground truth for the tumor on the MRL The tumor labels on the MR slices were determined manually by an expert by visually registering the MR slices with the corresponding regions on the histology slices. We evaluated our CAD system on a total of 33 two-dimensional (2-D) MR slices from five different 3-D MR prostate studies. Five slices from two different glands were used for training. Our feature combination scheme was found to outperform the individual texture features, and also other popularly used feature combination methods, including AdaBoost, ensemble averaging, and majority voting. Further, in several instances our CAD system performed better than the experts in terms of accuracy, the expert segmentations being determined solely from visual inspection of the MRI data. In addition, the intrasystem variability (changes in CAD accuracy with changes in values of system parameters) was significantly lower than the corresponding intraobserver and interobserver variability. CAD performance was found to be very similar for different training sets. Future work will focus on extending the methodology to guide high-resolution MRI-assisted in vivo prostate biopsies.